Network Model Research Articles

Research on optimizing the propagation path search of individualized products with multi-source design changes

Abstract The individualization and diversification of customer requirements are gradually affecting the product design and manufacturing process, and the production mode of enterprises is evolving towards customer-oriented mass individualized customization. The change in customer requirements is inevitable in the process of individualized product design, which is the key factor leading to the change in product design. This paper establishes the standard of individualized product parts and components association relationship through correlation analysis, and constructs the individualized product parts and components association network model based on the complex network theory; on this basis, comprehensively considering the influence of parts nodes and association relationship in the complex network, it calculates the intensity of change propagation through the node importance degree and the probability of change propagation, and carries out the search for multi-source design change propagation paths through the improved ant colony algorithm, and evaluates the influence of the change of customer requirement by taking the change rate of the network as the evaluation index, to help enterprises to decide the request.

Algorithm for simulating calligrapher’s stroke features using neural networks

In the field of calligraphy art, simulating the stroke features of calligraphers has always been a challenging task. Traditional methods often rely on manually designed rules or feature extraction algorithms, which are difficult to accurately capture calligraphy details and time-consuming. This article aimed to explore a more effective method to simulate the stroke features of calligraphers using neural network technology. This article mainly explored the simulation algorithm of calligrapher stroke features based on neural networks, including calligrapher stroke feature statistics, calligrapher stroke feature abstraction, and calligrapher stroke feature extraction. By using Convolutional Neural Network (CNN) to learn and analyze calligraphy works, a better performance neural network model was established to achieve automatic recognition and classification of calligrapher stroke features. By continuously optimizing model parameters, the accuracy of calligrapher stroke feature simulation can be improved. The average similarity rates for imitating stroke features of five calligraphers (regular script, cursive script, clerical script, seal script, and running script) using Artificial Neural Network (ANN) were 0.72, 0.62, 0.40, 0.33, and 0.53, respectively. The average similarity rates for imitating stroke features of 5 calligraphers (regular script, cursive script, clerical script, seal script, and running script) using CNN were 0.93, 0.78, 0.87, 0.67, and 0.80, respectively. The research results of this article promoted the inheritance and innovation of calligraphy art, and expanded the expression forms and application fields of calligraphy art.

Advanced Modulation Formats for 400 Gbps Optical Networks and AI-Based Format Recognition

The integration of communication and sensing (ICAS) in optical networks is an inevitable trend in building intelligent, multi-scenario, application-converged communication systems. However, due to the impact of nonlinear effects, co-fiber transmission of sensing signals and communication signals can cause interference to the communication signals, leading to an increased bit error rate (BER). This paper proposes a noncoherent solution based on the alternate polarization chirped return-to-zero frequency shift keying (Apol-CRZ-FSK) modulation format to realize a 4 × 100 Gbps dense wavelength division multiplexing (DWDM) optical network. Simulation results show that compared to traditional modulation formats, such as chirped return-to-zero frequency shift keying (CRZ-FSK) and differential quadrature phase shift keying (DQPSK), this solution demonstrates superior resistance to nonlinear effects, enabling longer transmission distances and better transmission performance. Moreover, to meet the transmission requirements and signal sensing and recognition needs in future optical networks, this study employs the Inception-ResNet-v2 convolutional neural network model to identify three modulation formats. Compared with six deep learning methods including AlexNet, ResNet50, GoogleNet, SqueezeNet, Inception-v4, and Xception, it achieves the highest performance. This research provides a low-cost, low-complexity, and high-performance solution for signal transmission and signal recognition in high-speed optical networks designed for integrated communication and sensing.

Single Well Production Prediction Model of Gas Reservoir Based on CNN-BILSTM-AM

In the prediction of single-well production in gas reservoirs, the traditional empirical formula of gas reservoirs generally shows poor accuracy. In the process of machine learning training and prediction, the problems of small data volume and dirty data are often encountered. In order to overcome the above problems, a single-well production prediction model of gas reservoirs based on CNN-BILSTM-AM is proposed. The model is built by long-term and short-term memory neural networks, convolutional neural networks and attention modules. The input of the model includes the production of the previous period and its influencing factors. At the same time, the fitting production and error value of the traditional gas reservoir empirical formula are introduced to predict the future production data. The loss function is used to evaluate the deviation between the predicted data and the real data, and the Bayesian hyperparameter optimization algorithm is used to optimize the model structure and comprehensively improve the generalization ability of the model. Three single wells in the Daniudi D28 well area were selected as the database, and the CNN-BILSTM-AM model was used to predict the single-well production. The results show that compared with the prediction results of the convolutional neural network (CNN) model, long short-term memory neural network (LSTM) model and bidirectional long short-term memory neural network (BILSTM) model, the error of the CNN-BILSTM-AM model on the test set of three experimental wells is reduced by 6.2425%, 4.9522% and 3.0750% on average. It shows that on the basis of coupling the empirical formula of traditional gas reservoirs, the CNN-BILSTM-AM model meets the high-precision requirements for the single-well production prediction of gas reservoirs, which is of great significance to guide the efficient development of oil fields and ensure the safety of China’s energy strategy.

