检索结果-内蒙古大学图书馆

Electronics, Communication and Signal Processing (ICECSP), International Conference on

作者： R. Geetha T. Vijayanandh Ananthi S.N. X. Mercilin Raajini V.S. Divya Sundar P Kumari Deepika Department of EEE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India Department of CSE School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering S.A Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha Engineering College Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science St. Joseph's College of Engineering Chennai Tamil Nadu India

ISBN: (数字)9798350364590

ISBN: (纸本)9798350375381

As time goes on and technology gets better, various data-sharing technologies are becoming more and more integrated into many different businesses. Therefore, data exchange and security are crucial for the data's value to be realized. Nevertheless, it is challenging to verify the authenticity of a basic data sharing method in order to detect electronic data usage traces. An further difficulty is the reluctance of data suppliers to provide their data. Employing Blockchain's distributed ledger, smart contract, data trust, and traceability features. For the purpose of facilitating secure access to data, this study introduces a blockchain-based data-sharing architecture that optimizes to circumvent the security and control issues associated with traditional centralized data sharing and administration. In addition, the research evaluates the practicality and safety of the prototype. Furthermore, this paper proposes a Secured data Management Scheme (SDMS) that utilizes blockchain technology to optimize data sharing efficiency. To assess the efficacy of this model, it is cross-validated with the conventional data Privacy Handler (DPH) method. While present centralized security solutions fail to meet security requirements in an IoT setting, blockchain technology provides a decentralized solution. Through the use of a blockchain and a WiFi-enabled network model, this article seeks to offer a secure communication framework for Internet of Things (IoT) devices. According to the results, attitudes and character quirks have a role in how the intelligence community plans to use a blockchain-based data-sharing model for integrating systems. This research demonstrated the viability of using blockchain technology in an intelligence community-centric data-sharing strategy.

关键词： Surveys data privacy Smart contracts Signal processing Blockchains Safety Security Internet of Things Computer crime Business

来源：评论

学校读者我要写书评

暂无评论

File Type Identification Classifier with Classification-by-Retrieval and One-Shot Learning

SSRN

引用

SSRN 2024年

作者： Lisker, Simona Butman, Ayelet Dubin, Ran Dvir, Amit Hajaj, Chen Department of Computer Science Holon Institute of Technology Holon 52 Golomb Street POB 305 Holon5810201 Israel Department of Computer Science Ariel Cyber Innovation Center Ariel University Kiryat Hamada St. Ariel4070000 Israel Department of Computer and Software Engineering Ariel Cyber Innovation Center Ariel University Kiryat Hamada St. Ariel4070000 Israel Department of Industrial Engineering and Management Data Science and Artificial Intelligence Research Center Ariel University Kiryat Hamada St. Ariel4070000 Israel

In classical malware detection methodologies, digitalforensics and file carving, file type classification holds a pivotalrole. However, it is still a challenge to accurately categorize an ever-growing diversity of file formats and *** approaches to address the issue have been introducedin recent years. Most approches use hand-crafted features, andsome use a compact neural network architectureapproach with explicit feature extraction. Nonetheless, thesemethods encounter some challenges, including training time fornew file types, dealing with an insufficient number of trainingexamples, the complexity of training, and their accuracylevel. Our paper introduces three novel, content-basedretrieval and identification, file type classificationapproaches, proactively addressing these identified *** three approaches significantly enhance accuracy andprioritize an intuitive method for swift integration of new filetypes using pre-trained models, thereby enhancing speed andreliability in file type detection. The first approach is basedon the principles of Natural Language Processing (NLP) andtransformer architecture. The second approach amalgamates anensemble of statistical features, OOXML files identifier and a pre-trained model usingtransfer *** meticulously evaluated the classification task, achieving an accuracy of 72.4% and 69.2%, respectively, for our first two approaches, surpassing the performance of the state-of-the-art convolutional neural network (CNN) based models described in the literature in terms of accuracy. Finally, our third approach of one-shot learning enables the identification of files with minimal examples, facilitating efficient training in a short period, and demonstrating a remarkable 100% accuracy in several scenarios. © 2024, The Authors. All rights reserved.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Transformers in medical image analysis

