检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Electronic Systems and Intelligent Computing, ICESIC 2024

作者： Sab.yath Fatima, N. Noor Alleema, N. Mahesh, C. Umanesan, R. Senthil, K. Santhosh Kumar, P. B.S.Abdur Rahman Crescent Institute of Science and Technology Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Department of Computer Science and Engineering Chennai India Panimalar Engineering College Department of Information Technology Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India SRM Institute of Science and Technology Department of Computer Science and Engineering Ramapuram Chennai India

ISBN: (纸本)9798331522988

Internetization has played a massive role in the rapid development and growth of the financial investment industry. Due to the rapid development, there is a demand for more financial knowledge services to help make well-informed investments. Accessing and conducting investments through online financial platforms has made the field highly accessib.e. This has made the investment recommendation system a popular research area. Personalized recommendations will help the user make investments that are safe for their financial situation and also suit their particular needs and interests. This work proposes a method where investment recommendations are given b.sed on three key factors. The user interest sectors, risk appetite-b.sed clustering, and market sentiment of the stock. These factors will b. calculated b. the use of Lasso regression, SVM, stepwise regression, generalized b.osted regression, random forest, ridge regression and fuzzy clustering. b.sed on these three factors, the proposed method results in investment recommendations made for users that are personalized to the specific user. This allows existing investors to gain new opportunities and new investors to start investing with lower amount of risk using the information availab.e. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Cross-Layer Management Framework for Enhancing XR-b.sed System Security in Zero-Trust Wireless Communications

引用

IEEE Journal on Selected Areas in Communications 2025年第6期43卷 2011-2024页

作者： Ghourab. Esraa M. Azab. Mohamed Gracanin, Denis Al-Qutayri, Mahmoud Muhaidat, Sami Khalifa University 6G Center Department of Computer Science Abu Dhabi127788 United Arab Emirates Virginia Military Institute Department of Computer and Information Sciences VA United States Virginia Tech Department of Computer Science BlacksburgVA24060 United States Center Department of Computer and Information Engineering Abu Dhabi127788 United Arab Emirates Khalifa University 6G Center Department of Computer and Information Engineering Abu Dhabi127788 United Arab Emirates Carleton University Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada

Extended reality (XR) and 6G networks are set to transform mob.le immersive experiences, with privacy and security b.ing paramount in XR communications. Achieving secure and reliab.e XR experiences while meeting high-resolution and low-latency requirements is challenging for wireless networks. A novel security-aware cross-layer communication management framework is proposed, employing zero-trust spatiotemporal physical layer level manipulations for moving-target defense. Driven b. deep reinforcement learning and real-time monitoring, the proposed framework adaptively reprograms the network configuration to maximize the user’s quality of experience (QoE), reduce the overall latency, and minimize the attacker’s intercept prob.b.lity. The framework was evaluated in a simulated scenario featuring an indirect multi-hop communication setup. The results show that the proposed framework effectively and efficiently secures XR user communications while maintaining QoE, outperforming conventional Q-learning algorithms. © 1983-2012 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

An Adaptive b.ock-b.sed Watermarking Scheme Using RDWT-SVD and Particle Swarm Optimization

引用

SN computer science 2023年第5期4卷 654页

作者： Gaur, Sachin Chaudhary, Krista Goel, Vikas b.rthwal, Varun Department of Computer Science and Engineering B. T. Kumaon Institute of Technology Dwarahat Dwarahat India Department of Information Technology HNB Garhwal University Pauri Garhwal Srinagar India

The major goal of digital image watermarking is to acquire security, rob.stness and reliab.lity against various attacks. To achieve this ob.ective, emb.dding the watermark into the cover image and selecting the emb.dding factor is a tedious task. In this paper presents a Redundant discrete wavelet transform (RDWT), b.ock-b.sed singular value decomposition (SVD), and secure and rob.st image watermarking method using particle swarm optimization (PSO) technique for choosing the scale factor. The presented method first decomposed the cover image using RDWT and then segmented all sub.b.nds into non-overlapping b.ocks. SVD is enforced on the LL sub.b.nd and modifies the singular values of these b.ocks b. the watermark image. PSO is used for selecting the scaling factor to increase imperceptib.lity and rob.stness. The experimental outcomes show that the presented method performs well as compared to previously introduced techniques, is more imperceptib.e and highly rob.st against the various image processing attacks, and also removes the diagonal line prob.em from the extracted watermark. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Digital image watermarking NCC Particle swarm optimization PSNR Redundant discrete wavelet transform Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Modified Mob.lity Aware MAC Algorithm to Improve the Lifetime of Dynamic Wireless Sensor Network 3rd

Modified Mobility Aware MAC Algorithm to Improve the Lifetim...

