Results 231 to 240 of about 11,518 (313)

Intelligent Eye Tracker Integrated with Cylindrical Capacitive Sensors for Chronic Fatigue Assessment

open access: yesAdvanced Sensor Research, Volume 4, Issue 7, July 2025.
A wearable capacitive eye tracker for chronic fatigue assessment is presented, utilizing cylindrically shaped capacitive sensors made of a carbon nanotube‐paper composite. By integrating a novel fatigue‐induction protocol with machine learning, the device achieves 0.75‐sensitivity and 0.73‐specificity, providing a practical alternative to existing ...
Tianyi Li   +6 more
wiley   +1 more source

Prediction of induction motor faults using machine learning. [PDF]

open access: yesHeliyon
Abdulkareem A   +4 more
europepmc   +1 more source

Microwave‐Assisted One‐Pot Synthesis of Alkyl Levulinates From Post‐Harvest Vegetable Waste

open access: yesAdvanced Sustainable Systems, EarlyView.
Vegetable waste is valorized through Soxhlet extraction using H₂O₂ and heteropolyacid (HPA), followed by material characterization (XRD, FTIR, TGA, DSC). A microwave‐assisted reaction at 170 °C for 30 min with HPA and alcohol yields bio‐based esters.
Ángel G. Sathicq   +5 more
wiley   +1 more source

Accurate and Efficient Behavioral Modeling of GaN HEMTs Using An Optimized Light Gradient Boosting Machine

open access: yesAdvanced Theory and Simulations, EarlyView.
Machine Learning (ML) and optimization have permeated almost every aspect of engineering applications. Recent years have seen great traction toward ML‐based GaN HEMT modelling. However, ML‐based GaN HEMT models are mostly developed using variants of Artificial Neural Network (ANN).
Saddam Husain   +2 more
wiley   +1 more source

Fault diagnosis of a CNC hobbing cutter through machine learning using three axis vibration data. [PDF]

open access: yesHeliyon
Tambake N   +5 more
europepmc   +1 more source

Predicting Fiber Length Characteristics of Recycled Cotton and Cellulose Fiber Blends Using Machine Learning Models

open access: yesAdvanced Theory and Simulations, EarlyView.
This study explores machine learning‐driven prediction of fiber length characteristics in sustainable yarn blends made from recycled cotton and Lyocell. By analyzing empirical data through models like Random Forest and Gradient Boosting, and interpreting results with SHAP, key fiber length features from the Staple Diagram and Fibrogram are identified ...
Tuser Tirtha Biswas   +2 more
wiley   +1 more source

Home - About - Disclaimer - Privacy