检索结果-内蒙古大学图书馆

Genetic-Chicken Swarm Algorithm for Minimizing Energy in Wireless Sensor Network

computer Systems Science & engineering 2023年第2期44卷 1451-1466页

作者： A.Jameer Basha S.Aswini S.Aarthini Yunyoung Nam Mohamed Abouhawwash Department of Computer Science and Engineering Hindusthan Institute of TechnologyCoimbatore641032India Department of Computer Science and Engineering Soonchunhyang UniversityAsan31538Korea Department of Mathematics Faculty of ScienceMansoura UniversityMansoura35516Egypt Department of ComputationalMathematics Science and Engineering(CMSE) Michigan State University East LansingMI48824USA.

Wireless Sensor Network(WSN)technology is the real-time applica-tion that is growing rapidly as the result of smart *** power is one of the most signiﬁcant resources in *** enhancing a power factor,the clustering techniques are *** the forward of data in WSN,more power is *** the existing system,it works with Load Balanced Cluster-ing Method(LBCM)and provides the lifespan of the network with scalability and *** the existing system,it does not deal with end-to-end delay and deliv-ery of *** overcoming these issues in WSN,the proposed Genetic Algo-rithm based on Chicken Swarm Optimization(GA-CSO)with Load Balanced Clustering Method(LBCM)is *** Algorithm generates chromosomes in an arbitrary method then the chromosomes values are calculated using Fitness *** Swarm Optimization(CSO)helps to solve the complex opti-mization ***,it consists of chickens,hens,and *** divides the chicken into *** Balanced Clustering Method(LBCM)maintains the energy during communication among the sensor nodes and also it balances the load in the *** proposed GA-CSO with LBCM improves the life-span of the ***,it minimizes the energy consumption and also bal-ances the load over the *** proposed method outperforms by using the following metrics such as energy efﬁciency,ratio of packet delivery,throughput of the network,lifetime of the sensor ***,the evaluation result shows the energy efﬁciency that has achieved 83.56%and the delivery ratio of the packet has reached 99.12%.Also,it has attained linear standard deviation and reduced the end-to-end delay as 97.32 ms.

关键词： Energy efﬁciency sensor nodes chicken swarm optimization load balanced clustering method wireless sensor network cluster heads load-balancing ﬁtness function

来源：评论

学校读者我要写书评

暂无评论

Scalable Modular Battery Management System Using Model-Based Approach for EV Applications 2

Scalable Modular Battery Management System Using Model-Based...

引用

2nd International Conference on Emerging Trends in Information technology and engineering, ic-ETITE 2024

作者： Kumar, Srinath Jawaharram, Vishnu Ram Balashivakumaran, R. Chandrakala, K.R.M. Vijaya Kumar, S. Sampath Nadar, Kannan Paulish Amrita School of Engineering Department of Electrical and Electronics Engineering Coimbatore India Institute of Technology Jijiga University Department of Electrical and Computer Engineering Ethiopia

ISBN: (纸本)9798350328202

The global automotive industry is in the phase where Internal Combustion vehicles are in decline and witnessing a shift towards sustainable development. The major parameter of a successful EV is an efficient battery pack and the protection for it which is the Battery management system (BMS). In this work model-based approach in the design of a Modular Battery Management System (BMS) takes into account various protection schemes such as over and under-voltage scenarios adopted in Li-ion batteries and monitoring the State of Charge (SoC) using the Coulomb Counting technique. The design and the simulation-based approach are adopted to study the behaviour of Li-ion Battery and BMS in a wide operational condition where the testing is difficult using MATLAB/Simulink. The proposed technique is a Modular Battery Management System that works on the Master-Slave Architecture. © 2024 IEEE.

关键词： Battery management systems

来源：评论

学校读者我要写书评

暂无评论

Deep Fake Video Detection using Neural Networks 15

Deep Fake Video Detection using Neural Networks

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Das, Ancy Y. Sinchana, G. Sushmitha, C.S. Venkatesh, L. Yasaswvene Department of Computer Science and Engineering BGS Institute of Technology Adichunchanagiri University Karnataka BG Nagara India

ISBN: (纸本)9798331300579

As of late, the multiplication of free profound learning programming apparatuses has fundamentally worked with the advancement of practical face trades in recordings, bringing about the development of "DeepFake" (DF) recordings with negligible hints of *** AI-generated media, commonly known as DF, can now be generated with relative ease using artificially intelligent ***, despite the simplicity of generating DF using AI tools, detecting such manipulated content remains a significant *** algorithms to identify DF is inherently *** expect to achieve promising results against a comprehensive dataset of fake videos sourced from standard repositories. © Grenze Scientific Society, 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Comparison between experimental and numerical results for piezoelectric signals generated in water-saturated cancellous bone by ultrasound irradiation

Comparison between experimental and numerical results for pi...