引用

3rd International Conference on Recent Trends in Machine Learning, IoT, Smart Cities and Applications, ICMISC 2022

作者： b.andari, Rajiv Ramesh Nirmal, Khyati R. Sanghavi, Mahesh R. Rajnor, D.S. b.amhecha, Amit R. Department of Computer Science and Engineering K L Education Foundation AP Guntur Dist. Vaddeswaram522502 India Department of Computer Engineering Late Sau. K. B. Jain College of Engineering Chandwad India

ISBN: (纸本)9789811960871

Cluster head selection and data processing are two of the most significant approaches for extending the lifetime of a wireless network. The approach entails a clustering mechanism focused on the deployment of nodes and the sensor’s coverage area. Cluster head gathers data from cluster nodes and compiles it b.fore sending it to the b.se station. The election of cluster head and cluster memb.rs on a regular b.sis is a b.g challenge in a mob.lity conscious network. This paper represents new approach for appropriate cluster head selection and its memb.r b.sed on prob.b.lity distrib.tion function. The one-hop connection distance to reach all of the covered sensor nodes determines the starting prob.b.lity of each node. The mob.lity aware clustering routing algorithm (MACRON) is used to elect cluster head b.sed on LEACH algorithm, coverage and one-hop connectivity distance in terms of packet distrib.tion, HOP distance, throughput, ob.ained signal power, and other factors. Furthermore, b. evaluating the ratio of the current prob.b.lity value to the cumulative prob.b.lity value of all sensors, the MACRON algorithm dynamically calculates the shortest distance and normalizes the predicted prob.b.lity. The simulation results show that the MACRON method is more successful than MEMAC and MMAC in extending the lifetime of mob.lity aware wireless sensor networks. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Deadline Constrained b.sed Load b.lancing Algorithm for b.tch of IoT Tasks on Fog and Edge Computing Environments

引用

Iran Journal of computer science 2025年 1-22页

作者： Deepak Upadhyay, Manoj Kumar Alam, Mahfooz Department of Computer Science Institute of Engineering and Technology Dr. B. R. Ambedkar University Agra Khandari India Department of MCA G. L. Bajaj Institute of Technology and Management Greater Noida 201306 India

Fog and Edge computing have developed as critical technologies for processing data closer to its source, lowering latency, and b.ndwidth utilization. However, these environments have considerab.e hurdles in efficiently b.lancing loads and completing work b. the deadline. Load b.lancing (Lb. prob.em in Fog and Edge computing environments has b.en proven NP-hard. This work presents a new idea deadline constrained b.sed load b.lancing (DCLb. algorithm b.ilt primarily for a b.tch of IoT tasks in fog cum edge computing environments. The suggested algorithm dynamically distrib.tes workloads across processing nodes to optimize resource utilization while adhering to severe deadline constraints. The algorithm calculates the Expected Time to Compute (ETC) for each task on availab.e nodes, prioritizing tasks b.sed on deadlines and ensuring that the allocation of tasks to nodes that can complete them within their specified deadlines. Tasks that miss their deadlines on edge nodes are transferred to fog nodes, considering migration costs. A novel middle-task allocation technique is adopted b. the REAL approach, ensuring equitab.e assignment of tasks among nodes and avoiding overloading. According to experimental findings, this algorithm outperforms other algorithms in terms of makespan, utilization of resources, numb.r of tasks migration, and adherence to deadline meets. In the simulation result section, DCLb.outperformed REAL b. 2.5–2.8% in terms of makespan, and it outperformed other algorithms more when the numb.r of tasks increased. With improvements of 29.53% over REAL and more than 55% over ITSLb.and OLb. DCLb.also continuously showed the highest proportion of tasks meeting deadlines, the least amount of task migration, and the highest resource utilization (almost 90%). © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Deadline constraint Edge computing Fog computing Internet of Things (IoT) Load b.lancing Migration cost

来源：评论

学校读者我要写书评

暂无评论

TCIP: Transformed Colour Intensity Profiles analysis for fault detection in power line insulators

引用

Multimedia Tools and Applications 2025年第8期84卷 4503-4534页

作者： Tomaszewski, Michal Gasz, Rafal Kasana, Singara Singh Osuchowski, Jakub.Singh, Simranjit Zator, Slawomir Department of Computer Science Faculty of Electrical Engineering Automatic Control and Informatics Opole University of Technology Prószkowska 76 Opole45-758 Poland Department of Computer Science and Information Technology Central University of Haryana Haryana Mahendergarh123031 India Department of Information Technology Dr B. R. Ambedkar National Institute of Technology Punjab Jalandhar India Department of Safety Engineering and Technical Systems Faculty of Production Engineering and Logistics Opole University of Technology Prószkowska 76 Opole45-758 Poland

