检索结果-内蒙古大学图书馆

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

作者： Rekha, D.S.B.N.S. Gottumukkala, V.S.S.P. Raju Durga, Poodi Venkata Vijaya Upendra, Kolapalli Jistnasai Eda, Shalini Dianakamal, Gudapati Vishnupur AP Bhimavaram India Shri Vishnu Engineering College For Women Department of Computer Science and Engineering Vishnupur AP Bhimavaram India Vishnu institute of technology Department of Computer Science and Engineering Vishnupur AP Bhimavaram India Vishnupur A.P Bhimavaram India

ISBN: (纸本)9798350377972

Nowadays cyberattacks are become a very serious problem in Networking, online transactions, and everywhere. So the complexity of network infrastructures has given serious difficulties for network security in recent years. To reduce cyberattacks Machine Learning(ML) has provided a reliable solution for network anomaly detection in various settings by including software-defined networks (SDNs), automobile networks, and the Internet of Things (IoT). This paper provides an overview of various machine learning (ML) methods for anomaly detection using supervised, unsupervised, and deep learning models. Long Short-Term Memory (LSTM) networks and Convolution Neural Networks (CNNs) are the best Deep Learning (DL) models for detecting complex and before undiscovered threats. In order to improve detection accuracy and computing efficiency, this work investigates the degree to which these techniques are applied in a number of contexts, including smart metering systems, vehicular ad hoc networks (VANETs), and Internet of Things network security. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Feedback Control Based on Trust for Varied Automation Transparency 1

Feedback Control Based on Trust for Varied Automation Transp...

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Dbritto, Ceres Lopes, Joel Bandyopadhyay, Krishnan Banerji, Nandan Mishra, Ishani Kandpal, Ankit St Louis United States Redmond United States Dayananda Sagar College of Engineering Department of Medical Electronics Engineering Karnataka Bengaluru India Sikkim Manipal Institute of Technology Sikkim Manipal University Department of Computer Science and Engineering Sikkim India New Horizon college of Engineering Department of Computer Science and Engineering Karnataka Bengaluru560103 India Bipin Tripathi Kumaon Institute of Technology Department of ECE Almora Dwarahat India

ISBN: (纸本)9798331518578

Interactions between people and automation depend heavily on human confidence in the latter. Lack of trust can cause people to not use automation, while too much trust can cause them to put their faith in a flawed autonomous system, which could have detrimental effects on them. Transparency and trust in automation are vital for the usefulness and security of human-robotization frameworks. The majority of the research that has been done on the trust that human operators have in robotics and automation has been an ongoing variable that has received little attention. paid to how trust changes over time. In order to fill this research void, we offer a study that examines how trust is dynamic. Using real-time trust measurements, we first discovered options to quantify trust of entirety, which we described as a metric that considers trust throughout the entire human-automation interaction experience. In this study, a feedback control strategy for powerfully changing mechanization straightforwardness and transparency concurring on client trust is analysed. The proposed approach tweaks mechanical way of behaving and correspondence by incorporating an input control component with a trust assessment model. The adequacy of the feedback control framework in improving errand execution and trust adjustment under different levels of computerization straightforwardness and transparency is checked utilizing MATLAB reenactments. © 2025 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Object-Based Image Analysis of Hyper Spectral Imagery Using Semantic Segmentation Techniques

Object-Based Image Analysis of Hyper Spectral Imagery Using ...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Sharma, Amit Kumar Bargavi, Manju Singh, Akhilendra Pratap College of Engineering Teetthanker Mahaveer University Uttar Pradesh Moradabad India Department of Computer Science and Information Technology Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350383348

Object-based image analysis of Hyperspectral Imagery using Semantic Segmentation strategies is a singular approach for analyzing far-off sensing statistics. This method leverages the energy of a superior system gaining knowledge of (ML) and computer vision algorithms to analyze multidimensional hyperspectral image datasets. The goal is to robustly organize pixels into clusters in step with their spectral and spatial traits. Those clusters are then used to give meaningful records approximately the content material of the photo., the enter pix are pre-processed to reduce noise and boom contrast. A semantic segmentation algorithm is then used to generate excessive-degree masks of the items of interest. The outcomes of those masks are mixed with the input hyperspectral statistics to create several feature vectors describing the spectral and texture homes of every cluster. Sooner or later, a device-mastering algorithm categorizes the gadgets consistent with their traits, presenting precise information about the items in the picture. © 2024 IEEE.