DEVELOPMENT AND SIMULATION OF SPIKE NEURAL NETWORK ARCHITECTURE

A review of different models of spike neural networks has been conducted. A spike type neural network is developed in the article. The mathematical model of exchange of neurotransmitters between neurons is proposed. An algorithm for network operation and neuron interaction is proposed, as well as an approach to training the network based on the formation of new connections from dendrites and increasing the signal transmission coefficient. The model of neural network was created in Python using the developed algorithm and mathematical model. To speed up the calculations, they were paralleled using the Numba library. The library Matplotlib was used for visual modelling and plotting the number of neurotransmitters on neurons. Experimental studies of the developed model of biological type network were carried out. It was shown that the developed network after training responds faster to the signals that were applied to it in the process of training.

Nash Bargaining-Based Coordinated Frequency-Constrained Dispatch for Distribution Networks and Microgrids

As the penetration of distributed renewable energy continues to increase in distribution networks, the traditional scheduling model that the inertia and primary frequency support of distribution networks are completely dependent on the transmission grid will place enormous regulatory pressure on the transmission grid and hinder the active regulation capabilities of distribution networks. To address this issue, this paper proposes a coordinated optimization method for distribution networks and microgrid clusters considering frequency constraints. First, the confidence interval of disturbances was determined based on historical forecast deviation data. On this basis, a second-order cone programming model for distribution networks with embedded frequency security constraints was established. Then, microgrids performed economic dispatch considering the reserves requirement to provide inertia and primary frequency support, and a stochastic optimization model with conditional value-at-risk was built to address uncertainties. Finally, a cooperative game between the distribution network and microgrid clusters was established, determining the reserve capacity provided by each microgrid and the corresponding prices through Nash bargaining. The model was further transformed into two sub-problems, which were solved in a distributed manner using the ADMM algorithm. The effectiveness of the proposed method in enhancing the operational security and economic efficiency of the distribution networks is validated through simulation analysis.

Robust Human Activity Recognition for Intelligent Transportation Systems Using Smartphone Sensors: A Position-Independent Approach

This study explores Human Activity Recognition (HAR) using smartphone sensors to address the challenges posed by position-dependent datasets. We propose a position-independent system that leverages data from accelerometers, gyroscopes, linear accelerometers, and gravity sensors collected from smartphones placed either on the chest or in the left/right leg pocket. The performance of traditional machine learning algorithms (Decision Trees (DT), K-Nearest Neighbors (KNN), Random Forest (RF), Support Vector Classifier (SVC), and XGBoost) is compared against deep learning models (Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Temporal Convolutional Networks (TCN), and Transformer models) under two sensor configurations. Our findings highlight that the Temporal Convolutional Network (TCN) model consistently outperforms other models, particularly in the four-sensor non-overlapping configuration, achieving the highest accuracy of 97.70%. Deep learning models such as LSTM, GRU, and Transformer also demonstrate strong performance, showcasing their effectiveness in capturing temporal dependencies in HAR tasks. Traditional machine learning models, including RF and XGBoost, provide reasonable performance but do not match the accuracy of deep learning models. Additionally, incorporating data from linear accelerometers and gravity sensors led to slight improvements over using accelerometer and gyroscope data alone. This research enhances the recognition of passenger behaviors for intelligent transportation systems, contributing to more efficient congestion management and emergency response strategies.

