Decision-level Fusion Research Articles

A digital shadow approach for enhancing process monitoring in wire arc additive manufacturing using sensor fusion

With the development of Industry 4.0 and smart manufacturing, improving production automation, intelligence, and digitalization has become a research trend in the Wire Arc Additive Manufacturing (WAAM) field. This study introduces a digital shadow that aims to improve the adaptiveness and dimensionality of monitoring systems in WAAM. Three sensors are used in the digital shadow: a welding electric signal sensor, a camera, and a laser profilometer to collect welding current and voltage data, image data, and point cloud data. The collected multi-scaled data are time and spatially synchronized by sampling multiple points along the welding path. Three ML algorithms are used for decision-making: Multi-layer Perceptron (MLP) classifier and YOLOv5 are used for time and spatial-scale detection, respectively, and a Variational Autoencoder (VAE) is used for the decision-level fusion. The system performance is then tested to detect defects and geometric errors in practical experiments and the results show that the overall F1 score is 0.791, including detecting, classifying, and analyzing the cause of defects. Additionally, the total predicting time is within 0.5 s, which is suitable for an in-process monitoring system.

Predicting rectal cancer tumor budding grading based on MRI and CT with multimodal deep transfer learning: A dual-center study

ObjectiveTo investigate the effectiveness of a multimodal deep learning model in predicting tumor budding (TB) grading in rectal cancer (RC) patients. Materials and methodsA retrospective analysis was conducted on 355 patients with rectal adenocarcinoma from two different hospitals. Among them, 289 patients from our institution were randomly divided into an internal training cohort (n = 202) and an internal validation cohort (n = 87) in a 7:3 ratio, while an additional 66 patients from another hospital constituted an external validation cohort. Various deep learning models were constructed and compared for their performance using T1CE and CT-enhanced images, and the optimal models were selected for the creation of a multimodal fusion model. Based on single and multiple factor logistic regression, clinical N staging and fecal occult blood were identified as independent risk factors and used to construct the clinical model. A decision-level fusion was employed to integrate these two models to create an ensemble model. The predictive performance of each model was evaluated using the area under the curve (AUC), DeLong's test, calibration curve, and decision curve analysis (DCA). Model visualization Gradient-weighted Class Activation Mapping (Grad-CAM) was performed for model interpretation. ResultsThe multimodal fusion model demonstrated superior performance compared to single-modal models, with AUC values of 0.869 (95% CI: 0.761–0.976) for the internal validation cohort and 0.848 (95% CI: 0.721–0.975) for the external validation cohort. N-stage and fecal occult blood were identified as clinically independent risk factors through single and multivariable logistic regression analysis. The final ensemble model exhibited the best performance, with AUC values of 0.898 (95% CI: 0.820–0.975) for the internal validation cohort and 0.868 (95% CI: 0.768–0.968) for the external validation cohort. ConclusionMultimodal deep learning models can effectively and non-invasively provide individualized predictions for TB grading in RC patients, offering valuable guidance for treatment selection and prognosis assessment.

Nondestructive detection of egg freshness based on a decision-level fusion method using hyperspectral imaging technology

Nondestructive detection of egg freshness based on a decision-level fusion method using hyperspectral imaging technology

Decision-level fusion detection method of hydrogen leakage in hydrogen supply system of fuel cell truck

The hydrogen supply system is the high-pressure section of fuel cell system, consisting of many valves, pipelines and joints. A hydrogen leak may occur due to the reduced sealing performance or crash accidents. Therefore, a quick and accurate hydrogen leakage detection method is essential to support hydrogen safety. The traditional multisensor-based hydrogen leakage detection method directly classifies the hydrogen leakage fault according to the hydrogen concentration. However, using hydrogen concentrations at local points to describe leak fault severity has significant limitations. A novel hydrogen leakage detection method based on Stacking ensemble machine learning is proposed to classify hydrogen leak rate. The hydrogen leakage simulations are performed to form the database containing a series of hydrogen leakage scenarios. The sensor placement is optimized and the features extracted from hydrogen concentration time series are selected by applying ReliefF algorithm. The model-based hydrogen leakage detection method is analyzed and fused with proposed hydrogen leakage detection method based on Stacking ensemble machine learning by applying decision-level fusion algorithm. Compared with traditional multisensor-based hydrogen leakage detection method, the detection time of proposed multisensor-based hydrogen leakage detection method is shorter under nearly 80% of all scenarios. The classification accuracy of the proposed hydrogen leakage detection method based on Stacking ensemble machine learning and model-based hydrogen leakage detection method is 92.1% and 93.5%, respectively. The probability of class is increased and classification accuracy can be improved through D-S evidence theory.