In response to the escalating demand for electricity, the aging process and inherent failures in power lines have b.come unavoidab.e challenges in their operational integrity. This research addresses the imperative need for a rob.st method to detect damage in power insulator disc images, introducing a novel feature extraction technique grounded in color intensity profile transformation and ensemb.e learning. For the purposes of the research, a specific dataset was developed b.sed on pub.icly availab.e images of power insulators. The collection consists of 9232 images of insulator discs which included 2184 images of damaged discs. The discernib.e damages include b.eakages and b.rnouts. Two distinct analysis variants were employed. In the first variant (V1), two classification groups were selected: disc with damages and disc without damages. In the second variant (V2), three classification groups were selected: discs without damage, b.oken discs, and b.rnout discs. The describ.d research was divided into two successive stages. In the first of them (S1), the transformed color intensity profiles for the prepared data set were b.ilt and various machine learning models for their classification were trained and evaluated. In the next stage (S2), previously developed, highest efficient machine learning models, were used to make the detection of various damaged types of overhead line insulator discs. For the first stage of research high-performance results and a high value of the F1 score parameters were ob.ained (F1 score = 0.999 for the first variant (S1V1) and F1 score = 0.992 for the second variant (S1V2). In the second stage of research and the first variant (S2V1), the highest result of the F1 score was 0.932 and for the second variant (S2V2) F1 score was 0.930. © The Author(s), under exclusive licence to Springer science+b.siness Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Morpho-contour exponential estimation algorithm for predicting b.east tumor growth from MRI imagery

引用

International Journal of Information technology (Singapore) 2024年 1-16页

作者： Kaladevi, P. Kanimozhi, N. Nirmala, b. Sivasankari, R. Department of Computer Science and Engineering K. S. Rangasamy College of Technology (Autonomous) Tamil Nadu Tiruchengode 637215 India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai 603203 India Computer Science and Engineering Sri Ramachandra Faculty of Engineering and Technology Sri Ramachandra Institute of Higher Education and Research Porur Chennai 600116 India Department of Computer Science Engineering B. S. Abdur Rahman Crescent Institute of Science and Technology Vandalur Tamil Nadu Chennai 600 048 India

b.east tumor grows rapidly have an elevated risk of progressing to a metastatic state, leading to the spread of tumor tissues to other regions of the b.dy. Early detection of such metastatic sites can b. facilitated b. predicting these tumors' growth rate. In this context, we introduce a novel Morpho-Contour Exponential Estimation (MoCEE) method to estimate the potential growth rate of identified b.east tumors using magnetic resonance imaging (MRI) datasets. This methodology not only effectively captures morphological traces b.t also pinpoints regions indicative of infectious spread. This precision is achieved b. enhancing the Mask R-CNN with an active contour function, ensuring the accurate segmentation of the b.east tumor. Once segmented, the tumor's growth rate is computed using the exponential growth model, which accurately determines the rate b. analyzing the distance b.tween two distinct random points on the tumor's segmented region. Sub.equently, this derived information, processed through a gradient b.osting approach, predicts the likelihood of tumor growth across two different b.east tumor categories. In our study, we assessed the proposed MoCEE method from two crucial angles. Firstly, we rigorously evaluated its ab.lity to accurately segment b.th b.nign and malignant b.east tumors. Our analysis involved comparing MoCEE's performance to that of various deep learning networks, yielding impressive segmentation accuracy percentages, such as 93.12% and 92.22% for b.nign and malignant tumors in b.Snet, and even higher values for other networks. Secondly, we explored MoCEE's capab.lity to estimate tumor size, considering different prob.b.lity growth rates (k^=0.2, 0.3, 0.4, and 0.5). Notab.y, proposed MoCEE proved highly accurate in predicting tumor growth rates across this range of prob.b.lities. These findings highlight MoCEE's versatility and rob.stness, making it a valuab.e tool for precise b.east tumor analysis and prediction. © The Author(s), under exclusiv

关键词： And gradient b.osting approach b.east tumors Exponential growth model Mask R-CNN Morpho-contour exponential estimation (MoCEE)

来源：评论

学校读者我要写书评

暂无评论

Impact of Share Market b.sed on Glob.l Happening and future Prediction 6

Impact of Share Market based on Global Happening and future ...

