检索结果-内蒙古大学图书馆

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Kotecha, Prajay Dhoka, Tanvi Bhatia, Jitendra Kumhar, Malaram Gupta, Rajesh Tanwar, Sudeep Jadav, Nilesh Kumar Department of Electronics and Communications Institute of Technology Nirma University Ahmedabad India Department of Computer Science and Engineering Institute of Technology Nirma University Ahmedabad India

In the rapidly changing world of new technologies, AI and ML have been delivered to the network's edge, allowing edge devices to compute simple models that can be applied later in practical applications. Edge computing allows the deployment of cloudlike services to the network edge. Moreover, it allows network devices to contribute to Federated Learning (FL) by using their processing power. Federated learning was developed when privacy and security concerns emerged among people. Here, multiple clients work together to solve machine-learning problems. Instead of collecting users' raw data, this technique protects user privacy by aggregating model parameters from each client to a central server. Even though FL techniques have several benefits, such as scalability and data privacy, when used with heterogeneous devices, they can introduce significant problems in processing complexity and speed. This paper thoroughly surveyed the important and efficient technological advancements based on edge federated learning. We review the widely used FL frameworks that effectively facilitate communication between clients and servers. We also present a case study on handwritten digit recognition using the MNIST dataset to state the effectiveness of federated learning. On applying this approach, we were able to achieve 94.56% accuracy. © 2024 Elsevier B.V.. All rights reserved.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

An Active Reconfigurable Mixer in GaN technology for 5G Power Amplifier Wi-Fi Communications 6

An Active Reconfigurable Mixer in GaN Technology for 5G Powe...

引用

6th Parul International Conference on engineering and technology, PICET 2024

作者： Kumar, Rajesh Babu, Tosif Abdul Gaffar Kanaujia, Binod Kumar Tiwari, Devesh Department of Computer Science & Engineering Galgotias College of Engineering &Technology Greater Noida India Department of Electronics & Communication of Engineering PIET Gujarat Vadodara India Department of Electronics & Communication of Engineering National Institute of Technology Jalandhar Jawaharlal Nehru University New Delhi110067 India Department of Computer Science & Engineering Graphic Science and Engineering Graphic Era Era Hill University Uttarakhand Dehradun India

ISBN: (纸本)9798350369748

The mixer's key attributes in this article are its high power output, high conversion gain, high efficiency, and good isolation between board positions. We have designed and implemented a mixer that can be reconfigured dynamically. Using a voltage gain of 12.3 dB, the local oscillator (LO) signal is amplified. The purpose of the active reconfigurable mixer is to enhance the cross-driver platform's performance. Alongside, with the occurrence of a mixer a high-power level is attained. It is noteworthy to highlight that the third-order intermodulation (IIP3) of the new configuration is -9 dBm, which is regarded as negligible. The mixer runs at 6 GHz and is powered by 0.15-µm GaN technology. © 2024 IEEE.

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Source IP Hashing Algorithm for Load Balancing in Cloud Server 6

Source IP Hashing Algorithm for Load Balancing in Cloud Serv...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Gokul, M. Rajkumar, N. Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Institute of Science and Technology Chennai India

ISBN: (纸本)9798331522667

The high trend in the adoption of online banking makes complex load balancing highly crucial to maximize computing capacity in the cloud, data management, and security. This research focuses on analyzing the Source IP Hashing method of load balancing where client requests are evenly distributed depending on their source IP address to provide persistence of client sessions and protect against session hijacking among other risks. The proposed framework, captured in Java, follows a systematic procedure of directing the client requests to the most appropriate servers using hash values generated from the IP address of the clients reducing server resource consumption. The paper also yields numerical results comparing throughput and system responsiveness with pretested significant enhancement affirming that even under high traffic the system achieves high responsiveness and reliability. This analysis proves that Source IP Hashing helps deliver high success rates in request routing while maintaining a 99% retention of session persistence and improving server utility. Thus, the study also proves that Source IP Hashing algorithm enhances the safety and security of data even when distributing the practical load among different servers, which makes it a more innovative solution for easing the problems of cloud-based financial services of the present days. © 2025 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Fast and Accurate Community Detection in Social Media Networks with a Multi-Algorithmic Approach

