In-service Research Articles

The Advantages and Disadvantages of Electric Vehicle Production and Its Future Prospects

Continued research and innovation on its technology can promote the development of the new energy vehicle industry and strengthen the rapid development of economy. China needs to import a lot of oil from abroad, posing risks of oil resources exhaustion in the future. In this context, it is particularly important to reduce dependence on oil resources and vigorously develop new energy vehicle technologies. This paper describes the development status of new energy vehicles, the advantages and disadvantages of the development of new energy vehicles. It emphasizes the development drawbacks of new energy trams and the feedback of the masses. The paper argues that, with the breakthrough of battery technology, the improvement of charging infrastructure and the popularization of intelligent networking functions, new energy vehicles are not only a means of transportation, but also an important part of intelligent travel solutions. New energy vehicles and their drive motor technologies will remain to be the main path toward the green revolution in the field of transportation and contribute to the construction of a low-carbon and environmentally friendly society.

Synthetic Data Generation for AI-Informed End-of-Line Testing for Lithium-Ion Battery Production

Lithium-ion batteries are a key technology in supply chains for modern electric vehicles. Their production is complex and can be prone to defects. As such, the detection of defective batteries is critical to ensure performance and consumer safety. Existing end-of-line testing relies heavily on electrical measurements for identifying defective cells. However, it is possible that not all pertinent information is encoded within the electrical measurements alone. Reversible expansion in lithium-ion cells is an indicator of lithiation within the cell, while irreversible expansion is a consequence of the ageing process; unexpected expansion may indicate the presence of undesirable defects. By measuring expansion in addition to electrical measurements, we aim to make better and faster quality predictions during end-of-line testing, thereby facilitating the early detection of potential defects. To make these predictions, we implement artificial intelligence algorithms to extract information from the measurements. Training these networks requires large training datasets, which are expensive to produce. In this paper, we demonstrate a first-order physical modelling approach for generating synthetic data to pre-train artificial intelligence algorithms that perform anomaly detection on lithium-ion battery cells at the end-of-line. The equivalent circuit model used to generate voltage curves could be fit to real data with a mean absolute error of less than 1%, and the expansion model could be fit to a mean absolute error of less than 2% of the measured values. By pretraining the artificial intelligence network using synthetic data, we can leverage existing physical models to reduce the amount of training data required.

Intelligent network intrusion detection system using optimized deep CNN-LSTM with UNSW-NB15

Intelligent network intrusion detection system using optimized deep CNN-LSTM with UNSW-NB15

A multi-source data-driven approach for navigation safety integrating computational intelligence and Bayesian networks

Ships often face various risks when sailing at sea, ranging from harsh natural environments to complex traffic conditions. To reduce the impact of these risks on ships and crews, this paper proposes a navigation risk assessment method that integrates computational intelligence (CI) techniques, such as fuzzy logic, with Bayesian networks (BNs) and utility theory. Firstly, a navigation risk assessment system is established using maritime data and expert knowledge, which evaluates risks from a spatial perspective by considering factors such as safeguard and accident conditions across different regions. Secondly, a fuzzy logic-based numerical and expert data transformation method is proposed to derive the prior probabilities of risk factors in BNs. The weighted fuzzy rule base is used to capture the dependencies among the risk factors. Finally, the probability distribution of navigation risk is determined by combining the prior probability and the dependencies, which are converted into risk index values through utility theory. Taking the grid-based navigation risk assessment of the South China Sea as an example, the effectiveness of this method is verified. The results of the study provide theoretical support for navigation risk assessment based on multi-source data and provide a reference for formulate maritime regulatory policies.

Artificial Intelligence in the Heart of Medicine: Transforming Arrhythmia Care with Intelligent Systems.

At a critical juncture in the ongoing fight against cardiovascular disease (CVD), healthcare professionals are striving for more informed and expedited decisionmaking. Artificial Intelligence (AI) promises to be a guiding light in this endeavor. The diagnosis of coronary artery disease has now become non-invasive and convenient, while wearable devices excel at promptly detecting life-threatening arrhythmias and treatments for heart failure. This study aimed to highlight the applications of AI in cardiology with a particular focus on arrhythmias and its potential impact on healthcare for all through careful implementation and constant research efforts. An extensive search strategy was implemented. The search was conducted in renowned electronic medical databases, including Medline, PubMed, Cochrane Library, and Google Scholar. Artificial Intelligence, cardiovascular diseases, arrhythmias, machine learning, and convolutional neural networks in cardiology were used as keywords for the search strategy. A total of 6876 records were retrieved from different electronic databases. Duplicates (N = 1356) were removed, resulting in 5520 records for screening. Based on predefined inclusion and exclusion criteria, 4683 articles were excluded. Following the full-text screening of the remaining 837 articles, a further 637 were excluded. Ultimately, 200 studies were included in this review. AI represents not just a development but a cutting-edge force propelling the next evolution of cardiology. With its capacity to make precise predictions, facilitate non-invasive diagnosis, and personalize therapies, AI holds the potential to save lives and enhance healthcare quality on a global scale.

