检索结果-内蒙古大学图书馆

Energy-Efficient-Enabled Edge-AI-IoT Integrated Traffic Incident Analysis and Avoidance of Secondary Incidents

IEEE Internet of Things Journal 2025年

作者： Chavhan, Suresh Deepika, Illa Sai Gupta, Deepak Rodrigues, Joel J P C Indian Institute of Science Education and Research Thiruvananthapuram School of Data Sciences India Indian Institute of Management Mumbai India Maharaja Agrasen Institute of Technology Dept. of Computer Science and Engineering Delhi India Chitkara University Chitkara University Institute of Engineering and Technology Punjab India Amazonas State University AM Manaus Brazil

Intelligent transportation systems (ITS) use information communication and technologies to provide road safety, traffic control, traffic congestion, accident avoidance, etc. Traffic accidents cause huge disruption of vehicle movements, road blockages, traffic jams, etc., known as secondary traffic incidents. These incidents in turn lead to huge CO2 emissions and fuel consumption, which directly impact the environment, reduce vehicle mileage, and unnecessary fuel waste. To reduce or avoid secondary traffic incidents, in this paper, we propose an Edge-AI-IoT integrated energy efficient system to detect, analyze, and predict the primary and secondary incidents. The proposed system uses the existing sensor technology like accelerometer, tilt, etc., to detect the accident and severity levels using Edge-AI-IoT, locally it analyzes and predicts the secondary incidents. The proposed system has been exhaustively simulated using real-time scenarios in OMENT++, Veins, and SUMO, and it was tested using the NVIDIA Jetson AGX Xavier edge device integrated with the ThingSpeak cloud platform. The proposed system is tested with performance parameters such as clearance time, accident detection, density of vehicles, speed of vehicles, CO2 emissions, and fuel consumption at different times of day. The simulation and real-time tested results show its real-time deployment. © 2025 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Classification of Awareness in Disorders of Consciousness Using Common Spatial Pattern

Classification of Awareness in Disorders of Consciousness Us...

引用

International Winter Workshop on Brain-Computer Interface (BCI)

作者： Chaewon Lee Sunho Lee Jitka Annen Ji-Hoon Jeong Marcello Massimini Silvia Casarotto Melanie Boly Olivier Bodart Aurore Thibaut Mario Rosanova Steven Laureys Olivia Gosseries Minji Lee Dept. Data Science The Catholic University of Korea Bucheon Republic of Korea Dept. Biomedical Software Engineering The Catholic University of Korea Bucheon Republic of Korea Dept. GIGA-Research & Neurology University and University Hospital of Liege Liege Belgium Dept. Data Analysis University of Ghent Ghent Belgium Dept. Computer Science Chungbuk National University Cheongju Republic of Korea Dept. Biomedical and Clinical Sciences “L. Sacco” University of Milan Milan Italy Dept. Psychiatry Wisconsin Institute for Sleep and Consciousness University of Wisconsin Madison USA Coma Science Group GIGA-Consciousness GIGA Research Center University of Liège Liège Belgium Centre du Cerveau Neurology department University Hospital of Liège Liège Belgium

ISBN: (数字)9798331521929

ISBN: (纸本)9798331521936

Advances in intensive care have improved the survival rate of patients with severe acute brain injury, but diagnostic errors for patients with disorders of consciousness are still high. Accurate diagnosis of these patients is very important because effective treatment can vary depending on the diagnosis. In this study, we propose a framework for classifying unresponsive wakefulness syndrome and minimally conscious state, focusing on awareness. In particular, power spectral density and common spatial patterns were used together, considering that spatial information is a key feature in consciousness. The 16 patients with unresponsive wakefulness syndrome and 14 with minimally conscious state underwent resting-state electroencephalography measurements. In addition, we compared the performance by utilizing each frequency (delta, theta, alpha, beta, gamma bands) related to consciousness. As a result, the highest accuracy of 95.06% was achieved by the EEGNet classifier, especially in the beta frequency band. We demonstrated that spatial information is very important in consciousness, as we observed that classification performance improved when common spatial patterns were used. These results provide insight into various frameworks for diagnosing patients with disorders of consciousness and may help patients survive by increasing the diagnosis rate in the future.