A Spatiotemporal Enhanced SMAP Freeze/Thaw Product (1980–2020) over China and Its Preliminary Analyses

The soil freeze/thaw (FT) state has emerged as a critical role in the ecosystem, hydrological, and biogeochemical processes, but obtaining representative soil FT state datasets with a long time sequence, fine spatial resolution, and high accuracy remains challenging. Therefore, we propose a decision-level spatiotemporal data fusion algorithm based on Convolutional Long Short-Term Memory networks (ConvLSTM) to expand the SMAP-enhanced L3 landscape freeze/thaw product (SMAP_E_FT) temporally. In the algorithm, the Freeze/Thaw Earth System Data Record product (ESDR_FT) is sucked in the ConvLSTM and fused with SMAP_E_FT at the decision level. Eight predictor datasets, i.e., soil temperature, snow depth, soil moisture, precipitation, terrain complexity index, area of open water data, latitude and longitude, are used to train the ConvLSTM. Direct validation using six dense observation networks located in the Genhe, Maqu, Naqu, Pali, Saihanba, and Shandian river shows that the fusion product (ConvLSTM_FT) effectively absorbs the high accuracy characteristics of ESDR_FT and expands SMAP_E_FT with an overall average improvement of 2.44% relative to SMAP_E_FT, especially in frozen seasons (averagely improved by 7.03%). The result from indirect validation based on categorical triple collocation also shows that ConvLSTM_FT performs stable regardless of land cover types, climate types, and terrain complexity. The findings, drawn from preliminary analyses on ConvLSTM_FT from 1980 to 2020 over China, suggest that with global warming, most parts of China suffer from different degrees of shortening of the frozen period. Moreover, in the Qinghai–Tibet region, the higher the permafrost thermal stability, the faster the degradation rate.

A novel data fusion based intelligent identification approach for working cycle stages of hydraulic excavators

Accurately identifying the stage of the excavator working cycle is the prerequisite to achieve the staged energy-saving control. However, current identification methods often overlook the influence of hydraulic system latency on identification results and depend on a single model, resulting in poor generalization performance of the identification approaches. Moreover, expert calibration system remains a necessary factor for improving identification accuracy. Aiming at these issues, a hybrid multi-scale feature extractor and a decision-level data fusion classifier approach (HMSFE-DFC) is proposed to identify the working cycle stages of excavator. The input signal employs mixed signals from the main pump pressure and the control current of the proportional solenoid valve to reduce the response delay caused by the single main pump pressure signal. A hybrid multi-scale feature extractor is constructed using a convolutional neural network temporal self-attention feature extraction mechanism and one-dimensional ResNet-50 architecture to extract multiscale features. To prevent overfitting, a decision-level data fusion classifier is used to fuse the decisions information of numerous classifiers. The accuracy of stage identification for 10 consecutive working cycles reaches 95.21%, which verifies its effectiveness.

Interval-based sparse ensemble multi-class classification algorithm for terahertz data

Terahertz time-domain spectroscopy (THz-TDS) has been widely used for food and drug identification. The classification information of a THz spectrum usually does not exist in the whole spectral band but exists only in one or several small intervals. Therefore, feature selection is indispensable in THz-based substance identification. However, most THz-based identification methods empirically intercept the low-frequency band of the THz absorption coefficients for analysis. In order to adaptively find out important intervals of the THz spectra, an interval-based sparse ensemble multi-class classifier (ISEMCC) for THz spectral data classification is proposed. In ISEMCC, the THz spectra are first divided into several small intervals through window sliding. Then the data of training samples in each interval are extracted to train some base classifiers. Finally, a final robust classifier is obtained through a nonnegative sparse combination of these trained base classifiers. With l1 -norm, two objective functions that based on Mean Square Error (MSE) and Cross Entropy (CE) are established. For these two objective functions, two iterative algorithms based on the Alternating Direction Method of Multipliers (ADMM) and Gradient Descent (GD) are built respectively. ISEMCC transforms the problem of interval feature selection and decision-level fusion into a nonnegative sparse optimization problem. The sparse constraint ensures only a few important spectral segments are selected. In order to verify the performance of the proposed algorithm, comparative experiments on identifying the origin of Bupleurum and the harvesting year of Tangerine peel are carried out. The base classifiers used by ISEMCC are Support Vector Machine (SVM) and Decision Tree (DT). The experimental results demonstrate that the proposed algorithm outperforms six typical classifiers, including Random Forest (RF), AdaBoost, RUSBoost, ExtraTree, and the two base classifiers, in terms of classification accuracy.

