检索结果-内蒙古大学图书馆

2025 International Conference on Intelligent Control, Computing and Communications, IC3 2025

作者： Sobana, P. Yaiaman, Gummagatta Vybhavi Kumar, A. Pradeep Karthi, S. Almusawi, Muntather Rani, Hema Sethu Institute of Technology Department of Computer Science Engineering Pulloor Tamil Nadu Kariapatti626115 India Gokaraju Rangaraju Institute of Engineering and Technology Department of Cse Telangana Hyderabad India Cmr College of Engineering & Technology Department of Ece Telanagana Hyderabad India Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil nadu Chennai India College of technical engineering The Islamic University Department of computers Techniques engineering Najaf Iraq Centre for Managament studies Gitarattan International Business School Delhi India

ISBN: (纸本)9798331527495

It has been established for a long time and has evolved correspondingly that actuators and sensor systems may be connected to the internet for the purpose of continuously monitoring and controlling biological phenomena. The term 'Internet of Things (IoT)' was first used to combine these methods into a coherent framework a little more than a decade earlier. The IoT based idea has evolved along with science, adopting new vocabulary that is suited for technical advancements and many applications sectors. The IoT has undergone modifications since its inception, and this study examines studies on how technical advancements have transformed it as well and encouraged the emergence of modified terms appropriate for certain fields. A three separate study of the literature was done using games companies and classification data warehouses. First step involved looking for proposed changes on the Iot devices principle & evaluating them to compute the similarity, disparities, and functionality that enable us to generate a number of links its progression. The 1st step involved identifying and briefly assessing the much more common names handed to it IoT for multiple areas. As underpinning innovation continues to advance and software update areas are put out, the research supports the assertion that a consensus on the IoT concept is still not established. With information and information solutions playing an important role in the panorama, recent developments have been somewhat restrained and its variants on possible applications are distinct. © 2025 IEEE.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "Early Parkinson's disease diagnosis using Transition Propagation Graph Neutral Network with Dynamic Hunting Leadership Optimization" [Biomed. Signal Proc. Contr. 101(25):107196/ 10.1016/***.2024.107196](S1746809424012540)(10.1016/***.2024.107196)

引用

Biomedical Signal Processing and Control 2025年 106卷

作者： Subasree, S. Priya, S. Brindha, S. Sakthivel, N.K. Sri Shakthi Institute of Engineering and Technology Tamil Nadu Coimbatore India Department of Computer Science and Engineering Nehru Institute of Engineering and Technology Tamil Nadu Coimbatore India Department of Computer Science and Applications St.Peter's Institute of Higher Education and Research Avadi Tamil Nadu Chennai India Department of Artificial Intelligence and Data Science Sri Shakthi Institute of Engineering and Technology Tamil Nadu Coimbatore India

I hope this message finds you well. I am writing to request an urgent correction to the affiliation and email ID associated with my article published in your journal on November 23, 2024. This update is crucial for the accurate representation of my contact information and for the acceptance of the paper by my university. If my affiliation is not updated, they won't allow me to sit for the exam. Kindly consider my situation and help me. Please update the Affiliation and Mail Id as follows: First Author: Dr. S. Subasree Dean (Academics), department of computer science and engineering (Cyber Security), Sri Shakthi Institute of engineering and technology, Coimbatore, Tamil Nadu, India 4th & Corresponding Author: Dr. N. K. Sakthivel Principal department of Artificial Intelligence and Data science, Sri Shakthi Institute of engineering and technology, Coimbatore, Tamil Nadu, India nksakthivel@*** I kindly request that the necessary changes be made as soon as possible. Thank you very much for your prompt attention to this matter. © 2025

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fusion-Brain-Net: A Novel Deep Fusion Model for Brain Tumor Classification

引用

Brain and Behavior 2025年第5期15卷 e70520页

作者： Kaya, Yasin Akat, Ezgisu Yıldırım, Serdar Department of Artificial Intelligence Engineering Adana Alparslan Turkes Science and Technology University Adana Turkey Department of Computer Engineering Adana Alparslan Turkes Science and Technology University Adana Turkey

