TRNS – Bidirectional Stochastic Damping & Signal Regularization
Lightweight physics-based technology that cleans noisy real-world signals and enables predictive fractal modeling — all running efficiently on edge hardware.
Proven Performance
Powered by our proprietary operator, TRNS (Temperature-Regularized Navier-Stokes)
| RMS reduction | SNR gains |
|---|---|
| 1.3X to +5.1X | +10dB to +31dB |
Results vary by signal type and noise level. Real-world examples include 7.19x RMS reduction on motion-contaminated wrist PPG (TROIKA dataset) and up to 10x+ in certain high-noise cases.
Reduces noise across diverse signals while preserving underlying structure
Suppresses motion artifacts, sensor noise, and baseline wander
Bidirectional operation: backward denoising + forward generative mode
Lightweight and real-time capable on standard embedded processors
No training data or black-box models required
Serves as an efficient pre-denoising layer for deep learning models, reducing AI compute and power requirements
Key Applications
Backward Mode – Denoising Applications
(Real-time noise suppression and artifact removal)
Medical sensors (PPG, ECG, ultrasound RF, infusion) – motion artifact and sensor noise reduction
Fluid dynamics & propulsion (engines, turbines, rockets) - real-time denoising of pressure, temperature, vibration, and flow sensors in high-performance systems
Data center liquid cooling systems – denoising flow, pressure, and temperature sensors in cooling loops
Oil & gas pipeline flow assurance & reservoir simulation – denoising multiphase flow and pressure sensors
Radio-frequency & long-range comms (cellular 5G/6G, radar, satellite, Wi-Fi, Bluetooth) – denoising weak or interfered signals
Consumer wearables – ANC headphones & earbuds – real-time acoustic noise cancellation under motion
Marine hydrodynamics & underwater acoustics – denoising acoustic and vibration signals
Microseismic & geothermal monitoring – noise reduction in seismic and downhole sensor data
Wind energy (turbine blade & wake flow) – denoising sensor data from turbines
LiDAR & 3D sensing – cleaning noisy point-cloud returns
HVAC & industrial ventilation – denoising airflow and thermal sensors
Edge-AI pre-denoising – lightweight pre-processing layer to reduce compute load
Forward Generative Mode – Prediction & Synthetic Modeling Applications
(Path-of-least-resistance fractal prediction and synthetic data generation)
Data center liquid cooling systems – predictive modeling of coolant flow and thermal distribution
Oil & gas pipeline flow assurance & reservoir simulation – synthetic multiphase flow and pressure prediction
Fluid dynamics & propulsion (engines, turbines, rockets) – generative modeling of turbulent flow, combustion, and pressure oscillations
Chemical processing & pharmaceuticals – generative simulation of reactor mixing and crystallization paths
Marine hydrodynamics & underwater acoustics – predictive modeling of hull/propeller flow and acoustic propagation
Wind energy (turbine blade & wake flow) – generative prediction of turbulent wakes and blade loading
HVAC & industrial ventilation – predictive airflow and thermal modeling
Synthetic data generation for AI/ML training – creating realistic time-series and flow data
Weather & climate modeling – generative prediction of turbulent atmospheric flows and storm paths
Material science & additive manufacturing – fractal modeling of crystal growth and solidification
Biological & tissue growth modeling – path-of-least-resistance simulation of vascular networks and wound healing
Traffic & urban flow prediction – generative modeling of vehicle, pedestrian, and crowd dynamics
Energy grid optimization & power flow modeling – predictive path-of-least-resistance for grid stability
Procedural content & simulation (gaming, CGI, digital twins) – real-time fractal generation of fluids and terrain
Drug discovery & molecular dynamics – generative modeling of molecular folding and diffusion paths
Our Licensing Model
Non-exclusive licenses are available across all categories.
Each licensee receives:
• Quick-Start Tuning Guide + example code
• Synthetic benchmark datasets
• Limited integration and tuning support
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Contact Us
For licensing discussions, technical or general questions, or partnership opportunities, please fill out the form below. We typically respond within 1-2 business days.
Technology and Applications
Additional categories and application examples are in development and will be added regularly
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
About Us
Meadows McKnight LLC was founded by husband-and-wife team Clinton and Jennifer Meadows in East Texas. The company exists to develop and license TRNS (Temperature-Regularized Navier-Stokes), a physics-based stochastic damping and signal regularization technology invented by Jennifer.
Jennifer developed TRNS through years of independent research, drawing on her background in medical laboratory science and business administration. What began as an effort to solve stubborn noise and artifact problems in real-world sensor data has evolved into a versatile framework with demonstrated results across medical devices, aerospace propulsion, data center cooling, RF communications, and other complex signal environments.
Clinton brings more than 15 years of hands-on experience in industrial operations, equipment reliability, continuous improvement, regulatory compliance, and strategic business development. He leads the operational, patent, and commercialization efforts, allowing Jennifer to focus on the technical innovation.
Together, they are building a lean, family-run company committed to practical, high-performance signal solutions. Their goal is to form non-exclusive licensing partnerships with organizations that can integrate TRNS into real products and systems — improving sensor accuracy, system efficiency, and reliability across multiple industries.
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 1 of 3
Data Cooling Systems
Real Chiller Signal Denoising Demonstration
Dataset Provenance
The dataset used in this demonstration is HVAC Energy Data (Chiller-focused), publicly available on Kaggle. It contains real operational measurements collected from a commercial chiller system in a building located in Singapore.Description
This demonstration applies the TRNS stochastic damping operator to real-world chiller signals. The raw data contains significant sensor noise mixed with meaningful operational dynamics such as varying chilled water flow rates, thermal load changes, and system transients. TRNS achieves a 1.87× RMS noise reduction while perfectly preserving critical system behavior essential for energy efficiency, predictive maintenance, and stable chiller control in data center liquid cooling infrastructure.
Denoised with TRNS
Performance Comparison
Performance ranges shown are typical values reported in literature and industry benchmarks for each method. Actual results vary by application and implementation.
Why TRNS Numbers Are Superior in Practice
In data center chiller systems, preserving true operational dynamics while removing sensor noise is critical for efficient control, energy optimization, and predictive maintenance. TRNS delivers a strong 1.87× RMS noise reduction while achieving perfect trend preservation (0.00% error) and good waveform correlation.
Many advanced machine learning approaches can achieve higher numerical reductions but frequently oversmooth the signal, removing legitimate transients (load changes, flow variations, thermal responses) that control systems and optimization algorithms depend on. TRNS provides a lightweight, physics-based solution that prioritizes real-world practical utility in challenging industrial environments.
Citation
Chiller Energy. (2021). Chiller Energy Data [Dataset]. Kaggle. Retrieved from https://www.kaggle.com/datasets/chillerenergy/chiller-energy-data
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 2 of 3
Data Cooling Systems
Real Cooling Tower Signal Denoising Demonstration
Dataset Provenance
The dataset used in this demonstration is the Cooling Tower Optimization Dataset from Kaggle, containing real operational data from an industrial cooling tower system collected between 2018 and 2024.Description
This demonstration applies the TRNS stochastic damping operator to real-world cooling tower signals. The raw data contains significant sensor noise and jitter mixed with meaningful operational dynamics such as load variations, thermal transients, and fan/pump cycling. TRNS achieves a 4.76× RMS noise reduction while preserving critical system behavior essential for energy optimization, predictive maintenance, and stable control in data center liquid cooling infrastructure.
Denoised with TRNS
Performance Comparison
Performance ranges shown are typical values reported in literature and industry benchmarks for each method. Actual results vary by application and implementation.
Why TRNS Numbers Are Superior in Practice
In data center cooling towers — a major energy consumer in liquid cooling systems — preserving true operational dynamics while removing sensor noise is critical for efficient control, energy optimization, and predictive maintenance. TRNS delivers a strong 4.76× RMS noise reduction while maintaining excellent fidelity to real transients (load changes, fan cycling, thermal responses).
Many advanced machine learning approaches can achieve higher numerical reductions but frequently oversmooth the signal, removing legitimate operational variations that control systems depend on. TRNS provides a lightweight, physics-based solution that prioritizes real-world practical utility in challenging industrial environments.
Citation
Ziya. (2024). Cooling Tower Optimization Dataset [Dataset]. Kaggle. Retrieved from https://www.kaggle.com/datasets/ziya07/cooling-tower-optimization-dataset
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 3 of 3
Data Cooling Systems
Real Data Center Liquid Cooling Signal Denoising Demonstration
Dataset Provenance
The dataset used in this demonstration is the Data Center Cold Source Control Dataset from Kaggle, containing real operational data from a modern data center’s cold source group control system (chillers and air handling units).Description
This demonstration applies the TRNS stochastic damping operator to real-world data center liquid cooling signals. The raw data contains significant sensor noise mixed with meaningful operational dynamics such as server workload changes, chiller cycling, and thermal transients. TRNS achieves a 4.46× RMS noise reduction while preserving critical system behavior essential for energy optimization, predictive maintenance, and stable control in data center liquid cooling infrastructure.