A multimodal emotion recognition system using deep convolution neural networks

Despite the progress in computer-technology, with regard to Human-Computer Interaction (HCI), emotion recognition is still a challenging problem. In this paper, we present a novel multimodal emotion recognition system capable of recognizing emotions from audio, video, and text data using deep convolution neural networks. The system is able to recognize happy, angry, sad, afraid, disgust, surprise and neutral emotions. We used three datasets to train and test the system, one set for each of the three input formats. The results show a recognition accuracy rate of 100% for audio, 69% for video, and 64% for text. When applying the decision-level fusion, the recorded accuracy rate is 80%. These results confirm that the system is effective in recognizing human emotions.

Brain identification of IBS patients based on GBDT and multiple imaging techniques.

The brain biomarker of irritable bowel syndrome (IBS) patients is still lacking. The study aims to explore a new technology studying the brain alterations of IBS patients based on multi-source brain data. In the study, a decision-level fusion method based on gradient boosting decision tree (GBDT) was proposed. Next, 100 healthy subjects were used to validate the effectiveness of the method. Finally, the identification of brain alterations and the pain evaluation in IBS patients were carried out by the fusion method based on the resting-state fMRI and DWI for 46 patients and 46 controls selected randomly from 100 healthy subjects. The results showed that the method can achieve good classification between IBS patients and controls (accuracy = 95%) and pain evaluation of IBS patients (mean absolute error = 0.1977). Moreover, both the gain-based and the permutation-based evaluation instead of statistical analysis showed that left cingulum bundle contributed most significantly to the classification, and right precuneus contributed most significantly to the evaluation of abdominal pain intensity in the IBS patients. The differences seem to suggest a probable but unexplored separation about the central regions between the identification and progression of IBS. This finding may provide one new thought and technology for brain alteration related to IBS.

Signed Fingermark Liveness Detection Method Based on Deep Residual Networks and Multimodal Decision Fusion

Fingermarks play an important role in document identification. At the same time, fingermarks on paper documents are often accompanied by signatures and background text, which introduce noise to the original fingermark textures and increase the difficulty of detection. A signed fingermark detection method based on deep residual networks and a decision-level fusion strategy was proposed to defend against spoofing attacks from fake fingermarks. Firstly, the multi-scale structure was introduced in the residual module, which improved the network’s depth and breadth without increasing the parameters. Then, the multi-probability label strategy was refined and employed to enhance the local encoding ability of the feature extraction. A score fusion strategy was designed, with weights allocated based on the difference in signed interference levels of local image blocks. Finally, a model fusion strategy based on evidence theory was suggested, which improved detection accuracy by leveraging complementarity between models. A large-scale fingermark database was established, which included real fingermarks made from real fingers and fake fingermarks made from various materials, and this was divided into two sub databases: signed and unsigned. The experimental results show that the proposed method achieves 96.16% accuracy based on the fingerprint dataset of the global liveness detection competition called LivDet2017 and achieves 99.30% accuracy based on the signed fingermark database, while it has good resistance to spoofing attacks from unknown materials.

SecureSense: Enhancing Person Verification through Multimodal Biometrics for Robust Authentication

Biometrics provide enhanced security and convenience compared to conventional methods of individual authentication. A more robust and effective method of individual authentication has emerged due to recent advancements in multimodal biometrics. Unimodal systems offer lower security and lack the robustness found in multimodal biometric systems. The research paper introduces a novel approach, employing multiple biometric modalities, including face, fingerprint, and iris, to authenticate users in a multimodal biometric system. The paper proposes the ”Secure Sense” framework, which combines multiple biometric modalities to improve person verification accuracy. The proposed system utilizes both web-based and real-time datasets. For the web-based dataset, we employed the Chicago Face dataset for facial data, the MMU1 dataset for iris data, and the SOCOfing dataset for fingerprint data. In real-time data collection, facial data is captured using a Zebronics Zeb-Gem webcam, fingerprint data is obtained using the Mantra MFS scanner, and iris data is collected using the Mantra MIS scanner. In the envisioned system, we introduce an innovative approach that employs a decision-level fusion technique across three unique biometric modalities, resulting in an impressive accuracy rate of approximately 93% across all modalities.