Fast and Accurate Community Detection in Social Media Networ...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Pabitha, P. Petchiammal, G. Eswari Anna University Department of Computer Technology MIT Campu Chromepet600044 India Knowledge Institute of Technology Department of Computer Science and Engineering Salem637504 India

ISBN: (纸本)9798331543617

Community detection is an essential technique for uncovering structural patterns in complex networks, such as social, biological, and information networks. In this paper to explore a hybrid approach to community detection by combining the label propagation algorithm and leiden algorithm. Although LPA is well known for its computational effectiveness in large- scale networks, because of its reliance on local label propagation, it frequently results in unstable and fractured communities. High- quality community structures are produced by the Leiden algorithm, which is more computationally expensive than the Louvain method but ensures well-connected communities by optimising modularity. Our goal in combining these two approaches is to take use of LPA's speed for quick community discovery and the Leiden algorithm's refinement powers for increased accuracy and stability. Large or dynamic networks where both real-time speed and community quality are crucial are best suited for the suggested hybrid method. The combination of these algorithms yields more cohesive and modular communities than either one working alone, as evidenced by experimental results on synthetic social network data. The method is a useful tool for large- scale network analysis because it strikes a balance between the necessity for strong and significant community structures and computational efficiency. © 2024 IEEE.

关键词： Community detection Label propagation leidens Louvain

来源：评论

学校读者我要写书评

暂无评论

Image Caption And Speech Generation Using LSTM And GTTS API 2

Image Caption And Speech Generation Using LSTM And GTTS API

引用

2nd International Conference on Augmented Intelligence and Sustainable Systems, ICAISS 2023

作者： Ram, K. Bhargav Venkatesh, B. Sree, Sala Pooja Sai Anilkumar, Chunduru Reddy, V. Surya Narayana Kodumuri, Bhavya Bvrit Hyderabad College of Engineering for Women Department of Computer Science and Engineering Hyderabad India Systems Engineer Infosys Hyderabad India Gmr Institute of Technology Dept of Information Technology Andhra Pradesh Rajam532127 India Vnr Vignana Jyothi Institute of Engineering and Technology Department of Computer Science and Engineering Hyderabad India Vidya Jyothi Institute of Technology Department of Computer Science and Engineering HYderabad India

ISBN: (纸本)9798350325799

Image Caption generation is one of the challenging tasks in the field of artificial intelligence. It is used to generate a textual description for a given picture. But due to, the recent advancement in deep learning techniques requires only one single end-to-end model to create a caption for the given image. This paper is intended to provide an image caption and speech generator used to generate a single-line description for a given image and audio/speech for the report generated. The researchers used a sophisticated pipeline of specifically designed models in the previous models. To achieve the proposed model, VGG16 and LSTM models are used to obtain descriptions for the image and GTTS API is used for the audio/speech generation. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Classification of Hidden Patterns in Cancer Genome using Deep Learning 4

Classification of Hidden Patterns in Cancer Genome using Dee...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Balamurugan, K.S. Navaneethakrishnan, Sundara Rajulu Srinivasulu, Senduru Kumutha, D. Surendran, R. Kalyani, G. Karpaga Vinayaga College of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Chengalpattu India Dhanalakshmi Srinivasan University Trichy Department of Computer Science and Engineering Samayapuram Campus Tiruchirappalli India Sathyabama Institute of science and Technology School of Computing Department of Computer Science and Engineering Chennai600119 India Jeppiaar Institute of Technology Department of Electronics and Communication Engg. Tamilnadu Sriperumbudur India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai602105 India RuralCare Innovators Llp Tamil Nadu Madurai India

