Questa è la nostra ultima selezione di pubblicazioni e brevetti in inglese sulle reti neurali, tra numerose riviste scientifiche online, classificate e focalizzate su rete neurale, neurone artificiale, epoch, architettura neurale, apprendimento automatico, apprendimento profondo e macchina vettoriale di supporto.
Motion Intention Recognition Techniques and Applications
Published on 2025-04-13 by Xu Zhang, Yonggang Qu, Gang Zhang, Zhiqiang Wang, Changbing Chen, Xin Xu @MDPI
Abstract: The global aging trend is becoming increasingly severe, and the demand for life assistance and medical rehabilitation for frail and disabled elderly people is growing. As the best solution for assisting limb movement, guiding limb rehabilitation, and enhancing limb strength, exoskeleton robots are becoming the focus of attention from all walks of life. This paper reviews the progress of research on upper limb exoskeleton robots, sEMG technology, and intention recognition technology. It analyzes [...]
Our summary: Review of research on upper limb exoskeleton robots, sEMG technology, and intention recognition technology. Analysis of literature using keyword clustering analysis. Discussion of application of sEMG technology, deep learning methods, and machine learning methods in human movement intention recognition by exoskeleton robots.
exoskeleton robots, sEMG technology, intention recognition, deep learning methods
Publication
Monitoring Opioid-Use-Disorder Treatment Adherence Using Smartwatch Gesture Recognition
Published on 2025-04-12 by Andrew Smith, Kuba Jerzmanowski, Phyllis Raynor, Cynthia F. Corbett, Homayoun Valafar @MDPI
Abstract: The opioid epidemic in the United States has significantly impacted pregnant women with opioid use disorder (OUD), leading to increased health and social complications. This study explores the feasibility of using machine learning algorithms with consumer-grade smartwatches to identify medication-taking gestures. The research specifically focuses on treatments for OUD, investigating methadone and buprenorphine taking gestures. Participants (n = 16, all female university students) simulated medic[...]
Our summary: Feasibility of using smartwatch gesture recognition to monitor medication-taking gestures for opioid use disorder treatment. High-performance machine learning algorithms analyzed data collected from female university students wearing Ticwatch smartwatches. Results show potential for enhancing medication adherence in OUD treatment.
smartwatch, gesture recognition, opioid use disorder, treatment adherence
Publication
Large-Scale Monitoring of Potatoes Late Blight Using Multi-Source Time-Series Data and Google Earth Engine
Published on 2025-03-11 by Zelong Chi, Hong Chen, Sheng Chang, Zhao-Liang Li, Lingling Ma, Tongle Hu, Kaipeng Xu, Zhenjie Zhao @MDPI
Abstract: Effective monitoring and management of potato late blight (PLB) is essential for sustainable agriculture. This study describes a methodology to improve PLB identification on a large scale. The method combines unsupervised and supervised machine learning algorithms. To improve the monitoring accuracy of the PLB regression model, the study used the K-Means algorithm in conjunction with morphological operations to identify potato growth areas. Input data consisted of monthly NDVI from Sentinel-2 an[...]
Our summary: Methodology to improve potato late blight identification on a large scale using multi-source time-series data and machine learning algorithms. Validation results show high accuracy with an F1 score of 0.95 and a validation RMSE of 20.50. The study presents a large-scale map of PLB distribution in China with an accuracy of 10 m.
monitoring, potato late blight, machine learning, Google Earth Engine
Publication
Integrating Kolmogorov–Arnold Networks with Time Series Prediction Framework in Electricity Demand Forecasting
Published on 2025-03-11 by Yuyang Zhang, Lei Cui, Wenqiang Yan @MDPI
Abstract: Electricity demand is driven by a diverse set of factors, including fluctuations in business cycles, interregional dynamics, and the effects of climate change. Accurately quantifying the impact of these factors remains challenging, as existing methods often fail to address the complexities inherent in these influences. This study introduces a time series forecasting model based on Kolmogorov–Arnold Networks (KANs), integrated with three advanced neural network architectures, Tempor[...]