关键词： algorithms Hyperspectral Imagery meaningful Object-based

来源：评论

学校读者我要写书评

暂无评论

Pre-Training and Fine-Tuning for Efficient Routing in Opportunistic Networks

Pre-Training and Fine-Tuning for Efficient Routing in Opport...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Hao, Jia Wu, Xiaorui Seah, Winston K. G. Zhang, Feng Xu, Gang College of Computer Science Engineering Research Center of Ecological Big Data Inner Mongolia University Ministry of Education Hohhot China School of Engineering & Computer Science Victoria University of Wellington Wellington New Zealand School of Computer and Information Technology Shanxi University Taiyuan China

ISBN: (纸本)9781665410205

In opportunistic networks, it is a challenge to find the best relay node instead of blindly selecting from among available nodes to forward messages and effectively transmit them to their destinations. By comparing the similarity between nodes, the next hop node that is most similar to the destination node is found in time. Existing node similarity-based opportunistic networks routing algorithms only calculate similarity between nodes according to nodes' properties that can be directly obtained from the network, such as the historical meeting record between nodes, etc. However, this superficial similarity calculation is obviously inadequate to describe the inherent dynamic nature of opportunistic networks at both spatial and temporal levels, and ignores the salient movement characteristics of nodes, resulting in poor routing performance. Therefore, this paper proposes an opportunistic network routing strategy based on pre-training and fine-tuning (PTFT) model. Firstly, an autoencoder is added to the graph neural network model to encode node movement behavior. Then, a pre-training graph neural network model in large scale opportunistic network scenarios is applied to learn potential features of nodes through fine-tuning. Finally, we calculate the similarity between nodes based on the node potential feature, thereby assisting the nodes to achieve an efficient routing decision. The simulation results show that our PTFT-based algorithm not only has superior performance compared to traditional routing algorithms, but also faster learning speed than other machine learning-based routing algorithms. © 2024 IEEE.

关键词： Routing algorithms

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Detection and Classification using Emperor Penguin Optimizer (EPO) based Region Convolutional Neural Network (RCNN) 2

Plant Disease Detection and Classification using Emperor Pen...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Shanbhog, Manjula Bhatia, Neha Singh, A Swathi Pavithra, M. School of Sciences Department of Computer Science Delhi NCR India Panipat Institute of Engineering and Technology Department of Information Technology Haryana Panipat India MIT-ADT School of Computing Department of Information and Technology Maharashtra Pune India Panimalar Engineering College Department of Computer Science and Business Systems Chennai India

ISBN: (纸本)9798350384277

Agriculture stands as India's most crucial industry, despite grappling with a 35% annual loss in crop yield attributed to plant diseases. Traditionally, the detection of plant diseases has been a laborious process, hampered by insufficient laboratory infrastructure and expert knowledge. Plant disease detection methods that are automated provide a useful way to expedite the labor-intensive process of keeping an eye on large-scale agricultural fields and recognizing disease symptoms as soon as they appear on plant leaves. Current developments in deep learning (DL) and computer vision have highlighted the benefits of creating autonomous models for plant disease identification based on visible symptoms on leaves. In this study, we propose a novel method for detecting and classifying plant diseases by combining the Emperor Penguin Optimizer (EPO) with a Region Convolutional Neural Network (RCNN). The suggested methodology uses EPO to improve the discriminative power of features extracted from plant pictures, allowing for a more robust and accurate classification procedure. The Classification Region Convolutional Neural Network (RCNN) is used to leverage spatial correlations within the image, allowing for exact disease region localization. The goal of this integration is to increase the overall efficiency and dependability of plant disease detection systems. The investigations made use of the well-known PlantVillage dataset, which comprises 54,305 data of different plant disease types in 38 categories. Furthermore, an analysis was carried out in comparison with similar advanced investigations. According to the experiment results, RCNN-EPO outperformed in terms of classification accuracy, achieving 94.552%. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Exploring Low Voltage and Low Power Techniques for High Performance ASIC Design