Enhanced skin cancer diagnosis: a deep feature extraction-based framework for the multi-classification of skin cancer utilizing dermoscopy images

Skin cancer is one of the most common, deadly, and widespread cancers worldwide. Early detection of skin cancer can lead to reduced death rates. A dermatologist or primary care physician can use a dermatoscope to inspect a patient to diagnose skin disorders visually. Early detection of skin cancer is essential, and in order to confirm the diagnosis and determine the most appropriate course of therapy, patients should undergo a biopsy and a histological evaluation. Significant advancements have been made recently as the accuracy of skin cancer categorization by automated deep learning systems matches that of dermatologists. Though progress has been made, there is still a lack of a widely accepted, clinically reliable method for diagnosing skin cancer. This article presented four variants of the Convolutional Neural Network (CNN) model (i.e., original CNN, no batch normalization CNN, few filters CNN, and strided CNN) for the classification and prediction of skin cancer in lesion images with the aim of helping physicians in their diagnosis. Further, it presents the hybrid models CNN-Support Vector Machine (CNNSVM), CNN-Random Forest (CNNRF), and CNN-Logistic Regression (CNNLR), using a grid search for the best parameters. Exploratory Data Analysis (EDA) and random oversampling are performed to normalize and balance the data. The CNN models (original CNN, strided, and CNNSVM) obtained an accuracy rate of 98%. In contrast, CNNRF and CNNLR obtained an accuracy rate of 99% for skin cancer prediction on a HAM10000 dataset of 10,015 dermoscopic images. The encouraging outcomes demonstrate the effectiveness of the proposed method and show that improving the performance of skin cancer diagnosis requires including the patient's metadata with the lesion image.

Modelling of Carbon Monoxide and Suspended Particulate Matter Concentrations in a Rural Area Using Artificial Neural Networks

Air pollution is a growing concern in rural areas where agricultural production can be reduced by it. This article analyses data obtained as part of a research project. The aim of this study is to understand the influence of atmospheric pressure, air temperature, air relative humidity, longitude and latitude of the location, and indoor and outdoor environment on local rural workplace diversity of air pollutants such as carbon monoxide (CO) and suspended particulate matter (SPM), as well as the contribution of these variables to changes in such air pollutants. The focus is on four topics: motivation, innovation and creativity, leadership, and social responsibility. Furthermore, this study developed an artificial neural network (ANN) model to predict CO and SPM concentrations in the air based on data collected from the mentioned inputs. The related sensors were assembled on an Arduino Mega 2560 board to form a field-portable device to detect air pollutants and meteorological parameters. The sensors included an MQ7 sensor for CO concentration measurement, a Sharp GP2Y1010AU0F dust sensor for SPM concentration measurement, a DHT11 sensor for air temperature and air relative humidity measurement, and a BMP180 sensor for air pressure measurements. The longitude and latitude of the location were measured using a smartphone. Measurements were conducted from 20 December 2021 to 16 July 2022. Results showed that the overall average outdoor CO and SPM concentrations were 10.97 ppm and 231.14 μg/m3 air, respectively. The overall average indoor concentrations were 12.21 ppm and 233.91 μg/m3 air for CO and SPM, respectively. Results showed that the ANN model demonstrated acceptable performance in predicting CO and SPM in both the training and testing phases, exhibiting a coefficient of determination (R2) of 0.575, a root mean square error (RMSE) of 1.490 ppm, and a mean absolute error (MAE) of 0.994 ppm for CO concentrations when applying the testing dataset. For SPM concentrations, the R2, RMSE, and MAE using the test dataset were 0.497, 30.301 μg/m3 air, and 23.889 μg/m3 air, respectively. The most influential input variable was air pressure, with contribution rates of 22.88% and 22.82% in predicting CO and SPM concentrations, respectively. The acceptable performance of the developed ANN model provides potential advances in air quality management and agricultural planning, enabling a more accurate and informed decision-making process regarding air pollution. The results of short-term estimation of CO and SPM concentrations suggest that the accuracy of the ANN model needs to be improved through more comprehensive data collection or advanced machine learning algorithms to improve the prediction results of these two air pollutants. Moreover, as even lower cost devices can predict CO and SPM concentrations, this study could lead to the development some kind of virtual sensor, as other air pollutants can be estimated from measurements of particulate matters.

