检索结果-内蒙古大学图书馆

International Conference on (IsCO) Intelligent systems and Control

作者： R. Anbarasi s. Gunasekaran Department of Computer Science and Engineering V.S.B Engineering College Karur India

A wireless sensor network is a peculiar kind of Ad-hoc network, made up of thousands of small devices which are called as sensor nodes used to monitor physical or environmental circumstances Clustering is a demanding task in Wireless sensor Networks for energy efficiency and network stability. In the existing method, a secure data transmission for cluster-based WsNs is presented in which the clusters are formed in a dynamic and periodic manner. A two secure and efficient data transmission protocols for CWsNs is presented which is called sET-Ibs and sET-IbOOs, by using the identity-based digital signature (Ibs) scheme and the identity-based online/ offline digital signature (IbOOs) scheme, respectively. but the obstacle in the existing method is there may point to leakage of user's public key and secret key in the case of compromised users in the sET-Ibs protocol and sET-IbOOs protocol is only energetic for the devices with high computational power. so, in order to overcome this problem a new technique is introduced which is called Enhanced secure Data Transmission protocol which is used to improve the sET-Ibs and sET-IbOOs protocol. In the improved sET-Ibs protocol, to enhance the security a new secret key is created by using the master secret key for every identity. Also, to confuse the attackers, encapsulation algorithm is used. In this process, the two cipher texts are used: one is valid cipher text and another one is invalid cipher text. These cipher texts are encapsulated with the corresponding author's encapsulated key. In order to improve the efficiency in the sET-IbOOs protocol, the improved sET-IbOOs protocol is proposed in which the online/offline attribute based encryption method is used. An experimental result shows that proposed method achieves high efficiency and high security.

关键词： Protocols Cryptography

来源：评论

学校读者我要写书评

暂无评论

A U-Net-like full convolutional pavement crack segmentation network based on multi-layer feature fusion

引用

International Journal of Pavement engineering 2025年第1期26卷

作者： Jin Wang Zhigao Zeng Fengxiang Huang R. simon sherratt Osama Alfarraj Amr Tolba Jianming Zhang a School of Computer and Communication Engineering Changsha University of Science and Technology Changsha People's Republic of China a School of Computer and Communication Engineering Changsha University of Science and Technology Changsha People's Republic of Chinad Key Laboratory of Safety Control of Bridge Engineering Ministry of Education (Changsha University of Science and Technology) Changsha People's Republic of China b Department of Biomedical Engineering The University of Reading Reading UK c Computer Science Department Community College King Saud University Riyadh Saudi Arabia

AbsTRACTCracks are an important indicator of pavement health, and it is difficult to achieve pixel-level segmentation of small and thin cracks. The existing network often experiences false segmentation and missed segmentation. Accordingly, a novel end-to-end U-Net-like full convolutional crack segmentation network is constructed. First, we propose a multi-layer feature fusion module to aggregate the texture and semantic features at each stage of encoder, so that the network can find smaller and thinner crack. second, we design a novel residual structure with a pointwise convolution. Each stage of the encoder and decoder incorporates a residual structure to facilitate the fusion of feature maps with different spatial dimensions. It can also prevent the gradient vanish in the network training process. Finally, we utilise the maximum unpooling to restore spatial structure in up-sampling, which exploits the indices of maximum feature value in down-sampling. Therefore, high-frequency information is better preserved to help accurately restore the details of crack edges. To verify the proposed network performance, experiments are carried out on four open datasets, the proposed network can achieve better performance among five classical networks.

关键词： Crack segmentation deep learning semantic segmentation pavement damage detection

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis of Deep Learning Methods for COvID-19 Detection and Classification

Comprehensive Analysis of Deep Learning Methods for COVID-19...

引用

2023 Annual International Conference on Emerging Research Areas: International Conference on Intelligent systems, AICERA/ICIs 2023

作者： Prabha, bindhu Divya, s.v. venkadesh, P. Noorul Islam Centre for Higher Education Dept. of Computer Applications Kanyakumari Tamil Nadu Kumarakovil India V.S.B College of Engineering Dept.of Cse Technical Campus Tamil Nadu Coimbatore India V.S.B College of Engineering Dept. of Ai & Ds Technical Campus Tamil Nadu Coimbatore India

ISBN: (纸本)9798350303452

The progress of precise recognition techniques and the evaluation of genetic connections are required because of the worldwide spread of COvID-19. As conventional techniques for COvID-19 detection are time-consuming and require accurate variables in order to minimize or cut short errors that could possibly occur, the COvID-19 epidemic's necessity for early diagnosis and surveillance led to the deployment of Deep Learning (DL) technology for efficient evaluation. Deep learning is a branch of artificial intelligence (AI) and Machine learning (ML), and due to its remarkable ability to assimilate new information, DL technology has quickly risen to prominence. Many DL architectures, like RNN, CNN, and long-term memory, can be utilized for forecasting, perdition, and classification of COvID-19. The intention of this paper is to conduct a comprehensive analysis of various deep learning methods, for detecting and classifying the COvID-19 virus using diverse data sources, such as chest X-rays, CT scans, and genomic sequences, to highlight their exceptional accuracy in identification. We also explore DL's involvement in analyzing the virus's genetic code, providing insight into how it evolved. It aims to deliver a summary of earlier research and its COvID-19 applications. © 2023 IEEE.