引用

2023 International Congress on Ultrasonics, ICU Beijing 2023

作者： Hosokawa, A. Department of Electrical and Computer Engineering National Institute of Technology Akashi College Akashi674-8501 Japan

The bone formation is considered to be accompanied by the piezoelectric effects in bone. Therefore, the piezoelectric effect under ultrasound irradiation should be elucidated to realize the effective healing. Then, the piezoelectric properties in cancellous bone have been attempted to clarify by complementing experiments and simulations with each other. In this paper, the piezoelectric signals generated in water-saturated cancellous bone by ultrasound irradiation were experimentally and numerically observed, and the effect of the trabecular orientation was investigated. The experimental observation was performed by the piezoelectric cell (PE-cell), which corresponds to an ultrasound receiver using the cancellous bone specimen as a piezoelectric element. The numerical observation was performed by the piezoelectric finite-difference time-domain (PE-FDTD) method, which is an elastic FDTD method with piezoelectric constitutive equations. In both the experimental and simulated results, the piezoelectric signal amplitude increased with the mean intercept lengths (MILs) of the trabecular elements and the pore spaces or the strength of the trabecular orientation. From the fact that the ultrasound propagation in water-saturated cancellous bone can depend on the trabecular orientation, it was considered that the ultrasound properties could be largely associated with the piezoelectric properties. © 2024 institute of Physics Publishing. All rights reserved.

关键词： Piezoelectricity

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Diabetic Retinopathy Using Pretrained Models: A Focus on Initial Stages 1

Early Detection of Diabetic Retinopathy Using Pretrained Mod...

引用

1st International Conference on Advanced Computing and Emerging Technologies, ACET 2024

作者： Raza, Md Aasif Dua, Mohit Berwal, Krishan National Institute of Technology Kurukshetra Department of Computer Engineering Kurukshetra India Military College of Telecommunication Engineering Department of Communication Engineering Mhow India

ISBN: (纸本)9798350367720

Early detection of diabetic retinopathy is crucial because this disease currently has no cure. Identifying the condition at an early stage can significantly help in halting its progression and preventing severe vision loss. Numerous studies have focused on the detection and classification of diabetic retinopathy using various machine learning and deep learning techniques. In this work, we aim to detect the disease in its initial stages using a pre-trained VGG16 model, which is proved to be efficient in many image recognition tasks by recent researchers. Our initial approach achieved an accuracy of 79%, indicating a promising potential for early detection. To further improve the detection accuracy, we incorporated Ben Graham's preprocessing method, which enhances the finer details of the retinal images. This enhancement led to a 5% increase in accuracy, resulting in a final accuracy of 84.40%. These results underscore the effectiveness of advanced preprocessing techniques combined with deep learning models in the early detection of diabetic retinopathy. © 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

Optimized Biometric Key Management System for Enhanced Security 11th

Optimized Biometric Key Management System for Enhanced Secu...

引用

11th International Conference on Intelligent Computing and Applications, ICRTC 2023

作者： Kaur, Prabhjot Kumar, Nitin School of Computing DIT University Uttarakhand India Department of Computer Science and Engineering National Institute of Technology Uttarakhand India Department of Computer Science and Engineering PEC Deemed to be University Chandigarh India