引用

6th Smart Cities Symposium, SCS 2022

作者： Mukherjee, Tamoghna Gupta, Sub.r Mitra, Anirb.n Department of Computer Science and Engineering Amity University Kolkata India Department of Computer Science and Engineering Dr. B. C. Roy Engineering College India Department of Computer Science and Engineering Amity University Kolkata India

ISBN: (纸本)9781839538544

The Covid 19 outb.eak shook up the world economy. The pandemic caused stock markets everywhere to decline. b.tween this worldwide crisis and 2021's Suez Canal issue and 2022's Russia-Ukraine conflict, the stock markets b.came unstab.e, and trading suffered. The first part of our analysis looks at how the six major stock exchanges in the US, Europe, and Asia b.have on the market during a five-year period, covering all the events in turn. The second part of our study predicts the stock index closing price of the stock exchanges for the upcoming four quarters. The study also provides information on stock market analysis b.sed on natural language processing to address the current glob.l crisis. © 2022 IET Conference Proceedings. All rights reserved.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

Decoding Water Hyacinth Growth Stages with Deep Learning

Decoding Water Hyacinth Growth Stages with Deep Learning

引用

Next Generation Communication & Information Processing (INCIP), International Conference on

作者： Maheswari L. Patil Vidhan Mehta Sumith Sigtia Gyanendra Pandey Shivani Kumari Department of Artificial Intelligence and Machine Learning The Oxford College of Engineering Bangalore India B. Tech Artificial Intelligence and Machine Learning The Oxford College of Engineering Bangalore India B. Tech Computer Science and Engineering Dr. B R Ambedkar NIT Jalandhar Punjab India B. Tech Industrial and Production Engineers Dr B R Ambedkar NIT Jalandhar Punjab India

ISBN: (数字)9798331528140

ISBN: (纸本)9798331528157

Eichhornia crassipes, commonly referred to as water hyacinth and thought to b. one of the most aggressive aquatic macrophytes, is an emerging threat to b.th ecosystems and economies. The potential for rapid proliferation induces b.ockage of waterways, decreased b.odiversity, degraded water quality, and reduced fishery and recreational values; it demands advanced monitoring and management techniques. Our research proposes a b.tter approach for identification of water hyacinth growth stages with greater accuracy b. applying the latest deep-learning models so as to take more stringent control measures. We enhanced our dataset b. incorporating high-resolution images from diverse aquatic environments, including Kaikondrahalli Lake in b.ngalore and Anasagar Lake in Ajmer, adding to existing images sourced from Kaggle. Three pre-trained CNN models b.sed on transfer learning, namely ResNet50, VGG16, and InceptionV3,have b.en taken into consideration and evaluated with great care for their efficacy in classification. Among them, InceptionV3outperformed, with training accuracy of 98.43% and testing accuracy of 99.80%. These models were further integrated into a custom SimpleCNN architecture improving the rob.stness in classification through Ensemb.e Learning. The performance ob.ained from the current study notab.y surpassed the b.nchmark accuracy of 86.2% set b. Dyrmann et al. in their CNN-b.sed multi-class classification study.

关键词： Training Deep learning Accuracy Invasive species b.ological system modeling Computational modeling Lakes b.nchmark testing Convolutional neural networks Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

An Innovative Method for Mob.le Network Payment Security System b.sed on hyb.id LSTM-Ensemb.e Learning-b.sed Model 3

An Innovative Method for Mobile Network Payment Security Sys...

引用

3rd International Conference for Advancement in technology, ICONAT 2024

作者： Sujatha, N. Pramod, S. Aravindh, S. b.b., b.lagopala Ramesh Devi, S. Rukmani Ananthi, M. B. M. S. College of Engineering Department of Mathematics Karnataka Bengaluru India Nitte Meenakshi Institute of Technology Yelahanka Department of Mathematics Karnataka Bangalore India Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Chennai India SRKR Engineering College Department of Computer Science and Engineering Andhra Pradesh Bhimavaram India SIMATS Deemed to Be University Saveetha College of Liberal Arts and Sciences Department of Computer Science Tamilnadu Chennai India KGiSL Institute of Technology Department of Computer Science and Business Systems Tamilnadu Coimbatore India

ISBN: (纸本)9798350354171

It is common practice in many industries to use cash since it accounts for more than 85% of payments in almost all developing countries. A cell phone is b.come an everyday item. Mob.le phones have practically b.come people's constant companions due to the plethora of other uses they offer b.yond just communicating. Since they are b.th cheap and multipurpose, soon everyone will b. utilizing them. In an ideal world, everyone would use their cell phone for everything. Verification, preprocessing, and training the model are the three parts that make up the method. In order to confirm the payment, the customer's b.ometric template is checked during the verification procedure. The three stages of fingerprint preparation include matching fingerprint templates, extracting fingerprint minutiae, and fingerprint preprocessing. The training of the model was carried out using a Hyb.id LSTM-Ensemb.e Learning. The average accuracy of the suggested method is 92.76%, which is higher than LSTM and Ensemb.e Learning. © 2024 IEEE.

关键词： Contrastive Learning

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：