检索结果-内蒙古大学图书馆

8th International Conference on Electronics, Materials engineering and Nano-Technology, IEMENTech 2025

作者： Kumari, Reetu Kumar, Sunil Amandeep Dutta, Kamlesh Kumari, Aparna Guru Jambheshwar University of Science and Technology Dept. of Computer Science & Engineering Haryana Hisar India Guru Jambheshwar University of Science and Technology Dept. of AI & Data Science Haryana Hisar India National Institute of Technology Hamirpur Dept. of Computer Science & Engineering Himachal Pardesh India Institute of Technology Nirma University Dept. of Computer Science & Engineering Gujarat Ahmedabad India

ISBN: (纸本)9798331520762

Internet has evolved from a network of connecting people to a network of connecting things, leading to a more complex and sophisticated network of Industrial Things, known as Industrial IoT (IIoT) today. This evolution has revolutionized the traditional Industrial system into real-time smarter systems that enhanced overall efficiency and productivity. Despite its benefits, the interconnected nature of IIoT, expanded the attack surface, exposing the systems to new crucial and complex cybersecurity threats. Several real time attacks on various industries as mentioned in this paper and the increasing cybersecurity cost over the years, clearly states the need of robust security solutions. To deeply understand the cybersecurity aspect, we provided a comprehensive study of attacks and vulnerabilities in this paper. In this paper, we did a indepth study of various IIoT related severe attacks and aspects related to these attacks, like vulnerabilities, impacts, potential solutions etc. We also provided future research directions to help the research community, to work upon and develop more robust and efficient cybersecurity solutions. © 2025 IEEE.

关键词： attacks cybersecurity etc IIoT Industrial IoT IoT vulnerabilities

来源：评论

学校读者我要写书评

暂无评论

Software Defined Network Based Next Generation Mobile Communication Network Architecture

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2024年第23期18卷 138-148页

作者： Kumar, Sumit Ben Sujin, B. Bhavani, K. Srilatha, Doddi Anand, Ketan Dept. of CSE Haridwar University Uttarakhand Roorkee India University of Technology and Applied Sciences Nizwa Oman Department of Computer Science and Business Systems Panimalar Engineering College Tamil Nadu Chennai India Department of CSE Koneru Lakshmaiah Education Foundation Telangana Hyderabad India Sreenidhi Institute of Science and Technology Telangana Hyderabad India

As mobile networks and network speeds become more prevalent, the demand for marketing strategies increases. The operators are thinking about this, and the development of 5G communication networks is one of their main concerns. As the need for higher transmission speeds increases, 5G networks face challenges of scalability and adaptability. The next-generation mobile network (NMCN-SDN) architecture proposed in this study is based on Software-Defined Networks (SDN). A new network model called computer-defined networking allows for dynamic network definition and programming. A network simulator is created to examine the efficiency of the built infrastructure under different network conditions, including throughput, latency, and resource consumption. In this paper, the comparison of end-toend latency between the standard communication architecture and the proposed NMCN-SDN architecture is done. The results show that the proposed architecture has less space in various conditions compared to existing communication architectures in various conditions. © 2024 by the authors of this article.

关键词： 5G end-to-end latency mobile communication resource utilization Software-Defined Networks (SDN) throughput

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis: Autism Spectrum Disorder Among Children Using Classification Models 2

A Comparative Analysis: Autism Spectrum Disorder Among Child...

引用

2nd International Conference on Ambient Intelligence in Health Care, ICAIHC 2023

作者： Srikar, Y. Himaanshu, V. Suryanarayana, G. Lnc Prakash, K. Saketha Rama, B.V. Vardhaman College of Engineering Dept: of CSE Hyderabad India Vardhaman College of Engineering Dept: of Information Technology Hyderabad India Hyderabad India Indian Institute of Information Technology Design and Manufacturing Dept: of Computer Science Engineering Kancheepuram Chennai India

ISBN: (纸本)9798350344882

Autism is a neurological condition marked by challenges with communication and social engagement, some recurring interests, and habits. It is a very complex and diverse condition that affects individuals, and there is no prescribed treatment for autism. Machine learning models have such potential to understand autism and provide more effective interventions for autistic patients. However, learning models are particularly challenging to read, making it challenging to understand how the model makes decisions and identify any biases in the model. These are important in the context of research on autism, where it is possible to assess the effects of inaccurate diagnosis or improper treatment recommendations. In this work, various algorithms are applied to an autism spectrum disorder (ASD) dataset with 931 samples and 103 features. Experimental results show that the predictive model Random Forest gives the highest accuracy, precision, recall, and Fl-Score with 100% compared to LR, GNB, KNN, SVM, and ID3. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Diving into Brain Complexity: Exploring Functional and Effective Connectivity Networks 18

Diving into Brain Complexity: Exploring Functional and Effec...

