检索结果-内蒙古大学图书馆

4th International Conference on Electronics and Sustainable Communication Systems, ICESC 2023

作者： Vyas, Manish Vijayaganth, R. Chandhok, Jigyasha Srivastava, Aviral Arumugam, S. Tiwari, Mohit College Name & Address: Vikrant Institute of Technology and Management Computer Science Department Indore India Artificial Intelligence and Data Science M.Kumarasamy College of Engineering Thalavapalayam Karur639113 India Tula's Institute of Engineering and Management Naac Grade A+ Accredited Institute Computer Science & Engineering UttarakhandDhoolkot Dehradun India Amity University Rajasthan NH 11 C kant kalwar Jaipur300202 India Periyar Maniammai Institute of Science & Technology Periyar Nagar Vallam Computer Science and Applications Thanjavur613403 India Bharati Vidyapeeth's College of Engineering Department of Computer Science and Engineering A-4 Rohtak RoadPaschim Vihar Delhi India

ISBN: (纸本)9798350300093

The term 'Internet of Things' (IoT) is used to describe the collection of data and the connectivity of items to the web that requires little to no human interaction. The IoT is a network of interconnected devices that can collect and disseminate information. Increased security and privacy worries accompany the launch of new devices due to the proliferation of Internet connections and the development of cutting-edge technology like the IoT. These days, the IoT is used everywhere, but especially in logistics, manufacturing, and healthcare. While these emerging IoT applications greatly enhance the usefulness of smart objects, they also present new security risks. Because of this, adapting existing intrusion detection systems (IDS) for use with IoT networks is a topic of intense study. Many IDS experts have found success with machine learning (ML) and deep learning (DL) techniques. By combining deep extraction through the Convolutional autoencoder with deep learning to identify the best features, this work delivers an improved IDS that can be used for anomaly detection. Improves to the deep learning approach include an evaluation of hyperparameter effectiveness, a stage of feature pruning using an autoencoder neural network, and an examination of the sturdiness of the most effective deep neural networks for circumstances exaggerated by Gaussian noise over some of the features in question. Despite the noise, the results show that the formed IoT dataset is useful for anomaly detection with deep learning methods. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Snapshot boosting: a fast ensemble framework for deep neural networks

引用

science China(Information sciences) 2020年第1期63卷 77-88页

作者： Wentao ZHANG Jiawei JIANG Yingxia SHAO Bin CUI Center for Data Science Peking University National Engineering Laboratory for Big Data Analysis and Applications Department of Computer Science Beijing Key Lab of Intelligent Telecommunications Software and Multimedia School of Computer ScienceBeijing University of Posts and Telecommunications Key Lab of High Confidence Software Technologies Department of Computer SciencePeking University

Boosting has been proven to be effective in improving the generalization of machine learning models in many fields. It is capable of getting high-diversity base learners and getting an accurate ensemble model by combining a sufficient number of weak learners. However, it is rarely used in deep learning due to the high training budget of the neural network. Another method named snapshot ensemble can significantly reduce the training budget, but it is hard to balance the tradeoff between training costs and diversity. Inspired by the ideas of snapshot ensemble and boosting, we propose a method named snapshot boosting. A series of operations are performed to get many base models with high diversity and accuracy, such as the use of the validation set, the boosting-based training framework, and the effective ensemble strategy. Last, we evaluate our method on the computer vision(CV) and the natural language processing(NLP) tasks, and the results show that snapshot boosting can get a more balanced trade-off between training expenses and ensemble accuracy than other well-known ensemble methods.

关键词： ensemble learning deep learning boosting neural network snapshot ensemble

来源：评论

学校读者我要写书评

暂无评论

Label-Free Biomolecule Detection with InP/AlGaAs Charge Plasma Dielectric-Modulated Vertical TFET Using TaN as Metal Gate

引用

IEEE Access 2025年 13卷 89667-89684页

作者： Elshafie, Hashim Alqahtani, Abdulrahman Saad Mubarakali, Azath Adarsh Rag, S. Venkatesh, M. Parthasarathy, P. King Khalid University College of Computer Science Department of Computer Engineering Abha61421 Saudi Arabia University of Bisha College of Computing and Information Technology Bisha67714 Saudi Arabia King Khalid University College of Computer Science Department of Informatics and Computer Systems Abha61421 Saudi Arabia Manipal Institute of Technology Department of Data Science and Computer Applications Manipal Academy of Higher Education Manipal576104 India CMR Institute of Technology Department of Electronics and Communication Engineering Karnataka Bengaluru560037 India