Denoised with TRNS
Performance Comparison
Performance ranges shown are typical values reported in literature and industry benchmarks for each method. Actual results vary by application and implementation.
Why TRNS Numbers Are Superior in Practice
In data center liquid cooling systems, preserving true operational dynamics while removing sensor noise is critical for efficient control, energy optimization, and predictive maintenance. TRNS delivers a strong 4.46× RMS noise reduction while achieving excellent trend preservation (0.04% error) and good waveform correlation.
Many advanced machine learning approaches can achieve higher numerical reductions but frequently oversmooth the signal, removing legitimate transients (workload changes, chiller cycling, thermal responses) that control systems depend on. TRNS provides a lightweight, physics-based solution that prioritizes real-world practical utility in challenging data center environments.
Citation
Python Developer. (2024). Data Center Cold Source Control Dataset [Dataset]. Kaggle. Retrieved from https://www.kaggle.com/datasets/programmer3/data-center-cold-source-control-dataset
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 1 of 7
Fluid Dynamics & Propulsion
Note In our demonstrations, we tune TRNS to achieve the best overall balance between noise reduction and preservation of real-world signal dynamics, rather than pursuing the absolute highest RMS number possible.
While TRNS parameters can be adjusted to reach higher RMS reductions (sometimes comparable to advanced machine learning methods), we intentionally prioritize practical performance. Excessive denoising frequently leads to oversmoothing, which can remove important physical transients, degradation trends, or operational signatures critical for real applications such as fault detection, predictive maintenance, and process control.
TRNS is designed to deliver strong, usable results that respect the underlying physics of the system.
Computational Fluid Dynamics (CFD) Laminar vs Turbulent Flow
Dataset Provenance
The dataset used in this demonstration is the Computational Fluid Dynamics - Laminar vs Turbulent Flow Dataset, publicly available on Kaggle. It contains simulated 2D channel flow data generated from the Navier-Stokes equations.Description
This dataset consists of 10,000 samples (5,000 laminar and 5,000 turbulent) with 14 features per sample, including spatial coordinates (x, y), velocity components (u, v), pressure (p), velocity gradients, and a categorical flow_type label.
It was generated using simplified Navier-Stokes-based simulations:
• Laminar flow based on the analytical Poiseuille solution with added noise.
• Turbulent flow evolved with a basic Navier-Stokes solver and random perturbations.
This dataset provides a direct mathematical connection to the Navier-Stokes equations that underpin the TRNS stochastic damping operator. It serves as an excellent testbed for evaluating denoising performance on velocity and pressure fields in fluid dynamics applications.
Velocity components (particularly u and v) were selected for this embodiment because they contain meaningful flow structures mixed with numerical noise and regime transitions — conditions representative of real-world challenges in propulsion systems, compressors, ducts, and aerodynamic design.
Denoised with TRNS
Performance Comparison
Performance ranges shown are typical values reported in literature and industry benchmarks for each method. Actual results vary by application and implementation.
Why TRNS Numbers Are Superior in Practice
TRNS achieves a strong 6.10× noise reduction while respecting the underlying physics of fluid flow. This makes it particularly valuable for post-processing CFD results in propulsion, aerospace, and turbomachinery applications, where preserving accurate velocity and pressure structures is critical for analysis and design validation.
Citation
Allanatrix. (2024). Computational Fluid Dynamics [Dataset]. Kaggle. Retrieved from https://www.kaggle.com/datasets/allanwandia/computational-fluid-dynamics
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 2 of 7
Fluid Dynamics & Propulsion
Gas Turbine CO and NOx Emission
Dataset Provenance
The dataset used in this demonstration is the Gas Turbine CO and NOx Emission Data Set, publicly available through the UCI Machine Learning Repository. It contains real operational measurements collected from an industrial gas turbine.Description
This dataset was collected from a real industrial gas turbine operating at full load over a one-year period. It includes approximately 367,000 hourly averaged records with key variables such as CO (Carbon Monoxide) and NOx (Nitrogen Oxides) emissions, along with ambient conditions (temperature, pressure, humidity) and turbine performance metrics.
The data reflects realistic operating conditions, including steady-state operation, transient events (load changes, startup/shutdown cycles), and natural sensor noise.
CO and NOx emission signals were selected for this embodiment because they are highly challenging — spiky, non-stationary, and mixed with operational and environmental noise. This dataset provides an excellent real-world testbed for evaluating the TRNS stochastic damping operator in gas turbine applications, where preserving critical combustion events while reducing noise is essential for emissions monitoring, combustion optimization, fault detection, and regulatory compliance.
Denoised with TRNS
Performance Comparison
Performance ranges shown are typical values reported in literature and industry benchmarks for each method. Actual results vary by application and implementation.
Why TRNS Numbers Are Superior in Practice
Emission signals contain important short-duration spikes that indicate combustion behavior. TRNS removes noise effectively while respecting these real physical events — something many heavier ML models tend to oversmooth.
This balanced 2.17× reduction delivers practical value by preserving critical transients needed for combustion optimization, fault detection, and regulatory compliance in gas turbine systems.
Citation
Tüfekci, P., & Kaynak, A. (2019). Gas Turbine CO and NOx Emission Data Set [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C5WC95
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 3 of 7
Fluid Dynamics & Propulsion
Gas Turbine Engine Fault Detection
Dataset Provenance
The dataset used in this demonstration is the Gas Turbine Engine Fault Detection Dataset, publicly available on Kaggle. It contains simulated yet realistic sensor readings and operational parameters from a gas turbine system.Description
This dataset consists of 1,386 records with multiple sensor channels, including temperatures (inlet/outlet), pressures, vibration levels, RPM, fuel flow rates, power output, and derived performance metrics. It includes both normal operation and injected fault conditions under varying load scenarios.
The data simulates realistic physical phenomena such as combustion dynamics, thermodynamic processes, mechanical vibrations, and fluid flow behavior typical of high-performance gas turbines. Realistic sensor noise and measurement variations are present, making it highly representative of field-deployed turbine monitoring systems.
Denoised with TRNS
Performance Comparison
Performance ranges shown are typical values reported in literature and industry benchmarks for each method. Actual results vary by application and implementation.
Why TRNS Numbers Are Superior in Practice
Advanced ML methods may achieve higher raw RMS numbers but frequently oversmooth critical transients and fault precursors. TRNS delivers a balanced 3.27× reduction that removes noise while respecting the underlying physics of gas turbine operation. This makes it especially valuable for predictive maintenance and early fault detection in propulsion and energy systems.
Citation
Ziya. (2024). Gas Turbine Engine Fault Detection Dataset [Dataset]. Kaggle. Retrieved from https://www.kaggle.com/datasets/ziya07/gas-turbine-engine-fault-detection-dataset
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 4 of 7
Fluid Dynamics & Propulsion
NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) Turbofan Engine Degradation Simulation Dataset, FD001 Subset
Data Provenance
The dataset used in this demonstration is the NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) Turbofan Engine Degradation Simulation Dataset, FD001 Subset. It is one of the most widely recognized benchmarks in Prognostics and Health Management (PHM) and Remaining Useful Life (RUL) prediction research.Description
This dataset was generated using NASA’s high-fidelity C-MAPSS simulation tool, which models realistic thermodynamic, mechanical, and control system dynamics of a large commercial turbofan engine. It includes run-to-failure trajectories with realistic sensor noise and manufacturing variations.
The FD001 subset (used in this embodiment) contains 100 training trajectories under a single operating condition with High-Pressure Compressor (HPC) degradation. Sensor 12 (HPC Outlet Pressure) was selected because it clearly shows long-term degradation trends mixed with high-frequency noise, making it an ideal test case for the TRNS stochastic damping operator.
This dataset closely mirrors real-world signals encountered in commercial aircraft engine monitoring systems used by major OEMs (GE, Pratt & Whitney, Rolls-Royce) and airlines. It remains the international standard benchmark for evaluating prognostic and health monitoring algorithms in aerospace applications.
Denoised with TRNS
Performance Comparison
Performance ranges shown are typical values reported in literature and industry benchmarks for each method. Actual results vary by application and implementation.
Why TRNS Numbers Are Superior in Practice
While some ML approaches can achieve higher raw RMS numbers, they frequently oversmooth the signal — removing not just noise but also legitimate degradation trends and fault precursors essential for accurate RUL prediction. TRNS delivers a balanced 2.4× noise reduction while respecting the underlying physics of turbofan engine operation.
Citation
Saxena, A., Goebel, K., Simon, D., & Eklund, N. (2008). Damage Propagation Modeling for Aircraft Engine Run-to-Failure Simulation. In Proceedings of the 1st International Conference on Prognostics and Health Management (PHM ’08), Denver, CO, USA.