INTELLIGENT MONITORING OF THE PHYSIOLOGICAL STATE OF AGRICULTURAL PRODUCTS USING UAV

The article discusses the technology for automated neural network monitoring of the vineyard’s physiological condition. Images of leaves, obtained using an unmanned aerial vehicle (UAV), are the main indicator of the physiological vineyard’s condition. The proposed solution is based on the integrated use of convolutional neural network method (CNN) and machine vision technologies. To determine the optimal neural network (NN) model, a variant analysis was carried out. In accordance with its results, the YOLOv7 model was chosen, which satisfies the introduced time limit and provides the required detection quality. The training of the YOLOv7 neural network was implemented in the Python environment using the PyTorch framework and the OpenCV computer vision library. The dataset consisting of 6320 images of grape leaves (including healthy and diseased ones) has been used for neural network training. The obtained results showed that the detection accuracy is at least 91%. Visualization of monitoring results has been carried out using heatmap, allowing to obtain information about vineyard physiological condition in dynamics. The proposed mathematical model allows to calculate the monitored vineyard’s area made by one complex per day. The obtained results showed that effective monitoring area using one DJI Phantom 4 UAV per day is 2.5 hectares.

A Hybrid Approach Integrating Physics-Based Models and Expert-Augmented Neural Networks for Ship Fuel Consumption Prediction

Abstract The International Maritime Organization’s recent approval of the 2023 strategy on reduction of greenhouse gas emissions amplifies the pressure on stakeholders to achieve net-zero emissions in shipping by 2050. Considering the anticipated predominance of traditional single-fuel engines into the next decade, due to their high efficiency and economic benefits, the implementation of operational measures stands as the foremost effective method for mitigating emissions and reducing fuel consumption. Accurate fuel consumption prediction is crucial for informed decision-making and operational efficiency. This paper introduces an innovative hybrid model, combining an advanced physics-based model with an expert-augmented neural network, offering superior fuel consumption predictions. Expert knowledge is integrated into the neural network model to enhance its learning capabilities. Performance is validated against DNV Navigator Insight and publicly available fuel consumption reporting data, demonstrating superiority over purely data-driven and physics-based models. This hybrid approach bridges accuracy and scalability for sustainable maritime operations.

Co-Phase Error Detection for Segmented Mirrors Based on Far-Field Information and Transfer Learning

The resolution of a telescope is closely related to its aperture size; however, the aperture of a single primary mirror telescope cannot be indefinitely enlarged due to design and manufacturing constraints. Segmented mirror technology can achieve the same resolution as a single primary mirror of equivalent aperture, provided that the segments are co-phased correctly. This paper proposes a method for high-precision detection of piston errors in segmented mirror telescope systems, based on far-field information and transfer learning. By training a ResNet-18 network model, this method can predict piston errors with high precision within 10 ms of a single-frame far-field diffraction image. Simulation results demonstrate that the method is robust to tip-tilt errors, wavefront aberrations, and noise. This approach is simple, fast, highly accurate in detection, and resistant to noise, providing a new solution for piston error detection in segmented mirror systems.

Impact localization of CFRP laminate based on FBG sensing and GWO-BP neural network

Carbon fiber reinforced plastic (CFRP) structures are susceptible to external energy impact during service, resulting in invisible damage. Therefore, accurate localization of these impact sites is crucial for the maintenance and safety of CFRP structures. In this paper, the strain data of the impact response of the CFRP laminate is obtained by using the fiber grating (FBG) sensor, and the data are mapped to the impact location by BP neural network. However, the traditional BP neural network is susceptible to local minima and slow convergence speed. Therefore, Grey Wolf optimization algorithm (GWO) is introduced in this study to optimize the BP neural network, which improves the convergence speed and positioning accuracy of the model. The experimental results show that the GWO-BP neural network model has excellent performance in impact positioning, with the maximum positioning error of 17.01 mm and the average positioning error of 13.05 mm. Compared with other machine learning methods, it has higher accuracy and efficiency.

Integrative analysis of single-cell transcriptomic and multilayer signaling networks in glioma reveal tumor progression stage

