Real-world Environments Research Articles

Recognition of Sheep Feeding Behavior in Sheepfolds Using Fusion Spectrogram Depth Features and Acoustic Features

In precision feeding, non-contact and pressure-free monitoring of sheep feeding behavior is crucial for health monitoring and optimizing production management. The experimental conditions and real-world environments differ when using acoustic sensors to identify sheep feeding behaviors, leading to discrepancies and consequently posing challenges for achieving high-accuracy classification in complex production environments. This study enhances the classification performance by integrating the deep spectrogram features and acoustic characteristics associated with feeding behavior. We conducted the task of collecting sound data in actual production environments, considering noise and complex surroundings. The method included evaluating and filtering the optimal acoustic features, utilizing a customized convolutional neural network (SheepVGG-Lite) to extract Short-Time Fourier Transform (STFT) spectrograms and Constant Q Transform (CQT) spectrograms’ deep features, employing cross-spectrogram feature fusion and assessing classification performance through a support vector machine (SVM). Results indicate that the fusion of cross-spectral features significantly improved classification performance, achieving a classification accuracy of 96.47%. These findings highlight the value of integrating acoustic features with spectrogram deep features for accurately recognizing sheep feeding behavior.

Detection of the Pigment Distribution of Stacked Matcha During Processing Based on Hyperspectral Imaging Technology

Color is a key indicator for evaluating the quality of tea during processing; various processing procedures can significantly affect the content of fat-soluble pigments of tea, which in turn affects the color and quality of finished tea. Therefore, there is an urgent demand for the fast, non-destructive detection of pigments of stacked tea during processing. This paper presents the use of hyperspectral imaging technology (HSI), combined with machine learning algorithms, to detect chlorophyll a, chlorophyll b, and carotenoids in stacked matcha tea during processing. Firstly, a quantitative relationship between HSI data of tea and their pigment contents was developed based on regression analysis, and the results showed that exceptional prediction performance was achieved by the partial least squares regression (PLSR) algorithm combined with the feature band algorithm of competitive adaptive reweighting (CARS), and the Rp2 values of detection models of chlorophyll a, chlorophyll b and carotenoids were 0.90465, 0.92068 and 0.62666, respectively. Then, these quantitative detection models were extended to each pixel in hyperspectral images, achieving point-by-point prediction of pigment components, so the distribution of pigments of stacked tea leaves during processing procedures was successfully visualized on the processing line in situ. By integrating a hyperspectral imaging system into the real-world environment, operators can monitor pigment levels in real time and thus dynamically adjust processing parameters based on real-time data. This study enhances pigment detection efficiency in tea processing, supports process optimization, and aids in quality control.

Offline Reinforcement Learning for Adaptive Control in Manufacturing Processes: A Press Hardening Case Study

Abstract This paper explores the application of offline reinforcement learning in batch manufacturing, with a specific focus on press hardening processes. Offline reinforcement learning presents a viable alternative to traditional control and reinforcement learning methods, which often rely on impractical real-world interactions or complex simulations and iterative adjustments to bridge the gap between simulated and real-world environments. We demonstrate how offline reinforcement learning can improve control policies by leveraging existing data, thereby streamlining the training pipeline and reducing reliance on high-fidelity simulators. Our study evaluates the impact of varying data exploration rates by creating five datasets with exploration rates ranging from ε=0 to ε=0.8. Using the conservative Q-learning algorithm, we train and assess policies against both a dynamic baseline and a static industry-standard policy. The results indicate that while offline reinforcement learning effectively refines behavior policies and enhances supervised learning methods, its effectiveness is heavily dependent on the quality and exploratory nature of the initial behavior policy.

Artificial Intelligence to Support the Training and Assessment of Professionals: A Systematic Literature Review

Advances in Artificial Intelligence (AI) and sensors are significantly impacting multiple areas, including education and workplaces. Following the PRISMA methodology, this review explores the current status of using AI to support the training and assessment of professionals. We examined 83 research papers, analyzing (1) the targeted professionals, (2) the skills assessed, (3) the AI algorithms utilized, (4) the data and devices employed, (5) data fusion techniques utilized, (6) the architecture of the proposed platforms, (7) the management of ethics and privacy, and (8) validations of the proposals. The review highlights a trend in evaluating healthcare professionals (especially surgeons) motivated by the critical role of hands-on training in these professions. Besides, the review reveals that data fusion techniques and certain technologies, like transfer learning and explainable AI, are not widely utilized despite their huge potential. Finally, the review underscores that most proposals remain within the research domain, lacking the integration and maturity needed for sustained use in real-world environments. Therefore, most of the proposals are not currently available to support the training of professionals. The insights of this review can guide researchers aiming to improve the training of professionals and, consequently, their education.