Dataset Reference Turbofan Engine Degradation Simulation Data Set. NASA Prognostics Center of Excellence (PCoE), NASA Ames Research Center, Moffett Field, CA. Available at: https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 5 of 7
Fluid Dynamics & Propulsion
NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) Turbofan Engine Degradation Simulation Dataset, FD002 Subset
Data Provenance
The dataset used in this demonstration is the FD002 subset of the NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) Turbofan Engine Degradation Simulation Dataset.Description
FD002 introduces six different operating conditions (varying altitude, Mach number, and throttle settings) while maintaining a single fault mode (High-Pressure Compressor degradation). It contains 260 training trajectories with realistic sensor noise and manufacturing variations.
Sensor 12 (HPC Outlet Pressure) was selected because it exhibits clear long-term degradation trends mixed with high-frequency noise across changing flight regimes. This subset tests the ability of denoising algorithms to generalize across different operational environments, closely mirroring real-world commercial aircraft operations where engines frequently transition between flight phases.
This dataset serves as a challenging benchmark for evaluating robustness under variable operating conditions.
Denoised with TRNS
Performance Comparison
Performance ranges shown are typical values reported in literature and industry benchmarks for each method. Actual results vary by application and implementation.
Why TRNS Numbers Are Superior in Practice
Achieving nearly 12× noise reduction across varying flight conditions while preserving degradation trends is particularly valuable for RUL prediction and engine health monitoring in real aircraft operations. TRNS delivers this balanced performance in a lightweight, training-free package suitable for onboard deployment.
Citation
Saxena, A., Goebel, K., Simon, D., & Eklund, N. (2008). Damage Propagation Modeling for Aircraft Engine Run-to-Failure Simulation. In Proceedings of the 1st International Conference on Prognostics and Health Management (PHM ’08), Denver, CO, USA.
Dataset Reference Turbofan Engine Degradation Simulation Data Set. NASA Prognostics Center of Excellence (PCoE), NASA Ames Research Center. Available at: https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 6 of 7
Fluid Dynamics & Propulsion
NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) Turbofan Engine Degradation Simulation Dataset, FD003 Subset
Data Provenance
Brief Provenance The dataset used in this demonstration is the FD003 subset of the NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) Turbofan Engine Degradation Simulation Dataset.Description FD003 uses a single operating condition but introduces two simultaneous fault modes (High-Pressure Compressor degradation + Fan degradation). It contains 100 training trajectories with realistic sensor noise.
Sensor 12 (HPC Outlet Pressure) was selected as it is sensitive to both fault modes and displays clear long-term degradation trends. This subset is particularly valuable for testing denoising performance when multiple failure mechanisms are active at the same time — a common scenario in real aircraft engines.
FD003 provides an important test of an algorithm’s ability to preserve critical degradation signals in the presence of compounded faults.
Denoised with TRNS
Performance Comparison
Performance ranges shown are typical values reported in literature and industry benchmarks for each method. Actual results vary by application and implementation.
Why TRNS Numbers Are Superior in Practice
TRNS delivers superior noise reduction while maintaining the long-term degradation trends that are essential for accurate Remaining Useful Life (RUL) prediction in aircraft engine prognostics. Unlike conventional denoising methods that can distort or flatten these critical trends, TRNS provides balanced regularization that improves signal clarity without sacrificing the underlying physics needed for reliable fault prediction and health management.
Citation
Saxena, A., Goebel, K., Simon, D., & Eklund, N. (2008). Damage Propagation Modeling for Aircraft Engine Run-to-Failure Simulation. In Proceedings of the 1st International Conference on Prognostics and Health Management (PHM ’08), Denver, CO, USA.
Dataset Reference Turbofan Engine Degradation Simulation Data Set. NASA Prognostics Center of Excellence (PCoE), NASA Ames Research Center. Available at: https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 7 of 7
Fluid Dynamics & Propulsion
NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) Turbofan Engine Degradation Simulation Dataset, FD004 Subset
Data Provenance
The dataset used in this demonstration is the FD004 subset of the NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) Turbofan Engine Degradation Simulation Dataset.Description
FD004 is the most complex and realistic subset, combining six operating conditions with two simultaneous fault modes (High-Pressure Compressor + Fan degradation). It contains 248–249 training trajectories and represents the highest level of difficulty in the CMAPSS suite.
Sensor 12 (HPC Outlet Pressure) was selected because it is highly responsive to both fault modes across varying flight conditions. This subset most closely mirrors real-world commercial turbofan engine operation, where engines experience changing environmental and load conditions while potentially developing multiple faults.
FD004 serves as the ultimate benchmark for evaluating the robustness, generalization, and practical applicability of denoising algorithms in aerospace propulsion systems.
Denoised with TRNS
Performance Comparison
Performance ranges shown are typical values reported in literature and industry benchmarks for each method. Actual results vary by application and implementation.
Why TRNS Numbers Are Superior in Practice
TRNS achieves exceptional 11.94× noise reduction while maintaining the critical long-term degradation trends needed for accurate Remaining Useful Life (RUL) prediction. In the highly challenging FD004 environment — with 6 operating conditions and 2 simultaneous fault modes — TRNS demonstrates strong generalization without oversmoothing important engine behavior.
Unlike many hybrid and deep learning approaches that can achieve high RMS numbers but often lose meaningful degradation signals, TRNS delivers a balanced, physics-based solution that preserves the operational dynamics essential for reliable prognostics in real-world multi-regime turbofan engine applications.
Citation
Saxena, A., Goebel, K., Simon, D., & Eklund, N. (2008). Damage Propagation Modeling for Aircraft Engine Run-to-Failure Simulation. In Proceedings of the 1st International Conference on Prognostics and Health Management (PHM ’08), Denver, CO, USA.
Dataset Reference Turbofan Engine Degradation Simulation Data Set. NASA Prognostics Center of Excellence (PCoE), NASA Ames Research Center. Available at: https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 1 of 3
Oil & Gas Pipeline Flow
Note In our demonstrations, we tune TRNS to achieve the best overall balance between noise reduction and preservation of real-world signal dynamics, rather than pursuing the absolute highest RMS number possible.
While TRNS parameters can be adjusted to reach higher RMS reductions (sometimes comparable to advanced machine learning methods), we intentionally prioritize practical performance. Excessive denoising frequently leads to oversmoothing, which can remove important physical transients, degradation trends, or operational signatures critical for real applications such as fault detection, predictive maintenance, and process control.
TRNS is designed to deliver strong, usable results that respect the underlying physics of the system.
Petrobras 3W Dataset (also known as 3W Dataset 2.0.0)
Dataset Provenance
The dataset used in this demonstration is the Petrobras 3W Dataset (also known as 3W Dataset 2.0.0), a realistic multivariate time-series dataset from offshore oil wells.Description
The 3W Dataset contains 1,984 instances (CSV files) of multivariate time-series data collected from Brazilian offshore oil wells. It includes both real operational data and high-fidelity simulations, with labeled undesirable events such as slugging, spikes, stuck pipe, and other flow anomalies.
Key sensors include Permanent Downhole Gauge (P-PDG) pressure and other critical measurements. The data reflects realistic conditions in offshore production, including sensor artifacts, multiphase flow turbulence, gas bubbles, pump interference, and environmental factors.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
TRNS achieves a strong 3.91× RMS noise reduction while effectively preserving critical pressure transients, flow events, and operational signatures that are essential for flow assurance and anomaly detection in offshore oil wells.
In the challenging environment of the Petrobras 3W dataset — with multiphase flow turbulence, gas bubbles, pump interference, and sensor artifacts — TRNS demonstrates excellent preservation of real dynamics without the oversmoothing often seen in heavier machine learning approaches. This balance of aggressive noise suppression and faithful signal retention makes TRNS particularly well-suited for real-time pipeline monitoring and predictive maintenance applications in the oil & gas industry.
Citation
Melo, A. F. R. R., et al. (2025). 3W Dataset 2.0.0: A realistic and public dataset with rare undesirable real events in oil wells. Scientific Data.
Original Publication Melo, A. F. R. R., et al. (2019). A realistic and public dataset with rare undesirable real events in oil wells. Journal of Petroleum Science and Engineering, 182, 106223. https://doi.org/10.1016/j.petrol.2019.106223
Dataset References
• Official Repository: https://github.com/petrobras/3W
• Kaggle Mirror: https://www.kaggle.com/datasets/afrniomelo/3w-dataset
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 2 of 3
Oil & Gas Pipeline Flow
Oil Well Operation Parameters (Well #807)
Dataset Provenance
The dataset used in this demonstration is the Oil Well Operation Parameters (2013–2021) – Well #807, publicly available on Kaggle. It contains daily operational data from a real Siberian oil well.Description
This dataset covers daily operational records from Well #807, drilled in 2013 in a northern Russian oil field. It spans 2013 to 2021 and includes key production parameters such as oil volume, gas volume, water volume, water cut (%), working hours, dynamic level, and reservoir pressure.
The data reflects real-world reservoir behavior, including natural production decline, pump operations, and environmental influences. Reservoir pressure and related signals contain realistic sensor noise and operational variations typical of field-deployed monitoring systems.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
Reservoir pressure changes slowly over long periods. In this case, TRNS delivers a balanced 1.07× RMS reduction that removes sensor and operational noise while carefully preserving the important long-term geological and production trends.