引用

Intelligent Medicine 2023年第1期3卷 59-78页

作者： Kelei He Chen Gan Zhuoyuan Li Islem Rekik Zihao Yin Wen Ji Yang Gao Qian Wang Junfeng Zhang Dinggang Shen Medical School of Nanjing University NanjingJiangsu 210093China National Institute of Healthcare Data Science at Nanjing University NanjingJiangsu 210093China BASIRA Laboratory Faculty of Computer and Informatics EngineeringIstanbul Technical UniversityIstanbulTurkey School of Science and Engineering ComputingUniversity of DundeeUK State Key Laboratory for Novel Software Technology Nanjing UniversityNanjingJiangsu 210093China School of Biomedical Engineering ShanghaiTech UniversityShanghai 201210China Department of Research and Development Shanghai United Imaging Intelligence Co.Ltd.Shanghai 200030China Shanghai Clinical Research and Trial Center Shanghai 201703China

Transformers have dominated the field of natural language processing and have recently made an impact in the area of computer *** the field of medical image analysis,transformers have also been successfully used in to full-stack clinical applications,including image synthesis/reconstruction,registration,segmentation,detection,and *** paper aimed to promote awareness of the applications of transformers in medical image ***,we first provided an overview of the core concepts of the attention mechanism built into transformers and other basic ***,we reviewed various transformer architectures tailored for medical image applications and discuss their *** this review,we investigated key challenges including the use of transformers in different learning paradigms,improving model efficiency,and coupling with other *** hope this review would provide a comprehensive picture of transformers to readers with an interest in medical image analysis.

关键词： Transformer Medical image analysis Deep learning Diagnosis Registration Segmentation Image synthesis Multi-task learning Multi-modal learning Weakly-supervised learning

来源：评论

学校读者我要写书评

暂无评论

UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition

arXiv

引用

arXiv 2023年

作者： Li, Qiufu Jia, Xi Zhou, Jiancan Shen, Linlin Duan, Jinming National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Computer Vision Institute Shenzhen University China School of Computer Science University of Birmingham United Kingdom Aqara Lumi United Technology Co. Ltd China Alan Turing Institute United Kingdom SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Sample-to-class-based face recognition models can not fully explore the cross-sample relationship among large amounts of facial images, while sample-to-sample-based models require sophisticated pairing processes for training. Furthermore, neither method satisfies the requirements of real-world face verification applications, which expect a unified threshold separating positive from negative facial pairs. In this paper, we propose a unified threshold integrated sample-to-sample based loss (USS loss), which features an explicit unified threshold for distinguishing positive from negative pairs. Inspired by our USS loss, we also derive the sample-to-sample based softmax and BCE losses, and discuss their relationship. Extensive evaluation on multiple benchmark datasets, including MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace, demonstrates that the proposed USS loss is highly efficient and can work seamlessly with sample-to-class-based losses. The embedded loss (USS and sample-to-class Softmax loss) overcomes the pitfalls of previous approaches and the trained facial model UniTSFace exhibits exceptional performance, outperforming state-of-the-art methods, such as CosFace, ArcFace, VPL, AnchorFace, and UNPG. Our code is available at https://***/CVI-SZU/UniTSFace. © 2023, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

ExpoNAS: Using Exposure-based Candidate Exclusion to Reduce NAS Space for Heterogeneous Pipeline of CNNs

ExpoNAS: Using Exposure-based Candidate Exclusion to Reduce ...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Huijuan Duan Danghui Wang Xingting Zhao Kuizhi Mei Jihe Wang School of Computer Science Northwestern Polytechnical University Xi'an China Engineering Research Center of Embedded System Integration Ministry of Education Northwestern Polytechnical University Xi'an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi'an China

Efficiently deploying neural network models on heterogeneous edge systems faces unique challenges. Two major issues are underutilized pipelines caused by hardware heterogeneity and explosive growth of architecture search space. To address these challenges, we propose ExpoNAS, a framework enabling fast deployment-oriented neural architecture search on heterogeneous platforms. ExpoNAS evaluates model partitioning and deployability before search to meet accuracy and latency constraints. However, repeated partitioning leads to exponential growth in architecture search space. We first observe a strong correlation between operational exposure and accuracy improvement, and then we propose an exposure-based reduction technique that excludes the operations of low exposure. By removing these non-critical operations, the exposure-based pruning successfully reduces architecture search time. Our experiments on popular datasets show that the ExpoNAS pipelined design improves execution efficiency by a factor of 2 compared to traditional batch processing. Without compromising accuracy, ExpoNAS is able to reduce the architecture search time by 47.5% for discovering high-accuracy networks, compared to the SOTA NAS strategies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PoBTx(Proof of Block and Transaction): An Efficient Consensus Algorithm for IoT Business Blockchain

PoBTx(Proof of Block and Transaction): An Efficient Consensu...