Problem: Brain tumors are among the most prevalent and lethal diseases. Early diagnosis and precise treatment are crucial. However, the manual classification of brain tumors is a laborious and complex task. Aim: This study aimed to develop a fusion model to address certain limitations of previous works, such as covering diverse image modalities in various datasets. Method: We presented a hybrid transfer learning model, Fusion-Brain-Net, aimed at automatic brain tumor classification. The proposed method included four stages: preprocessing and data augmentation, fusion of deep feature extractions, fine-tuning, and classification. Integrating the pre-trained CNN models, VGG16, ResNet50, and MobileNetV2, the model enhanced comprehensive feature extraction while mitigating overfitting issues, improving the model's performance. Results: The proposed model was rigorously tested and verified on four public datasets: Br35H, Figshare, Nickparvar, and Sartaj. It achieved remarkable accuracy rates of 99.66%, 97.56%, 97.08%, and 93.74%, respectively. Conclusion: The numerical results highlight that the model should be further investigated for potential use in computer-aided diagnoses to improve clinical decision-making. © 2025 The Author(s). Brain and Behavior published by Wiley Periodicals LLC.

关键词： brain tumor classification fusion of CNN transfer learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Software Demands Using Fuzzy-Based Evaluation Techniques 1st

Optimizing Software Demands Using Fuzzy-Based Evaluation Tec...

引用

1st International Conference on Innovation and Emerging Trends in Computing and Information Technologies, IETCIT 2024

作者： Rubi Singh, Jagendra Sahu, Dinesh Prasad Tiwari, Mohit Shaik, Nazeer Shrivastav, A.K. School of Education Lovely Professional University Jalandhar India School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of Computer Science and Engineering Bharati Vidyapeeth’s College of Engineering Delhi India Department of Artificial Intelligence and Data Science Rajalakshmi Institute of Technology Tamil Nadu Chennai India Ambala Mullana India

ISBN: (纸本)9783031808418

The purpose of this study was to show the benefits of fuzzy logic in software scaling. We made use of fuzzy logic systems and logic, including sets rules and inference, to cope with uncertainty in making decisions;by the way all three of those have been used. We found different degrees of set membership during ten trials, which would change to reflect how much the software today was needed in real life. Decisions produced by fuzzy inference systems exhibited both adaptability and context-dependency, illustrating possible pathways toward better software demand optimization strategies. Further, we took measurements like response time, throughput, and resource utilization both before & after fuzzy optimization. In all experiments we put the system under realistic working conditions, looking for changes in speed, through better resource usage. The response time was reduced, throughput increased, and resource utilizations improved. These results suggest that fuzzy-based methods not only facilitate a better user experience but enhance software performance. In a word, this study represents an advance in software engineering optimization methods. It draws attention to software demand’s inherent uncertainties and emphasizes the importance of fuzzy logic. With fuzzy evaluation techniques, this research’s achievement was thus to open up practical means of improving decision-making processes and optimizing the vital performance indicator, enabling people to create computer systems that are more reliable and practical. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： computer circuits

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT-Driven Smart Home Security and Automation with a GCN Model

Enhancing IoT-Driven Smart Home Security and Automation with...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Sreelakshmi Ganti Ravi Kumar Vankayalapati P. Krishnamoorthy Pallavi S Thakare Ullal Akshatha Nayak P Vignesh Department of Electronics and Communication Engineering Geethanjali College of Engineering and Technology Medchal India Equinix Texas USA Department of Computer Science and Engineering Sasi Institute of Technology & Engineering West Godavari India Department of Information Technology Dr D. Y. Patil Institute of Technology Pimpri India Department of Information Science and Engineering Nitte Meenakshi Institute of Technology Bangalore India Department of Mathematics KCG College of Technology Chennai India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

A network of computing devices and sensors, the Internet of Things (IoT) rapidly exchanges data to assess circumstances and propose new services. Intelligent home technologies rely on IoT. Contemporary smart home systems offer automatic lighting control, smoke detectors, temperature sensors, and smart lock installations. But these technologies raise serious privacy and security concerns. Security flaws let hackers access sensitive data, sendoff false alarms, and take control monitoring systems. Smart home technology is vulnerable to many threats because consumers are wary of it. Recommended steps are preprocessing, sensing, and model training. Preparing raw, unstructured data for analysis. DHT11 humidity and temperature sensors and HC-SR501 PIR motion detectors collect data. It trained the model using Multiscale DGCN data. Better than GCN and BiLSTM, Multiscale DGCN performs. It uses Internet of Things-based smart home security data well, with an average accuracy rate of 93.87%. Identifying outliers in sensor data solves major smart home security challenges. Increasing smart home system accuracy reduces security concerns and boosts user trust, which may drive adoption.

关键词： Temperature sensors Accuracy Bidirectional long short term memory Smart homes DH-HEMTs Safety Security Internet of Things Integrated circuit modeling Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

Enhancing Alzheimer's Disease Detection Using Optimized Attribute Selection and Random Forest Classifier for Improved Accuracy

Enhancing Alzheimer's Disease Detection Using Optimized Attr...