Rather than chasing the highest possible RMS number, we prioritize maintaining real reservoir dynamics. This makes TRNS more practical for reservoir monitoring and flow assurance than methods that risk oversmoothing critical slow-varying signals.
Citation
Zalevskikh, R. (2022). Oil well operation parameters (2013-2021) [Dataset]. Kaggle. Retrieved from https://www.kaggle.com/datasets/ruslanzalevskikh/oil-well
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 3 of 3
Oil & Gas Pipeline Flow
Predictive Maintenance Oil & Gas Pipeline
Data Provenance
The dataset used in this demonstration is the Predictive Maintenance Oil & Gas Pipeline Dataset, publicly available on Kaggle. It contains real-world operational sensor readings from oil and gas pipelines.
Description
This dataset includes 1,000 records of operational sensor data from pipeline systems, with key variables such as Maximum Pressure (psi), flow-related measurements, temperature, corrosion impact estimates, and maintenance labels.
The data simulates realistic pipeline conditions encountered in upstream and midstream operations, including pressure transients, sensor noise, and operational variability typical of multiphase flow in oil & gas pipelines. It is highly representative of challenges faced in commercial SCADA and IoT-based pipeline monitoring systems.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
This real-data example using actual pipeline sensor readings demonstrates that TRNS delivers a strong 2.75× RMS noise reduction while effectively preserving critical operational dynamics such as pressure fluctuations, flow variations, and transient events that are essential for flow assurance, leak detection, and predictive maintenance in oil and gas pipelines.
In the challenging real-world environment of pipeline monitoring — with sensor noise, pump interference, and multiphase flow turbulence — TRNS achieves a practical balance that removes unwanted noise without oversmoothing important physical signatures. Many advanced machine learning approaches can report higher RMS numbers but frequently remove legitimate operational transients, reducing their usefulness for real-time decision making.
Citation
Waqas, M. (2024). Predictive Maintenance Oil and Gas Pipeline Data [Dataset]. Kaggle. https://www.kaggle.com/datasets/muhammadwaqas023/predictive-maintenance-oil-and-gas-pipeline-data
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 1 of 1
Consumer Wearables
Microsoft Scalable Noisy Speech Dataset (MS-SNSD)
Dataset Provenance
The dataset used in this demonstration is from the Microsoft Scalable Noisy Speech Dataset (MS-SNSD). Specifically, we used a clean speech signal mixed with real-world babble noise, which is representative of challenging acoustic environments such as crowded offices, public transport, or busy public spaces.
Description
This demonstration applies the TRNS stochastic damping operator to real noisy speech data (babble noise mixed with clean speech). TRNS achieves strong noise reduction while preserving speech intelligibility and natural temporal structure. The result highlights TRNS’s potential for real-time audio processing in consumer devices such as headphones, earbuds, and hearing aids.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
TRNS delivers a strong 8.35× RMS noise reduction on challenging babble noise while maintaining clear speech intelligibility and natural sound quality.
In real-world audio applications, simply maximizing numerical noise reduction often leads to oversmoothing that distorts speech and reduces usability. TRNS is intentionally balanced to remove unwanted background noise while preserving the important characteristics of human speech — offering practical, high-performance enhancement suitable for consumer audio devices.
Citation
Reddy, C. K. A., et al. (2020). "The INTERSPEECH 2020 Deep Noise Suppression Challenge." Proc. Interspeech 2020, pp. 2492–2496.
Microsoft Scalable Noisy Speech Dataset (MS-SNSD). Available at: https://github.com/microsoft/MS-SNSD
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 1 of 10
Medical
Wearable Health Monitoring with TRNS Photoplethysmography (PPG) Denoising Demonstration (TROIKA Dataset)
Dataset Provenance
The dataset used in this demonstration is from the TROIKA dataset, part of the IEEE Signal Processing Cup 2015. It contains real wrist-worn PPG recordings captured during physical exercise.Description
This dataset includes simultaneous PPG and three-axis accelerometer signals recorded from subjects performing intensive physical activity (walking and running). The recordings contain severe motion artifacts, sensor noise, and baseline wander — conditions highly representative of real-world challenges in wearable heart rate monitoring, heart-rate variability (HRV) analysis, and peripheral perfusion assessment.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
TRNS achieves strong 7.19x noise reduction while preserving the essential pulsatile waveform morphology critical for accurate heart rate and HRV estimation. This makes it particularly valuable for wearable health devices, where motion artifacts frequently degrade signal quality during daily activities and exercise.
TRNS is training-free and computationally lightweight, making it highly suitable for real-time implementation on low-power wearable processors.
Citation
Zhang, Z., Pi, Z., & Liu, B. (2015). TROIKA: A general framework for heart rate monitoring using wrist-type photoplethysmographic signals during intensive physical exercise. IEEE Transactions on Biomedical Engineering, 62(2), 522–531. https://doi.org/10.1109/TBME.2014.2359372
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 2 of 10
Medical
Infusion Pump Rate Denoising with TRNS Real-World Smart Infusion Pump Signal Enhancement Demonstration
Dataset Provenance
The dataset used in this demonstration is from the VitalDB high-fidelity multi-parameter vital signs database, publicly available on PhysioNet. Specifically, we used Case 16 (perioperative surgical patient) and the track Orchestra/PPF20_RATE (real smart infusion pump delivery rate).Description
VitalDB contains real intraoperative vital signs and device data collected from surgical patients. The infusion pump rate signal includes clinically important features such as steady delivery rates, bolus events, and step changes, contaminated by sensor noise, quantization effects, and delivery irregularities typical of smart infusion pumps.
The raw infusion pump flow rate signal was selected because it contains critical therapeutic delivery information mixed with real-world noise — conditions representative of challenges in accurate drug administration, occlusion detection, under-infusion alerts, and overall patient safety in hospital settings.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
TRNS achieves a strong 1.89× noise reduction while respecting the underlying mechanics of infusion pump delivery. This makes it particularly valuable for real-time processing in smart infusion pumps, where preserving accurate delivery rates, bolus peaks, and detecting clinically dangerous conditions (occlusions, free-flow, under-delivery) is critical for patient safety.
In our demonstrations, we tune TRNS to achieve the best overall balance between noise reduction and preservation of real-world delivery dynamics, rather than pursuing the absolute highest RMS number possible.
While TRNS parameters can be adjusted to reach higher RMS reductions, we intentionally prioritize practical performance. Excessive denoising frequently leads to oversmoothing, which can mask important flow variations or bolus events critical for safe medication administration.
TRNS is designed to deliver strong, usable results that respect the underlying physics and clinical requirements of infusion therapy systems.
Citation
Lee, H., & Jung, C. (2022). VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients (version 1.0.0). PhysioNet. https://doi.org/10.13026/czw8-9p62
Lee, HC., Park, Y., Yoon, S.B. et al. VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients. Sci Data 9, 279 (2022). https://doi.org/10.1038/s41597-022-01377-6
Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation, 101(23), e215–e220.
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 3 of 10
Medical
Real In-Vivo Pre-Beamformed Ultrasound RF Channel Data from the PICMUS 2016 Challenge (Carotid Artery Scan of a Human Subject)
Dataset Provenance
The dataset used in this demonstration is real in-vivo pre-beamformed ultrasound RF channel data from the PICMUS 2016 challenge (carotid artery scan of a human subject).
Description
This demonstration applies the TRNS stochastic damping operator to real in-vivo ultrasound RF A-line data from a human carotid artery. The raw signals contain typical electronic noise and high-frequency fluctuations. TRNS achieves an 8.27× RMS noise reduction while preserving clinically important echo structures and tissue interfaces essential for high-quality beamformed imaging.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
In medical ultrasound imaging, preserving fine tissue structures and echo details is critical for diagnostic accuracy. TRNS delivers a strong 8.27× RMS noise reduction while maintaining the integrity of clinically relevant echo reflectors and interfaces.
Many advanced machine learning approaches can achieve higher numerical reductions but frequently oversmooth important anatomical features, reducing image quality and diagnostic confidence. TRNS provides a balanced, physics-based solution that prioritizes real-world clinical utility in real-time ultrasound systems.
Citation
PICMUS 2016 In-Vivo Dataset. CREATIS Laboratory (INSA Lyon), IEEE International Ultrasonics Symposium 2016 Challenge. Available at: https://www.creatis.insa-lyon.fr/Challenge/IEEEIUS2016/
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 4 of 10
Medical
Real ECG Motion Artifact Denoising Demonstration
Dataset Provenance
The dataset used in this demonstration is the Motion Artifact Contaminated ECG Database (macecgdb) from PhysioNet, containing real single-channel ECG recordings with heavy motion artifacts collected from subjects performing physical activities.Description
This demonstration applies the TRNS stochastic damping operator to real-world motion-contaminated ECG signals. The raw traces contain severe motion artifacts, baseline wander, and muscle noise typical of ambulatory and wearable monitoring. TRNS achieves a 1.40× RMS noise reduction while preserving clinically critical features such as QRS complexes, P-waves, and overall waveform morphology essential for accurate heart rate and arrhythmia detection.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
In ECG monitoring — especially wearable and ambulatory devices — preserving true cardiac features while removing motion artifacts is critical for reliable diagnosis and reducing false alarms. TRNS delivers a balanced 1.40× RMS noise reduction while maintaining the integrity of physiological waveforms.
