检索结果-内蒙古大学图书馆

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Sree, M. Ramya Siddhartha, Mettu Reddy, Poli Vamsi Vardhan Singh, Tripty Nair, Rekha R. Amrita Vishwa Vidyapeetham Amrita School of Computing Dept. of Computer Science and Engineering Bengaluru India Alliance University Alliance School of Advanced Computing Dept. of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350370249

Lung diseases are wide group of diseases related to the respiratory system, and is ranging from acute infections to chronic disorders with multifactorial causes. Recognition of the lung disease is very crucial in the proper diagnosis, forecasting through prognosis, and remedies. Hence proposed lung disease classification with feature extraction technique. The proposed work carried out feature extraction with Gray-Level Co-occurrence Matrix (GLCM) and Local Phase Quantization (LPQ) combined with Convolutional Neural Network(CNN). The goal is to create a model that reduces diagnostic errors, ensuring more precise early detection and classification of pulmonary disorders. This initiative facilitates the advancement of pulmonary medicine by promoting accurate radiologic imaging, while future directions emphasize integrating medical workflows to enable personalized and timely diagnosis and treatment. Additionally, the ResNet model demonstrates superior performance in hernia detection, achieving a test accuracy of 89.43% for GLCM based feature extraction and Pneumonia detection with 79.20% test accuracy for LPQ based feature extraction. © 2024 IEEE.

关键词： CNNs Deep learning Early detection Feature extraction GLCM Local Phase Quantization Lung disease diagnosis Medical imaging Texture analysis

来源：评论

学校读者我要写书评

暂无评论

COMPARING WSN PERFORMANCE: TRADITIONAL VS. SDN APPROACH

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer science 2024年第4期86卷 81-94页

作者： Hamad, Diyar Jamal Yalda, Khirota Gorgees Okumus, Ibrahim Taner Tapus, Nicolae Faculty of Automatic Control and Computer Science University of Science and Technology POLITEHNICA Bucharest Soran Technical college Erbil Polytechnic University Erbil Iraq Computer Engineering Kahramanmaras Sutcu Imam University Kahramanmaras Turkey Dept. of Computer Science University of Science and Technology POLITEHNICA Bucharest Romania

The proliferation of Wireless Sensor Networks (WSN) in various applications has necessitated the exploration of network architectures that can ensure efficient, scalable, and reliable communication. This study presents a comparative performance evaluation of traditional networking paradigms and Software-Defined Networking (SDN)-based architectures within WSN. Utilizing the Floodlight SDN controller and Mininet-WiFi emulator, we conducted a series of experiments across three different network topologies, varying the number of hosts and access points. The performance metrics focused on are average latency, packet loss percentage, and throughput. The results demonstrate a considerable improvement in all measured parameters under the SDN-based environment compared to the traditional setup. Specifically, SDN environments consistently showcased lower latency, minimal packet loss, and higher throughput, with the most notable difference observed in smaller network configurations. The findings suggest that SDN, with its centralized control plane, can significantly enhance the performance of WSNs, particularly in scenarios demanding rapid scalability and dynamic traffic management. This study underscores the potential of SDN architectures in optimizing WSN operations and lays the groundwork for future research in this domain. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Floodlighting

来源：评论

学校读者我要写书评

暂无评论

DMDA: A Computational Resource Allocation Approach for IoT Devices in Fog Computing 4

DMDA: A Computational Resource Allocation Approach for IoT D...

引用

4th International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2024

作者： Pramono, Luthfan Hadi Shen, Shan-Hsiang National Taiwan University of Science and Technology Dept. of Computer Science and Information Engineering Taipei Taiwan

ISBN: (纸本)9798331506490

Fog Computing enables the efficient offloading of computational tasks from IoT Devices to Fog nodes, enhancing processing efficiency and reducing latency. This paper introduces the Dynamic Matching with Deferred Acceptance (DMDA) algorithm, designed to optimize the allocation of GPU and CPU resources within Fog Computing environments, specifically for smart city applications. The DMDA algorithm allocates resources to IoT Devices based on parameters such as data type, computational load, priority, and responsiveness. Devices processing image or video data are given priority for GPU allocation, while other devices are assigned to CPUs based on their cumulative performance scores. Devices with lower priority are reassigned to CPU resources or excluded when resource availability is exhausted, significantly enhancing performance under high-demand scenarios. The algorithm employs a Mixed-Integer Linear Programming (MILP) model to maximize the aggregate score of allocated devices while adhering to resource constraints. Experiments conducted with 50 to 1,000 devices demonstrate that both the total Device Score rate and Allocated Device rate reach 100%, indicating optimal allocation. Empirical findings show that the DMDA algorithm improves resource utilization, reduces processing times, and ensures effective workload distribution across large-scale IoT deployments. © 2024 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Routing and Charge Planning Strategies for Ridesharing EV Fleets 11

Routing and Charge Planning Strategies for Ridesharing EV Fl...