Optimizing Bandwidth Allocation in Converged Networks Using Hybrid Deep Learning Model

The demand for high-speed network services and the increasing development of network traffic have led to the popularity of converged networks, which mix various services over a single infrastructure. However, because of the variety of application requirements and resource constraints, ensuring quality of service (QoS) in these networks is difficult. Conventional methods for allocating bandwidth are frequently static, reactive, and inefficient, which results in less-than-ideal network performance. We provide a unique deep learning method to optimize bandwidth allocation in convergent networks in order to overcome this. We create and use three deep learning models: Deep Q-Networks (DQN), Generative Adversarial Networks (GAN), and a special LSTM-based DQN model. We assess each model's performance using an extensive dataset. Our results show that the Novel DQN model performs better than the other models in terms of minimum packet loss, increased accuracy, decreased latency, throughput maximization, spectral efficiency optimization, bit error rate reduction, fairness assurance, and effective channel resource use. Better service quality is the outcome of these upgrades, which also significantly increase upload and download speeds. Our empirical studies demonstrate our methodology's usefulness in real-world scenarios and open the door to intelligent network management solutions that facilitate better QoS, efficient bandwidth allocation, and improved user experiences in converged networks.

Assessment of deep learning technique for fully automated mandibular segmentation.

This study aimed to assess the precision of an open-source, clinician-trained, and user-friendly convolutional neural network-based model for automatically segmenting the mandible. A total of 55 cone-beam computed tomography scans that met the inclusion criteria were collected and divided into test and training groups. The MONAI (Medical Open Network for Artificial Intelligence) Label active learning tool extension was used to train the automatic model. To assess the model's performance, 15 cone-beam computed tomography scans from the test group were inputted into the model. The ground truth was obtained from manual segmentation data. Metrics including the Dice similarity coefficient, Hausdorff 95%, precision, recall, and segmentation times were calculated. In addition, surface deviations and volumetric differences between the automated and manual segmentation results were analyzed. The automated model showed a high level of similarity to the manual segmentation results, with a mean Dice similarity coefficient of 0.926 ± 0.014. The Hausdorff distance was 1.358 ± 0.466 mm, whereas the mean recall and precision values were 0.941 ± 0.028 and 0.941 ± 0.022, respectively. There were no statistically significant differences in the arithmetic mean of the surface deviation for the entire mandible and 11 different anatomic regions. In terms of volumetric comparisons, the difference between the 2 groups was 1.62 mm³, which was not statistically significant. The automated model was found to be suitable for clinical use, demonstrating a high degree of agreement with the reference manual method. Clinicians can use open-source software to develop custom automated segmentation models tailored to their specific needs.

Soft Actor–Critic optimization for efficient NOMA uplink in intelligent vehicular networks

Soft Actor–Critic optimization for efficient NOMA uplink in intelligent vehicular networks

Optimizing Secure Communication in Intelligent Transportation Networks with Certificate-less Authorization in VANETs

As an outcome of technology progress, among the most widely used design models in intelligent transportation networks is Vehicular Ad-hoc Networks (VANETs). Assistance for Vehicle to Vehicle (V2V) connectivity is offered via VANETs. Automobile access to actual time traffic, weather, and transportation data is made possible via VANETs, which also assure traffic safety and effectiveness. The legitimacy of an organisation providing data is a crucial factor that must be taken seriously in order to ensure secure interaction in VANETs. In regards to safety mutual identification along with safe distribution of keys in VANETs continue to pose certain disadvantages considering that numerous protocols that have been suggested. However, since they depend on the authorised authority, they are susceptible to assaults through the firewall and Reliable Control (RC), which may raise safety issues amongst customers. we provide a certificate less secure authorization system that lessens the load on automobiles' internal storage and satisfies the delay criterion by doing away with certificate. The suggested system is strong and resistant against attacks from malevolent users

A deep learning analysis for dual healthcare system users and risk of opioid use disorder