Comparison of CNN-Based Architectures for Detection of Different Object Classes

(1) Background: Detecting people and technical objects in various situations, such as natural disasters and warfare, is critical to search and rescue operations and the safety of civilians. A fast and accurate detection of people and equipment can significantly increase the effectiveness of search and rescue missions and provide timely assistance to people. Computer vision and deep learning technologies play a key role in detecting the required objects due to their ability to analyze big volumes of visual data in real-time. (2) Methods: The performance of the neural networks such as You Only Look Once (YOLO) v4-v8, Faster R-CNN, Single Shot MultiBox Detector (SSD), and EfficientDet has been analyzed using COCO2017, SARD, SeaDronesSee, and VisDrone2019 datasets. The main metrics for comparison were mAP, Precision, Recall, F1-Score, and the ability of the neural network to work in real-time. (3) Results: The most important metrics for evaluating the efficiency and performance of models for a given task are accuracy (mAP), F1-Score, and processing speed (FPS). These metrics allow us to evaluate both the accuracy of object recognition and the ability to use the models in real-world environments where high processing speed is important. (4) Conclusion: Although different neural networks perform better on certain types of metrics, YOLO outperforms them on all metrics, showing the best results of mAP-0.88, F1-0.88, and FPS-48, so the focus was on these models.

A Detailed Inspection of Machine Learning Based Intrusion Detection Systems for Software Defined Networks

The growing use of the Internet of Things (IoT) across a vast number of sectors in our daily life noticeably exposes IoT internet-connected devices, which generate, share, and store sensitive data, to a wide range of cyber threats. Software Defined Networks (SDNs) can play a significant role in enhancing the security of IoT networks against any potential attacks. The goal of the SDN approach to network administration is to enhance network performance and monitoring. This is achieved by allowing more dynamic and programmatically efficient network configuration; hence, simplifying networks through centralized management and control. There are many difficulties for manufacturers to manage the risks associated with evolving technology as the technology itself introduces a variety of vulnerabilities and dangers. Therefore, Intrusion Detection Systems (IDSs) are an essential component for keeping tabs on suspicious behaviors. While IDSs can be implemented with more simplicity due to the centralized view of an SDN, the effectiveness of modern detection methods, which are mainly based on machine learning (ML) or deep learning (DL), is dependent on the quality of the data used in their modeling. Anomaly-based detection systems employed in SDNs have a hard time getting started due to the lack of publicly available data, especially on the data layer. The large majority of existing literature relies on data from conventional networks. This study aims to generate multiple types of Distributed Denial of Service (DDoS) and Denial of Service (DoS) attacks over the data plane (Southbound) portion of an SDN implementation. The cutting-edge virtualization technology is used to simulate a real-world environment of Docker Orchestration as a distributed system. The collected dataset contains examples of both benign and suspicious forms of attacks on the data plane of an SDN infrastructure. We also conduct an experimental evaluation of our collected dataset with well-known machine learning-based techniques and statistical measures to prove their usefulness. Both resources we build in this work (the dataset we create and the baseline models we train on it) can be useful for researchers and practitioners working on improving the security of IoT networks by using SDN technologies.

Towards Water Systems Security and Sustainability Using Deep Learning

Wastewater treatment plants (WWTPs) face significant challenges due to varying influent conditions, multiple operational constraints, and a constant lack of reliable datasets to manage and monitor water quality and flow using automated approaches. This paper introduces a novel framework showcasing soft sensors that are aimed at enhancing the sustainability and security of wastewater quality indicators using deep learning. We develop a trustworthy soft sensor that utilizes artificial intelligence (AI) approaches to provide nitrate NO3 predictions at the WWTP, as well as context-based evaluations to estimate overall predictive uncertainty. Contextual elements are injected into the model to allow for more accurate and relevant water quality monitoring, especially in different conditions (such as rain and snow). In addition, in this paper, we present a time-series Generative Adversarial Network (GAN), namely H2OGAN to address data scarcity and to improve model training by generating synthetic data that mirrors the statistical properties of water datasets from both controlled and real-world environments. Data in turn also train against data poisoning attacks on water supply systems, rendering these systems more secure. Our results indicate the potential uses of the integration of soft sensors and H2OGAN to significantly improve the operational efficiency of WWTPs by providing robust AI-driven tools for offering secure and sustainable water monitoring solutions.