关键词： Deep learning Accuracy Biological system modeling Pattern classification Focusing Signal processing Brain modeling Particle measurements Electroencephalography Robustness

来源：评论

学校读者我要写书评

暂无评论

Next Generation Intelligent Traffic Signal Control: Empowering Electronics Consumers with Edge-AIoT Capabilities

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Chavhan, Suresh Doswada, Rohit Gupta, Deepak Gunjal, Saymam Rodrigues, Joel J.P.C. School of Data Sciences Indian Institute of Science Education and Research Kerala Thiruvananthapuram India C-DoT Karnataka Bangalore India Dept. of Computer Science and Engineering Maharaja Agrasen Institute of Technology Delhi India Centre for Research Impact and Outcome Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Science and Engineering University of Visvesvaraya College of Engineering Karnataka Bangalore India Federal University of Piaui PI Teresina Brazil

Traffic congestion has become a major issue that is being faced by the majority of road users. The increasing vehicle usage, and the lack of space and funds to construct new transport infrastructure, further complicates the issue. In this scenario, it is important to come up with an intelligent and economical solution that improves the quality of road users' service. The problem with the traffic handling framework is signal timings are fixed which is not adaptive to the density of vehicles. To address this issue we propose an Edge-Augument Artificial Intelligence of Things (AIoT) road user cooperation for traffic management. The proposed system efficiently utilizes electronic devices to learn and adapt to changing traffic conditions in real-time. By optimizing the traffic signal timings based on the actual traffic conditions, adaptive systems reduce delay, improve traffic flow, reduce fuel consumption and pollution, and improve the electronics consumers' and road users' experiences. The proposed system has been tested with real-time experiments by integrating Electronic devices like cameras, smartphones, and AGX Xavier (edge device) with Cloud (ThingSpeak). The proposed system is verified by simulating the proposed system in the SUMO traffic simulator and its reliability is concluded by comparing the waiting time, depart delay, running, and halt time with the existing traditional method. © 2025 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Interpretable Analysis of Oral Mucosal Lesions Using U-Net and Quantum Approaches

Interpretable Analysis of Oral Mucosal Lesions Using U-Net a...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Aparna M Anna Liza Sibi Prachi Kumari Golla Ram Senthil Kumar T. Somasundaram K. Vindhya Savithri Dept. of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India Dept. of Artificial Intelligence and Data Science School of AI Amrita Vishwa Vidyapeetham Coimbatore India Department of Mathematics Amrita School of Physical Sciences Amrita Vishwa Vidyapeetham Coimbatore India Dept. of Oral & Maxillofacial Pathology and Microbiology Amrita School of Dentistry AIMS Ponekkara PO Kochi India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

Oral mucosal lesions are abnormal changes found in the tissue of the mouth. They can be painful and may include abnormal cell growths, as well as rare tongue and hard- palate disorders. They may result from infections, inflamma- tory processes, trauma, autoimmune conditions, or precancerous changes. A recent study found a 59.6% prevalence of oral mucosal lesions among elderly individuals, highlighting a signif- icant association with factors such as age over 65, male gender, tobacco habits, and denture usage. Thus, lesions can significantly impact a patient's quality of life, necessitating accurate diagnosis and timely intervention. In this study, we use a combination of two advanced technologies-U-Net, a deep learning model, and quantum computing-to analyze medical images of oral health. We use a publicly available dataset containing labeled images classified as ‘Lesion’ and ‘Oral Cavity,’ focusing only on lesion detection. Our results show that while the U-Net model achieves 95.02% segmentation accuracy, the quantum approach using QCNN achieves 74.5% accuracy. Although the quantum model does not outperform U-Net in segmentation, it demonstrates potential for future research in quantum-enhanced medical imaging. To measure how well our method works, we use different evaluation techniques, including Dice Coefficient, Intersection over Union (IoU), accuracy, precision, recall, and F1-score. Our results indicate that while quantum computing has shown high accuracy in previous research for classification tasks, its application to segmentation-particularly in oral lesion detection-faces challenges such as lower accuracy, quantum noise, and hardware constraints. This research highlights the potential of integrating AI and quantum approaches for medical diagnosis while acknowledging the need for further improvements in quantum seamcntation models.