关键词： COvID-19

来源：评论

学校读者我要写书评

暂无评论

Active self-training for weakly supervised 3D scene semantic segmentation

引用

Computational visual Media 2024年第3期10卷 425-438页

作者： Gengxin Liu Oliver van Kaick Hui Huang Ruizhen Hu College of Computer Science&Software Engineering Shenzhen UniversityShenzhen 518060China School of Computer Science Carleton UniversityOttawa K1S 5B6Canada

since the preparation of labeled datafor training semantic segmentation networks of pointclouds is a time-consuming process, weakly supervisedapproaches have been introduced to learn fromonly a small fraction of data. These methods aretypically based on learning with contrastive losses whileautomatically deriving per-point pseudo-labels from asparse set of user-annotated labels. In this paper, ourkey observation is that the selection of which samplesto annotate is as important as how these samplesare used for training. Thus, we introduce a methodfor weakly supervised segmentation of 3D scenes thatcombines self-training with active learning. Activelearning selects points for annotation that are likelyto result in improvements to the trained model, whileself-training makes efficient use of the user-providedlabels for learning the model. We demonstrate thatour approach leads to an effective method that providesimprovements in scene segmentation over previouswork and baselines, while requiring only a few userannotations.

关键词： semantic segmentation weakly supervised self-training active learning

来源：评论

学校读者我要写书评

暂无评论

smart swimming Pool Management system (ssPMs) using IoT

Smart Swimming Pool Management System (SSPMS) using IoT

引用

2023 IEEE International Conference on Innovative Data Communication Technologies and Application, ICIDCA 2023

作者： sangeetha, A. Krishnan, R. santhana Kumar, G. Praveen Julie, E. Golden Ganesh, R. Karthik Robinson, Y. Harold PSNA College of Engineering and Technology Department of Information Technology Dindigul India SCAD College of Engineering and Technology Department of Electronics and Communication Engineering Tirunelveli India V.S.B Engineering College Department of Information Technology Karur India Anna University Department of Computer Science and Engineering Regional Campus Tirunelveli India SCAD College of Engineering and Technology Department of Computer Science and Engineering Tirunelveli India Francis Xavier Engineering College Department of Computer Science and Engineering Tirunelveli India

ISBN: (纸本)9798350397208

swimming has become one of the major routines nowadays among people. People mostly use swimming pools for exercise or recreation. According to statistics one hour of swimming burns 30% more calories than one hour of running. so many people prefer swimming to keep their body fit. but few people use the swimming pool without having proper swimming skills. This leads to loss of their lives. Around the world nearly 42 people drown per hour. The pH level of water in the swimming pool should be between 7.4 to 7.6. The high pH water can cause rashes on human skin and scaling on pool equipment. Low pH causes eye irritation, skin irritation etc. Hence, a smart system is required to monitor the pH level of the water and to track the condition of the swimmers inside the pool. so with the support of few sensors and Arduino, an automatic swimming pool monitoring system, which is capable of sensing the pH level of the water available in swimming pool and condition of the swimmers is developed. The proposed system will also update all the observed status in the cloud with the support of the Internet facility. © 2023 IEEE.

关键词： swimming pools

来源：评论

学校读者我要写书评

暂无评论

New power-aware multicast algorithm for mobile Ad hoc networks

引用

IEEE Potentials 2013年第2期32卷 32-35页

作者： varaprasad, G. Wahidabanu, R.s.D. Department of Computer Science and Engineering B.M.S. College of Engineering Bangalore 560 019 India Dept of Electronics and Communication Engineering Government College of Engineering Salem 636 036 India

A mobile ad hoc network (MANET) is a decentralized network that consists of mobile nodes. Each node operates with the limited battery power to forward the data packets from the source to a group of the nodes. In a MANET, multicast is a very useful communication system for group-oriented applications, where one-tomany propagations are needed frequently in critical situations. This article presents a new power-aware multicasting algorithm for MANETs. Here, it uses the residual battery energy for the multicasting from the source to a group of destinations. The proposed model increases the lifetime of the nodes and the network lifetime. The simulation work shows better results in terms of the node lifetime and network lifetime as compared to other models, ODMRP and AMRoute. If the group size is 12, then the proposed model has kept the nodes alive for 8,100 s, whereas the ODMRP and AMRoute models have kept the nodes alive for 7,400 s and 6,400 s respectively. © 1988-2012 IEEE.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

A new biometric using sclera vein recognition for human identification

A new biometric using sclera vein recognition for human iden...