引用

Augmented intelligence and Sustainable Systems (ICAISS), International Conference on

作者： M. C Jobin Christ D. Kalaiyarasi Janani G K. Senthamilselvan D Kirubakaran N. S. Gowri Ganesh Department of Biomedical Engineering Rajalakshmi Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering Panimalar Engineering College Chennai Tamil Nadu Department of Information Technology RMD Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering R.M.K Engineering College Chennai Tamilnadu India Department of Artificial Intelligence and Data Science Saveetha Engineering College Chennai Tamil Nadu India

The rise of Internet of Things (IoT) networks has brought about numerous challenges in Industry 4.0 that can be addressed by blockchain technology. However, conventional business blockchain algorithms are inadequate for large-scale IoT systems and need to be adapted to make them scalable for IoT. This may require simplifying complex consensus-based security measures. This paper proposes a novel Proof of Block and Transaction (PoBTx) consensus algorithm, combining the advantages of Proof of Trade (PoT) and Proof of Block (PoB) approaches. PoBTx is tailored for IoT networks, addressing energy and computational constraints. The comprehensive analysis demonstrates its improvements in security, computation time, memory, and throughput compared to traditional consensus algorithms, making PoBTx a promising solution for large-scale IoT networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bayesian Optimal Experiment Design for Sloppy Systems

引用

IFAC-PapersOnLine 2022年第23期55卷 121-126页

作者： Prem Jagadeesan Karthik Raman Arun K. Tangirala Department of Chemical Engineering Indian Institute of Technology (IIT) Madras Department of Biotechnology Bhupat and Jyoti Mehta School of Biosciences IIT Madras Robert Bosch Centre for Data Science and Artificial Intelligence (RBCDSAI) IIT Madras Centre for Integrative Biology and Systems mEdicine (IBSE) IIT Madras Chennai 600 036 India

In complex dynamical systems, precise and accurate estimation of parameters and quality of predictions depends on the information contained in the experimental data. Choosing experimental schemes that maximize information contained in the data is known as Optimal Experimental Design (OED). Fisher Information Matrix and variance-covariance matrix are the central ideas of OED. However, using OED in a class of models known as sloppy models renders the model less predictive, even though the parameters are estimated with substantial precision. This work introduces a new information gain index as an experiment design criterion in the Bayesian framework. The proposed design criterion is based on what is known as the Bhattacharyya coefficient. Our previous studies show that the information gain index indicates a loss of practical identifiability. Further, it is also an indication of sloppy and stiff parameters. Hence, we extend the information index and its interpretation to joint Gaussian distributions; then, using simulations, we demonstrate that the new experiment design criterion selects experiments that minimize prediction and parameter uncertainty in sloppy models.

关键词： Bayesian Optimal Experiment Design Sloppy Models Bhattacharyya Coefficient

来源：评论

学校读者我要写书评

暂无评论

Kron-based Model-order Reduction of Open Mass-action Kinetics Chemical Reaction Networks

arXiv

引用

arXiv 2022年

作者： Negara, Mohamad Agung Prawira Burohman, Azka Muji Jayawardhana, Bayu The Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen Groningen9747AG Netherlands Electrical Engineering Faculty of Engineering University of Jember Jl. Kalimantan Tegalboto No.37 Krajan Timur Sumbersari Kec. Sumbersari Jawa Timur Kabupaten Jember68121 Indonesia The Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence Faculty of Science and Engineering University of Groningen Groningen9747AG Netherlands

We propose a Kron-based model-order reduction method for mass-action kinetics chemical reaction networks (CRN) with constant inflow and proportional outflow. The reduced-order models preserve the CRN structure and we establish that the resulting reduced-order models have the same DC-gain or zero-moment as that of the full-order ones. Subsequently, we present the spectrum interlacing property of the Kron-reduced open CRN and propose the use of Gramians-based approach for single-species single-substrate chemical network to get the upper-bound of approximation error and to use it in determining a good set of nodes to be removed systematically. Finally, we evaluate the applicability and efficacy of our results in two well-known biochemical kinetic models: the activated sludge model (ASM) 1 and McKeithan’s T-cell receptor model. © 2022, CC BY.