关键词： Deep learning Image segmentation Quantum computing Accuracy Computational modeling Hardware Computational efficiency Lesions Artificial intelligence Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Auto Text Correction Using NLP Techniques

Auto Text Correction Using NLP Techniques

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： Nalla Srivarsha Gummadi Nithin Shanmugasundaram Hariharan Bibhuti Bhusan Dash Subrata Chowdhury Sudhansu Shekhar Patra Department of Artificial Intelligence and Data Science Vardhaman College of Engineering Hyderabad India School of Computer Applications Kalinga Institute of Industrial Technology (KIIT) Deemed to be University Bhubaneswar India Dept. of Computer Science and Engineering Sreenivasa Institute of Technology and Management Studies(A) Chittoor Andhra Pradesh India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

Auto text correction is a fundamental tool in modern Natural Language Processing (NLP) that upgrades user involvement by decreasing typographical and linguistic errors in composed content. This extends leverages progressed NLP procedures to create a strong and proficient auto-correction framework that precisely predicts and corrects content input errors in real-time. The framework utilizes a combination of deep learning models, such as sequence-to-sequence models and transformers, in conjunction with conventional strategies like n-grams and edit distance algorithms. By analyzing the context and structure of input sentences, the model is able to offer relevant rectifications, making it versatile to different dialects and user composing styles. Moreover, we investigate diverse assessment measurements and compare different calculations to optimize the precision and productivity of the correction system. The arrangement has potential applications in word processors, mobile keyboards, and other content input platforms where high accuracy and low latency are crucial.

关键词： Productivity Program processors Keyboards Linguistics Transformers Prediction algorithms Natural language processing Real-time systems Low latency communication Mobile computing

来源：评论

学校读者我要写书评

暂无评论

Real-Time IoT Cybersecurity using Machine Learning-based AI Threat Detection System to Train Generative Robots

Real-Time IoT Cybersecurity using Machine Learning-based AI ...

引用

Trends in Material science and Inventive Materials (ICTMIM), International Conference on

作者： P Srilakshmi Koushik Reddy Chaganti Talachendri Suryam Sweety Julia I D. Chaithanya Jami Kavitha Department of CSE G Pulla Reddy Engineering College Dept. of Computer and Information Systems University of the Cumberlands Department of CSE (DATA SCIENCE) Vignan Institute of Technology and Science Department of AI&ML Malla Reddy University Department of CSE CVR College of Engineering Department of CSE Sanketika Vidya Parishad Engineering College

ISBN: (数字)9798331501488

ISBN: (纸本)9798331501495

Existing security protocols encounter major cybersecurity difficulties because the online devices' growing popularity continues to spread across networks. These security protocols are ineffective because they do not properly handle current cyber threats. The main goal of this study involves developing enhanced IoT cybersecurity through the development of a threat detection system which brings together adversarial training and deep learning models (CNN-LSTM) and Federated Learning (FL). The system enables distributed Internet of Things devices to work on security model development through Federated Learning while maintaining total privacy of their information. Security procedures controlled by generative artificial intelligence robots alongside real-time attack protection functions decrease security response durations. Through its Federated CNN-LSTM model the system upholds a 1.2% false positive rate alongside a 98.3% accuracy evaluation and 160 milliseconds of exact threat tracking time. The designed system sustains a minimal occurrence of incorrect alarm activations. The developed system provides real-time security for the Internet of Things framework because it enables adaptive protection systems while preserving user privacy in current IoT settings.

关键词： Training Privacy Protocols Federated learning Real-time systems Threat assessment Internet of Things Computer security Protection Robots

来源：评论

学校读者我要写书评

暂无评论

Optimizing Production and Inventory Management for Defective Items in Manufacturing Systems

Optimizing Production and Inventory Management for Defective...