ISBN: (纸本)9798331540364

The complex structures in cancer genomes are obtained through the revolution of high-throughput technology. The major challenge involves the interpretation of complex sceneries of genomic alterations with the impact of diagnosis and prognosis. The proposed system includes deep-learning techniques that provide optimum solutions for evaluating hidden patterns of the cancer genome. They help to extract important information such as mutation and detection of therapeutic targets. The proposed system involves the aid of a Convolutional Neural Network, Recurrent Neural Network with Long Short Term Memory networks. They help in obtaining intricate genomic data. This is achieved through the spatial relationship and sequential dependencies within the genetic elements. The large-scale genomic datasets are trained which helps to learn the differentiation between the driver and passenger mutations. The genetic alterations provide information regarding the cancer progression. The deep learning model helps in the identification of desperate mutations with exclusive patterns that contribute to tumor development. The important aspect involves the prediction of prognosis. This includes the model to train and learn from the cumulative knowledge of patients in accordance with the genomic profiles. An accurate prognosis and personalized treatments are obtained by analyzing certain parameters such as gene expression, gene mutation and clinical data structures. These optimization techniques help in the identification of complex relationships in the identification of therapeutical compounds. © 2024 IEEE.

关键词： Genome

来源：评论

学校读者我要写书评

暂无评论

Improved Energy Balancing based Data Forwarding incorporating Whale optimization Technique in Underwater Acoustic Sensor Network 3

Improved Energy Balancing based Data Forwarding incorporatin...

引用

3rd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2024

作者： Bhairavi, R. Thiruveni, M. Anita Christaline, J. Ashokkumar, N. Chandra, I. Nagarajan, P. Srm Institute of Science and Technology Department of Ece Chennai Vadapalani India Psna College of Engineering and Technology Department of Ece Dindigul India Vit Chennai School of Computer Science and Engineering India Department of Electronics and Communication Engineering Andhra Pradesh Tirupati India Rajalakshmi Institute of Technology Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798350369083

UWASN has various challenges such as minimal bandwidth availability, long propagation delay, increased energy exhaustion, increased deployment cost and security. The routing protocols should facilitate an enhanced data forwarding towards sink nodes. In this paper, an Improved Energy Balancing based Data Forwarding incorporating Whale optimization Technique (IEBDF-WO) is proposed to effectively elect optimal forwarders to participate in the routing process. The Whale optimization algorithm has three phases namely, scouring phase, encompassing phase and final bubble net raiding phase for facilitating enhanced data transmission towards sink node. The proposed technique determines a fitness function by using the weighted depth difference WD, Potential Relay Count (PRC), Residual energy of each potential relay node. The performance of the proposed IEBDF-WO technique is analyzed and is collated with the existing Energy-Efficient Probabilistic Depth-Based Routing (EEPDBR) technique. It is seen that, for a network comprising of 200 nodes, the proposed scheme has improved Packet Delivery Ratio of 96.04% while minimizing the end to end delay, energy tax and average number of hops. © 2024 IEEE.

关键词： encompassing phase fitness function potential relay count scouring phase whale optimization

来源：评论

学校读者我要写书评

暂无评论

Optimal Energy Forecasting Using Hybrid Recurrent Neural Networks

引用

Intelligent Automation & Soft Computing 2023年第4期36卷 249-265页

作者： Elumalaivasan Poongavanam Padmanathan Kasinathan Kulothungan Kanagasabai Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and TechnologyChennai600062India Department of Electrical and Electronics Engineering Agni College of TechnologyChennai600130India Department of Information Science and Technology Anna UniversityChennai600025India