IntroductionTumor microenvironments (TMEs) encompass complex ecosystems of cancer cells, infiltrating immune cells, and diverse cell types. Intercellular and intracellular signals within the TME significantly influence cancer progression and therapeutic outcomes. Although computational tools are available to study TME interactions, explicitly modeling tumor progression across different cancer types remains a challenge.MethodsThis study introduces a comprehensive framework utilizing single-cell RNA sequencing (scRNA-seq) data within a multilayer network model, designed to investigate molecular changes across glioma progression stages. The heterogeneous, multilayered network model replicates the hierarchical structure of biological systems, from genetic building blocks to cellular functions and phenotypic manifestations.ResultsApplying this framework to glioma scRNA-seq data allowed complex network analysis of different cancer stages, revealing significant ligand‒receptor interactions and key ligand‒receptor-transcription factor (TF) axes, along with their associated biological pathways. Differential network analysis between grade III and grade IV glioma highlighted the most critical nodes and edges involved in interaction rewiring. Pathway enrichment analysis identified four essential genes—PDGFA (ligand), PDGFRA (receptor), CREB1 (TF), and PLAT (target gene)—involved in the Receptor Tyrosine Kinases (RTK) signaling pathway, which plays a pivotal role in glioma progression from grade III to grade IV.DiscussionThese genes emerged as significant features for machine learning in predicting glioma progression stages, achieving 87% accuracy and 93% AUC in a 3-year survival prediction through Kaplan-Meier analysis. This framework provides deeper insights into the cellular machinery of glioma, revealing key molecular relationships that may inform prognosis and therapeutic strategies.

A Machine-Learning Approach to Mitigate Ground Clutter Effects in the GPM Combined Radar-Radiometer Algorithm (CORRA) Precipitation Estimates

Abstract In this study, a machine-learning based methodology is developed to mitigate the effects of ground clutter on precipitation estimates from the Global Precipitation Mission Combined Radar-Radiometer Algorithm. Ground clutter can corrupt and obscure precipitation echo in radar observations, leading to inaccuracies in precipitation estimates. To improve upon previous work, this study introduces a general machine learning (ML) approach that enables a systematic investigation and a better understanding of uncertainties in clutter mitigation. To allow for a less restrictive exploration of conditional relations between precipitation above the lowest clutter-free bin and surface precipitation, reflectivity observations above the clutter are included in a fixed-size set of predictors along with the precipitation type, surface type, and freezing level to estimate surface precipitation rates, and several ML-based estimation methods are investigated. A Neural Network Model (NN) is ultimately identified as the best candidate for systematic evaluations, as it is computationally fast to apply while effective in applications. The NN provides unbiased estimates; however, it does not significantly outperform a simple bias correction approach in reducing random errors in the estimates. The similar performance of other ML approaches suggests that the NN’s limited improvement beyond bias removal is due to indeterminacies in the data rather than limitations in the ML approach itself.

HGNN−BRFE: Heterogeneous Graph Neural Network Model Based on Region Feature Extraction

With the strong capability of heterogeneous graphs in accurately modeling various types of nodes and their interactions, they have gradually become a research hotspot, promoting the rapid development of the field of heterogeneous graph neural networks (HGNNs). However, most existing HGNN models rely on meta−paths for feature extraction, which can only utilize part of the data from the graph for training and learning. This not only limits the data generalization ability of deep learning models but also affects the application effect of data−driven adaptive technologies. In response to this challenge, this study proposes a new model—heterogeneous graph neural network based on regional feature extraction (HGNN−BRFE). This model enhances performance through an “extraction−fusion” strategy in three key aspects: first, it efficiently extracts features of neighboring nodes of the same type according to specific regions; second, it effectively fuses information from different regions and hierarchical neighbors using attention mechanisms; third, it specially designs a process for feature extraction and fusion targeting heterogeneous type nodes, ensuring that the rich semantic and heterogeneity information within the heterogeneous graph is retained while maintaining the node’s own characteristics during the node embedding process to prevent the loss of its own features and potential over−smoothing issues. Experimental results show that HGNN−BRFE achieves a performance improvement of 1–3% over existing methods on classification tasks across multiple real−world datasets.

Medium and long-term regional water demand prediction using Harris hawks optimisation–backpropagation neural network model

Medium and long-term regional water demand prediction using Harris hawks optimisation–backpropagation neural network model

Predicting Mutual Fund Stress Levels Utilizing SEBI’s Stress Test Parameters in MidCap and SmallCap Funds Using Deep Learning Models

Abstract: The Association of Mutual Funds of India (AMFI), under the direction of the Securities and Exchange Board of India (SEBI), provided open access to various risk parameters with respect to MidCap and SmallCap funds for the first time from February 2024. Our study utilizes AMFI datasets from February 2024 to September 2024 which consisted of 14 variables. Among these, the primary variable identified in grading mutual funds is the stress test parameter, expressed as number of days required to liquidate between 50% and 25% of the portfolio, respectively, on a pro-rata basis under stress conditions as a response variable. The objective of our paper is to build and test various neural network models which can help in predicting stress levels with the highest accuracy and specificity in MidCap and SmallCap mutual funds based on AMFI’s 14 parameters as predictors. The results suggest that the simpler neural network model architectures show higher accuracy. We used Artificial Neural Networks (ANN) over other machine learning methods due to its ability to analyze the impact of dynamic interrelationships among 14 variables on the dependent variable, independent of the statistical distribution of parameters considered. Predicting stress levels with the highest accuracy in MidCap and SmallCap mutual funds will benefit investors by reducing information asymmetry while allocating investments based on their risk tolerance. It will help policy makers in designing controls to protect smaller investors and provide warnings for funds with unusually high risk.

