检索结果-内蒙古大学图书馆

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

作者： Suresh, Helina Rajini Amutha, M. Tamizharasi, A. Jaya Krishna, A.P. Lalitha, S. Nithya, P. Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India Sona College of Technology Department of ECE Tamil Nadu Salem India R.M.D. Engineering College Department of Computer Science and Engineering Kavarapettai Tamil Nadu Chennai India Sona College of Technology Department of Electronics and Communication Engineering Tamilnadu Salem India Arunai Engineering College Department of Computer Science and Engineering Tamil Nadu Tiruvannamalai India

ISBN: (纸本)9798350317558

Everyone is ware that a wide range of problems affect skin structure, function, and appearance. Dermatological issues or dermatoses are common names used to represent the skin related illness. Early detection of skill llness is possible by employing Artificial Intellengence. A wide range of artificial intelligence techniques have been devised to promptly detect and diagnose skin problems. In this article we are proposing Mobilenetv2 and LSTM algorithms to identify skin disorders at an early stage. The combination of MobileNetV2 and LSTM (Long Short-Term Memory) for skin disease detection involves leveraging a convolutional neural network (CNN) for image feature extraction and a recurrent neural network (RNN) with LSTM units for sequence modeling, this architecture aims to capture both spatial and temporal dependencies in skin image data, making it well-suited for skin disease detection tasks. The method shown in this study can identify five distinct diseases with ease, and with accuracy rates of 99.2%. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Innovative Deep Learning Solutions for Image Forgery Detection 1

Innovative Deep Learning Solutions for Image Forgery Detecti...

引用

1st Asian Conference on Communication and Networks, ASIANComNet 2024

作者： Mutar, Mohammed Hasan Al-Fatlawy, Ramy Rasool, Hussein Ali Ghafour, Rizgar Rahman Abbas, Fatima Hashim Hashim, Dulfikar Jawad Imam Ja'afar Al-Sadiq University College of Information Technology Department of Computer Technical Engineering Al-Muthanna Iraq The Islamic University College of Technical Engineering Department of Computer Technical Engineering Najaf Iraq Altoosi University College Department of Computer Science Najaf Iraq National University of Science and Technology Dhi Qar Iraq Al-Mustaqbal University Medical Laboratories Techniques Department Hillah Iraq Mazaya University College Department of Computer Techniques Engineering DhiQar Iraq

ISBN: (纸本)9798350367003

Digital image forgery detection is crucial in addressing the rapid spread of fake information through manipulated images, especially on social media platforms. Traditional techniques often focus on specific types of forgery, limiting their effectiveness in real-world scenarios. Traditional methods heavily depend on manual feature engineering, which often results in overlooked manipulations, decreased accuracy, adaptability, and scalability issues when handling large datasets or high-resolution images. Deep learning has emerged as a powerful tool for addressing the challenges associated with image forgery detection. The proposed work introduces an innovative method for detecting image forgeries using deep learning techniques, employing convolutional neural networks (CNNs) and specifically evaluating the performance of the EfficientNetb7 model. This method leverages transfer learning to detect copy-move image forgery. It involves generating featured images by calculating the difference between the input image and compressed versions, which are then fed into pre-trained CNN model. The model undergo fine-tuning to adapt to forgery detection. Additionally, the output of the forgery detection process includes both text and audio. This combination enhances the accessibility and interpretability of the detection results, making them more understandable for users with different sensory preferences or impairments. This added feature ensures that the detection outcomes are easily comprehensible and usable across a broader range of users and applications. © 2024 IEEE.

关键词： CNN deep learning digital image EfficientNetb7 forged detection Rapid spread

来源：评论

学校读者我要写书评

暂无评论

An Empirical Analysis of Load Balancing Issues in Fog Computing Environment 2

An Empirical Analysis of Load Balancing Issues in Fog Comput...