Multi-modal sarcasm detection based on Multi-Channel Enhanced Fusion model

The voluminous quantity of data accessible on social media platforms offers insight into the sentiment disposition of individual users, where multi-modal sarcasm detection is often confounding. Existing sarcasm detection methods use different information fusion methods to combine information from different modalities but ignore hidden information within modalities and inconsistent information between modalities. Discovering the implicit information within the modalities and strengthening the information interaction between modalities is still an important challenge. In this paper, we propose a Multi-Channel Enhanced Fusion (MCEF) model for cross-modal sarcasm detection to maximize the information extraction between different modalities. Specifically, text extracted from images acts as a new modality in the front-end fusion models to augment the utilization of image semantic information. Then, we propose a novel bipolar semantic attention mechanism to uncover the inconsistencies among different modal features. Furthermore, a decision-level fusion strategy from a new perspective is devised based on four models to achieve multi-channel fusion, each with a distinct focus, to leverage their advantages and mitigate the limitations. Extensive experiments demonstrate that our model surpasses current state-of-the-art models in multi-modal sarcasm detection.

A Hybrid System for Defect Detection on Rail Lines through the Fusion of Object and Context Information.

Defect detection on rail lines is essential for ensuring safe and efficient transportation. Current image analysis methods with deep neural networks (DNNs) for defect detection often focus on the defects themselves while ignoring the related context. In this work, we propose a fusion model that combines both a targeted defect search and a context analysis, which is seen as a multimodal fusion task. Our model performs rule-based decision-level fusion, merging the confidence scores of multiple individual models to classify rail-line defects. We call the model "hybrid" in the sense that it is composed of supervised learning components and rule-based fusion. We first propose an improvement to existing vision-based defect detection methods by incorporating a convolutional block attention module (CBAM) in the you only look once (YOLO) versions 5 (YOLOv5) and 8 (YOLOv8) architectures for the detection of defects and contextual image elements. This attention module is applied at different detection scales. The domain-knowledge rules are applied to fuse the detection results. Our method demonstrates improvements over baseline models in vision-based defect detection. The model is open for the integration of modalities other than an image, e.g., sound and accelerometer data.

An Emotion Recognition Method Based on Eye Movement and Audiovisual Features in MOOC Learning Environment

In recent years, more and more people have begun to use massive online open course (MOOC) platforms for distance learning. However, due to the space–time isolation between teachers and students, the negative emotional state of students in MOOC learning cannot be identified timely. Therefore, students cannot receive immediate feedback about their emotional states. In order to identify and classify learners’ emotions in video learning scenarios, we propose a multimodal emotion recognition method based on eye movement signals, audio signals, and video images. In this method, two novel features are proposed: feature of coordinate difference of eyemovement (FCDE) and pixel change rate sequence (PCRS). FCDE is extracted by combining eye movement coordinate trajectory and video optical flow trajectory, which can represent the learner’s attention degree. PCRS is extracted from the video image, which can represent the speed of image switching. A feature extraction network based on convolutional neural network (CNN) (FE-CNN) is designed to extract the deep features of the three modals. The extracted deep features are inputted into the emotion classification CNN (EC-CNN) to classify the emotions, including interest, happiness, confusion, and boredom. In single modal identification, the recognition accuracies corresponding to the three modals are 64.32%, 74.67%, and 71.88%. The three modals are fused by feature-level fusion, decision-level fusion, and model-level fusion methods, and the evaluation experiment results show that the method of decision-level fusion achieved the highest score of 81.90% of emotion recognition. Finally, the effectiveness of FCDE, FE-CNN, and EC-CNN modules is verified by ablation experiments.