引用

Visual Analytics and Data Visualization (ICVADV), International Conference on

作者： A. Sathiya CH Hussaian Basha Vasanth. S Jasphin Jeni Sharmila P Prabakaran S R. Indhumathi Department of Electronics and Communication Engineering M.Kumarasamy College of Engineering (Autonomous) Karur Department of Electrical and Electronics Engineering SR University Warangal Department of Electronics and communication Engineering Rajalakshmi Institute of Technology Chennai Department of computer science and Engineering Chennai Institute of Technology Chennai Department of Electronics and communication Engineering CMS College of Engineering and Technology Coimbatore Department of Biomedical Engineering Velalar College of Engineering and Technology Erode

ISBN: (数字)9798331521394

ISBN: (纸本)9798331521400

This research aims at improving the identification of Alzheimer's dementia by using the optimized attribute selection method and preliminary diagnosis data-driven learning algorithm, namely Random Forest Classifier. Alzheimer's is a progressive neurological disorder exhibiting barriers in preliminary diagnosis primarily due to the high density and intricate nature of medical information. In this study, attribute selection techniques are used to minimize the data dimensionality, by selecting only key features for classification with low computational complexity and improved model accuracy. The Random Forest Classifier is used because it is accurate, can process big data and because of its diverse uses. Through selecting the most relevant features of the model, it provides a prominent level of precise and acute identification of the early stage of Alzheimer's and could significantly enhance the medical treatment effects. The outcomes from this study indicate that feature optimization can be used interchangeably with preliminary diagnosis data-driven learning algorithms for accurate disease prediction.

关键词： Accuracy Computational modeling Volume measurement Visual analytics Classification algorithms Alzheimer's disease Slabs Random forests Medical diagnostic imaging Monitoring

来源：评论

学校读者我要写书评

暂无评论

IoT-Integrated Convolutional Neural Network for Accurate Vehicle Acoustic Signal Analysis

IoT-Integrated Convolutional Neural Network for Accurate Veh...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： P. Sasikala K Subha Sharmini Venkatesan Sorakka Ponnappan K. R. Kavitha K. Gunasekaran C. Srinivasan Department of Mathematics Vinayaka Mission's Kirupananda Variyar Engineering College Vinayaka Mission's Research Foundation (Deemed to be University) Salem India Department of Electrical and Electronics Engineering SRM Institute of Science and Technology Kattankulathur Chennai India Department of Mechanical Engineering Sathyabama Institute of Science and Technology Chennai India Department of Electronics and Communication Engineering Sona College of Technology Salem India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

This paper examines the use of IoT-integrated Convolutional Neural Networks (CNNs) for precise analysis of vehicle audio signals. The context highlights the growing intricacy of vehicle systems and the need for advanced monitoring methods. Acoustic signals generated by different vehicle components may provide significant insights about vehicle health; nevertheless, traditional analysis techniques are often ineffective. The Internet of Things (IoT) technology allows real-time data collection from sensors installed on vehicles, which is then analyzed using CNNs to identify certain patterns and abnormalities in auditory signals. The approaches used include using IoT sensors to record various vehicle noises and utilizing CNNs for feature extraction and classification, providing great defect detection precision. The results indicate the system's capacity to detect engine faults, braking deficiencies, and other mechanical concerns early, enabling quick treatments. It presents a novel methodology for vehicle monitoring, enhancing predictive maintenance, safety, and performance, with prospects for future developments in autonomous diagnostics. The proposed system improved vehicle acoustic signal processing using IoT and CNN models, achieving high accuracy of 99% in anomaly detection, preventive maintenance, and real-time traffic monitoring.

关键词： Training Accuracy Noise Real-time systems Acoustics Sensor systems Sensors Convolutional neural networks Internet of Things Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

Multi-UAV-Enabled Energy-Efficient Data Delivery for Low-Altitude Economy: Joint Coded Caching, User Grouping, and UAV Deployment

引用

IEEE Internet of Things Journal 2025年

作者： Wei, Qing Li, Ruoguang Bai, Wenle Han, Zhu North China University of Technology School of Information Beijing100144 China Hohai University College of Information Science and Engineering Changzhou213200 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