Many advanced machine learning approaches can achieve higher numerical reductions but frequently distort or oversmooth important cardiac features, leading to reduced clinical reliability. TRNS provides a lightweight, physics-based solution that prioritizes real-world clinical utility in challenging real-patient environments.
Citation
Behravan, V., Glover, N. E., Farry, R., Shoaib, M., & Chiang, P. Y. (2015). Rate-Adaptive Compressed-Sensing and Sparsity Variance of Biomedical Signals. IEEE International Conference on Body Sensor Networks (BSN).
PhysioNet. Motion Artifact Contaminated ECG Database (version 1.0.0). https://physionet.org/content/macecgdb/1.0.0/
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 5 of 10
Medical
Chemotherapy Infusion Pump Signal (Synthetic Dataset)
Dataset Provenance
The dataset used in this demonstration is a high-fidelity synthetic Chemotherapy Infusion Flow dataset specifically engineered for this patent embodiment.
Description
This demonstration applies the TRNS stochastic damping operator to realistic synthetic chemotherapy infusion pump signals. The synthetic data simulates a steady baseline infusion rate of 50 mL/h with slow physiological variations and realistic high-frequency artifacts from pump mechanics and sensor noise. TRNS achieves a +19.2 dB SNR improvement and 9.2× RMS error reduction compared to the known ground-truth clean signal.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
In critical medical applications such as chemotherapy infusion monitoring, preserving the true underlying flow trend is more important than simply maximizing numerical noise reduction. TRNS delivers a strong 9.2× RMS error reduction while faithfully maintaining the steady delivery rate and slow physiological variations essential for safe and accurate infusion.
Many advanced machine learning approaches can report higher RMS numbers but frequently oversmooth clinically relevant signals, potentially masking important anomalies. TRNS provides a balanced, physics-based solution that prioritizes real-world usability and patient safety in oncology settings.
Citation
Meadows, J. (2026). Synthetic Chemotherapy Infusion Flow Dataset for TRNS Validation [Synthetic Dataset]. Generated by Jennifer Meadows for Non-provisional Patent Application #19/671,179. Available via associated Colab notebook.
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 6 of 10
Medical
Hemodialysis Arterial Pressure (Synthetic Dataset)
Dataset Provenance
The dataset used in this demonstration is a high-fidelity synthetic Hemodialysis Arterial Pressure dataset specifically engineered for this patent embodiment.
Description
This demonstration applies the TRNS stochastic damping operator to realistic synthetic arterial blood line pressure signals from a hemodialysis machine. The synthetic data simulates a baseline arterial pressure of approximately 120 mmHg with slow physiological drift, periodic high-amplitude roller pump oscillations, and realistic sensor noise and patient movement artifacts. TRNS achieves a +18.3 dB SNR improvement and 8.2× RMS error reduction compared to the known ground-truth clean signal.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
In hemodialysis monitoring, preserving the true physiological pressure trends is critical for patient safety. TRNS delivers a strong 8.2× RMS error reduction while maintaining the slow-varying arterial pressure dynamics needed to detect important clinical events such as hypotension, occlusions, or clotting.
Citation
Meadows, J. (2026). Synthetic Hemodialysis Arterial Pressure Dataset for TRNS Validation [Synthetic Dataset]. Generated by Jennifer Meadows for Non-provisional Patent Application #19/671,179. Available via associated Colab notebook.
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 7 of 10
Medical
Enteral Nutrition Delivery Signal Denoising with TRNS Realistic Feeding Pump Flow Rate Enhancement Demonstration
Dataset Provenance
This demonstration uses a high-fidelity synthetic enteral feeding pump flow rate dataset specifically generated to simulate real clinical conditions in enteral nutrition therapy.
Description
The synthetic dataset represents a 12-hour continuous enteral feeding session with the following realistic characteristics:
• Nominal continuous delivery rate of 60 mL/h (typical for adult patients)
• Slow diurnal physiological variation (~8-hour cycle)
• Occasional small bolus deliveries
• Periodic roller pump mechanical artifacts
• Gaussian sensor noise and occasional occlusion-like transients
The raw flow rate signal was selected because it contains clinically important delivery patterns mixed with mechanical and sensor noise — conditions representative of real-world challenges in enteral nutrition pumps, including accurate volume tracking, occlusion detection, under-delivery alerts, and free-flow prevention.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
TRNS achieves a strong 5.7× RMS error reduction (verified against ground truth) while respecting the underlying mechanics of enteral feeding delivery. This makes it particularly valuable for real-time processing in enteral feeding pumps, where preserving accurate steady-state flow, bolus events, and detecting clinically dangerous conditions (occlusions, under-infusion, free-flow) is critical for patient safety.
In our demonstrations, we tune TRNS to achieve the best overall balance between noise reduction and preservation of real-world delivery dynamics, rather than pursuing the absolute highest RMS number possible.
Note While TRNS parameters can be adjusted to reach higher RMS reductions, we intentionally prioritize practical performance. Excessive denoising frequently leads to oversmoothing, which can mask important flow variations or occlusion signatures critical for safe nutritional delivery.
TRNS is designed to deliver strong, usable results that respect the underlying physics and clinical requirements of enteral feeding systems.
Citation
Meadows, J. (2026). Synthetic Enteral Feeding Pump Flow Rate Dataset for TRNS Demonstration [Synthetic Dataset]. Generated for non-provisional patent application #19/671,179.
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 8 of 10
Medical - Sleep Apnea
Sleep Apnea ECG Signal Denoising with TRNS Real-World Ambulatory ECG Enhancement Demonstration
Dataset Provenance
The dataset used in this demonstration is the Apnea-ECG Database, publicly available on PhysioNet. It contains real overnight ECG recordings from patients with suspected obstructive sleep apnea, including expert annotations for apnea events.Description
This dataset includes multi-hour ECG recordings sampled at 100 Hz, capturing typical real-world challenges in ambulatory monitoring such as baseline wander, motion artifacts, electrode noise, and muscle interference. For this embodiment, we used Record a01 — a representative overnight recording commonly used for sleep apnea and heart rate variability research.
The raw ECG waveform contains clinically critical features (QRS complexes, P-waves, and T-waves) mixed with significant non-stationary noise. This represents typical conditions encountered in wearable sleep monitors, Holter devices, and clinical cardiology.
The ECG signal (normalized) was selected because it contains meaningful cardiac electrical activity mixed with physiological and motion artifacts — conditions representative of real-world challenges in sleep apnea detection, arrhythmia screening, and cardiovascular monitoring.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
TRNS achieves a strong 1.68× noise reduction while respecting the underlying electrophysiology of the heart. This makes it particularly valuable for real-time processing in wearable devices and bedside monitors, where preserving QRS morphology, P-waves, and T-waves is critical for accurate apnea detection and heart rate variability analysis.
In our demonstrations, we tune TRNS to achieve the best overall balance between noise reduction and preservation of real-world clinical features, rather than pursuing the absolute highest RMS number possible.
While TRNS parameters can be adjusted to reach higher RMS reductions, we intentionally prioritize practical performance. Excessive denoising frequently leads to oversmoothing, which can distort important cardiac transients essential for medical diagnosis.
TRNS is designed to deliver strong, usable results that respect the underlying physiological characteristics of the signal.
Citation
Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation, 101(23), e215–e220. Dataset: Apnea-ECG Database. Available at: https://physionet.org/content/apnea-ecg/
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 9 of 10
Medical - Sleep Apnea
CPAP Respiratory Flow Denoising with TRNS Real-World Respiratory Signal Enhancement Demonstration
Dataset Provenance
The dataset used in this demonstration is the CPAP Pressure and Flow Data from a Local Trial of 30 Adults at the University of Canterbury, publicly available on PhysioNet.Description
This dataset contains high-quality airway pressure and bidirectional flow measurements collected from 30 healthy adults (balanced sex, diverse ages 19–58, including smokers, vapers, and asthmatics) breathing on CPAP at two PEEP levels (4 cmH₂O and 7 cmH₂O) across multiple controlled breathing rates. Data was acquired using a custom dual-Venturi sensor system at 100 Hz.
For this embodiment, we analyzed real CPAP flow signals that contain meaningful respiratory dynamics (inspiratory/expiratory transitions, flow limitation) mixed with sensor noise, mask leaks, and movement artifacts. This represents typical conditions encountered in clinical sleep medicine and home CPAP therapy.