A Space Infrared Dim Target Recognition Algorithm Based on Improved DS Theory and Multi-Dimensional Feature Decision Level Fusion Ensemble Classifier

Space infrared dim target recognition is an important applications of space situational awareness (SSA). Due to the weak observability and lack of geometric texture of the target, it may be unreliable to rely only on grayscale features for recognition. In this paper, an intelligent information decision-level fusion method for target recognition which takes full advantage of the ensemble classifier and Dempster–Shafer (DS) theory is proposed. To deal with the problem that DS produces counterintuitive results when evidence conflicts, a contraction–expansion function is introduced to modify the body of evidence to mitigate conflicts between pieces of evidence. In this method, preprocessing and feature extraction are first performed on the multi-frame dual-band infrared images to obtain the features of the target, which include long-wave radiant intensity, medium–long-wave radiant intensity, temperature, emissivity–area product, micromotion period, and velocity. Then, the radiation intensities are fed to the random convolutional kernel transform (ROCKET) architecture for recognition. For the micromotion period feature, a support vector machine (SVM) classifier is used, and the remaining categories of the features are input into the long short-term memory network (LSTM) for recognition, respectively. The posterior probabilities corresponding to each category, which are the result outputs of each classifier, are constructed using the basic probability assignment (BPA) function of the DS. Finally, the discrimination of the space target category is implemented according to improved DS fusion rules and decision rules. Continuous multi-frame infrared images of six flight scenes are used to evaluate the effectiveness of the proposed method. The experimental results indicate that the recognition accuracy of the proposed method in this paper can reach 93% under the strong noise level (signal-to-noise ratio is 5). Its performance outperforms single-feature recognition and other benchmark algorithms based on DS theory, which demonstrates that the proposed method can effectively enhance the recognition accuracy of space infrared dim targets.

Computer Vision-Based Real-Time Identification of Vehicle Loads for Structural Health Monitoring of Bridges

Coupling effects of various loading conditions can cause deflections, settlements and even failure of in-service bridges. Although it is one of the most critical loads, unfortunately, loading conditions of moving vehicles are difficult to capture in real time by bridge monitoring systems currently in place for sustainable operation. To fully understand the status of a bridge, it is essential to obtain instantaneous vehicle load distributions in a dynamic traffic environment. Although there are some methods that can identify overweight vehicles, the captured vehicle-related information is scattered and incomplete and thus cannot support effective bridge structural health monitoring (BSHM). This study proposes a noncontact, vision-based approach to identification of vehicle loads for real-time monitoring of bridge structural health. The proposed method consists of four major steps: (1) establish a dual-object detection model for vehicles using YOLOv7, (2) develop a hybrid coordinate transformation model on a bridge desk, (3) develop a multiobject tracking model for real-time trajectory monitoring of moving vehicles, and (4) establish a decision-level fusion model for fusing data on vehicle loads and positions. The proposed method effectively visualizes the 3D spatiotemporal vehicular-load distribution with low delay at a speed of over 30FPS. The results show that the hybrid coordinate transformation ensures that the vehicle position error is within 1 m, a 5-fold reduction compared with the traditional method. Wheelbase is calculated through dual-object detection and transformation and is as the primary reference for vehicle position correction. The trajectory and real-time speed of vehicles are preserved, and the smoothed speed error is under 5.7%, compared with the speed measured by sensors. The authors envision that the proposed method could constitute a new approach for conducting real-time SHM of in-service bridges.

Improving Traffic Accident Severity Prediction Using Convoluted Features and Decision-Level Fusion of Models

Although there have been improvements in traffic safety measures, the frequency of traffic accidents continues to persist. Developing countries experience a significant impact from traffic accidents with respect to fatalities and property damage. Traffic accidents happen for multiple reasons, involving traffic conditions, driving violations, driver misjudgments, and so forth. Severe casualties may lead to fatalities; therefore, accident severity prediction might help reduce the chances of fatalities. This research makes use of a U.S. road accident dataset that contains the most relevant 32 factors related to accidents. For obtaining accurate prediction of traffic accident severity, this research proposes a solution based on an ensemble of random forest and support vector classifiers that is trained using deep convoluted features. Features are extracted from the road accident dataset using a convolutional neural network (CNN). The performance of models using original features and CNN features is analyzed that shows the superiority of convoluted features. Experimental results involving the use of several well-known machine learning models indicate that the proposed model can obtain an accuracy of 99.99% for traffic accident severity prediction. The efficacy of the proposed model is validated against existing state-of-the-art approaches.