引用

International Symposium on Advanced Computing and Communication (ISACC)

作者： Khandakar Rabbi Ahmed Arafat Hossain MD Amaddus Bepary Asif Mahathir Mohammad Mustafizur Rahaman MD Arafat Dewan Miyan Research Institute International University of Business Agriculture and Technology Dhaka Bangladesh Dept. of Business Data Analytics Central Michigan University Mt Pleasant USA Dept. of Business Administration and Management Southern California State University Los Angeles CA Dept. of Business Administration and Management Southern California State University USA Dept. of Cloud Engineering Westcliff University Irvine CA Dept. of Computer Science Los Angeles City College Los Angeles USA

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

Manufacturing defective items is one of the challenges for production efficiency and inventory control. Conventional approaches like Economic Order Quantity (EOQ) and Just-in-Time (JIT) often fall short of the flexibility needed to respond to quality variations in real time. It promotes defect detection and control by employing machine learning (ML) for inventory management. Four classifiers were tested using the UCI SECOM dataset (Bagging, AdaBoost, Gradient Boosting, and Random Forest) to identify defective items. We used effective preprocessing techniques to boost model performance, such as SMOTE for class balancing and PCA for reducing dimensionality and standardization. The bagging and random forest classifiers produced 96.6% and 96.9% test accuracies, with good precision and recall scores. Within this context, we propose an Adaptive Inventory Management Framework comprising machine learning algorithms incorporating predictive analytics to reduce waste, optimize production scheduling(s), and improve resource allocation. These results are consistent with defining Industry 4.0 strategies and show that ML has the potential to transform defect management and inventory optimization in manufacturing systems.

关键词： Production Quality control Inventory management Real-time systems Fourth Industrial Revolution Random forests Optimization Bagging Manufacturing systems Defect detection

来源：评论

学校读者我要写书评

暂无评论

Hybrid K-Means and Firefly Algorithm-Based Load Balancer for Dynamic Task Scheduling in Fog Computing for Postoperative Healthcare Systems

Hybrid K-Means and Firefly Algorithm-Based Load Balancer for...

引用

Advanced Computing Technologies (ICoACT), International Conference on

作者： N. Jagadish Kumar Rakesh Premkumar L. Maria Michael Visuwasam Gopalakrishnan Arjunan G. Yuyaraj C. Tharun Kumar Dept of Data Science and Business Systems SRM Institute of Science and Technology Chennai Tamil Nadu India School of Informatics and Computing Indiana University Bloomington USA Dept. of AI & DS RMK College of Engineering and Technology Puduvoyal Chennai India Accenture Bangalore India Dept of CSE (5 years Integrated) Sri Sai Ram Engineering College Chennai Tamil Nadu India Dept. of CSBS Sri Sai Ram Engineering College Chennai Tamil Nadu India

ISBN: (数字)9798331509859

ISBN: (纸本)9798331509866

In fog computing for postoperative healthcare systems, efficient task scheduling and load balancing are crucial for improving response time, energy efficiency, makespan, and the overall performance of the system. This manuscript introduces a novel hybrid load balancing framework that amalgamates KMeans clustering with the Firefly Algorithm (FA) to tackle the dynamic task scheduling complexities inherent in fog-based healthcare environments. The K-Means methodology is employed to categorize tasks according to their computational necessities and resource requirements, thereby establishing clusters that facilitate optimized resource distribution. The Firefly Algorithm, recognized for its proficiency in addressing optimization challenges, is harnessed to ascertain the optimal scheduling arrangement within each task cluster by adept.y modifying task allocation among fog nodes in response to light intensity, which is directly proportional to the overall performance of the system. Empirical findings indicate that the proposed mechanism markedly surpasses conventional algorithms regarding the optimization of response time, makespan, cost, and energy consumption, thereby presenting a viable solution for the management of postoperative care within healthcare systems employing fog computing infrastructure. The results substantiate that our proposed model enhances response time by 18%, makespan by 17%, energy consumption by 15%, cost by 17%, and level of load balance by 18%.

关键词： Processor scheduling Heuristic algorithms Clustering algorithms Medical services Optimal scheduling Dynamic scheduling Load management Time factors Resource management Edge computing

来源：评论

学校读者我要写书评

暂无评论

Adaptive Optimization and Resource Allocation (AORA) Model for IoT-Edge Computing Using Hybrid Newton-Raphson and Dolphin Echolocation Algorithm (HNR-DEA) Technique

Adaptive Optimization and Resource Allocation (AORA) Model f...