引用

18th IEEE International Conference on Emerging Technologies, ICET 2023

作者： Siddique, Abu Bakar Khalid, Hassan Bin Ali, Raja Hashim University of Europe for Applied Sciences Dept. of Technology & Software Engineering Berlin Germany Gik Institute of Engg. Sciences & Technology Faculty of Computer Science & Engineering Topi Pakistan

ISBN: (纸本)9798350328172

The human brain's intricate functions are under-pinned by a vast network of synapses that enable chemical impulses between neurons. Neuroscientists employ two key approaches, functional and effective connectivity, to understand the brain's complexity, focusing on its operations, cognition, and behavior. While both methods utilize graph theory for network analysis, functional connectivity, which investigates associated brain activity, has seen more substantial research efforts than effective connectivity, which examines information processing's inter-regional impacts. In this research paper, we aim to present an extensive examination of the emerging discipline that combines graph theory with the analysis of brain characteristics, shedding light on how these characteristics arise from the interactions among different groups of neurons. Our primary focus lies in exploring the diverse cognitive and neurological applications that leverage functional Magnetic Resonance Imaging (fMRI) as a tool. Additionally, we offer a comprehensive overview of the methods employed to construct brain networks based on functional and efficient connections. Throughout the discussion, we emphasize the advantages and limitations associated with these approaches. © 2023 IEEE.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis to Review Products based on Machine Learning 4

Sentiment Analysis to Review Products based on Machine Learn...

引用

4th International Conference on Inventive Research in Computing Applications, ICIRCA 2022

作者： Saha, Sumit Sett, Aishik Karmakar, Samit Institute of Engineering and Management Dept. of Electronics & Communication Engineering Kolkata India University of Kalyani Dept. of Computer Science and Engineering Kolkata India

ISBN: (数字)9781665497077

ISBN: (纸本)9781665497077

In this study, a method is proposed to represent the corresponding viewpoints and features in the form of graphs for observing the sentiment of the subscribers based on product review. The aim is to observe and empathize the situations based on real time with sentimental analysis using deep learning and machine learning. Nowadays machine learning and deep learning is applied for the solutions of the problems in computer vision, voice recognition, image processing and convolutional neural network. In this work, a convolutional neural network model has been proposed which attains a better outcome than other methods. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Multi-Scale Learning Assisted Neural Network for Improved Object Detection in Complex Environments 9

A Multi-Scale Learning Assisted Neural Network for Improved ...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Karthikayani, K. Vadlamani, Subramanyam M. Prasad, M.V.Siva Thatipudi, Jayendra Gopal Kalaivaani, P.C.D. Upadhyay, Shrikant Srm Institute of Science and Technology Chennai India Anurag engineering college Department of Cse Kodad India University of North Texas Dept. of Computer Science United States Kongu Engineering College Dept of Cse Perundurai638060 India Mlr Institute of Technology Department of Ece Hyderabad India

ISBN: (纸本)9798350377972

Object detection in complex environments presents significant challenges due to the variability in object scales, occlusions, and cluttered backgrounds. This paper proposes a Multi-Scale Learning Assisted Neural Network designed to improve object detection accuracy in such scenarios. The proposed model integrates multi-scale learning, hybrid attention mechanisms, and an advanced feature fusion strategy to enhance its ability to detect objects across various scales and complexities. The model was evaluated against nine state-of-the-art object detection models, including YOLOv4, Faster R-CNN, SSD, EfficientNet, RetinaNet, CenterNet, Cascade R-CNN, FCOS, and Mask R-CNN. Experimental results demonstrate that the proposed model outperforms existing models, achieving an accuracy of94.25%, precision of93.50%, recall of92.70%, and an F1-score of93.10%. Additionally, the model exhibits a balanced trade-off between inference time and model size, making it suitable for real-world applications where performance and resource efficiency are critical. The high IoU (87.50%) and mAP (89.20%) scores further validate the model's robustness in accurately detecting and localizing objects in complex environments. This study highlights the potential of the proposed model to significantly improve object detection tasks, particularly in challenging and dynamic real-world scenarios. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Data Sovereignty Provision Blockchain for Remote Healthcare Service 6

Data Sovereignty Provision Blockchain for Remote Healthcare ...

引用

6th International Conference on Information Systems and computer Networks, ISCON 2023

作者： Ryu, Hyunho Kim, Hyunsung Agarwal, Saurabh Sharma, Dilip Kumar Kapito, Beaton Ali, Patrick Kyungil University Dept. of Smart Security Gamasilgil 50 Kyungsan Kyungbuk Korea Republic of Amity University Uttar Pradesh Dept. of Computer Science and Engineering Noida201313 India GLA University Dept. of Computer Science and Engineering Mathura281406 India University of Malawi Mathematical Sciences Department P.O.Box 280 Zomba Malawi

