检索结果-内蒙古大学图书馆

9th International Conference on Integrated Circuits and Microsystems, ICICM 2024

作者： Chen, Zhikang Zhang, Yuejun Ren, Mingze Xia, Donghao Wang, Pengjun Zhang, Huihong Wen, Liang Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo China College of Electrical and Electronic Engineering Wenzhou University Wenzhou China China Coast Guard Academy Department of Electronic Technology Ningbo China

ISBN: (纸本)9798331509453

With the rise of the Internet of Things, smart healthcare with remote monitoring and diagnosis enables patients to reduce the number and duration of hospitalizations, thereby reducing the pressure on doctors. However, the transmission data of disease detection chips is susceptible to cache attacks, leading to user health data leakage. Hardware level encryption design has become a research hotspot. Firstly, by adding a Mask channel at the upper level of each convolution layer, the preprocessed data is transmitted simultaneously with the obfuscated data, and the channel exchange during transmission is utilized to protect user privacy;Secondly, there is a redundancy mechanism between the input matrix and weight matrix of the storage module, and invalid values are added to the redundant parts to prevent cache attacks from stealing user information;Finally, add multi temporal obfuscation to the first input data to achieve the different lengths between the first and subsequent data. The protection circuit designed in this article achieves user privacy protection on the basis of only increasing hardware overhead by 2.5%, power consumption overhead by 3.61%, and not affecting disease monitoring accuracy. © 2024 IEEE.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Malware Detection System 3

Machine Learning Based Malware Detection System

引用

3rd International Conference on Advancement in Electronics and Communication engineering, AECE 2023

作者： Varshney, Gunjan Varshney, Sudeep Suman, Amrit Chouhan, Kuldeep Suman, Preetam Jss Academy of Technical Education Department of Electrical Engineering Uttar Pradesh Noida India Sharda School of Engineering & Technology Computer Science and Engineering Uttar Pradesh Greater Noida India Vit University Computer Science and Engineering Madhya Pradesh Bhopal India

ISBN: (纸本)9798350330724

As today's time is more dependent towards the internet, there are various types of malwares are being developed on daily basis, as per report presented by Kaspersky around 560,000 instances of malware created daily. Malware are being developed in such a way that they can replicate and change their signature based on the types of detection system present in organization. Due to urge of variety of malwares it is enables security researchers to shift towards use of Machine Learning for better protection towards variety of security systems. Use of machine learning makes the whole thing more productive and responsive. In this research we have suggested a system that detects diversity of viruses depending on their types response to the system, for the initial phase we have taken a Dataset of Malwares which contains 96,724 malware samples and 41,323 binaries, executable and dynamic link libraries which are legit files. Also we have contrasted the different types of machine learning Techniques which can be used for creating these types of system. © 2023 IEEE.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

Subspace Rotation Algorithm for Training Restricted Hopfield Network

Subspace Rotation Algorithm for Training Restricted Hopfield...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Ci Lin Tet Yeap Iluju Kiringa Electrical Engineering and Computer Science University of Ottawa

ISBN: (数字)9798331527235

ISBN: (纸本)9798331527242

This paper introduces the Subspace Rotation Algorithm (SRA) for training the Restricted Hopfield Network (RHN) as an auto-associative memory. SRA is a gradient-free subspace tracking method based on Singular Value Decomposition (SVD) to update the weight matrix. Despite having slightly worse time complexity than Back-propagation (BP) theoretically, in practice, SRA completes training faster since it requires fewer iterations to converge. Comparative analysis with BP for training RHN reveals that SRA consistently reaches the optimal solution, whereas BP fails to achieve comparable performance if the weight initialization is not within the appropriate basin of attraction. Experiments involving the memorization of 10, 50, and 100 patterns from the MNIST dataset show that RHN trained with SRA exhibits better robustness to noisy and corrupted patterns compared to RHN trained with BP. These findings suggest that SRA offers a more reliable and effective method for training RHNs in applications needing high tolerance to input distortions.

关键词： Training Hopfield neural networks Distortion Robustness Noise measurement Matrix decomposition Time complexity Artificial intelligence Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Med-Tuning: A New Parameter-Efficient Tuning Framework for Medical Volumetric Segmentation 7

Med-Tuning: A New Parameter-Efficient Tuning Framework for M...