ISBN: (纸本)9789819717231

Biometric cryptosystems are security tools that use an individual’s distinctive physical or behavioral characteristics to secure sensitive data. Any biometric cryptosystem’s effectiveness is dependent on how well the features are extracted. The suggested solution uses an evolutionary algorithm to first optimize the retrieved attributes. Second, fuzzy vault is used to safeguard these optimized features. The fuzzy vault system is a well-known biometric cryptography device that creates a vault by using a polynomial equation, protecting the biometric information. However, if an attacker has access to the polynomial equation, the security of the fuzzy vault scheme may be jeopardized. The shuffled frog leaping algorithm (SFLA) method has been suggested as a way to improve the security of the fuzzy vault technique in order to overcome this drawback. The SFLA is a meta-heuristic optimization method that resolves challenging optimization issues by simulating the social behavior of frogs. This meta-heuristic technique is used in this paper’s suggested strategy to produce and secure optimized points. The experiments are performed onn AMI and MMU2 databases. The results achieve higher levels of performance compared to the traditional schemes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Detection Using Machine Learning Approaches: A Review 4th

Plant Disease Detection Using Machine Learning Approaches: A...

引用

4th International Conference on Data, engineering, and Applications, IDEA 2022

作者： Saraf, Puja Dipak Patil, Jayantrao Bhaurao Department of Computer Engineering R. C. Patel Institute of Technology Shirpur425405 India

ISBN: (纸本)9789819700363

Agriculture plays an important role in the country’s development, and it is the key source of food for the population of the world. But in developing countries like India, Pakistan and Nepal, the condition of the agriculture sector is getting worse day by day. There are many reasons behind it, but one of the reasons is the degeneration of crops by pests and disease. Agriculture solely depends on the biological health of the seeds, crops, information on weather conditions soils and biotic features liable for the crop diseases. Robust diagnostic methods are accomplished by dispensation and scrutinizing large quantities of records near get additional consistent material and ample more accurate predictions remain vital. Deep learning, image processing, soft computing and data mining are likely to play a vital role in recognizing plant diseases. This paper aims to review existing studies and investigations using the recent practices to solve a variety of agricultural problems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Federated Learning in Edge Computing Environment 2

Performance Evaluation of Federated Learning in Edge Computi...

引用

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

Skin cancer detection using deep learning 10

Skin cancer detection using deep learning

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Arun, K.A. Palmer, Matthew Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Karunya Nagar Coimbatore641114 India

ISBN: (纸本)9798350353068

Skin cancer is a prevalent and sometimes lethal condition for which early detection is essential to the best course of treatment. Using dermatoscopic images, convolutional neural networks (CNNs) have demonstrated potential as automated methods for identifying skin cancer. This research presents a unique CNN-based method that uses a carefully chosen dataset that includes a wide range of benign and malignant lesions to diagnose skin cancer. Preprocessing the pictures, training CNN models, and assessing the outcomes using standard metrics like accuracy, precision, recall, and F1-score are the steps in the process. The method works effectively in accurately identifying skin lesions and distinguishing between instances that are benign and those that are malignant, according to extensive testing. Furthermore, a comparison with more traditional approaches highlights the benefit of deep learning in dermatological applications. Furthermore, the results' clinical implications and Possible approaches to incorporating automated technologies into dermatological practice are looked at. By demonstrating the ground-breaking potential of deep learning for skin cancer diagnosis, this work adds to the growing body of research in the field of healthcare. The code created for this project is noteworthy for achieving an astounding 95% accuracy rate, which further confirms the effectiveness of the suggested CNN-based strategy. This work highlights the need of multidisciplinary collaboration between computer science and medicine to address urgent healthcare concerns and develop computer-aided diagnostics. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

MPEG-DASH Multi-View Video and Audio Transmission QoE Over HTTP/2 Stream

MPEG-DASH Multi-View Video and Audio Transmission QoE Over H...

引用

2024 International Conference on Advanced Technologies for Communications, ATC 2024

作者： Wakayama, Yamato Nunome, Toshiro Graduate School of Engineering Nagoya Institute of Technology Computer Science Program Department of Engineering Nagoya466-8555 Japan

ISBN: (纸本)9798350353983

In this paper, we consider multi-view video and audio streaming using MPEG-DASH, which enables to transmit video tailored to the network conditions over HTTP communication. This paper uses HTTP/2 instead of HTTP/1.1, which the authors previously used. HTTP/2 manages a series of request-response exchanges called a stream, which is assigned a unique stream ID. We perform a subjective experiment under various network conditions to evaluate application-level QoS and QoE. From the evaluation results, we investigate the effect of the HTTP/2 stream on the video and audio quality of the users in the multi-view video transmission scenario. © 2024 IEEE.

关键词： Audio streaming

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：