引用

IEEE International Conference on Computational Intelligence and Computing Research

作者： A. suganya M. sivitha Dept. of Computer Science and Engineering V.S.B Engineering College Karur India

biometrics is a technique of identity verification that is based on the principle of measurable physiological characteristics like vein patterns from sclera region. sclera vein is a new biometric recognition method for human identification. sclera vessel pattern's images are saturated and the arrangement of vessel patterns is multi layered and also it is quite complex to extract the features of vein from sclera. In order eliminate high frequency noise components present in sclera, low pass filter is used. To extract the features, a set of vessel segments combine to create Y shaped branches often belonging to same sclera layer. Mapping scheme is based on Y shaped structure in the sclera that is observed to be more stable feature and is used to efficiently eliminate the most unlikely matches. The observational result shows that the proposed method can dramatically provide more secure authentication without compromising the recognition accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High level performance in multiple relay networks

High level performance in multiple relay networks

引用

IEEE International Conference on Computational Intelligence and Computing Research

作者： v. Eswaramurthy A. P. v. Raghavendra Dept. of Computer Science and Engineering V.S.B Engineering College Karur India

A relay network is a broad class of network topology commonly used in networks, where the source and destination are interconnected by means of a some nodes. In such a network the source and destination cannot transmit data each other directly, because the distance between the source and destination is greater than the transmission range between them, hence the demand for intermediate node(s) to relay. Relay nodes in applying network coding, follow the decode-and-forward protocol. In proposed work, we consider a peer-to-peer (P2P) network in which peers receive and forward a linear combination of the exogenous data packets. To check out the integrity of the received packets, a key signature vector are generated at the source node and broadcasted to all nodes where it is used to check the integrity of the received packets. There are several information theoretic algorithms for mitigating falsified data injection effects are proposed. The network modeling used in these works is composed of a single source, multiple intermediate nodes which utilize network coding. We consider a multiple access relay network where multiple sources send independent data to a single destination through multiple relays, which may interject falsified data into the network. To detect the malevolent relays and dispose (efface) data from them, trace bits are embedded in the information data at each source node.

关键词： Peer-to-peer computing Relay networks (telecommunications) Reliability Decoding Network coding security

来源：评论

学校读者我要写书评

暂无评论

Transparent Ensemble Deep Learning for Intrusion Detection in Industrial Internet of Things 1

Transparent Ensemble Deep Learning for Intrusion Detection i...

引用

1st International Conference on Innovations in Communications, Electrical and computer engineering, ICICEC 2024

作者： sneha, M. Prasad, G.R. B.M.S College of Engineering Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350376517

The growing complexity and scale of Industrial Internet of Things (IIoT) networks have made them increasingly vulnerable to cyber-attacks, underscoring the need for reliable and precise Intrusion Detection systems (IDs). However, many existing IDs solutions face challenges such as high false-positive rates, limited detection accuracy, and a lack of transparency in their decision-making processes, which hinders their practical application. This work presents an advanced IDs based on ensemble deep learning specifically designed for IIoT networks to overcome these limitations. The suggested system integrates a number of deep learning models, such as Artificial Neural Networks (ANNs), Convolutional Neural Networks (CNNs), and LAssO, to harness their unique advantages and enhance detection capabilities. Moreover, the system integrates explainability methods, such as Random Forest, linear regression, and Local Interpretable Model-agnostic Explanations (LIME), to offer clear and interpretable perspectives on the process of making decisions. Intrusion Detection system (IDs) proposed in this study is trained and tested using the ToN-IoT dataset, a comprehensive IIoT dataset that encompasses diverse network traffic data and various attack scenarios. Experimental findings indicate that the ensemble model notably improves detection accuracy while lowering false-positive rates compared to traditional baseline models. The incorporation of Random Forest, linear regression, and LIME enhances the system's transparency by helping to elucidate the role of individual features in the forecasts of the model, thereby making the system more interpretable additionally reliable. This research advances the field by introducing a scalable, precise, and explainable IDs for IIoT networks, with strong potential to enhance cybersecurity in industrial settings. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

One-shot Approach for Multilingual Classification of Indic scripts

One-Shot Approach for Multilingual Classification of Indic S...

引用

2022 International Conference on Innovative Trends in Information Technology, ICITIIT 2022

作者： Mittur, Ajay shankar, Aravindh R Narasimhan, Adithya B.M.S. College of Engineering Computer Science and Engineering Bengaluru India

ISBN: (纸本)9781665406703

The use of multiple languages with different scripts is a common theme in India. There is an emerging need to digitise documents that may be handwritten or available solely as images. This necessitates a system for multilingual classification of different Indic scripts and the subsequent character recognition into digitised standards such as Unicode. However, a learning system for various languages with multiple character combinations can be computationally expensive and prove arduous with a dearth of available data. In this paper, the one-shot learning approach to the optical character recognition of different languages is explored, where there is a need to accurately classify the character given only one example of every additional class introduced. siamese neural networks are used for learning and to tune a network to work with entirely new, unseen data. Compelling results are attained in the classification of characters in nine different Indian languages using this approach with an accuracy ranging from 77.72 to 91.83 across the Indic languages in the best case. © 2022 IEEE.

关键词： Optical character recognition

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：