Non-terrestrial network (NTN) enabled low-altitude economy (LAE) has emerged as a promising economic paradigm that leverages advanced air mobility (AAM) vehicles to revolutionize connectivity in the six-generation (6G) era. By deploying unmanned aerial vehicles (UAVs) as flying edge nodes, wireless caching can significantly alleviate network congestion and reduce latency, enabling the efficient handling of massive terrestrial user requests in LAE applications. However, the limited energy and storage capacity of UAVs pose significant challenges to provide persistent and diverse content delivery services. To address such limitations, this paper proposes a multi-UAV-enabled coded caching scheme for energy-efficient data delivery, in which both the communication coverage and cache hit are satisfied. Taking into account the dynamics of user mobility and user preferences, we design an energy minimization problem with the joint optimization of coding vectors, caching variables, user grouping, and updated UAV locations. We initially deploy UAVs using a constrained K-means clustering algorithm based on user locations, and evaluate the clustering effectiveness with the silhouette coefficient. Then, we solve this problem by proposing a multi-UAV enabled coded caching optimization (MUCCO) scheme, embedded with a novel projected distance-based user grouping method, semidefinite programming (SDP), and matching theory. The simulation results demonstrate that the proposed MUCCO scheme can achieve low energy consumption compared to other schemes, with scalable user density and file library size. © 2025 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

A novel approach for handling missing data to enhance network intrusion detection system

Cyber Security and Applications

引用

Cyber Security and Applications 2025年 3卷

作者： Tahir, Mahjabeen Abdullah, Azizol Udzir, Nur Izura Kasmiran, Khairul Azhar Department of Computer Science & Information Technology University Putra (UPM) Selangor Serdang 43400 Malaysia Department of Computer Engineering Sir Syed University of Engineering & Technology Sindh Karachi 75300 Pakistan

Managing missing data is a critical challenge in Intrusion Detection System (IDS) datasets, significantly affecting the performance of deep learning models. To address this issue, we introduce DeepLearning_Based_MissingData_Imputation (DMDI), a novel method designed to enhance the quality of input data by efficiently handling missing values. Our approach employs the Random Missing Value (RMV) algorithm to simulate missing data, enabling thorough testing and comparison of various imputation techniques. The DMDI method integrates a stacked denoising autoencoder with Gradient Boosting to improve imputation accuracy. We evaluated the effectiveness of our approach through three experimental phases: generating missing data, imputing missing values, and assessing imputation models. Using the NSL-KDD and UNSW-NB15 datasets, our results demonstrate significant improvements in the performance of five different classifiers (SVM, KNN, Logistic Regression, Decision Tree, and Random Forest) after imputation. On average, our method achieved accuracy improvements ranging from 0.95 to 0.97 across these classifiers compared to baseline imputation methods. Detailed analysis using Python 3 validates our findings, demonstrating enhanced model performance and robustness. This study underscores the necessity of precise missing data imputation for enhancing deep learning tasks, particularly in anomaly detection systems. It provides a reliable solution for managing missing data in IDS datasets. © 2024

关键词： Autoencoder Gradient Boosting Intrusion detection Machine learning Missing data Imputation Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Marine Robot for Underwater Surveillance

Marine Robot for Underwater Surveillance

引用

IEEE Students' Conference on Electrical, Electronics and computer science (SCEECS)

作者： Vishnu Gowda H P Deepa N Reddy Tejas B Gowda Shrikala R Yogitha H N Student of Department of Electronics and Communication Engineering BMS Institute of Technology and Management Bengaluru India Department of Electronics and Communication Engineering BMS Institute of Technology and Management Bengaluru India Student of Department of Computer Science Engineering BMS Institute of Technology and Management Bengaluru India

ISBN: (数字)9798331529833

ISBN: (纸本)9798331529840

Underwater surveillance has become a crucial area of research, particularly for marine exploration and environmental monitoring, with marine robots playing a vital role. These robots, equipped with sensors and cameras, capture real-time data and images from underwater environments, reducing the need for human intervention in hazardous areas. However, a major challenge in this field is developing reliable communication networks, as underwater environments face limitations in bandwidth, range, and signal attenuation, hindering real-time data transmission. This paper presents a simple marine robot prototype based on the Raspberry Pi Model 4B, utilizing Electronic Speed Controllers (ESCs) and brushless motors for efficient movement. The robot's body is manually designed using 3D printing technology, with PETG (polyethylene terephthalate glycol) material chosen for its water resistance, durability, and buoyancy. The design ensures the robot’s stability and functionality underwater, offering a cost-effective solution for marine robotics while underscoring the need for improved underwater communication technologies.

关键词： Underwater communication Robot vision systems Video surveillance Three-dimensional printing Real-time systems Stability analysis Sensors Robots Marine robots Testing

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：