Mixed reality applications in upper extremity surgery: the future is now.

Mixed reality refers to the integration of virtual reality into the real-world environment. This digital content can be interacted with in real time. The emergence of mixed reality technology has been made possible by the introduction of head-mounted displays, which are being utilized across multiple surgical specialties. In upper extremity surgery, mixed reality has widespread applications in trauma, corrective surgery, arthroplasty, arthroscopy, and oncology. Preoperatively, mixed reality allows for complex 3D planning. Intraoperatively, surgeons can access this 3D data in a sterile environment. While in its infant stages, mixed reality is likely to become a powerful tool for intraoperative guidance and navigation. Mixed reality can change the paradigm of communication, as it allows the sharing of visual data from the surgeon's perspective, enabling remote assistance and participation.

Unreal that feels real: artificial intelligence-enhanced augmented reality for treating social and occupational dysfunction in post-traumatic stress disorder and anxiety disorders

ABSTRACT Background: Fear- and trauma-related conditions, such as post-traumatic stress disorder (PTSD) and social phobia, often manifest as socially avoidant behaviours, which commonly contribute to social and occupational disability transdiagnostically. While gold-standard treatments (i.e. exposure therapy, psychotropic medications) are effective, they are hindered by high dropout rates and limited impact on real-world functioning. Furthermore, most existing interventions only target symptom reduction, with few addressing avoidance-related deficits in social and occupational functioning. Objectives: This methods paper introduces an innovative augmented reality exposure therapy (ARET) technology designed to address the limitations of traditional interventions for anxiety disorders and PTSD, by directly targeting social and occupational dysfunction through exposure to real-life social contexts. Method: We introduce an ARET system, using artificial intelligence (AI)-driven, augmented reality (AR) technology, that enables exposure to realistic scenarios within the patient's real-world environment, fostering contextual generalization and functional improvement. Featuring holographic three-dimensional humans, precise surface mapping, wireless mobility, and telemedicine capabilities, the software provides customizable exposure scenarios to transform an environment into various spaces (e.g. grocery store, house party) with diverse human characters, as well as flexible AI-driven human interactions tailored to individual needs. Results: We share observations and feedback from the treatment of first responders with PTSD. Patients found the technology easy to use, with immersive realism, active engagement, and strong emotional responses needed for effective exposure therapy. Advances in AI-driven character development and AR hardware accessibility support the wider adoption of ARET by clinicians. Conclusion: By bridging the gap between clinical interventions and real-world functioning, ARET offers a transformative approach to addressing the pervasive impact of psychiatric disorders on social and occupational outcomes.

Direct piriform-to-auditory cortical projections shape auditory-olfactory integration.

In a real-world environment, the brain must integrate information from multiple sensory modalities, including the auditory and olfactory systems. However, little is known about the neuronal circuits governing how odors influence and modulate sound processing. Here, we investigated the mechanisms underlying auditory-olfactory integration using anatomical, electrophysiological, and optogenetic approaches, focusing on the auditory cortex as a key locus for cross-modal integration. First, retrograde and anterograde viral tracing strategies revealed a direct projection from the piriform cortex to the auditory cortex. Next, using in vivo electrophysiological recordings of neuronal activity in the auditory cortex of awake male or female mice, we found that odors modulate auditory cortical responses to sound. Finally, we used in vivo optogenetic manipulations during electrophysiology to demonstrate that olfactory modulation in auditory cortex, specifically, odor-driven enhancement of sound responses, depends on direct input from the piriform cortex. Together, our results identify a novel role of piriform-to-auditory cortical circuitry in shaping olfactory modulation in the auditory cortex, shedding new light on the neuronal mechanisms underlying auditory-olfactory integration.Significance Statement All living organisms exist within multisensory environments, yet there is a lack in our understanding of how the brain integrates multisensory information. This work highlights a direct piriform-to-auditory cortical circuit governing auditory-olfactory integration. Our results shed new light on a relatively understudied area of multisensory research, promising a more robust understanding of how animals and humans perceive and interact within complex environments.