This study introduces a label-free biosensing method for biomolecule detection utilizing an InP/AlGaAs charge plasma dielectric-modulated vertical tunnel field-effect transistor (InP/AlGaAs VTFET) featuring TaN as the metal gate. The device comprises a nanocavity beneath the gate metal adjacent to the tunnelling junction, where biomolecules engage with the dielectric material, resulting in fluctuations in the drain current. A twin metal gate architecture with laterally split dielectrics is employed to eliminate short-channel effects. The biosensor has exceptional sensitivity, attaining a peak drain current sensitivity of 2.5 × 10 cm2 for biomolecules such as albumin (k = 7). The gadget proficiently identifies biomolecules with varying dielectric constants and charge distributions, enabling adaptable label-free detection of diverse targets. The study examines the influence of dielectric constant on critical metrics such as Energy Band Diagrams, Drain Current, Drain Sensitivity, and subthreshold swing (SS). The overlap between the source and pocket regions, along with the introduction of an auxiliary gate, optimizes the electrical characteristics. Simulation results show that the proposed InP/AlGaAs VTFET achieves a maximum sensitivity of 3.5 × 103, outperforming configurations without overlap (2 × 103), highlights the potential of proposed InP/AlGaAs VTFET for scalable, high-sensitivity, label-free biomolecule detection. © 2013 IEEE.

关键词： Junction gate field effect transistors

来源：评论

学校读者我要写书评

暂无评论

Search-in-Memory (SiM): Reliable, Versatile, and Efficient data Matching in SSD's NAND Flash Memory Chip for data Indexing Acceleration

arXiv

引用

arXiv 2024年

作者： Chen, Yun-Chih Chang, Yuan-Hao Kuo, Tei-Wei The Department of Computer Science TU Dortmund Germany The Institute of Information Science Academia Sinica Taipei115 Taiwan Department of Computer Science and Information Engineering High Performance and Scientific Computing Center Center of Data Intelligence: Technologies Applications and Systems of National Taiwan University Taiwan

To index the increasing volume of data, modern data indexes are typically stored on SSDs and cached in DRAM. However, searching such an index has resulted in significant I/O traffic due to limited access locality and inefficient cache utilization. At the heart of index searching is the operation of filtering through vast data spans to isolate a small, relevant subset, which involves basic equality tests rather than the complex arithmetic provided by modern CPUs. We introduce the Search-in-Memory (SiM) chip, which demonstrates the feasibility of performing data filtering directly within a NAND flash memory chip, transmitting only relevant search results rather than complete pages. Instead of adding complex circuits, we propose repurposing existing circuitry for efficient and accurate bitwise parallel matching. We demonstrate how different data structures can use our flexible SIMD command interface to offload index searches. This strategy not only frees up the CPU for more computationally demanding tasks, but it also optimizes DRAM usage for write buffering, significantly lowering energy consumption associated with I/O transmission between the CPU and DRAM. Extensive testing across a wide range of workloads reveals up to a 9X speedup in write-heavy workloads and up to 45% energy savings due to reduced read and write I/O. Furthermore, we achieve significant reductions in median and tail read latencies of up to 89% and 85% respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Maximum likelihood based estimation with quasi oppositional chemical reaction optimization algorithm for speech signal enhancement

引用

International Journal of Information Technology (Singapore) 2022年第6期14卷 3265-3275页

作者： Kaur, Inderjeet Nassa, Vinay Kumar Kavitha, T. Mohan, Prakash Velmurugan, S. Department of Computer Science and Engineering Ajay Kumar Garg Engineering College Uttar Pradesh Ghaziabad India Department of Artificial Intelligence & Data Science Sharad Institute of Technology College of Engineering Maharashtra Yadrav-Kohiapur India Department Computer Applications Kongu Engineering College Perundurai Tamil Nadu Erode India Data Science and Analytics Center Karpagam College of Engineering Tamil Nadu Coimbatore India Department of Computer Science and Engineering Vel Tech Multi Tech Dr. RR & Dr.SR Engineering College Tamil Nadu Chennai India