The opioid crisis has disproportionately affected U.S. veterans, leading the Veterans Health Administration to implement opioid prescribing guidelines. Veterans who receive care from both VA and non-VA providers—known as dual-system users—have an increased risk of Opioid Use Disorder (OUD). The interaction between dual-system use and demographic and clinical factors, however, has not been previously explored. We conducted a retrospective study of 856,299 patient instances from the Washington DC and Baltimore VA Medical Centers (2012–2019), using a deep neural network (DNN) and explainable Artificial Intelligence to examine the impact of dual-system use on OUD and how demographic and clinical factors interact with it. Of the cohort, 146,688(17%) had OUD, determined through Natural Language Processing of clinical notes and ICD-9/10 diagnoses. The DNN model, with a 78% area under the curve, confirmed that dual-system use is a risk factor for OUD, along with prior opioid use or other substance use. Interestingly, a history of other drug use interacted negatively with dual-system use regarding OUD risk. In contrast, older age was associated with a lower risk of OUD but interacted positively with dual-system use. These findings suggest that within the dual-system users, patients with certain risk profiles warrant special attention.

Internet of Vehicles Security Improvement Based Controller Area Network and Artificial Intelligence

Internet of Vehicles Security Improvement Based Controller Area Network and Artificial Intelligence

Machine Learning Algorithms for Intrusion Detection in WSNs

Machine learning (ML) has emerged as a potent tool for optimizing network performance and extending network lifespans. By automating complex data processing tasks, ML algorithms enable real-time solutions that optimize resource allocation and utilization. ML's ability to process vast, intricate datasets with speed and precision empowers networks to adapt dynamically to evolving demands. [13]. Wireless Sensor Networks (WSNs), composed of interconnected sensor and sink nodes, exemplify the transformative potential of ML. These distributed, decentralized networks inherently possess self-organization and self-healing capabilities. By integrating ML techniques, WSNs can significantly enhance their efficiency, reliability, and scalability, enabling a wide array of applications, from environmental monitoring to military operations. As advancements in electronics and wireless communication continue to drive WSN evolution, the fusion of ML and WSNs promises to unlock new horizons in network intelligence and performance. However, WSNs face several challenges, including resource constraints such as limited memory, processing power, and energy. Additionally, the physical infrastructure of WSNs must be secured to protect sensitive data, especially in privacy-critical applications. To address these challenges, the integration of machine learning offers a promising solution. By leveraging ML techniques, WSNs can adapt to dynamic environments, optimize energy consumption, and detect and mitigate potential security threats. This enables the deployment of WSNs in diverse applications, from environmental monitoring to smart cities, while ensuring data privacy and system security. Keywords: Intrusion Detection System (IDS), Security, Wireless Sensor Network (WSN), Attacks, Reinforcement Learning (RL), Denial-of-Service (DoS), Networks, Machine Learning (ML)

Unified monitoring and telemetry platform supporting network intelligence in optical networks

In recent years, machine-learning (ML) applications have generated considerable interest and shown great potential in optimizing optical network management, such as quality of transmission estimation, traffic prediction, and resource allocation. However, these applications often require large datasets for training, inference, and updating, while network operators are generally reluctant to disclose their data due to privacy concerns and the sensitivity of operational information. Most open-source datasets typically lack transparency regarding network specifics, such as topology details and device configurations, making data acquisition and ML model training more difficult. In response, this paper presents a unified monitoring and telemetry platform that leverages distributed and centralized time-series databases on InfluxDB, a Kafka-based telemetry pipeline, and advanced ML applications. The separation of distributed and centralized databases improves data management flexibility and scalability. The Kafka-based telemetry pipeline ensures high-throughput, low-latency data streaming with end-to-end latency under 0.05 s through optimized partitioning. Additionally, integrating Kafka and InfluxDB allows for real-time data visualization from multiple sources, improving transparency and supporting real-time data streaming for network applications. By implementing this advanced telemetry and ML architecture, network operators can build a more intelligent, responsive, and resilient optical network infrastructure.

Construction of an Intelligent Medical Monitoring System Network for Exercise Rehabilitation Based on the Internet of Things