A proactive defense method against eavesdropping attack in SDN-based storage environment

The integration of Software-Defined Networking (SDN) in storage centers aims to enhance storage performance. However, this integration also introduces new concerns, particularly the potential eavesdropping attacks that pose a substantial risk to data privacy. By issuing flow tables (e.g., via compromised SDN switches), attackers can conveniently collect target traffic and extract confidential information with session reassembly methods. To proactively mitigate such attacks by preventing session reassembly, various moving target defense methods, such as end hopping, have been proposed. However, this study uncovers several deficiencies within existing end hopping methods. To address these deficiencies, we propose a novel linkage-field-based self-synchronizing end hopping method, which obfuscates end information (e.g., IP, Port) and linkage fields (e.g., sequence number and ID number) without third-party assistance. Furthermore, to counter the potential invalidation of end hopping methods resulting from brute-force reassembly of a small number of sessions, we propose a fake segment injection method. Extensive experiments have been conducted both in simulation and real-world environment to evaluate the effectiveness of our proposed methods. The results demonstrate that our proposed methods can effectively defend against eavesdropping attacks with acceptable performance overhead.

Linking theory and practice to advance sustainable healthcare: the development of maturity model version 1.0.

Climate change and increased awareness of planetary health have made reducing ecological footprints a priority for healthcare organizations. However, improving healthcare's environmental impact remains difficult. Numerous researchers argue these difficulties are caused by healthcare's environmental impact being multidimensional, influenced throughout the healthcare chain, and often has downstream consequences that are hard to identify or to measure. Even though existing research describes many successful approaches to reduce healthcare's environmental impact, a robust multidimensional framework to assess this impact is lacking. This research aims at developing a maturity model for sustainable healthcare that could be used for self-assessment by healthcare professionals to identify improvement actions and for sharing best practices in environmental sustainability. A design-oriented approach for maturity model development was combined with an expert panel and six case studies to develop, refine and expand the maturity model for environmentally sustainable healthcare. A maturity model was developed containing four domains: 'Governance', 'Organization Structures', 'Processes', and 'Outcomes and Control'. Applying the model in real-world environments demonstrated the model's understandability, ease of use, usefulness, practicality and ability to identify improvement actions for environmental sustainability in healthcare organizations. This study found that healthcare practitioners could apply the maturity model developed and tested in this study in several hours without training to help them gain valuable insights into the environment footprint of the healthcare setting they worked in. Systematically implementing the model developed in this study could help address the urgent need to mitigate the substantial environmental impact of healthcare. These implementations can help evaluate and improve the maturity model.

A Survey on Emerging Trends and Applications of 5G and 6G to Healthcare Environments

A delay, interruption, or failure in the wireless connection has a significant impact on the performance of wirelessly connected medical equipment. Researchers presented the fastest technological innovations and industrial changes to address these problems and improve the applications of information and communication technology. The development of the 6G communication infrastructure was greatly aided by the use of Block-chain technology, artificial intelligence (AI), virtual reality (VR), and the Internet of Things (IoT). In this paper, we comprehensively discuss 6G technologies enhancement, its fundamental architecture, difficulties, and other issues associated with it. In addition, the outcomes of our research help make 6G technology more applicable to real-world medical environments. The most important thing that this study has contributed is an explanation of the path that future research will take and the current state of the art. This study might serve as a jumping-off point for future researchers in the academic world who are interested in investigating the possibilities of 6G technological developments.

The Trail Making Test in Virtual Reality (TMT-VR): The Effects of Interaction Modes and Gaming Skills on Cognitive Performance of Young Adults

Virtual Reality (VR) is increasingly used in neuropsychological assessments due to its ability to simulate real-world environments. This study aimed to develop and evaluate the Trail Making Test in VR (TMT-VR) and investigate the effects of different interaction modes and gaming skills on cognitive performance. A total of 71 young female and male adults (aged 18–35) with high and low gaming skills participated in this study. Participants completed the TMT-VR using three interaction modes as follows: eye-tracking, head movement, and controller. Performance metrics included task completion time and accuracy. User experience, usability, and acceptability of TMT-VR were also examined. Results showed that both eye tracking and head movement modes significantly outperformed the controller in terms of task completion time and accuracy. No significant differences were found between eye tracking and head movement modes. Gaming skills did not significantly influence task performance using any interaction mode. The TMT-VR demonstrates high usability, acceptability, and user experience among participants. The findings suggest that VR-based assessments can effectively measure cognitive performance without being influenced by prior gaming skills, indicating potential applicability for diverse populations.