引用

11th International Conference on Vehicle Technology and Intelligent Transport systems, VEHITS 2025

作者： Singh, Ashutosh Gupta, Arobinda Dept. of Computer Science & Engineering Indian Institute of Technology KharagpurWB-721302 India

ISBN: (纸本)9789897587450

Ridesharing systems have become an important part of urban transportation. At the same time, electric vehicle (EV) adoption is also growing at a fast pace as an eco-friendly and sustainable transportation option. To operate a ridesharing system with EV fleets, scheduling an EV fleet to serve passenger requests requires consideration of both the requests, and the available charge and potential future charge requirements of the EVs. In this paper, we address the problem of scheduling EVs by a ridesharing operator, and propose four algorithms that schedule passenger requests while taking into consideration charging requirements of the EVs. Detailed simulation results are presented on a real world data set to show that the algorithms perform well. Copyright © 2025 by SCITEPRESS - science and Technology Publications, Lda.

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

TotCareBot: A Comprehensive Approach Towards Enhancing Early Childhood Education through Robotics 5

TotCareBot: A Comprehensive Approach Towards Enhancing Early...

引用

5th International Conference on Circuits, Control, Communication and Computing, I4C 2024

作者： Chougala, Manjula R Sushma, B. Bhayyar, Akshata S Bhandarkar, Abhay Pavithra, P.N. Ramaiah Institute of Technology Dept. of Computer Science and Engineering Bangalore India Ramaiah Institute of Technology Department of Computer Science Engineering Bengaluru India

ISBN: (纸本)9798331528539

Robots have emerged as versatile tools with significant potential to enhance teaching and learning environments, including classrooms, laboratories, play homes, crèches, and even at home. Their engaging nature can captivate young children, boosting motivation and interest. This paper proposes a methodology for an Educational Robot (ER) designed for play homes. The ER is capable of moving around the classroom, monitoring children, analyzing their emotions, responding appropriately, and alerting the teacher when necessary. The proposed system aims to leverage the positive impact of expressive behaviors in robots, such as storytelling and pampering. Our findings indicate that expressive robot narration is as effective as that of a human displaying similar behaviors and even surpasses a static, inexpressive human narrator. Furthermore, the robot excels in conveying educational content, although its limited emotional expression slightly reduces its effectiveness in narrating emotionally rich stories. This research underscores the potential of ERs to create dynamic and interactive learning experiences for young children, fostering both their cognitive and emotional development. © 2024 IEEE.

关键词： Educational robots

来源：评论

学校读者我要写书评

暂无评论

Analysing Breast Cancer Classification Using Explainable Artificial Intelligence 12

Analysing Breast Cancer Classification Using Explainable Art...

引用

12th International Conference on Internet of Everything, Microwave, Embedded, Communication and Networks, IEMECON 2024

作者： Fardeen, Kazi Bhaduri, Harshadeep Hazra, Soham Mondal, Praloy Manna, Sarbajit Si, Tapas Dept. of Computer Science & Electronics Ramakrishna Mission Vidyamandira Belur Math West Bengal Howrah711202 India Dept. of Computer Science & Engineering University of Engineering & Management Rajasthan Jaipur India

ISBN: (纸本)9798350387315

Worldwide, breast cancer is becoming the most serious illness that affects women. It is believed that early diagnosis and treatment of breast cancer can increase survival rates and decrease the need for surgery. Machine Learning model is very reliant on features for their proper training. However, understanding how a prediction is being affected by specific features is very important for a model’s interpretation. Understanding what features support a prediction is important as it provides some transparency to the inner workings of the model. Gaussian Naive Bayes (GNB), Decision Tree (DT), Random Forest (RF), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM) are used to classify the breast cancer data, and accuracy, sensitivity, specificity, false-positive rate, precision, F1-score, and Geometric-Mean (GM) are used for the performance assessment. Furthermore, Multi-Criteria Decision Making (MCDM) is used to evaluate overall performance assessment based on the aforementioned performance measures and DT is found to be best among all the classifiers. Finally, an Explainable AI model namely LIME is used to interpret the predicted outcomes and impact of the different features of the data on the model’s prediction. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

AI-Powered DeepFake Defense 3

AI-Powered DeepFake Defense

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Chaitra, M. Kushal, B. Likhitha, H. Priyanka, H.R. Bnm Institute of Technology Affiliated to Vtu Dept. of Computer Science and Engineering Bengaluru India