Dopamine builds and reveals reward-associated latent behavioral attractors

AbstractPhasic variations in dopamine levels are interpreted as a teaching signal reinforcing rewarded behaviors. However, behavior also depends on the motivational, neuromodulatory effect of phasic dopamine. In this study, we reveal a neurodynamical principle that unifies these roles in a recurrent network-based decision architecture embodied through an action-perception loop with the task space, the MAGNet model. Dopamine optogenetic conditioning in mice was accounted for by an embodied network model in which attractors encode internal goals. Dopamine-dependent synaptic plasticity created “latent” attractors, to which dynamics converged, but only locally. Attractor basins were widened by dopamine-modulated synaptic excitability, rendering goals accessible globally, i.e. from distal positions. We validated these predictions optogenetically in mice: dopamine neuromodulation suddenly and specifically attracted animals toward rewarded locations, without off-target motor effects. We thus propose that motivational dopamine reveals dopamine-built attractors representing potential goals in a behavioral landscape.

Application of Isokinetic Dynamometry Data in Predicting Gait Deviation Index Using Machine Learning in Stroke Patients: A Cross-Sectional Study

Background: Three-dimensional gait analysis, supported by advanced sensor systems, is a crucial component in the rehabilitation assessment of post-stroke hemiplegic patients. However, the sensor data generated from such analyses are often complex and challenging to interpret in clinical practice, requiring significant time and complicated procedures. The Gait Deviation Index (GDI) serves as a simplified metric for quantifying the severity of pathological gait. Although isokinetic dynamometry, utilizing sophisticated sensors, is widely employed in muscle function assessment and rehabilitation, its application in gait analysis remains underexplored. Objective: This study aims to investigate the use of sensor-acquired isokinetic muscle strength data, combined with machine learning techniques, to predict the GDI in hemiplegic patients. This study utilizes data captured from sensors embedded in the Biodex dynamometry system and the Vicon 3D motion capture system, highlighting the integration of sensor technology in clinical gait analysis. Methods: This study was a cross-sectional, observational study that included a cohort of 150 post-stroke hemiplegic patients. The sensor data included measurements such as peak torque, peak torque/body weight, maximum work of repeated actions, coefficient of variation, average power, total work, acceleration time, deceleration time, range of motion, and average peak torque for both flexor and extensor muscles on the affected side at three angular velocities (60°/s, 90°/s, and 120°/s) using the Biodex System 4 Pro. The GDI was calculated using data from a Vicon 3D motion capture system. This study employed four machine learning models—Lasso Regression, Random Forest (RF), Support Vector regression (SVR), and BP Neural Network—to model and validate the sensor data. Model performance was evaluated using mean squared error (MSE), the coefficient of determination (R2), and mean absolute error (MAE). SHapley Additive exPlanations (SHAP) analysis was used to enhance model interpretability. Results: The RF model outperformed others in predicting GDI, with an MSE of 16.18, an R2 of 0.89, and an MAE of 2.99. In contrast, the Lasso Regression model yielded an MSE of 22.29, an R2 of 0.85, and an MAE of 3.71. The SVR model had an MSE of 31.58, an R2 of 0.82, and an MAE of 7.68, while the BP Neural Network model exhibited the poorest performance with an MSE of 50.38, an R2 of 0.79, and an MAE of 9.59. SHAP analysis identified the maximum work of repeated actions of the extensor muscles at 60°/s and 120°/s as the most critical sensor-derived features for predicting GDI, underscoring the importance of muscle strength metrics at varying speeds in rehabilitation assessments. Conclusions: This study highlights the potential of integrating advanced sensor technology with machine learning techniques in the analysis of complex clinical data. The developed GDI prediction model, based on sensor-acquired isokinetic dynamometry data, offers a novel, streamlined, and effective tool for assessing rehabilitation progress in post-stroke hemiplegic patients, with promising implications for broader clinical application.