The nation deserves to learn what India’s future energy demand will be in order to plan and implement an energy *** energy demand will have to be fulﬁlled by an adequate mix of existing energy sources,considering the con-straints imposed by future economic and social changes in the direction of a more sustainable *** energy demand,on the other hand,is a tricky task because it is inﬂuenced by numerous *** a result,an macro model with only a few factors that may be predicted globally,rather than a detailed ana-lysis for each of these variables,is *** this work,a hybrid approach is proposed for identifying the optimal generation-based mix of electricity systems in *** approach is developed by combing Recalling-Enhanced Recurrent Neural Network(RERNN)and Giza Pyramids Construction(GPC).RERNN pos-sesses selective memory features whereas GPC is a meta-heuristic algorithm that deals with different sets of *** goal of this approach is to assess the present load requirements and production proﬁle to understand the current requirement and its production *** on regards to electricity load proﬁle involving the generation of all power plants,capacity factors and transmission limits were gathered from different sources including the Indian National Load Dispatch Centre,Central Electricity Authority database,annual reports of India and regional load dispatching *** proposal has introduced the RERNN technique to analyze the optimal time series whereas the GPC technique is involved in the optimization of RERNN *** present work is simu-lated in MATLAB and the performance assessed with different *** present technique gives an effective results in terms of accuracy,computational efﬁciency and feasibility.

关键词： Electricity generation demand RERNN GPC time series prediction

来源：评论

学校读者我要写书评

暂无评论

A Survey on Human Face Emotion Recognition using Machine Learning Models 9

A Survey on Human Face Emotion Recognition using Machine Lea...

引用

9th International Conference on Advanced Computing and Communication Systems, ICACCS 2023

作者： Yuvaraj, S. Franklin, J. Vijay Prakash, V.S. Anandaraj, A. Subha, R. Sri Eshwar College of Engineering Department of Computer Science and Engineering Coimbatore India Bannari Amman Institute of Technology Department of Computer Science and Engineering Erode India Kristu Jayanti College Department of Computer Science Bangalore India

ISBN: (纸本)9798350397376

Human Face Emotion Recognition (HFER) is a field that studies the human state of mind through different facial expressions. In this paper, the comparative study is made on four different machine learning methods such as CNN, Bidirectional Convolutional LSTM, Multiple Pipelines, and Transfer Learning algorithms based on the various universal human emotions like Happy, Sad, Surprise, Fear, Anger, Disgust, Neutral and Contempt. Two Image data sets that carry static images with a different set of emotions are used in the methods and the accuracy level of each method is compared and analysed along with other metrics such as Precision, Recall, and F1 Scores are also considered. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection System in Wireless Sensor Networks using Modified Recurrent Neural Network with Long Short-Term Memory 2

Intrusion Detection System in Wireless Sensor Networks using...

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Ramkumar, K. Alzubaidi, Laith H. Malathy, V. Venkatesh, T. Kruthika, C.G. Srm Institute of Science and Technology Department of Computer Science and Engineering Chennai India The Islamic University Najaf Iraq Sr University School of Engineering Department of Ece Telangana India Kpr Institute of Engineering and Technology Department of Ece Coimbatore India Nitte Meenakshi Institute of Technology Department of Ai and Ml Bengaluru India

ISBN: (纸本)9798350317558

Leveraging deep learning, Intrusion Detection Systems (IDS) for Wireless Sensor Networks (WSN) enhance security through advanced analytics, detecting and mitigating network intrusions in real-time for robust protection. Evaluations and scalability considerations are critical for improving the applicability and robustness of intrusion detection systems based on deep learning techniques. This paper introduces a novel approach: a modified Recurrent Neural Network with Long Short-Term Memory (RNN-LSTM) for IDS in WSN classification, utilizing the NSL-KDD dataset. Rigorous performance validation demonstrates outstanding metrics, including an accuracy of 99.95%, precision at 99.93%, and a robust recall of 95.69%, with the F1-score reaching 99.80%, surpassing benchmarks set by existing methods. Notably, current approaches like Deep Neural Network (DNN), Convolutional Neural Network-LSTM (CNN-LSTM), Conditional Generative Adversarial Network (CGAN), and Stacked Autoencoders-DNN (SAE-DNN) face limitations in achieving optimal accuracy and robustness. The proposed RNN-LSTM method exhibits significant advancements in addressing these challenges for effective intrusion detection in WSN © 2024 IEEE.

关键词： Convolutional Neural Network Deep Neural Network Intrusion Detection System Long Short-Term Memory Wireless Sensor Network

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：