Exploring Low Voltage and Low Power Techniques for High Perf...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Ganesh, D. Chaudhary, Chetan Verma, Pradeep Kumar Department of Computer Science and Information Technology Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India College of Engineering Teerthanker Mahaveer University Uttar Pradesh Moradabad India

ISBN: (纸本)9798350383348

Exploring Low Voltage and coffee strength strategies for high-performance ASIC layout is a study mission that focuses on building and developing new and modern strategies that allow for the optimization of semiconductor design systems. Low Voltage and low strength (LVLP) techniques are increasingly utilized to reap the ultimate intention of ASIC designs: maximum overall performance with minimum power requirements. If you want to attain this, numerous interrelated parameters have to be considered. These parameters are chip length, circuit efficiency, device power dissipation, area/overall performance alternate-offs, and clock velocity. This research assignment explores various LVLP design techniques that may be used to optimize ASIC designs and bring about progressed overall performance. Those techniques consist of dynamic voltage scaling, clock gating, lively electricity control, and adaptive body biasing. These strategies can be evaluated in opposition to today's enterprise practices, and the handiest one might be followed in subsequent tiers of this study's task. The output of this research task will permit ASIC designers to construct complex designs that have the maximum overall performance at the lowest feasible power consumption as compared to the existing counterparts. This stepped-forward efficiency will allow ASIC designers to build merchandise that might be of greater value and powerful in addition to being less complicated to manufacture and debug. © 2024 IEEE.

关键词： Adaptive Construct Consumption Counterparts Maximum Optimization Strategies

来源：评论

学校读者我要写书评

暂无评论

Emerging Battery Technologies for High-Power Electric Vehicles

Emerging Battery Technologies for High-Power Electric Vehicl...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Bhuvana, J. Pandeya, Megha Vishnoi, Rahul Department of Computer Science and Information Technology Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India College of Engineering Teerthanker Mahaveer University Uttar Pradesh Moradabad India

ISBN: (纸本)9798350383348

Battery technology for electric-powered automobiles has been evolving rapidly in recent years. With the increased demand for excessive-energy electric-powered automobiles (EVs), new battery technologies are rising to satisfy the energy requirements of these motors. These encompass lithium-ion, nickel-metal hydride, and lithium-sulfur batteries. Every one of those technologies has its blessings and disadvantages, in addition to its very own obstacles. Lithium-ion batteries provide high power density, lengthy cycle existence, and exact overall performance over a huge temperature range. They are additionally capable of speedy charging and discharging. However, they are high priced and have higher rate capability necessities than different battery technologies. Moreover, lithium-ion batteries are prone to degradation over time, making them improper for packages requiring high cycle life. Nickel-steel hydride batteries provide a lower-value alternative to lithium-ion batteries. They are also able to fast charging and discharge. However, their strength density and strength-to-weight ratio are a great deal lower than that of lithium-ion batteries. © 2024 IEEE.

关键词： Charging Degradation Evolving Requirements Technologies Temperature

来源：评论

学校读者我要写书评

暂无评论

Intelligent wearable vision systems for the visually impaired in Saudi Arabia

引用

Neural Computing and Applications 2025年第14期37卷 8571-8591页

作者： Talaat, Fatma M. El-Shafai, Walid Soliman, Naglaa F. Algarni, Abeer D. El-Samie, Fathi E. Abd Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Faculty of Computer Science and Engineering New Mansoura University Gamasa35712 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Navigating the world with visual impairments presents unique challenges, often limiting independence and safety. This research introduces SafeStride, a novel algorithm designed to empower visually impaired individuals through real-time obstacle detection and navigation assistance. SafeStride functions through five interconnected phases: sensor data acquisition, data preprocessing, obstacle detection, path planning, and feedback and guidance. A combination of ultrasonic sensors, cameras, and inertial measurement units (IMUs) feed comprehensive environmental data into the system, enabling accurate obstacle detection and safe path planning. Evaluating SafeStride's performance involved the MNIST dataset for image recognition and a dedicated indoor object detection dataset. Additionally, comparisons were made against three deep learning models—convolutional neural network (CNN), long short-term memory (LSTM), and gated recurrent unit (GRU). The results showcased SafeStride's high accuracy and effectiveness in both obstacle detection and classification. Beyond its impressive performance, SafeStride represents a significant leap forward in navigation aids for the visually impaired. By offering a comprehensive solution that enhances safety and independence in diverse environments, it holds immense potential to improve the lives of countless individuals. Future efforts will focus on further optimizing the algorithm and testing its real-world capabilities, paving the way for a future where safe and independent navigation becomes a reality for all. All three deep learning models (CNN, LSTM, GRU) excelled in the experiment, achieving high accuracy above 0.98, strong recall and F1-scores near 0.99, and exceptional AUC-ROC scores exceeding 0.9998. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Comparing Boosting and Bagging Algorithms for Image Classification