引用

2nd International Conference on Data science and Information System, ICDSIS 2024

作者： Kumar, K. R. Prasanna Siddesh, G.M. Ananda Babu, J. M S Ramaiah Institute Of Technology Department Of Computer Science & Engineering Bangalore India M S Ramaiah Institute Of Technology Department Of Artificial Intelligence & Data Science Bangalore India Malnad College Of Engineering Department Of Information Science And Engineering Hassan India

ISBN: (纸本)9798350381665

Fog Computing (FC) is a distributed paradigm that complements cloud computing in terms of service delivery. By extending storage and computation of the network edge, fog systems enable location awareness and mobility support, while also resolving the issue of service computing for delay-sensitive applications. A crucial component of fog networks is load balancing, which prevents fog nodes from becoming under or overloaded. In recent years, only a limited number of studies have been conducted on load-balancing methods in fog networks. This paper provides a thorough assessment of the load-balancing techniques used in fog computing, covering approximate, accurate, fundamental, and hybrid methods. This paper also examines load balancing metrics in fog networks, including all benefits and drawbacks associated with the selected load balancing algorithms. The evaluation methods considered for each study are investigated. Additionally, the primary unresolved issues and potential developments for these systems are discussed. © 2024 IEEE.

关键词： Virtualization

来源：评论

学校读者我要写书评

暂无评论

An upgraded variant of backtracking search algorithm and its application to COVID-19 CT images segmentation

引用

Multimedia Tools and Applications 2025年 1-57页

作者： Debnath, Sanjib Nama, Sukanta Chakraborty, Sanjoy Saha, Apu Kumar Mirjalili, Seyedali Department of Computer Science & Engineering National Institute of Technology Agartala Tripura Agartala799046 India Department of Science & Humanities Gomati District Polytechnic Fulkumari Tripura Udaipur799013 India Department of Information Technology Bir Bikram Memorial College Tripura Agartala India Department of Mathematics National Institute of Technology Agartala Tripura Agartala799046 India Center for Artificial Intelligence Research and Optimization Torrens University Australia Brisbane Australia Faculty of Electrical Engineering and Computer Science VŠB-TU Ostrava Ostrava Czech Republic University Research and Innovation Center Obuda University Budapest Hungary Department of Computer Science & Engineering The ICFAI University Tripura Tripura 799210 India

To improve the performance of the original backtracking search algorithm (BSA), this work combines BSA with a centralized population initialization and an elitism-based local escape operator and proposes a new, improved variant of BSA called CiBSA. BSA's performance is improved by centralized population initialization regarding search capability, convergence speed, and capacity to jump out of the local optimum. The suggested algorithm's elitism-based local escape operator method prevents BSA searching slowness and enhances convergence rates and local search efficiency. The performance of the proposed algorithm has been tested on a set of 54 test suites. An extensive comparison with other recent meta-heuristics algorithms (MA) demonstrates that both methodologies substantially assist BSA in boosting the quality of its solutions and speeding up the convergence rate. The proposed CiBSA is then applied to a real-world problem: image segmentation using Kapur's entropy function. The proposed CiBSA is successfully applied to the segmentation of COVID-19 CT images using Kapur's entropy for grey-scale images. Considering the performance matrices Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Feature Similarity Index (FSIM), and Intersection over Union (IoU), the suggested CiBSA outperformed conventional MA algorithms. In COVID-19 CT image segmentation trials, CiBSA has superior segmentation capability and adaptability at varied threshold levels than other approaches. As a result, CiBSA has a lot of potential for enhancing COVID-19 diagnosis accuracy. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Deep learning based assistive technology on audio visual speech recognition for hearing impaired

引用

International Journal of Cognitive Computing in engineering 2022年 3卷 24-30页

作者： Kumar, L Ashok Renuka, D Karthika Rose, S Lovelyn Shunmuga priya, M.C. Wartana, I Made Department of Electrical and Electronics Engineering PSG College Of Technology Coimbatore India Department of Information Technology PSG College Of Technology Coimbatore India Department of Computer Science and Engineering PSG College Of Technology Coimbatore India Department of Information Technology PSG College Of Technology Coimbatore India India