引用

7th International Conference on Medical Imaging with Deep Learning, MIDL 2024

作者： Shen, Jiachen Wang, Wenxuan Chen, Chen Jiao, Jianbo Liu, Jing Zhang, Yan Song, Shanshan Li, Jiangyun School of Automation and Electrical Engineering University of Science and Technology Beijing China Center for Research in Computer Vision University of Central Florida United States School of Computer Science University of Birmingham United Kingdom Institute of Automation Chinese Academy of Sciences China

The "pre-training then fine-tuning (FT)" paradigm is widely adopted to boost the model performance of deep learning-based methods for medical volumetric segmentation. However, conventional full FT incurs high computational and memory costs. Thus, it is of increasing importance to fine-tune pre-trained models for medical volumetric segmentation tasks in a both effective and parameter-efficient manner. In this paper, we introduce a new framework named Med-Tuning to realize parameter-efficient tuning (PET) for medical volumetric segmentation task and an efficient plug-and-play module named Med-Adapter for task-specific feature extraction. With a small number of tuned parameters, our framework enhances the 2D baselines’s precision on segmentation tasks, which are pre-trained on natural images. Extensive experiments on three benchmark datasets (CT and MRI modalities) show that our method achieves better results than previous PET methods on volumetric segmentation tasks. Compared to full FT, Med-Tuning reduces the fine-tuned model parameters by up to 4×, with even better segmentation performance. Our project webpage is at https://***/Med-Tuning/. © 2024 CC-BY 4.0, J. Shen, W. Wang, C. Chen, J. Jiao, J. Liu, Y. Zhang, S. Song & J. Li.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Hypertension Disease Predictions with Various Models Using Data science Framework 22

Hypertension Disease Predictions with Various Models Using D...

引用

6th International Conference on Medical and Health Informatics, ICMHI 2022

作者： Alizargar, Azadeh Tan, Tan-Hsu Chang, Yang-Lang Alkhaleefah, Mohammad College of Electrical Engineering and Computer Science Department of Electrical Engineering National Taipei University of Technology Taiwan

ISBN: (纸本)9781450396301

Hypertension is a common disease which may lead to incurable situation if it is not well-treated. By extracting knowledge from large datasets, data mining can be used for the hypertension prediction and diagnosis. In this research, three data mining techniques, the support vector machine (SVM), k-nearest neighbors (k-NN), and decision tree, were developed to predict the hypertension with two datasets. These techniques were implemented on Google Colab using Python codes. Experimental results illustrate that the accuracy and area under the receiver operating characteristic (ROC) curve performance of all these three techniques on first dataset is 81% and 80.64% for the SVM, 74% and 73.97% for the k-NN, and 74% and 73.86% for the decision tree, respectively. The accuracy and ROC curve performance of these three approaches on the second dataset were 73% and 72.48% for the SVM, 76% and 75.75% for the k-NN model, and 75% and 74.49% for the decision tree, respectively. The results indicate that the SVM, k-NN, and decision tree, are effective in predicting the hypertension based on the obtained important features of the patients, and the k-NN is among the best choice. © 2022 ACM.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Non-intrusive soil carbon content quantification methods using machine learning algorithms:A comparison of microwave and millimeter wave radar sensors

引用

Journal of Automation and Intelligence 2023年第3期2卷 152-166页

作者： Di An YangQuan Chen Electrical Engineering&Computer Science University of CaliforniaMerced95343CAUSA Department of Mechanical Engineering University of CaliforniaMerced95343CAUSA

Agricultural and forestry biomass can be converted to biochar through pyrolysis gasification,making it a significant carbon source for *** biochar to soil is a carbon-negative process that helps combat climate change,sustain soil biodiversity,and regulate water ***,quantifying soil carbon content conventionally is time-consuming,labor-intensive,imprecise,and expensive,making it difficult to accurately measure in-field soil carbon’s effect on storage water and *** address this challenge,this paper for the first time,reports on extensive lab tests demonstrating non-intrusive methods for sensing soil carbon and related smart biochar applications,such as differentiating between biochar types from various biomass feedstock species,monitoring soil moisture,and biochar water retention capacity using portable microwave and millimeter wave sensors,and machine *** methods can be scaled up by deploying the sensor in-field on a mobility platform,either ground or *** paper provides details on the materials,methods,machine learning workflow,and results of our *** significance of this work lays the foundation for assessing carbon-negative technology applications,such as soil carbon content *** validated our quantification method using supervised machine learning algorithms by collecting real soil mixed with known biochar contents in the *** results show that the millimeter wave sensor achieves high sensing accuracy(up to 100%)with proper classifiers selected and outperforms the microwave sensor by approximately 10%–15%accuracy in sensing soil carbon content.