关键词： Kinetics

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Networks based Meta-Learning for Network Intrusion Detection

arXiv

引用

arXiv 2023年

作者： Sohail, Anabia Ayisha, Bibi Hammed, Irfan Zafar, Muhammad Mohsin Alquhayz, Hani Khan, Asifullah Pattern Recognition Lab Department of Computer & Information Sciences Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Department of Computer Science Faculty of Computing and Artificial Intelligence Air University E-9 Islamabad Pakistan Faculty of Computer Science and Engineering Ghulam Ishaq Khan Institute of Engineering Sciences and Technology Topi District Swabi Khyber Pakhtunkhwa23640 Pakistan Department of Computer Science and Information College of Science in Zulfi Majmaah University Al-Majmaah11952 Saudi Arabia Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan

The digitization of different components of industry and inter-connectivity among indigenous networks have increased the risk of network attacks. Designing an intrusion detection system to ensure security of the industrial ecosystem is difficult as network traffic encompasses various attack types, including new and evolving ones with minor changes. The data used to construct a predictive model for computer networks has a skewed class distribution and limited representation of attack types, which differ from real network traffic. These limitations result in dataset shift, negatively impacting the machine learning models' predictive abilities and reducing the detection rate against novel attacks. To address the challenges, we propose a novel deep neural network based Meta-Learning framework;INformation FUsion and Stacking Ensemble (INFUSE) for network intrusion detection. First, a hybrid feature space is created by integrating decision and feature spaces. Five different classifiers are utilized to generate a pool of decision spaces. The feature space is then enriched through a deep sparse autoencoder that learns the semantic relationships between attacks. Finally, the deep Meta-Learner acts as an ensemble combiner to analyze the hybrid feature space and make a final decision. Our evaluation on stringent benchmark datasets and comparison to existing techniques showed the effectiveness of INFUSE with an F-Score of 0.91, Accuracy of 91.6%, and Recall of 0.94 on the Test+ dataset, and an F-Score of 0.91, Accuracy of 85.6%, and Recall of 0.87 on the stringent Test-21 dataset. These promising results indicate the strong generalization capability and the potential to detect network attacks. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing YOLOv5 with Custom Attention Mechanism for Defect Detection in Photovoltaic Power System Thermal Imaging

Enhancing YOLOv5 with Custom Attention Mechanism for Defect ...

引用

2024 8th International Conference on Electrical, Mechanical and Computer engineering (ICEMCE)

作者： Juntao Liu Junjie Liu Kaicheng Zhou Xueliang Zeng Daozheng Sun Heping Yu College of Information Engineering Nanchang Hangkong University Nanchang Jiangxi Province China College of Material Engineering Fujian Agriculture and Forestry University Fuzhou Fujian Province China College of Transportation and Civil Engineering Fujian Agriculture and Forestry University Fuzhou Fujian Province China College of Information Science and Engineering Zhejiang Sci-Tech University Hangzhou Zhejiang Province China College of Artificial Intelligence and Big Data Hefei University Hefei Anhui Province China College of Electrical Engineering Xi’an University of Technology Shaanxi province China

ISBN: (数字)9798331506230

ISBN: (纸本)9798331506247

Existing deep learning models for defect detection in photovoltaic system thermal imaging may face issues such as suboptimal detection performance and limited defect types. Therefore, this paper proposes an enhanced YOLOv5n model based on a one-step strategy, incorporating a custom attention mechanism to improve the focus on critical information. The model features a network structure designed for lightweight processing and integrates custom attention modules and optimization techniques for object detection and post-processing, which improves model accuracy to some extent. Experimental results indicate that the model with the attention module achieved a minimum loss value of $\mathbf{22.225} \%$ during training, significantly lower than the 29.279% achieved without the module. The optimized model attained a standard deviation of 2.4772 on a public dataset, demonstrating higher stability and accuracy, and effectively performing defect detection and real-time monitoring tasks in photovoltaic system thermal imaging.

关键词： Photovoltaic systems Training YOLO Attention mechanisms Accuracy Imaging Stability analysis Thermal stability Standards Defect 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：