Assistive technology would be an immense benefit for hearing impaired people by using Audio Visual Speech Recognition (AVSR). Around 466 million people worldwide suffer from hearing loss. Hearing impaired student rely on lip reading for understanding the speech. Lack of trained sign language facilitators and high cost of assistive devices are some of the major challenges faced by hearing impaired students. In this work, we have identified a visual speech recognition technique using cutting edge deep learning models. Moreover, the existing VSR techniques are erroneous. Hence to address the gaps identified, we propose a novel technique by fusion the results from audio and visual speech. This study proposes a new deep learning based audio visual speech recognition model for efficient lip reading. In this paper, an effort has been made to improve the performance of the system significantly by achieving a lowered word error rate of about 6.59% for ASR system and accuracy of about 95% using lip reading model. © 2022

关键词： Assistive technology

来源：评论

学校读者我要写书评

暂无评论

Support Vector Machine Classification Model Based on Grey Wolf Optimizer 7

Support Vector Machine Classification Model Based on Grey Wo...

引用

7th IEEE International Conference on Information Systems and computer Aided Education, ICISCAE 2024

作者： Han, Xinxin Wang, Jibin Zheng, Kaiyuan He, Dingkun Lu, Dandan School of Computer Science and Technology Southwest University of Science and Technology Mianyang China Chang Chien College Nantong University Nantong China School of Computer Science Beijing Information Science & Technology University Beijing China School of National Defense Science Southwest University of Science and Technology Mianyang China Dept. Engineering Technology Center Southwest University of Science and Technology Mianyang China

ISBN: (纸本)9798350350760

This paper proposes a support vector machine (SVM) classification model based on the grey wolf optimizer (GWO) to solve high-dimensional nonlinear classification problems in industrial production and daily life. To address the sensitivity of traditional SVM to parameter settings, this study utilizes the global search capability and fast convergence characteristics of the grey wolf optimizer to optimize the key parameters of SVM, including the penalty parameter C and the width parameter g of the radial basis function (RBF). By using the best accuracy rate achieved through five-fold cross-validation as the target function, the precise adjustment of SVM parameters was realized. Experiments using the Italian wine dataset were conducted for verification, and the results showed that the GWO-SVM model achieved a 100% accuracy rate on the test set, proving that the model has high classification accuracy and good generalization ability in handling complex classification problems. ©2024 IEEE.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Environmental Safety: Design and Development of IoT based Air Quality Monitoring System 5

Enhancing Environmental Safety: Design and Development of Io...

引用

5th International Conference on Image Processing and Capsule Networks, ICIPCN 2024

作者： Janaki, K. Eapen, Maya Meera, M.Minu Bhendale, Manisha Amol Arun, S. Krishnamoorthy, R. Department of Computer Science Chennai India Jerusalem College of Engineering Department of CSE Chennai India Justice Basheer Ahmed Sayeed College for Women Dept of Computer science Chennai India Bharati Vidyapeeth College of Engineering Department of Instrumentation engineering Maharashtra Mumbai India Jerusalem College of Engineering Department of ECE Chennai India Chennai Institute of Technology Centre for Advanced Wireless Integrated Technology Chennai India

ISBN: (纸本)9798350367171

Vehicle exhaust is the leading source of air pollution in cities, which is harmful to people and wildlife alike. To create a method for monitoring air pollution that is both effective and inexpensive. Workers will be alerted and data about polluting areas that have been verified for proximity will be notified via the suggested method. Using the ESP32 Wi-Fi module, the suggested system gathers data from a number of sensors-including those for air quality, temperature, and humidity-and uploads it to the cloud. There has been an unprecedented increase in industrial activity over the past few years, making air quality monitoring an absolute need. The degree to which human actions impact air quality should be made public knowledge. An air pollution monitoring system utilizing the NodeMCU based WiFi aided microcontroller is proposed in this research. The IoT based Air Quality Monitoring Scheme (IoTAQMS) uses Internet of Things (IoT) technology to track and analyze air quality in real-time. It then uploads the data to a remote server, where it is updated through the internet. To ensure the effectiveness of the system, it was cross-validated with the Classical Air Quality Monitoring System (CAQMS). The developed technology accurately measured the air quality. The outcome was shown on the interface of the specified hardware and could be accessible through the cloud server on any intelligent mobile device or personal computer. In industries where monitoring pollution levels of harmful gases are critical, the suggested approach might be useful. Additional pollution data is utilized to notify employees that the air quality in their immediate vicinity is unhealthy. © 2024 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Lemon Perfection: Leveraging VGG16 Deep Learning for Superior Quality Assessment 2

Lemon Perfection: Leveraging VGG16 Deep Learning for Superio...