Intercalated amygdala dysfunction drives avoidance extinction deficits in the Sapap3 mouse model of obsessive-compulsive disorder

The avoidance of aversive stimuli through negative reinforcement learning is critical for survival in real-world environments, which demand dynamic responding to both positive and negative stimuli that often conflict with each other. Individuals with obsessive-compulsive disorder (OCD) commonly exhibit impaired negative reinforcement and extinction, perhaps involving deficits in amygdala functioning. An amygdala subregion of particular interest is the intercalated nuclei of the amygdala (ITC) which has been linked to negative reinforcement and extinction, with distinct clusters mediating separate aspects of behavior. This study focuses on the dorsal ITC cluster (ITCd) and its role in negative reinforcement during a complex behavior that models real-world dynamic decision making. We investigated the impact of ITCd function on negative reinforcement and extinction by applying fiber photometry measurement of GCamp6f signals and optogenetic manipulations during a platform-mediated avoidance task in a mouse model of OCD-like behavior: the Sapap3-null mouse. We find impaired neural activity in the ITCd of male and female Sapap3-null mice to the encoding of negative stimuli during platform-mediated avoidance. Sapap3-null mice also exhibit deficits in extinction of avoidant behavior, which is modulated by ITCd neural activity. Sapap3-null mice fail to extinguish avoidant behavior in platform-mediated avoidance, due to heightened ITCd activity. This deficit can be rescued by optogenetically inhibiting ITCd during extinction. Together, our results provide insight into the neural mechanisms underpinning negative reinforcement deficits in the context of OCD, emphasizing the necessity of ITCd in responding to negative stimuli in complex environments.

Differential Analysis of Modern Text Spotting Methods : A Systematic Review

Text spotting, the task of detecting and recognizing text within images, is vital in applications like document analysis, autonomous navigation, and surveillance. The motivation for this review arises from the growing need for accurate automated text extraction methods, driven by the surge of visual data and the complexity of real-world environments. Despite advances in deep learning and computer vision, current text spotting techniques face significant challenges, including handling complex backgrounds, curved or distorted text, varied font styles, and low-resolution images. These limitations restrict their effectiveness in diverse, real-world settings. This systematic review aims to conduct a differential analysis of modern text spotting methods, highlighting their strengths, weaknesses, and performance in addressing such challenges. The objectives are to evaluate state-of-the-art techniques, identify gaps in the field, and propose future research directions. By critically synthesizing recent literature, this review provides insights that can help enhance the robustness and accuracy of text spotting systems, making them more adaptable to real-world conditions.

Character region extraction of wheel water meter based on object detection

Currently, research on automatic meter reading mainly focuses on meter reading recognition, while neglecting the fundamental role of counter detection in the entire automatic meter reading system. In fact, only by accurately locating the counter area can the influence of dial factors be completely eliminated, thus ensuring the accuracy and reliability of subsequent water meter reading recognition. In view of this phenomenon, the focus of this study is on the counter detection stage. Firstly, a target detection-based image skew correction method is proposed to solve the problem of image skew caused by shooting angle and other reasons. This method ensures the accuracy of subsequent counter area positioning and the neatness of cutting effect. Secondly, a semi-supervised target detection training method is proposed to solve the problem of time and manpower costs required in large-scale data situations. In addition, we have made publicly available a dataset containing 1070 water meter images for non-commercial purposes, which can be obtained from the Github11https://github.com/QuanhuiZhao/water-datasets.. Finally, we evaluated our model on three completely different datasets and compared it with the best positioning results of other models. The experimental results show that compared with other models, the proposed model in this paper has improved the positioning accuracy by 5.82%, 5.96%, and 9.20% on three datasets respectively. Furthermore, in the final visualization comparison, the model accurately identifies the counter region even when faced with complex real-world environments.