关键词： Soil carbon content sensing Carbon sequestration Microwave radar Millimeter wave radar Proximal sensing Machine learning

来源：评论

学校读者我要写书评

暂无评论

GPU Side-Channel Attack Classification for Targeted Secure Shader Mitigation

引用

SN computer science 2024年第8期5卷 1148页

作者： Lungu, Nelson Patra, Sudhansu Shekhar Mishra, Manoj Ranjan Dash, Bibhuti Bhusan Sasmal, Gopal Charan Pattnayak, Parthasarathi Singh, Satyendr Gourisaria, Mahendra Kumar Department of Electrical and Electronics Engineering University of Zambia Lusaka Zambia School of Computer Applications Kalinga Institute of Industrial Technology (KIIT) Deemed to be University Bhubaneswar India MCA Department Trident Academy of Creative Technology Bhubaneswar India Computer Science and Engineering Department BML Munjal University Gurugram India School of Computer Engineering Kalinga Institute of Industrial Technology (KIIT) Deemed to be University Bhubaneswar India

Graphics processing units (GPUs) provide massively parallel processing capabilities, enabling accelerated computation across diverse applications. However, their parallel architecture and shared resources also introduce significant security vulnerabilities, especially side-channel attacks that can compromise sensitive data. This article presents a systematic classification of GPU side-channel attack vectors, including power analysis, timing analysis, electromagnetic analysis, and combined attacks. This taxonomy proposes countermeasures for the NVIDIA GeForce RTX 3090 GPU to mitigate these threats. The countermeasures encompass hardware techniques such as isolated execution environments, secure memory partitioning, and hardware random number generators to reduce the attack surface. Software methods, including constant-time algorithms, data-independent execution paths, masking, and oblivious memory access, are also implemented to eliminate timing and cache side channels. Comprehensive experiments demonstrate the effectiveness of the countermeasures, achieving up to 95% reduction in power analysis leakage, 90% in timing analysis, and 92% in electromagnetic analysis with acceptable performance overheads. The secure shader programming framework provides robust mitigation against GPU side-channel attacks while maintaining efficiency and compatibility with the RTX 3090 architecture. This work contributes vital insights and solutions for analysing GPU security vulnerabilities, designing focused countermeasures, and enabling confidential computing leveraging modern GPU capabilities. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Graphics processing units security Hardware countermeasures NVIDIA GeForce RTX 3090 Secure shader Side-channel attacks Software mitigation

来源：评论

学校读者我要写书评

暂无评论

Identification and Containment of Intrusion Attacks in an IIoT Network based on Machine Learning and Blockchain Technology 2

Identification and Containment of Intrusion Attacks in an II...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Motamarri, Nikhita Satish, G. Uma, H.R. Barve, Amit Patil, Harshal Taqui, Syed Noeman Potti Sreeramulu Chalavadhi Mallikarjuna Rao College of Engineering and Technology Department of Computer Science and Engineering Vijayawada Andhra Pradesh 520001 India Sree Dattha Institute of Engineering and Science Department of Electrical and Electronics Engineering Sheriguda Ibrahimpatnam Telangana Hyderabad501510 India BGS Institute of Technology Adichunchanagiri University Department of Computer Science and Engineering Mandya Karnataka 571448 India Parul Institute of Engineering and Technology Parul University Department of Computer Science and Engineering Gujarat 391760 India Department of Computer Science and Engineering Pune Maharashtra 412115 India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of VLSI Microelectronics Tamilnadu Chennai602105 India