Our summary: Integrating Kolmogorov-Arnold Networks with advanced neural network architectures improves accuracy, robustness, and adaptability in electricity demand forecasting. The study introduces a model based on KANs integrated with TCN, BiLSTM, and Transformer to address the complexities in forecasting UK electricity demand, showcasing the potential of KANs in predictive analytics.
Kolmogorov-Arnold Networks, Time Series Prediction Framework, Electricity Demand Forecasting, Neural Network Architectures
Publication
Takagi–Sugeno–Kang Fuzzy Neural Network for Nonlinear Chaotic Systems and Its Utilization in Secure Medical Image Encryption
Published on 2025-03-11 by Duc Hung Pham, Mai The Vu @MDPI
Abstract: This study introduces a novel control framework based on the Takagi–Sugeno–Kang wavelet fuzzy neural network, integrating brain imitated network and cerebellar network. The proposed controller demonstrates high robustness, making it an excellent candidate for handling intricate nonlinear dynamics, effectively mapping input–output relationships and efficiently learning from data. To enhance its performance, the controller’s parameters are fi[...]
Our summary: Novel control framework based on Takagi-Sugeno-Kang wavelet fuzzy neural network, high robustness, parameters fine-tuned using Lyapunov stability theory, superior learning capabilities and outstanding performance metrics, synchronization technique applied to secure transmission of medical images, experimental results confirm effectiveness and reliability.
Takagi-Sugeno-Kang, Fuzzy Neural Network, Secure Medical Image Encryption, Nonlinear Chaotic Systems
Publication
Predictive Modelling of Alkali-Slag Cemented Tailings Backfill Using a Novel Machine Learning Approach
Published on 2025-03-11 by Haotian Pang, Wenyue Qi, Hongqi Song, Haowei Pang, Xiaotian Liu, Junzhi Chen, Zhiwei Chen @MDPI
Abstract: This study utilizes machine learning (ML) techniques to predict the performance of slag-based cemented tailings backfill (CTB) activated by soda residue (SR) and calcium carbide slag (CS). An experimental database consisting of 240 test results is utilized to thoroughly evaluate the accuracy of seven ML techniques in predicting the properties of filling materials. These techniques include support vector machine (SVM), random forest (RF), backpropagation (BP), genetic algorithm optimization of BP[...]
Our summary: Utilizing ML techniques to predict CTB performance, evaluating accuracy of 7 ML techniques, developing dynamic growth model
Predictive Modelling, Machine Learning, Alkali-Slag Cemented Tailings, Backfill
Publication
User interface for machine learning model restructuring
Patent published on the 2025-03-06 in WO under Ref WO2025048813 by STEM IA INC [US] (Goldstein Adam Julian Cisneros [us])
Abstract: Described is a system for a user interface enabling restructuring of a machine learning model by accessing a machine learning model, generating a user interface depicting a graphical representation of the machine learning model, presenting the user interface to a user. The system receives a selection from the user of the user-selectable interface element, and in response to the selection from the user of the user-selectable interface element: restructures the internal architecture of the machine[...]
Our summary: System enabling user interface for restructuring machine learning model, generating graphical representation, and presenting to user.
User interface, machine learning model, restructuring, graphical representation
Patent
Changing node clusters in artificial intelligence models
Patent published on the 2025-03-06 in WO under Ref WO2025048809 by STEM AI INC [US] (Goldstein Adam Julian Cisneros [us])
Abstract: Described is a system for dynamic changing a number of groups of nodes in a machine learning model by accessing an artificial intelligence model, the artificial intelligence model being configured to both modify the network of the artificial intelligence model and perform an inference in response to receiving input data, receiving, by the artificial intelligence model, the input data, and processing the received input data using the artificial intelligence model. The processing of the input data[...]
Our summary: System for dynamic changing node clusters in artificial intelligence models, modifying network based on cluster values, generating inference output.
node clusters, artificial intelligence models, machine learning, dynamic changing
Patent