ISBN: (纸本)9798350346961

Remote healthcare services provide more opportunities for communication between doctors and patients, strengthening their relationships and improving patient satisfaction and loyalty. However, those services face specific security and privacy challenges that constrain growth. Furthermore, patients' information is scattered in several hospitals with various formats, which does not provide the data sovereignty of patients. Data sovereignty is a way for any service to control or regain its data. This paper proposes a privacy-preserving blockchain for remote healthcare services to solve these issues. There is only one database of patient electronic health records in our data structure, and various hospitals could use it. The proposed data structure keeps the patient's electronic health records and the doctor's diagnosis and prescription data separate. Each entity in our system has different access rights to its role. The proposed system is based on some security primitives, including pseudonym policy, delegation, data encryption, and digital signature, depending on the privacy requirements. The proposed blockchain could be a solution against the previous centralized system and provide remote healthcare services' data sovereignty, privacy, and security.. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Explainable Multiclass Blood Cell Classification: Combining Custom CNNs with SHAP

Explainable Multiclass Blood Cell Classification: Combining ...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Md. Ismiel Hossen Abir Shantanu Dey Anik Hasibul Islam Peyal Dept. of Computer Science & Engineering International Standard University Dhaka Bangladesh Dept. of Software Engineering Daffodil International University Birulia Savar Dhaka Bangladesh Dept. of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Blood cell classification is a crucial task in medical diagnostics. This work can identify different blood cell types that play essential roles in the immune system and overall body function. This research introduces a custom Convolutional Neural Network (CNN) model with SHAP for explainable multiclass classification of blood cell images. We classify eight types of blood cells—basophil, eosinophil, erythroblast, immunoglobulin (Ig), lymphocyte, monocyte, neutrophil, and platelet. An ablation study was conducted to optimize the CNN architecture. We compared its performance with eleven transfer learning models, including VGG16, ResNet101, and EfficientNet variants. Our model achieved 92.60% accuracy while maintaining lower complexity. The use of SHAP provides transparency by highlighting crucial features in the model’s decision-making process.

关键词： Training Accuracy Microprocessors Transfer learning Lymphocytes computer architecture Convolutional neural networks Medical diagnosis Blood Testing

来源：评论

学校读者我要写书评

暂无评论

Discovering Efficient Fused Layer Configurations for Executing Multi-Workloads on Multi-Core NPUs

Discovering Efficient Fused Layer Configurations for Executi...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Younghyun Lee Hyejun Kim Yongseung Yu Myeongjin Cho Jiwon Seo Yongjun Park Dept. of Artificial Intelligence Hanyang University Dept. of Computer Science and Engineering Yeonsei University Dept. of Computer Science Hanyang University SAPEON Korea Inc

ISBN: (数字)9783981926385

ISBN: (纸本)9798350348606

As the AI industry grows rapidly, Neural Processing Units (NPUs) have been developed to deliver AI services more efficiently. One of the most important challenges for NPUs is task scheduling to minimize off-chip memory accesses, which may occur significant performance overhead. To reduce memory accesses, multiple convolution layers can be fused into a fused layer group, which offers numerous optimization opportunities. However, in most Convolutional Neural Networks (CNNs), when multiple layers are fused, the on-chip memory utilization of the fused layers gradually decreases, resulting in non-flat memory usage. In this paper, we propose a scheduling search algorithm to optimize the fusion of multiple convolution layers while reducing the peak on-chip memory usage. The proposed algorithm aims to find a schedule that simultaneously optimizes execution time and peak on-chip memory usage, despite a slight increase in off-chip memory accesses. It organizes the search space into a graph of possible partial schedules and then finds the optimal path. As a result of the improved on-chip memory usage, multiple workloads can be executed on multi-core NPUs with increased throughput. Experimental results show that the fusion schedule explored by the proposed method reduced on-chip memory usage by 39%, while increasing latency by 13%. When the freed on-chip memory was allocated to other workloads and the two workloads were executed concurrently in a multi-core NPU, a 32% performance improvement could be achieved.

关键词： Industries Schedules Job shop scheduling Convolution Processor scheduling Throughput System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Investigating Requirements and Expectations of Wearable Telexistence Robotic Systems

Investigating Requirements and Expectations of Wearable Tele...

引用

IEEE International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA)

作者： Abdullah Iskandar Mohammed Al-Sada Osama Halabi Tatsuo Nakajima Dept. of Computer Science and Engineering Waseda University Tokyo Japan Dept. of Computer Science and Engineering Qatar University Doha Qatar

Telexistence refers to various technologies that enable a high sense of embodiment and interaction capabilities with remote environments. Although numerous telexistence systems have been explored in previous works of literature, no prior studies have investigated the usability of telexistence systems for daily use. Therefore, this study focuses on Piton, which is a novel wearable telexistence robot which has a high degree of freedom in a snake-shaped design. Piton offers a unique opportunity for remote interaction and manipulation in diverse environments, owing to its flexible movement, which enables users to adapt to various scenarios with ease. The robot's wearability is also an essential feature that allows the user to wear it as a backpack. However, despite its promising features, deeper investigation is necessary to explore potential use cases for Piton in users' daily lives and the challenge of Piton.

关键词：

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：