Exercise rehabilitation refers to a rehabilitation method that restores or improves human motor function through scientific, systematic, and regular exercise training, and it has a very wide range of applications. This paper explored the construction of an intelligent medical monitoring system network for sports rehabilitation based on the Internet of Things (IoT) technology. The system consists of a wireless sensor acquisition module for collecting sports rehabilitation data, a data storage and analysis module for cloud management and deep learning analysis, and a medical monitoring module for remote supervision and patient interaction. The system aimed to achieve personalized exercise rehabilitation plans through real-time monitoring and data collection of patients, and provide remote medical monitoring services to improve the rehabilitation effect and quality of life of patients. The system architecture adopted the IoT technology and cloud storage technology, and combined the deep learning convolutional neural network (CNN) model to achieve remote monitoring and data analysis. The monitoring center of the system can monitor patients’ physiological indicators, exercise status, and rehabilitation effects in real time through IoT wireless sensors, and upload the data to the cloud platform for storage and analysis. Doctors and patients can access data through mobile phones or computers and communicate online. The data showed that when measuring a patient’s heart rate using wireless sensors, the measurement accuracy mostly exceeded 99.8%, and some samples had detection accuracy up to 100%. In addition, traditional sensors can detect heart rates up to 5.1[Formula: see text]s, while wireless sensors can detect heart rates up to 1.28[Formula: see text]s. The CNN had a maximum recall rate of 99.51%, a precision of 99.68%, and an accuracy rate of 99.8% in the classification of psychological data of rehabilitation patients. The experimental results indicated that the system can achieve comprehensive monitoring and effective management of the patient’s rehabilitation process, and its operation is stable and has good practical value.

New Energy Access Distribution Network Line Loss Management Based on Deep Learning and Fuzzy Algorithm

This paper introduces a novel method for managing line losses in energy access distribution networks, utilizing deep learning and fuzzy algorithms. As new energy sources become more integrated into distribution networks, traditional line loss management techniques struggle to address the complexities and uncertainties that arise. To tackle this issue, a comprehensive model for line loss management is developed, leveraging the predictive strengths of deep learning alongside the fuzzy algorithm’s capability to handle uncertainty. The deep learning model forecasts the operational conditions of the power grid following the integration of new energy. At the same time, the fuzzy algorithm assesses and adjusts potential line losses, facilitating effective management of distribution network line losses. The model is trained and validated using a comprehensive dataset from the IEEE 39-Bus System, with performance metrics like Accuracy, F1-score, and recall rate evaluated against traditional models like CNN and GAT. The results show that the FGAN model achieves an accuracy of 96.32%, an F1-score of 95.17%, and a recall rate of 97.05%, significantly outperforming baseline models. Experimental findings indicate that this proposed method substantially reduces line losses and improves the efficiency and reliability of the distribution network. This research offers a fresh perspective on line loss management for intelligent distribution networks in the context of new energy integration, demonstrating considerable practical value.

Review of Research on Hydrostatic Transmission Systems and Control Strategies

In response to the issues of low energy recovery efficiency, single- and low-capacity energy storage methods, and insufficiently diverse control strategies in hydrostatic transmission systems, this paper analyzes hydrostatic systems from the perspectives of hydraulic principles and control strategies. Hydrostatic transmission systems are divided into three types: pump-controlled hydraulic systems, secondary regulation hydraulic systems, and adaptive regulation systems. The design concepts and working principles of hydraulic systems are discussed, and the control strategies for hydrostatic transmission systems are categorized into torque control, fuzzy control, and optimal control strategies. Operating conditions are analyzed, and the advantages and disadvantages of traditional control strategies are compared. The results show that utilizing techniques such as adaptive regulation to reduce the loss of energy in the transfer process and in the transformation of secondary components, as well as combining a variety of methods for integrated control, can effectively improve the efficiency of these systems. The development direction of hydrostatic transmission systems is also discussed, including further development into oil–hydraulic hybrid systems, utilization of artificial intelligence technology and network technology, optimized design concepts, and the intelligence of hydrostatic transmission systems.

Securing the Future of E-Commerce: How Scalable Software Transforms Online Shopping

The exponential growth of e-commerce has necessitated robust security measures to protect digital transactions and consumer data. This technical exploration delves into how scalable software architectures revolutionize online shopping security through advanced encryption, authentication, and fraud prevention mechanisms. The transformation of traditional security approaches through zero-trust initiatives, multi-factor authentication, and microservices architecture demonstrates significant improvements in threat detection and response capabilities. Machine learning and artificial intelligence enhance real-time fraud detection, enabling instantaneous transaction analysis while maintaining seamless customer experiences. Behavioral biometrics, device intelligence, and collaborative threat detection networks further strengthen the security infrastructure. The implementation of comprehensive security frameworks, including tokenization and encrypted payment processing, not only safeguards sensitive data but also builds consumer trust. Enhanced compliance measures and transparent security policies establish a foundation for sustainable e-commerce growth, while adaptive security systems continuously evolve to counter emerging threats, ensuring the resilience of digital retail platforms in an increasingly complex threat landscape.