ISBN: (数字)9798331515911

ISBN: (纸本)9798331515911

Deepfake technology, known for its ability to produce convincingly face-swapped videos, presents significant risks to privacy, security, and public trust. Misuse of this technology for spreading misinformation, defamation, and influencing politics is on the rise, creating a pressing need for more effective detection mechanisms. As deepfake generation methods continue to advance, conventional detection techniques are increasingly unable to keep up, often falling short in accuracy and adaptability. This project aims to create an AI-driven detection system specialized in identifying face-swap deepfakes. The system focuses on subtle irregularities in facial details, movements, and the synchronization between audio and visuals. Employing neural network models such as Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and Capsule Networks, it pinpoints anomalies like unnatural expressions, atypical skin textures, and lighting inconsistencies. The system achieves high reliability with metrics including accuracy (96%), precision (95%), recall (94%), and F1 score (95%), showing marked improvement compared to traditional techniques. It outperforms existing methods such as XceptionNet (92%) on the Celeb-DF dataset, underscoring its superior generalizability and robustness. This scalable solution has broad applications in media, law enforcement, and cybersecurity, reinforcing efforts to combat deepfake threats and fostering improved trust and security across various sectors. © 2025 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Enhanced Adaptive Video Streaming for Resource-Constrained UAVs through Dynamic Region-of-Interest Tile Swapping 10

Enhanced Adaptive Video Streaming for Resource-Constrained U...

引用

10th International Conference on Applied system Innovation, ICASI 2024

作者： Hsu, Tz-Heng Ju, Rui-Han Horng, Gwo-Jiun Southern Taiwan University of Science and Technology Dept. of Computer Science and Information Engineering Tainan Taiwan

ISBN: (纸本)9798350394924

Real-time video transmission via unmanned aerial vehicles (UAVs) is significantly impacted by latency issues. Using Region of Interest (ROI) tile segmentation methods, video streaming techniques can dynamically adjust the encoding bitrate, assign various priorities to distinct video tiles, and specify different quality quantization factors. High-efficiency video tile encoding techniques, combined with ROI-based streaming methods, can meet various Quality of Service (QoS) criteria. However, dynamically assigning quantization factors for different tiles has the disadvantage of increasing the encoding system's complexity. This study presents a method to dynamically swap ROI tiles to lower the complexity of the encoding system, making it suitable for UAVs with limited computational capacities. By adopting the proposed adaptive video streaming transmission method with tile-swapping strategy, it is feasible to enhance the visual quality in critical areas for resource-constrained UAV devices. © 2024 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Mango Crop Health: A Deep Learning Approach for Precise Identification of Leaf Diseases 10

Revolutionizing Mango Crop Health: A Deep Learning Approach ...

引用

10th International Conference on Advanced Computing and Communication systems, ICACCS 2024

作者： Navadharani, N. Mouthami, K. Devipriya, R. Anandamurugan, S. Kpr Institute of Engineering and Technology Dept. of Computer Science Engineering Coimbatore India Kongu Engineering College Dept. of Information Technology Erode India

ISBN: (纸本)9798350384369

Plant diseases pose significant challenges to the agricultural sector, leading to decreased crop production and financial losses. Mango, being a popular fruit worldwide, is susceptible to various leaf diseases. Traditional diagnosis of these disorders requires labor-intensive and time-consuming manual picture interpretation. To address this issue, deep learning models have been utilized to enhance the precision and effectiveness of identifying leaf illness in mango crops. In this study, ResNet50, ResNext50, Convnet, and Conventv2 deep learning models were compared to find the most successful approach. The results demonstrated that the Conventv2 model achieved the highest accuracy of 98.21%. The major aim of the research work is improvising sustainable agricultural practices by leveraging advanced technology for accurate plant disease classification. The findings have implications for improving mango crop management and ensuring a more sustainable and efficient agricultural industry. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Recognition of Human Anomalies Using Convolution Neural Network

Recognition of Human Anomalies Using Convolution Neural Netw...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing systems, ADICS 2024

作者： Parella, Teja Ponnam, Balakrishna Santhiya, P. Praveen, A. Sujihelen, L. Sathyabama Institute Of Science And Technology Dept. Of Computer Science And Engineering Tamilnadu Chennai600119 India

ISBN: (纸本)9798350364828

By instantly identifying suspicious occurrences, people, and things, smart CCTV systems greatly improve monitoring capacities. In this research, we investigate how to enhance CCTV video stream anomaly detection using state-of-the-art machine-vision and machine-learning techniques, namely UNET and ALEXNET. In contrast to more conventional methods that depend on supervised learning, this research makes use of uncontrolled and semi-supervised learning techniques to tackle the variety and complexity of anomalies. Using algorithms like UNET and ALEXNET, the system can learn to spot outliers on its own, with little to no help from humans. Because it can tell the difference between normal and abnormal situations, this method improves monitoring efficiency and decreases false alarms. In addition, the system maintains original quality for unusual occurrences while keeping typical video at a lower level, optimizing storage economy. By combining UNET and ALEXNET algorithms, smart CCTV systems may detect suspicious events before they happen, which increases security and allows for faster reactions to any dangers. © 2024 IEEE.

关键词： 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：