Assessment of sleep patterns in dementia and general population cohorts using passive in-home monitoring technologies

BackgroundNocturnal disturbances are a common symptom experienced by People Living with Dementia (PLWD), and these often present prior to diagnosis. Whilst sleep anomalies have been frequently reported, most studies have been conducted in lab environments, which are expensive, invasive and not natural sleeping environments. In this study, we investigate the use of in-home nocturnal monitoring technologies, which enable passive data collection, at low cost, in real-world environments, and without requiring a change in routine.MethodsClustering analysis of passively collected sleep data in the natural sleep environment can help identify distinct sub-groups based on sleep patterns. The analysis uses sleep activity data from; (1) the Minder study, collecting in-home data from PLWD and (2) a general population dataset (combined n = 100, >9500 person-nights).ResultsUnsupervised clustering and profiling analysis identifies three distinct clusters. One cluster is predominantly PLWD relative to the two other groups (72% ± 3.22, p = 6.4 × 10−7, p = 1.2 × 10−2) and has the highest mean age (77.96 ± 0.93, p = 6.8 × 10−4 and p = 6.4 × 10−7). This cluster is defined by increases in light and wake after sleep onset (p = 1.5 × 10−22, p = 1.4 × 10−7 and p = 1.7 × 10−22, p = 1.4 × 10−23) and decreases in rapid eye movement (p = 5.5 × 10−12, p = 5.9 × 10−7) and non-rapid eye movement sleep duration (p = 1.7 × 10−4, p = 3.8 × 10−11), in comparison to the general population.ConclusionsIn line with current clinical knowledge, these results suggest detectable dementia sleep phenotypes, highlighting the potential for using passive digital technologies in PLWD, and for detecting architectural sleep changes more generally. This study indicates the feasibility of leveraging passive in-home technologies for disease monitoring.

From Generative AI to Objective-Driven Systems: A Paradigm Shift in Artificial Intelligence

Marwan Omar 1Illinois Institute of Technology Email: momar3@iit.edu Abstract The rapid advancement of Artificial Intelligence (AI), particularly in the domain of generative models, has led to impressive achievements in content creation and natural language processing. However, these models are inherently limited by their reliance on pattern recognition and lack of true understanding. In contrast, Objective-Driven AI offers a promising alternative by focusing on goal-oriented behavior, causal reasoning, and the development of world models. This paper explores the limitations of generative AI, highlighting its inability to grasp context, causality, and ethical considerations. It then presents the concept of Objective-Driven AI, emphasizing its potential to operate effectively in complex, real-world environments where understanding and reasoning are critical. The paper concludes with a discussion of future research directions, including advanced world modeling techniques, ethical AI, and robustness against adversarial attacks, which are essential for the further development of Objective-Driven AI systems. Keywords Objective-Driven AI, Generative AI, Causal Reasoning, World Modeling, Ethical AI, Artificial Intelligence, Adversarial Attacks, Machine Learning, Autonomous Systems

L-GraphSAGE: A Graph Neural Network-Based Approach for IoV Application Encrypted Traffic Identification

Recently, with a crucial role in developing smart transportation systems, the Internet of Vehicles (IoV), with all kinds of in-vehicle devices, has undergone significant advancement for autonomous driving, in-vehicle infotainment, etc. With the development of these IoV devices, the complexity and volume of in-vehicle data flows within information communication have increased dramatically. To adapt these changes to secure and smart transportation, encrypted communication realization, real-time decision-making, traffic management enhancement, and overall transportation efficiency improvement are essential. However, the security of a traffic system under encrypted communication is still inadequate, as attackers can identify in-vehicle devices through fingerprinting attacks, causing potential privacy breaches. Nevertheless, existing IoV traffic application models for encrypted traffic identification are weak and often exhibit poor generalization in some dynamic scenarios, where route switching and TCP congestion occur frequently. In this paper, we propose LineGraph-GraphSAGE (L-GraphSAGE), a graph neural network (GNN) model designed to improve the generalization ability of the IoV application of traffic identification in these dynamic scenarios. L-GraphSAGE utilizes node features, including text attributes, node context information, and node degree, to learn hyperparameters that can be transferred to unknown nodes. Our model demonstrates promising results in both UNSW Sydney public datasets and real-world environments. In public IoV datasets, we achieve an accuracy of 94.23%(↑0.23%). Furthermore, our model achieves an F1 change rate of 0.20%(↑96.92%) in α train, β infer, and 0.60%(↑75.00%) in β train, α infer when evaluated on a dataset consisting of five classes of data collected from real-world environments. These results highlight the effectiveness of our proposed approach in enhancing IoV application identification in dynamic network scenarios.