Intelligent Bayesian Neural Networks for Stochastic SVIS Epidemic Dynamics: Vaccination Strategies and Prevalence Fractions with Wiener Process

Real-time forecasting of infectious diseases is crucial for effective public health management, particularly during outbreaks. When infectious disease predictions are based on mechanistic models, they can guide resource allocation and help evaluate the potential effects of different interventions. However, accurately parametrizing these models in real time presents a challenge, as timely information on behavioral shifts, interventions and transmission pathways is often lacking. This investigation leverages the artificial neural networks with the Bayesian regularization (BR-ANN) backpropagation approach to examine the dynamical pathogen spread with Wiener process incorporation. The stochastic differential model is structured into susceptible, vaccinated, infectious and susceptible (SVIS) compartments. The Kloeden–Platen–Schurz (KPS) computing paradigm for the stochastic differential system is utilized to generate synthetic datasets by applying transformations to key factors, including the population recruitment ratio, transmission ratio of vulnerable individuals, natural death rate of the population, vaccination rate of vulnerable individuals, total population size, immune loss ratio of susceptible individuals, recovery rate and mortality rate from the disease among infected individuals. Random selection from the generated datasets is exploited for the training and testing procedures for constructing the BR-ANN networks. The significance of the proposed scheme for various stochastic SVIS system scenarios is endorsed by the comprehensive assessments of the BR-ANN approach that are conducted by means of extensive experimentations and comparison with the reference KPS solutions of the SVIS system in terms of MSE optimal performance plots, absolute errors, autocorrelation analysis, regression indices and error histograms.

A two-tier optimization strategy for feature selection in robust adversarial attack mitigation on internet of things network security

Adversarial attacks were commonly considered in computer vision (CV), but their effect on network security apps rests in the field of open investigation. As IoT, AI, and 5G endure to unite and understand the potential of Industry 4.0, security events and incidents on IoT systems have been enlarged. While IoT networks efficiently deliver intellectual services, the vast amount of data processed and collected in IoT networks also creates severe security concerns. Numerous research works were keen to project intelligent network intrusion detection systems (NIDS) to avert the exploitation of IoT data through smart applications. Deep learning (DL) models are applied to perceive and alleviate numerous security attacks against IoT networks. DL has a considerable reputation in NIDS, owing to its robust ability to identify delicate differences between malicious and normal network activities. While a diversity of models are aimed at influencing DL techniques for security protection, whether these methods are exposed to adversarial examples is unidentified. This study introduces a Two-Tier Optimization Strategy for Robust Adversarial Attack Mitigation in (TTOS-RAAM) model for IoT network security. The major aim of the TTOS-RAAM technique is to recognize the presence of adversarial attack behaviour in the IoT. Primarily, the TTOS-RAAM technique utilizes a min-max scaler to scale the input data into a uniform format. Besides, a hybrid of the coati–grey wolf optimization (CGWO) approach is utilized for optimum feature selection. Moreover, the TTOS-RAAM technique employs the conditional variational autoencoder (CVAE) technique to detect adversarial attacks. Finally, the parameter adjustment of the CVAE model is performed by utilizing an improved chaos African vulture optimization (ICAVO) model. A wide range of experimentation analyses is performed and the outcomes are observed under numerous aspects using the RT-IoT2022 dataset. The performance validation of the TTOS-RAAM technique portrayed a superior accuracy value of 99.91% over existing approaches.

The Role of Learning Analytics in Evaluating Course Effectiveness

This study aims to examine the use of learning analytics in course evaluation within higher education institutions, in order to identify effective methodologies and best practices for leveraging data to improve educational effectiveness. Following the PRISMA guidelines, a systematic literature search was conducted in Scopus, yielding 34 relevant studies published between 2015 and 2024 for analysis. The results reveal six key categories of learning analytics applications: sentiment analysis, questionnaire analysis, engagement analysis, topic classification, predictive modelling, and performance analysis. The data sources for learning analytics applications primarily include questionnaires and learning management systems. While descriptive analysis was found to be the most commonly employed analytical technique, advanced techniques such as machine learning, artificial intelligence, and social network analysis are becoming more prominent. The studies addressed a wide range of elements associated with course evaluation, including course design, content quality, assignments, instructional strategies, workload, feedback mechanisms, and the integration of technology. These findings highlight the importance of adopting holistic approaches to capture the multifaceted nature of student experiences. This study also uncovers major limitations in the existing research, such as small sample sizes, potential biases due to the use of survey-based methods, and challenges in generalising findings across disciplines. These insights underscore the need for further research to enhance the methodologies used in course evaluations. This study contributes to advancing learning analytics practices and emphasises the importance of innovative approaches for evaluating and improving course effectiveness.