In recent times, speech enhancement (SE) becomes a significant process in the field of speech signal processing. Since the speech signal in real time gets affected by background noise, the efficacy of the speech-based applications gets severely affected. The SE techniques have gained considerable attention in the usage of speaker recognition, video conferences, speech broadcast, speech-enabled biometric systems, smartphones, hearing aid, and so on. Numerous conventional SE and machine learning (ML) models have been employed for processing and removing the additive noise from the speech signal. This paper presents a novel Maximum Likelihood Based Estimation with Quasi Oppositional Chemical Reaction Optimization (MLE-QOCRO) algorithm for speech signal enhancement. The presented MLE-QOCRO algorithm follows three-stage processes namely preprocessing, mask generation, and spectral filtering. Besides, the mask generation process involves QOCRO algorithm to classify the speech signal into noise or speech frames. In addition, MLE based spectral filtering technique is employed at the final stage to get enhanced speech signals. A set of experiments were performed to highlight the improved performance of the proposed MLE-QOCRO algorithm, and the results are investigated in terms of several performance measures. Speech signal augmentation using the unique MLE-QOCRO algorithm, which combines maximum likelihood estimation with quasi-opposing chemical reaction optimization, is the subject of this paper. The QOCRO algorithm is used in the mask generation process in the model to distinguish between noise and speech frames in the input speech signal. A spectral filtering method based on MLE is also utilized to improve the voice signal at the very end. The resultant experimental values pointed out the enhanced outcome of the proposed MLE-QOCRO algorithm over the other compared techniques. © 2022, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Appl

关键词： Chemical reaction optimization Maximum likelihood Spectral filtering Speech signal enhancement

来源：评论

学校读者我要写书评

暂无评论

Research and Innovation in Next Generation Security and Privacy in Industry 5.0 Iot 6

Research and Innovation in Next Generation Security and Priv...

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Navale, Geeta S. Madala, Ravikiran Managuli, Manjunath Jayalakshmi, N. Kadiravan, G. Rawat, Ruchira Sinhgad Institute of Technology and Science Department of Computer Engineering Maharashtra Pune India Ph.D Information Technology Network and Data Center Engineer University of Cumberlands DurhamNC United States KLS Gogte Institute of Technology Department of Electronics and Communication Engineering Karnataka Belagavi India PSNA College of Engineering and Technology Master of Computer Applications Tamilnadu Dindigul India KL Deemed to Be University Department of Computer Science and Information Technology Andhra Pradsh India Graphic Era Deemed to Be University Department of Computer Science and Engineering Uttrakhand Dehradun India

ISBN: (纸本)9798350304480

The objective of the newest manufacturing paradigm, known as 'Industry 5.0,'is to combine human intelligence with cutting-edge technology like the Internet of Things (IoT), artificial intelligence (AI), and robots to develop production systems that are incredibly effective and adaptable. But as we rely more on these technologies, we face additional privacy and security issues that might affect how dependable and trustworthy these systems are. In this report, we examine the most recent advancements in security and privacy for Industry 5.0 IoT and pinpoint the newest trends, obstacles, and possibilities. We also cover how these changes may affect manufacturing in the future and provide advice to scholars, practitioners, and policymakers. © 2023 IEEE.

关键词： artificial intelligence cyber-physical systems human-machine collaboration Industry 5.0 Internet of Things IoT manufacturing privacy robotics security

来源：评论

学校读者我要写书评

暂无评论

An Efficient Machine Learning Based data Auditing Scheme for Cloud Users

An Efficient Machine Learning Based Data Auditing Scheme for...

引用

Computational Intelligence, Networks and Security (ICCINS), International Conference on

作者： A. Vamshi R. Eswari X. I. Nirmal Joel A. Divine Regan Department of Computer Applications National Institute of Technology Tiruchirappalli India Department of Data Science St. Joseph's College Tiruchirappalli India

With the wide spread of the digital world, IoT devices generate huge amounts of data and store it in cloud servers as they have less storage space. When data is outsourced to the cloud servers, IoT device users lose control of it, which means the confidentiality and integrity of the data can be compromised. Further, several Third-Party Auditors (TPAs) are available to check the integrity of the data. But most of the TPAs are based on trust. In some cases, TPAs are being hired by Cloud data centers and in some cases, the TPAs may have direct connection with data consumers. In both the cases, there is a bias and the data may be at high risk. Therefore, to overcome the trust issue, in this paper an Efficient Machine Learning based data Auditing Scheme for Cloud Users is proposed using a hybrid recommendation system. A repository is maintained which keeps track of all TPA's history. The user submits auditing request to the repository which will run the recommendation system to select appropriate TPA to check the integrity of the user data in the cloud. It chooses the best TPA and gives the auditing results to the user. The proposed scheme reduces the risk of user data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based Anomaly Detection in IOT Sensing Devices for Optimal Security 2

Machine Learning-based Anomaly Detection in IOT Sensing Devi...