The raw respiratory flow signal was selected because it contains clinically important breathing patterns mixed with non-stationary noise — conditions representative of real-world challenges in CPAP optimization, work of breathing assessment, and advanced respiratory monitoring.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
TRNS achieves a strong 2.95× noise reduction while respecting the underlying physiology of respiratory flow. This makes it particularly valuable for real-time processing in CPAP devices and polysomnography (PSG) systems, where preserving accurate inspiratory/expiratory transitions and flow limitation features is critical for therapy optimization and clinical assessment.
In our demonstrations, we tune TRNS to achieve the best overall balance between noise reduction and preservation of real-world breathing dynamics, rather than pursuing the absolute highest RMS number possible.
While TRNS parameters can be adjusted to reach higher RMS reductions, we intentionally prioritize practical performance. Excessive denoising frequently leads to oversmoothing, which can remove important respiratory transients critical for accurate lung mechanics estimation and apnea detection.
TRNS is designed to deliver strong, usable results that respect the underlying physiological characteristics of the signal.
Citation
Guy, E., Knopp, J., & Chase, G. (2022). CPAP Pressure and Flow Data from a Local Trial of 30 Adults at the University of Canterbury (version 1.0.1). PhysioNet. https://doi.org/10.13026/xfae-vv63
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 10 of 10
Medical - Sleep Apnea
Sleep Apnea Nasal Airflow Denoising with TRNS Real-World Respiratory Signal Enhancement Demonstration
Dataset Provenance
The dataset used in this demonstration is a synthetic nasal airflow signal modeled after real polysomnography (PSG) recordings from sleep apnea patients. It simulates typical clinical conditions encountered in sleep medicine monitoring.Description
This synthetic dataset represents a 10-minute overnight PSG segment with realistic breathing patterns (approximately 15 breaths per minute) interrupted by multiple apneic events lasting 20–30 seconds each. The signal includes clinically relevant features such as sinusoidal breathing cycles and abrupt flatlines during apnea, corrupted by realistic artifacts: low-frequency baseline wander, broadband sensor noise, and intermittent movement spikes.
The raw nasal airflow waveform was selected because it contains critical diagnostic information (breathing rhythm and apneic cessations) mixed with non-stationary noise — conditions representative of real-world challenges in sleep apnea detection, AHI scoring, and respiratory monitoring using nasal cannula sensors.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
TRNS achieves a strong 1.50× RMS error reduction (verified against ground truth) while respecting the underlying physiology of breathing. This makes it particularly valuable for real-time processing in polysomnography systems and home sleep apnea testing devices, where preserving accurate breathing cycles and sharp apneic flatlines is critical for reliable event detection and AHI scoring.
In our demonstrations, we tune TRNS to achieve the best overall balance between noise reduction and preservation of real-world respiratory dynamics, rather than pursuing the absolute highest RMS number possible.
While TRNS parameters can be adjusted to reach higher RMS reductions, we intentionally prioritize practical performance. Excessive denoising frequently leads to oversmoothing, which can remove important apneic cessations and breathing transitions critical for accurate diagnosis in sleep medicine.
TRNS is designed to deliver strong, usable results that respect the underlying physiological characteristics of the signal.
Citation
This demonstration uses a high-fidelity synthetic nasal airflow signal carefully modeled after real clinical polysomnography (PSG) recordings to simulate typical sleep apnea scenarios.
For real-world validation and further testing, similar high-quality respiratory signals can be found in the following public repositories:• Apnea-ECG Database Goldberger, A. L., Amaral, L. A. N., Glass, L., Hausdorff, J. M., Ivanov, P. Ch., Mark, R. G., … & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation, 101(23), e215–e220. https://doi.org/10.1161/01.CIR.101.23.e215 Dataset: https://physionet.org/content/apnea-ecg/
• CPAP Pressure and Flow Data from a Local Trial of 30 Adults Guy, E., Knopp, J., & Chase, G. (2022). CPAP Pressure and Flow Data from a Local Trial of 30 Adults at the University of Canterbury (version 1.0.1). PhysioNet. https://doi.org/10.13026/xfae-vv63These datasets provide real clinical respiratory signals suitable for validating denoising methods intended for sleep apnea monitoring and CPAP therapy optimization.
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 1 of 3
Radio Frequency & Long-Range Comms
Received Signal Strength (RSS) data from the KTH/RSS
Dataset Provenance
The dataset used in this demonstration is real indoor trace, collected by a mobile robot in an indoor environment. It is part of the CRAWDAD (Community Resource for Archiving Wireless Data At Dartmouth) project.Description
This demonstration applies the TRNS stochastic damping operator to real indoor Received Signal Strength (RSS) traces. The raw signals contain significant high-frequency noise from fast fading and measurement jitter. TRNS achieves a 1.88× RMS noise reduction while preserving the important large-scale fading trends essential for wireless link quality estimation, handover decisions, and indoor localization.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
In wireless communication systems, preserving the underlying large-scale fading trends is critical for reliable link estimation and localization. TRNS delivers a balanced 1.88× RMS noise reduction while maintaining these meaningful propagation characteristics.
Many advanced machine learning approaches can achieve higher numerical reductions but frequently oversmooth important slow-fading trends, reducing their practical usefulness. TRNS provides a lightweight, physics-based solution that prioritizes real-world usability in challenging indoor radio environments.
Citation
KTH/RSS Dataset. CRAWDAD (Community Resource for Archiving Wireless Data At Dartmouth). Available at: https://crawdad.org/kth/rss/
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 2 of 3
Radio Frequency & Long-Range Comms
Real Wi-Fi Received Signal Strength (RSSI)
Dataset Provenance
The dataset used in this demonstration is a real Wi-Fi Received Signal Strength (RSSI) indoor trace collected from wireless access points in an indoor environment.Description
This demonstration applies the TRNS stochastic damping operator to real indoor Wi-Fi RSSI signals. The raw traces contain significant high-frequency noise due to fast fading, multipath propagation, and measurement jitter. TRNS achieves a 1.64× RMS noise reduction while preserving the important large-scale fading trends essential for wireless link quality estimation and indoor positioning systems.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
In wireless communication systems, preserving large-scale fading trends is critical for reliable link estimation and localization. TRNS delivers a balanced 1.64× RMS noise reduction while maintaining these meaningful propagation characteristics.
Many advanced machine learning approaches can achieve higher numerical reductions but frequently oversmooth important slow-fading trends, reducing their practical usefulness. TRNS provides a lightweight, physics-based solution that prioritizes real-world usability in challenging indoor radio environments.
Citation
Yuen, B. (2024). Wi-Fi and Bluetooth RSSI SQI Indoor Localization [Dataset]. Kaggle. https://www.kaggle.com/datasets/brosnanyuen/wi-fi-and-bluetooth-rssi-sqi-indoor-localization
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 3 of 3
Radio Frequency & Long-Range Comms
WiFi RSS Fingerprint Localization Signal Denoising Demonstration
Dataset Provenance
The dataset used in this demonstration is the WiFi RSS Fingerprint Localization Dataset, containing real indoor Received Signal Strength (RSS) measurements collected from multiple reference access points in a laboratory environment.Description
This demonstration applies the TRNS stochastic damping operator to real WiFi RSS fingerprint data. The raw signals (e.g., reference node r1) exhibit significant high-frequency noise from multipath propagation, fast fading, and measurement jitter. TRNS achieves a 3.25× RMS noise reduction while preserving the essential large-scale fading trends critical for accurate indoor localization and fingerprinting algorithms.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
In WiFi fingerprint-based indoor localization, preserving large-scale signal trends is essential for accurate position estimation and reliable system performance. TRNS delivers a strong 3.25× RMS noise reduction while maintaining these meaningful propagation characteristics.
Many advanced machine learning approaches can achieve higher numerical reductions but frequently oversmooth important spatial patterns, degrading localization accuracy. TRNS provides a lightweight, physics-based solution that prioritizes real-world practicality for indoor positioning, handover optimization, and IoT wireless systems.
Citation
Alhmiedat, T. (2023). WiFi RSS Fingerprint Dataset for Indoor Localization [Dataset]. Kaggle. https://www.kaggle.com/datasets/tareqalhmiedat/wifi-rss-fingerprint-dataset
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 1 of 3
Chemical Processing & Pharmaceuticals
Pharmaceutical Fermentation Process Monitoring with TRNS IndPenSim Penicillin Production Denoising Demonstration
Dataset Provenance
The dataset used in this demonstration is the IndPenSim (Industrial Penicillin Simulation) dataset, publicly available on Kaggle. It is a large-scale simulated biopharmaceutical manufacturing dataset based on a 100,000 litre penicillin fermentation system.Description
This dataset was generated using an advanced mathematical simulation of a penicillin fermentation process (IndPenSim). It contains 100 batches with realistic process measurements and simulated Raman spectroscopy data. The batches represent different control strategies (recipe-driven, operator-controlled, and advanced process control) and include both normal operation and fault conditions.