Comparing Boosting and Bagging Algorithms for Image Classifi...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Chaudhary, Chetan Gupta, Arun Murugan, R. Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India College of Engineering Teetthanker Mahaveer University Uttar Pradesh Moradabad India Department of Computer Science and Information Technology Bangalore India

ISBN: (纸本)9798350383348

Boosting and bagging are famous ensembles gaining knowledge of algorithms for photo classes. Each algorithm depends upon combining a couple of classifiers to enhance generalization accuracy, at the same time as using specific techniques to generate a final model and boosting works by using training more than one vulnerable classifier iteratively, deciding on new classifiers that concentrate on miscategorized examples from earlier rounds. Bagging then uses the same classifier with extraordinary subsets of the education dataset to generate more than one classifiers that are then blended. In phrases of generalization accuracy, boosting algorithms outperform bagging due to their capability to focus more on tough-to-classify examples. However, boosting can be more computationally intensive in phrases of education time than bagging because it continually updates and trains new vulnerable classifiers. Furthermore, boosting algorithms can also be afflicted by low bias and low variance problems, making them vulnerable to overfitting. In conclusion, boosting and bagging are effective strategies for picture type, with boosting algorithms presenting superior generalization accuracy and bagging algorithms being computationally greener. Relying on the task, the perfect method may be determined. © 2024 IEEE.

关键词： algorithm computationally generalization miscategorized vulnerable

来源：评论

学校读者我要写书评

暂无评论

Generalized Index Modulation System and Application for Satellite Communications 6

Generalized Index Modulation System and Application for Sate...

引用

6th IEEE Novel Intelligent and Leading Emerging sciences Conference, NILES 2024

作者： Ghorib, Khaled A. Abdelaziz, Amr Darwesh, Ahmed F. Mohasseb, Yahya Military Technical College Dept. of Communication Engineering Cairo Egypt Arab Academy for Science Technology and Maritime Transport Dept. of Computer Engineering Cairo Egypt

ISBN: (纸本)9798350378511

The generalized index modulation (G-IM) technique provides an improvement in bit error rate (BER), spectral efficiency (SE), and/or energy efficiency (EE) over traditional digital modulation schemes. However, G-IM techniques suffer from the propagation of errors due to the incorrect detection of indices for higher modulation order (M > 4). To alleviate the risk of error propagation, the enhancement of the correct indices detection probability is a crucial requirement for G-IM systems. This paper presents an error propagation-free generalized index modulation (G-IM) system with adaptive coding modulation in which the indices bits are coded independently on the information bits. The main focus of this study is to derive a quantitative relation between the target system BER and the required indices error rate and, hence, to derive the overall system error probability. In particular, an analytical total BER formula for the error propagation-free G-IM system is provided and compared to the total BER of the classical counterpart modulation techniques. Hence, a direct relationship between the BER of index bits and the ordinary modulation BER is represented, providing an approximate threshold after which the target BER of the G-IM system outperforms the traditional modulation techniques. To validate our established results, the G-IM system with low density parity check code with binary phase shift keying modulation technique (LDPC-BPSK), as a simple satellite coding-modulation scheme which is used in satellite digital video broadcasting TV (DVB-T2) and deep-space communications, is described as a possible direct application for the G-IM system. once the index BER exceeds the threshold, the LDPC-BPSK modulated G-IM system significantly outperforms the classical BPSK modulation while keeping the same EE or SE yet on the expense of added encoder complexity. Moreover, once the index error tends to the zero point, the total G-IM BER reaches its lower limit, a 3 dB gain, thanks t

关键词： Binary phase shift keying

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：