引用

2nd International Conference on data science and Information System, ICDSIS 2024

作者： Karthiga, S. Ravisankar, P. Vijayarajeswari, R. Pushpa, N. Vino, T. Dobhal, Dinesh Srm Institute Of Science And Technology Department Of Computer Science And Applications Chennai Ramapuram India Simats Saveetha College Of Liberal Arts And Sciences Department Of Commerce General Chennai Thandalam India Sona College Of Technology Department Of Information Technology Tamilnadu Salem India R P Sarathy Institute Of Technology Department Of Artificial Intelligence And Data Science Tamil Nadu Salem India Sathyabama Institute Of Science And Technology Department Of Ece Tamil Nadu Chennai India Graphic Era Deemed To Be University Uttarakhand Dehradun India

ISBN: (纸本)9798350381665

The Internet of Things (IoT) is well-known as a new detecting paradigm for interacting with the real world in Industry 4.0. With IoT, major security concern arises in data communication between remote location and the data server. data obtained from the different sensor devices have to be transmitted securely. Implementing Machine Learning algorithms increases the security as well as the efficiency of the IoT devices. In this research work, MQTT protocol is implemented for data transmission services in Internet of Things enabled devices. The research utilized historical information from a smart manufacturing plant's tracking sensor, control devices, and IoT cameras. The findings of this research work 5rimproved plant efficacy and security, resulting in quicker and more efficient reactions to uncommon incidents. Outcomes indicate a considerable influence on intelligent manufacturing plant effectiveness and security. Advanced detection of anomalies led to quicker and more efficient reactions to odd events, reducing significant occurrences and enhancing safety. Moreover, technique improvement and IoT infrastructure enhanced productivity by minimizing downtime and maximizing resource use. The suggested study compares machine learning-based protection measures to past studies on IoT protection and identifying anomalies in industrial settings, demonstrating their usefulness. Researchers saw a rise of 14% in the detection of anomalies and a 2% drop in false positives after training machine learning models. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Research on instance-level data cleaning technology

Research on instance-level data cleaning technology

引用

2021 International Conference on Artificial Intelligence, Big data and Algorithms, CAIBDA 2021

作者： Ying, KangHui Hu, WenYu Chen, Jin Bo Li, Guo Nong Fujian University of Technology College of Computer Science and Mathematics Fujian Provincial Key Laboratory of Big Data Mining and Applications Fuzhou China

ISBN: (纸本)9781665424905

Effectivedata analysis and data mining are based on data availability and data quality. data cleaning is a commonly used technique to improve data quality. Instance-level data cleaning is an important part of data cleaning. The focus is on the comparison and analysis of the detection and cleaning methods of attributes and recorded values in the instance-level data cleaning technology, and the experimental analysis of the repeated record cleaning methods. This paper introduces the application field of data cleaning technology represented by the electrical engineering field combined with the application situation, and provides valuable selection suggestions for the characteristics of different data sets and the applicable instancelevel data cleaning technology. Summarizing and analyzing the existing detection and cleaning technology methods, it is concluded that instance-level data cleaning has a lot of research and development space in long text, unstructured data and specific fields. Finally, the challenges and development directions of the instance-level data cleaning technology are prospected. © 2021 IEEE.

关键词： Cleaning

来源：评论

学校读者我要写书评

暂无评论

Image Feature Detection and Clustering for UAV Multiple Obstacles Avoidance 1

引用

16th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2020 in conjunction with the 13th International Conference on Frontiers of Information Technology, applications and Tools, FITAT 2020

作者： Zhao, Baohua Sung, Tien-Wen Zhang, Xin Fujian Provincial Key Laboratory of Big Data Mining and Applications College of Computer Science and Mathematics Fujian University of Technology Fuzhou China

ISBN: (数字)9789813364202

ISBN: (纸本)9789813364196

In the past decade, a lot of researches have been done on the topic of real-time obstacle avoidance of Unmanned Aerial Vehicle (UAV). For example, the use of Light Detection and Ranging (LIDAR), ultrasonic sensors, and now more popular visual sensors can effectively avoid obstacles. Although these methods are simple and effective, there are few of UAV real-time obstacle avoidance for complex environments, and most of them are used to avoid a single obstacle. When facing multiple obstacles, they cannot choose the optimal strategy, which inevitably consumes more power and time. In view of the complex environment that UAV may face multiple obstacles, in order to avoid multiple obstacles with minimum efforts in the process of real obstacle avoidance, this paper proposes a new method to detect multiple obstacles. Firstly, it extracts obstacle feature points, and then uses unsupervised clustering algorithm in machine learning to divide the feature points of different obstacles into different categories, and finally detects the obstacles represented by convex hull of same category feature points. The method is simple and effective. This paper compares the time of several popular feature point detection and unsupervised clustering algorithms through experiments and estimates the approximate relationship between the number of feature points detected and the distance when the UAV approaches the obstacle, which is a priori study for the future practical obstacle avoidance link. It summarizes which algorithm can save more time and is more suitable for real-time obstacle avoidance of multiple obstacles. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Clustering algorithms

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：