Enhancing Road Extraction in Large-Scale Complex Terrain through Multi-Source Remote Sensing Image Fusion and Optimization

In large-scale remote sensing scenarios characterized by intricate terrain, the straightforward road imaging features in synthetic aperture radar (SAR) images make them susceptible to interference from other elements such as ridges, compromising the robustness of conventional SAR image road extraction methods. This paper introduces a method that integrates Gaofen-3 (GF-3) with a resolution of 3.0 m, Digital Elevation Models (DEMs), and Gaofen-2 (GF-2) remote sensing image data with a resolution of 4.0 m, aiming to improve the performance of road extraction in complex terrain. Leveraging DEMs, this study addresses the limitations in feature-based SAR algorithms, extending their application to complex remote sensing scenarios. Decision-level fusion, integrating SAR and multispectral images, further refines road extraction precision. To overcome issues related to terrain interference, including fragmented road segments, an adaptive rotated median filter and graph-theory-based optimization are introduced. These advancements collectively enhance road recognition accuracy and topological precision. The experimental results validate the effectiveness of the multi-source remote sensing image fusion and optimization methods. Compared to road extraction from multispectral images, the F1-score of the proposed method on the test images increased by 2.18%, 4.22%, and 1.4%, respectively.

A Geoscience-Aware Network (GASlumNet) Combining UNet and ConvNeXt for Slum Mapping

Approximately 1 billion people worldwide currently inhabit slum areas. The UN Sustainable Development Goal (SDG 11.1) underscores the imperative of upgrading all slums by 2030 to ensure adequate housing for everyone. Geo-locations of slums help local governments with upgrading slums and alleviating urban poverty. Remote sensing (RS) technology, with its excellent Earth observation capabilities, can play an important role in slum mapping. Deep learning (DL)-based RS information extraction methods have attracted a lot of attention. Currently, DL-based slum mapping studies typically uses three optical bands to adapt to existing models, neglecting essential geo-scientific information, such as spectral and textural characteristics, which are beneficial for slum mapping. Inspired by the geoscience-aware DL paradigm, we propose the Geoscience-Aware Network for slum mapping (GASlumNet), aiming to improve slum mapping accuracies via incorporating the DL model with geoscientific prior knowledge. GASlumNet employs a two-stream architecture, combining ConvNeXt and UNet. One stream concentrates on optical feature representation, while the other emphasizes geo-scientific features. Further, the feature-level and decision-level fusion mechanisms are applied to optimize deep features and enhance model performance. We used Jilin-1 Spectrum 01 and Sentinel-2 images to perform experiments in Mumbai, India. The results demonstrate that GASlumNet achieves higher slum mapping accuracy than the comparison models, with an intersection over union (IoU) of 58.41%. Specifically, GASlumNet improves the IoU by 4.60~5.97% over the baseline models, i.e., UNet and ConvNeXt-UNet, which exclusively utilize optical bands. Furthermore, GASlumNet enhances the IoU by 10.97% compared to FuseNet, a model that combines optical bands and geo-scientific features. Our method presents a new technical solution to achieve accurate slum mapping, offering potential benefits for regional and global slum mapping and upgrading initiatives.

A Rapid Response System for Elderly Safety Monitoring Using Progressive Hierarchical Action Recognition.

The global trend of population aging presents an urgent challenge in ensuring the safety and well-being of elderly individuals, especially those living alone due to various circumstances. A promising approach to this challenge involves leveraging Human Action Recognition (HAR) by integrating data from multiple sensors. However, the field of HAR has struggled to strike a balance between accuracy and response time. While technological advancements have improved recognition accuracy, complex algorithms often come at the expense of response time. To address this issue, we introduce an innovative asynchronous detection method called Rapid Response Elderly Safety Monitoring (RESAM), which relies on progressive hierarchical action recognition and multi-sensor data fusion. Through initial analysis of inertial sensor data using Kernel Principal Component Analysis (KPCA) and multi-class classifiers, we efficiently reduce processing time and lower the false-negative rate (FNR). The inertial sensor identification serves as a pre-filter, enabling the identification of filtered abnormal signals. Decision-level data fusion is then executed, incorporating skeleton image analysis based on ResNet and the inertial sensor data from the initial step. This integration enables the accurate differentiation between normal and abnormal behaviors. The RESAM method achieves an impressive 97.4% accuracy on the UTD-MHAD database with a minimal delay of 1.22 seconds. On our internally collected database, the RESAM system attains an accuracy of 99%, ranking among the most accurate state-of-the-art methods available. These results underscore the practicality and effectiveness of our approach in meeting the critical demand for swift and precise responses in healthcare scenarios.