引用

Advanced Computing Technologies (ICoACT), International Conference on

作者： N. Jagadish Kumar Rakesh Premkumar L. Maria Michael Visuwasam Gopalakrishnan Arjunan A. Shiny K. Dharani Dept of Data Science and Business Systems SRM Institute of Science and Technology Chennai Tamil Nadu India School of Informatics and Computing Indiana University Bloomington USA Dept. of AI & DS RMK College of Engineering and Technology Puduvoyal Chennai India Accenture Bangalore India Dept of CSE (5 years Integrated) Sri Sai Ram Engineering College Chennai Tamil Nadu India Dept. of CSBS Sri Sai Ram Engineering College Chennai Tamil Nadu India

ISBN: (数字)9798331509859

ISBN: (纸本)9798331509866

The swift expansion of Internet of Things (IoT) applications demands the implementation of real-time data processing and low-latency communication, thereby posing challenges to conventional cloud computing paradigms. This study confronts these issues by amalgamating edge computing with hybrid optimization methodologies, and introduces the AORA (Adaptive Optimization and Resource Allocation) framework. The AORA framework capitalizes on intelligent task scheduling, dynamic resource allocation, and energy-efficient approaches to augment the performance of edge *** research methodology encompasses the collection and preprocessing of data derived from IoT devices, feature extraction, prediction of resource demand, and the optimization of task offloading. It employs the Hybrid Newton Raphson and Dolphin Echolocation Algorithm (HNR-DEA) methodology, which synergizes Newton Raphson optimization technique for faster convergence rate around local optima with bio-inspired Dolphin Echolocation Algorithm (DEA) for comprehensive global *** Experimental outcomes reveal considerable advancements, including a 45% reduction in average latency, a 38% decrease in overall energy consumption, and a 23% enhancement in resource utilization. Furthermore, the model attained a 97% task completion rate alongside consistently elevated network throughput. Simulations were executed in CloudSim with 100 IoT devices generating dynamic workloads and edge servers equipped with multi-core processors. The experimental framework utilized Google Cluster data to replicate workload variations, thereby ensuring scalability and robustness. These results underscore the AORA model's potential as a resilient and scalable solution for real-time IoT applications.

关键词： Adaptation models Computational modeling Scalability Prediction algorithms Real-time systems Internet of Things Resource management Newton method Optimization Dolphins

来源：评论

学校读者我要写书评

暂无评论

FogMedX-Transform: A Transformer-Based Task Interoperability Framework for Energy-Efficient Fog-Enabled IoMT

FogMedX-Transform: A Transformer-Based Task Interoperability...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： R Jayakarthik Sajja Suneel Jayendra Gopal Thatipudi V. Jaganraja Minesh Vohra Gopinath D Dept of Computer science Saveetha College of Liberal Arts and Sciences SIMATS Department of CSE(Data Science) Institute of Aeronautical Engineering Dundigal Hyderabad Telangana India Dept. of Computer Science University of North Texas Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai India School of Mechanical Engineering Lovely Professional University Phagwara Department of Computer Science Kristu Jayanti College (Autonomous) Bengaluru Karnataka India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

The increasing speed of Internet of Medical Things (IoMT) development requires framework approaches that secure, efficient, and scalable for healthcare data management. The study presents FogMedX-Transform as a Transformer-based task interoperability framework purposebuilt for energy-efficient fog-enabled IoMT systems. A customized Transformer design utilizing multi-head selfattention allows the framework to deliver timely critical healthcare data processing alongside optimized energy usage. This model demonstrated a 98.7% task interoperability success rate coupled with a 97.5% anomaly detection accuracy that exceeded results from conventional models based in fog environments and the cloud. The framework improved performance through latency reduction between 50% and 70% and energy consumption minimization reached between 25% to 40% thus proving its effectiveness in resource administration. The scalability tests proved steady system functionality when dealing with different device quantities and built-in security features blocked data breaches and had a false positive rate of 2.3% during testing. FogMedX-Transform demonstrates the capability for healthcare transformation through its union of fog computing and deep learning technology integration according to test results.

关键词： Deep learning Performance evaluation Internet of Medical Things data breach Transformers data processing Energy efficiency Real-time systems Interoperability Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：