The reactor temperature signal was selected for this embodiment because it contains meaningful process dynamics mixed with realistic sensor and process noise — conditions highly representative of real-world challenges in biopharmaceutical manufacturing, process monitoring, predictive maintenance, and fault detection.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
TRNS achieves a strong 2.27× noise reduction while respecting the underlying physics and dynamics of biopharmaceutical fermentation processes. This makes it particularly valuable for real-time process monitoring in penicillin and other biologic drug production, where maintaining accurate temperature control and detecting subtle deviations is critical for product quality, yield, and regulatory compliance.
TRNS is training-free and lightweight, offering excellent practical value for edge deployment in biotechnology facilities.
Citation
Goldrick S., Stefan A., Lovett D., Montague G., Lennox B. (2015). The development of an industrial-scale fed-batch fermentation simulation. Journal of Biotechnology, 193:70-82.
Goldrick S., Duran-Villalobos C., Jankauskas K., Lovett D., Farid S.S., Lennox B. (2019). Modern day control challenges for industrial-scale fermentation processes. Computers and Chemical Engineering.
Dataset: IndPenSim (Industrial Penicillin Simulation). Kaggle. Available at: https://www.kaggle.com/datasets/stephengoldie/big-databiopharmaceutical-manufacturing
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 2 of 3
Chemical Processing & Pharmaceuticals
Chemical Process Monitoring with TRNS Reactor Temperature Denoising Demonstration
Dataset Provenance
The dataset used in this demonstration is the Synthetic Chemical Process Monitoring Time-Series Dataset. It is a realistic simulated industrial sensor dataset designed to emulate real-world process historian data from continuous chemical reactor systems.Description
This dataset simulates a continuous chemical reactor system with realistic industrial sensor behavior, control dynamics, seasonal effects, multiple operating regimes, and gradual fault development. It contains 10,000 time samples of reactor temperature with clear underlying process dynamics (sinusoidal variations and regime shifts) mixed with Gaussian sensor noise and sparse artifacts.
The data reflects typical challenges in industrial process monitoring, including slow drifts, operational regime transitions, and superimposed measurement noise — conditions representative of real-world chemical manufacturing, predictive maintenance, and fault detection applications.
The reactor temperature signal was selected for this embodiment because it contains meaningful process structures mixed with realistic noise, making it an excellent test case for evaluating denoising performance on industrial time-series data.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
TRNS achieves a strong 1.20× noise reduction while respecting the underlying physics and dynamics of chemical processes. This makes it particularly valuable for real-time process monitoring in chemical plants, where preserving accurate process trends and detecting subtle anomalies is critical for safety, efficiency, and product quality.
In our demonstrations, we tune TRNS to achieve the best overall balance between noise reduction and preservation of real-world process dynamics, rather than pursuing the absolute highest RMS number possible.
While TRNS parameters can be adjusted to reach higher RMS reductions, we intentionally prioritize practical performance. Excessive denoising frequently leads to oversmoothing, which can remove important process transients critical for fault detection and optimal control.
TRNS is designed to deliver strong, usable results that respect the underlying chemical and physical characteristics of the process.
Citation
Chemical Process Monitoring Time-Series Dataset (2025). Synthetic industrial chemical reactor simulation data. Kaggle. CC0: Public Domain.
Chemical Process Monitoring Time-Series Dataset
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 3 of 3
Chemical Processing & Pharmaceuticals
Chemical Process Monitoring with TRNS Tennessee Eastman Process Denoising Demonstration
Dataset Provenance
The dataset used in this demonstration is the Tennessee Eastman Process (TEP) simulation dataset, a widely recognized benchmark in chemical engineering for process monitoring, fault detection, and control system evaluation.Description
The Tennessee Eastman Process simulates a realistic industrial chemical production plant involving multiple unit operations (reactor, condenser, compressor, separator, and stripper). It contains 52 measured process variables under normal and faulty operating conditions.
For this embodiment, we applied TRNS to the variable xmeas_8 from the fault-free training dataset. This signal represents a key process measurement containing meaningful process dynamics mixed with realistic sensor and process noise — conditions representative of real-world challenges in chemical manufacturing, reactor monitoring, and industrial process control.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
TRNS achieves a strong 8.12× noise reduction while respecting the underlying physics and dynamics of chemical processes. This makes it particularly valuable for real-time process monitoring in chemical plants, where preserving accurate process trends and detecting subtle anomalies is critical for safety, efficiency, and product quality.
In our demonstrations, we tune TRNS to achieve the best overall balance between noise reduction and preservation of real-world process dynamics, rather than pursuing the absolute highest RMS number possible.
While TRNS parameters can be adjusted to reach higher RMS reductions, we intentionally prioritize practical performance. Excessive denoising frequently leads to oversmoothing, which can remove important process transients critical for fault detection and optimal control.
TRNS is designed to deliver strong, usable results that respect the underlying chemical and physical characteristics of the process.
Citation
Rieth, C. A., et al. (2017). Issues and Advances in Anomaly Detection Evaluation for Joint Human-Automated Systems. Applied Human Factors and Ergonomics Conference.
Dataset: Tennessee Eastman Process Simulation Data. Available via Harvard Dataverse: https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/6C3JR1
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 1 of 1
LiDAR & 3D Sensing
Single-Photon Counting Denoising with TRNS Quantum Photonics Embodiment
Dataset Provenance
This demonstration uses a high-fidelity synthetic single-photon counting time series specifically generated to emulate real experimental conditions in quantum photonics.Description
The synthetic dataset simulates realistic single-photon counting signals with the following characteristics:
• Background noise with Gaussian baseline (~1.25 cps)
• Multiple transient photon bursts modeled as exponential decays
• Poisson-distributed noise (standard for photon counting statistics)
• Total length: 50,000 samples
This data closely mimics real-world signals from Time-Correlated Single Photon Counting (TCSPC), quantum dot fluorescence, nitrogen-vacancy centers, and SPAD-based single-photon detectors. The raw photon count signal was selected because it contains critical transient photon arrival bursts mixed with Poisson noise — conditions representative of real challenges in quantum optics, fluorescence lifetime imaging, and single-photon detection systems.
Denoised with TRNS
Figure 1: Full Time Series (TRNSSinglePhotonFullView.png – 300 DPI)
Figure 2: Zoomed-in Peak Preservation (TRNSSinglePhotonZoom.png – 300 DPI) Samples 28,000 – 31,000
Figure 3: Additional Peak Zoom (TRNSSinglePhotonZoom2.png – 300 DPI) Samples 5,000 – 8,000
Performance Comparison
Why TRNS Numbers Are Superior in Practice
TRNS achieves a strong 2.51× RMS noise reduction while respecting the underlying Poisson statistics of single-photon detection. This makes it particularly valuable for quantum photonics applications, where preserving sharp transient photon bursts is critical for accurate timing, lifetime estimation, and single-molecule detection.
In our demonstrations, we tune TRNS to achieve the best overall balance between noise reduction and preservation of real-world photon arrival features, rather than pursuing the absolute highest RMS number possible.
While TRNS parameters can be adjusted to reach higher RMS reductions, we intentionally prioritize practical performance. Excessive denoising frequently leads to oversmoothing, which can remove important photon bursts critical for quantum sensing and imaging applications.
TRNS is designed to deliver strong, usable results that respect the underlying quantum statistics of the signal.
Citation
This demonstration uses a high-fidelity synthetic single-photon counting time series specifically engineered to emulate real experimental conditions in quantum photonics research.
For real-world validation and further testing, comparable Time-Correlated Single Photon Counting (TCSPC) datasets are publicly available, including:
• BrightEyes-TTM Datasets — raw time-tagged photon data from fluorescence lifetime imaging. Available on Zenodo: https://doi.org/10.5281/zenodo.4912656 (Rossetta et al., 2022).
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 1 of 3
Microseismic & Geothermal Monitoring
Microseismic & Earthquake Monitoring with TRNS Seismic Waveform Denoising Demonstration (1988 Spitak Armenia Earthquake)
Dataset Provenance
The dataset used in this demonstration is from the GSN stations for the 1988 Spitak Armenia Earthquake, Report Number 88-004. It contains high-quality broadband seismic recordings from the Global Seismographic Network (GSN).Description
On December 7, 1988, the devastating Spitak Earthquake struck Armenia. This dataset includes recordings from multiple GSN stations capturing the mainshock and aftershocks. The traces contain strong seismic signals mixed with ambient noise and instrument artifacts — conditions highly representative of real-world challenges in earthquake monitoring, early warning systems, and microseismic analysis.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
TRNS achieves a strong 11.39× noise reduction while preserving the essential seismic waveform characteristics and phase arrivals critical for earthquake analysis. This makes it particularly valuable for improving signal clarity in earthquake monitoring networks, aftershock detection, and seismic hazard assessment — especially in regions with high cultural or ambient noise.
TRNS is training-free and lightweight, offering excellent suitability for real-time processing on seismic stations and global monitoring arrays.
Citation
GSN stations for 1988 Spitak Armenia Earthquake. (1988). Report Number 88-004. Incorporated Research Institutions for Seismology (IRIS) Global Seismographic Network. Data available in MSEED format.