ISBN: (纸本)9798350327533

The Blockchain technology is leveraged to establish a secure and tamper-resistant decentralized ledger, providing a transparent and immutable record of all transactions and communications within the IoT network. By implementing smart contracts, we ensure the integrity and authenticity of device interactions, mitigating the risk of unauthorized access and data manipulation. Complementing the Blockchain, Machine Learning (ML) algorithms are employed to analyze and identify patterns indicative of malicious activities. The proposed system employs anomaly detection models, trained on historical data, to continuously monitor and adapt to emerging threats. This dynamic threat detection mechanism enhances the ability of the IoT network to recognize and respond to sophisticated intrusion attempts in real-Time. Furthermore, the proposed framework incorporates a decentralized identity management system using Blockchain, ensuring that only authenticated and authorized devices can participate in the IoT network. This not only safeguards against unauthorized access but also protects the privacy and integrity of the data generated and exchanged by IoT devices. To validate the effectiveness of our approach, we conducted experiments in a simulated IoT environment, considering various attack scenarios. The results demonstrate a significant improvement in the overall security posture of the IoT network, with reduced false positives and swift identification of intrusions. In conclusion, the integration of Blockchain and ML techniques provides a robust and adaptive defense mechanism for IoT device networks. This holistic approach addresses the challenges of security, privacy, and data integrity, paving the way for a more resilient and trustworthy IoT ecosystem in the face of evolving cyber threats. © 2024 IEEE.

关键词： Blockchain Integrity Internet of Things (IoT) Intrusion Intrusion Detection System Machine Learning Security

来源：评论

学校读者我要写书评

暂无评论

Predicting Heart Failure Survival: A Machine Learning Approach with Explainable AI

Predicting Heart Failure Survival: A Machine Learning Approa...

引用

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Chowdhury, Aritra Dey, Sourav Hossain, Sohrab Hasan, Mehdi Chowdhury, Sunzida East Delta University Department of Computer Science and Engineering Chittagong Bangladesh Chittagong University of Engineering and Technology Department of Electrical and Electronic Engineering Chittagong Bangladesh East Delta University School of Science Engineering and Technology Chittagong Bangladesh Yeshiva University Graduate School of Computer Science and Engineering New York United States University of Cumberlands Department of Information Science New York United States

ISBN: (纸本)9798331529765

Heart failure is one of the global health issues that is needed for precise prognostic instruments. In order to predict survival and time-to-event outcomes in patients with heart failure, this study assesses machine learning techniques. Most effective prediction models are determined for heart failure prognosis by combining clinical information and evaluating model performance. According to the results, the LightGBM classifier had the lowest accuracy at 77%, while the SVM classifier had the highest accuracy at 88%. These findings suggest that machine learning can greatly improve clinical judgement in cardiovascular medicine and advance patient-focused treatment. © 2024 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Optimal Resource Allocation Method for Device-to-Device Communication in 5G Networks

引用

computers, Materials & Continua 2022年第4期71卷 1-15页

作者： Fahd N.Al-Wesabi Imran Khan Saleem Latteef Mohammed Huda Farooq Jameel Mohammad Alamgeer Ali M.Al-Sharafi Byung Seo Kim Department of Computer Science King Khalid UniversityMuhayel AseerKSA Faculty of Computer and IT Sana’a UniversityYemen Department of Electrical Engineering University of Engineering and TechnologyPeshawarPakistan Department of Medical Instrumentation Techniques Engineering Electrical Engineering Technical CollegeMiddle Technical UniversityBaghdad10013Iraq Department of Information Systems King Khalid UniversityMayahel AseerKSA Department of Computer Science College of Computers and Information TechnologyUniversity of BishaKSA Department of Software and Communications Engineering Hongik UniversityKorea

With the rapid development of the next-generation mobile network,the number of terminal devices and applications is growing ***,how to obtain a higher data rate,wider network coverage and higher resource utilization in the limited spectrum resources has become the common research goal of ***-to-Device(D2D)communication technology and other frontier communication technologies have ***-to-Device communication technology is the technology that devices in proximity can communicate directly in cellular *** has become one of the key technologies of the fifth-generation mobile communications system(5G).D2D communication technology which is introduced into cellular networks can effectively improve spectrum utilization,enhance network coverage,reduce transmission delay and improve system throughput,but it would also bring complicated and various interferences due to reusing cellular resources at the same *** resource management is one of the most challenging and importing issues to give full play to the advantages of D2D *** resource allocation is an important factor that needs to be addressed in D2D ***,this paper proposes an optimization method based on the game-matching *** main idea is to model the optimization problem of the quality-of-experience based on user fairness and solve it through game-matching *** results show that the proposed algorithm effectively improved the resource allocation and utilization as compared with existing algorithms.

关键词： D2D communication resource allocation optimization networks

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：