NSF SAGE: MDA : 88-004
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 2 of 3
Microseismic & Geothermal Monitoring
Microseismic & Geothermal Monitoring with TRNS Borehole Seismic Denoising Demonstration (BOSE Dataset)
Dataset Provenance
The dataset used in this demonstration is from the Bermuda Oblique Seismic Experiment (BOSE), Report Number 77-001, conducted in 1977. The data consists of active-source oblique seismic recordings using borehole seismometers.Description
The Bermuda Oblique Seismic Experiment (BOSE) was conducted at DSDP Hole 417D. It contains SEGY files with multi-channel borehole seismometer recordings. These traces capture real microseismic signals mixed with ambient noise and instrument artifacts — conditions highly representative of challenges in microseismic monitoring, geothermal reservoir characterization, induced seismicity detection, and borehole seismic analysis.
The file BOSEdepth16_SW.segy was selected for this embodiment. It contains meaningful seismic wave arrivals and low-amplitude coherent energy embedded in noisy background.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
TRNS achieves a strong 4.40× noise reduction while preserving the essential low-amplitude coherent waveforms and seismic arrivals critical for event detection and subsurface imaging. This makes it particularly valuable for microseismic monitoring in geothermal projects, carbon storage surveillance, and induced seismicity studies, where maintaining signal fidelity is essential for accurate interpretation.
TRNS is training-free and lightweight, offering excellent suitability for real-time processing on seismic arrays and edge nodes.
**Citation
Bermuda Oblique Seismic Experiment (BOSE), Report Number 77-001. Woods Hole Oceanographic Institution (WHOI). Seismic Network XC_1977. Data available through the Geothermal Data Repository and related seismic archives.
EarthScope Data Server
https://data.earthscope.org/archive/assembled/77-001/
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 3 of 3
Microseismic & Geothermal Monitoring
Geothermal Monitoring with TRNS Bottomhole Temperature Denoising Demonstration (Stanford Thermal Earth Model)
Dataset Provenance
The dataset used in this demonstration is from the Stanford Thermal Earth Model for the Conterminous United States, publicly available through the Geothermal Data Repository (DOI: 10.15121/2324793).Description
This dataset contains aggregated bottomhole temperature measurements across the United States, including location, depth, state, source, and temperature values. A physics-informed graph neural network was used to develop national temperature-at-depth maps. The raw data includes significant measurement noise and spatial variability typical of geothermal well data.
For this embodiment, the data was sorted by depth to create more coherent vertical temperature profiles before applying TRNS. This preprocessing step transforms the aggregated spatial dataset into structured depth-ordered sequences that better represent geothermal gradients and allow more effective denoising while preserving meaningful geological trends.
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
TRNS achieves a strong 21.16× noise reduction after sorting the data by depth. This significant improvement demonstrates the method’s ability to clean noisy bottomhole temperature measurements while preserving important geothermal gradients and structural features.
Such performance is particularly valuable for geothermal resource assessment, well characterization, thermal modeling, and subsurface temperature mapping — where reducing measurement noise directly improves model accuracy and exploration success.
TRNS is training-free and lightweight, making it highly suitable for integration into geothermal data processing workflows.
Citation
Aljubran, M., & Horne, R. (2024). Stanford Thermal Earth Model for the Conterminous United States [Data set]. Geothermal Data Repository. Stanford University. https://doi.org/10.15121/2324793
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page #
Category
Title
Dataset Provenance
Denoised with TRNS
Performance Comparison
Why TRNS Numbers Are Superior in Practice
Citation
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 1 of 3
Featured Datasets
NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) Turbofan Engine Degradation Simulation Dataset, FD004 Subset
Data Provenance
The dataset used in this demonstration is the FD004 subset of the NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) Turbofan Engine Degradation Simulation Dataset.Description
FD004 is the most complex and realistic subset, combining six operating conditions with two simultaneous fault modes (High-Pressure Compressor + Fan degradation). It contains 248–249 training trajectories and represents the highest level of difficulty in the CMAPSS suite.
Sensor 12 (HPC Outlet Pressure) was selected because it is highly responsive to both fault modes across varying flight conditions. This subset most closely mirrors real-world commercial turbofan engine operation, where engines experience changing environmental and load conditions while potentially developing multiple faults.
FD004 serves as the ultimate benchmark for evaluating the robustness, generalization, and practical applicability of denoising algorithms in aerospace propulsion systems.
Denoised with TRNS
Performance Comparison
Performance ranges shown are typical values reported in literature and industry benchmarks for each method. Actual results vary by application and implementation.
Why TRNS Numbers Are Superior in Practice
TRNS achieves exceptional 11.94× noise reduction while maintaining the critical long-term degradation trends needed for accurate Remaining Useful Life (RUL) prediction. In the highly challenging FD004 environment — with 6 operating conditions and 2 simultaneous fault modes — TRNS demonstrates strong generalization without oversmoothing important engine behavior.
Unlike many hybrid and deep learning approaches that can achieve high RMS numbers but often lose meaningful degradation signals, TRNS delivers a balanced, physics-based solution that preserves the operational dynamics essential for reliable prognostics in real-world multi-regime turbofan engine applications.
Citation
Saxena, A., Goebel, K., Simon, D., & Eklund, N. (2008). Damage Propagation Modeling for Aircraft Engine Run-to-Failure Simulation. In Proceedings of the 1st International Conference on Prognostics and Health Management (PHM ’08), Denver, CO, USA.
Dataset Reference Turbofan Engine Degradation Simulation Data Set. NASA Prognostics Center of Excellence (PCoE), NASA Ames Research Center. Available at: https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 2 of 3
Wearable Health Monitoring with TRNS Photoplethysmography (PPG) Denoising Demonstration (TROIKA Dataset)
Dataset Provenance
The dataset used in this demonstration is from the TROIKA dataset, part of the IEEE Signal Processing Cup 2015. It contains real wrist-worn PPG recordings captured during physical exercise.Description
This dataset includes simultaneous PPG and three-axis accelerometer signals recorded from subjects performing intensive physical activity (walking and running). The recordings contain severe motion artifacts, sensor noise, and baseline wander — conditions highly representative of real-world challenges in wearable heart rate monitoring, heart-rate variability (HRV) analysis, and peripheral perfusion assessment.
Denoised with TRNS
Performance Comparison
Performance ranges shown are typical values reported in literature and industry benchmarks for each method. Actual results vary by application and implementation.
Why TRNS Numbers Are Superior in Practice
TRNS achieves strong 7.19x noise reduction while preserving the essential pulsatile waveform morphology critical for accurate heart rate and HRV estimation. This makes it particularly valuable for wearable health devices, where motion artifacts frequently degrade signal quality during daily activities and exercise.
TRNS is training-free and computationally lightweight, making it highly suitable for real-time implementation on low-power wearable processors.
Citation
Zhang, Z., Pi, Z., & Liu, B. (2015). TROIKA: A general framework for heart rate monitoring using wrist-type photoplethysmographic signals during intensive physical exercise. IEEE Transactions on Biomedical Engineering, 62(2), 522–531. https://doi.org/10.1109/TBME.2014.2359372
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved
Page 3 of 3
Computational Fluid Dynamics (CFD) Velocity Field 6.10× RMS noise reduction
Dataset Provenance
The dataset used in this demonstration is the Computational Fluid Dynamics - Laminar vs Turbulent Flow Dataset, publicly available on Kaggle. It contains simulated 2D channel flow data generated from the Navier-Stokes equations.Description
This dataset consists of 10,000 samples (5,000 laminar and 5,000 turbulent) with 14 features per sample, including spatial coordinates (x, y), velocity components (u, v), pressure (p), velocity gradients, and a categorical flow_type label.
It was generated using simplified Navier-Stokes-based simulations:
• Laminar flow based on the analytical Poiseuille solution with added noise.
• Turbulent flow evolved with a basic Navier-Stokes solver and random perturbations.
This dataset provides a direct mathematical connection to the Navier-Stokes equations that underpin the TRNS stochastic damping operator. It serves as an excellent testbed for evaluating denoising performance on velocity and pressure fields in fluid dynamics applications.
Velocity components (particularly u and v) were selected for this embodiment because they contain meaningful flow structures mixed with numerical noise and regime transitions — conditions representative of real-world challenges in propulsion systems, compressors, ducts, and aerodynamic design.
Performance ranges shown are typical values reported in literature and industry benchmarks for each method. Actual results vary by application and implementation.
Why TRNS Numbers Are Superior in Practice
TRNS achieves a strong 6.10× noise reduction while respecting the underlying physics of fluid flow. This makes it particularly valuable for post-processing CFD results in propulsion, aerospace, and turbomachinery applications, where preserving accurate velocity and pressure structures is critical for analysis and design validation.
Citation
Allanatrix. (2024). Computational Fluid Dynamics [Dataset]. Kaggle. Retrieved from https://www.kaggle.com/datasets/allanwandia/computational-fluid-dynamics
Meadows McKnight LLC • Patent Pending • U.S. Patent Application No. 19/671,179 © 2026 All Rights Reserved