引用

2nd International Conference Computational and Characterization Techniques in engineering and sciences, IC3TES 2024

作者： Kaur, Arpanpreet Govindrao, Panchal Sandeep Mahajan, Shubham Chitkara University Institute of Engineering and Technology Chitkara University Punjab India G H Raisoni College of Engineering and Management Dept of Computer Engineering Pune India Department Of Computer Science Delhi-NCR India

ISBN: (纸本)9798350364699

This work intends to improve lemon quality evaluation by means of photo categorization applied with the VGG16 deep learning model. Lemons need perfect quality control to keep their attraction and commercial success;their vibrant colour, acidic taste, and high vitamin C content call for this. Early diagnosis of quality problems can help to enhance consumer satisfaction and lower post-harvest losses. From a Kaggle dataset, the research groups 2,523 images - each with 300x300 pixels - into empty backdrop, great quality, and horrible quality lemons. Having been trained and tested on this dataset, the VGG16 model - known for its accuracy and efficiency in picture classification - achieves an incredible 97% classification success rate. Research on automated photo classification show that it increases efficiency, lowers labour costs, and offers smart data-driven analysis to help to maximize production processes and so raise lemon industry general profitability. © 2024 IEEE.

关键词： Data quality

来源：评论

学校读者我要写书评

暂无评论

Price-Discrimination Game for Distributed Resource Management in Federated Learning

IEEE Networking Letters

引用

IEEE Networking Letters 2024年第2期6卷 124-128页

作者： Zhang, Han Yang, Halvin Zhang, Guopeng China University of Mining and Technology School of Computer Science and Technology Xuzhou221116 China University College London Department of Electronic and Electrical Engineering LondonWC1E 7JE United Kingdom

In federated learning (FL) systems, the parameter server (PS) and clients form a monopolistic market, where the number of PS is far less than the number of clients. To improve the performance of FL and reduce the cost to incentive clients, this letter suggests distinguishing the pricing of FL services provided by different clients, rather than applying the same pricing to them. The price is differentiated based on the performance improvements brought to FL by clients and their heterogeneity in computing and communication capabilities. To this end, a price-discrimination game (PDG) is formulated to comprehensively address the distributed resource management problems in FL, including multi-objective trade-off, client selection, and incentive mechanism. As the PDG includes a mixed-integer nonlinear programming problem, a distributed semi-heuristic algorithm with low computational complexity and low communication overhead is designed to solve the Nash equilibrium (NE) of the PDG. The simulation result verifies that the NE achieves a good tradeoff between the training loss, training time, and the cost of motivating clients to participate in FL. © 2019 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Adaptive Course Tracking Control of an Unmanned Surface Vehicle with State and Input Quantization 13

Adaptive Course Tracking Control of an Unmanned Surface Vehi...

引用

13th International Conference on Information science and technology, ICIST 2023

作者： Ning, Jun Ma, Yifan Li, Tieshan Chen, C.L. Philip College of Navigation Dalian Maritime University Dalian China College of Automation Engineering University of Electronic Science and Technology of China Chengdu China College of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798350313925

This paper considers the course tracking control of an unmanned surface vehicle with state and input quantization, aiming to saving communication resources and improving system efficiency. The radial basis function neural network (RBF-NN) is used to approximate the model uncertainty. A linear analytical model is used to describe the input quantization process. The adaptive neural network quantization controller does not need the prior information of quantization parameters. Then the stability of the unquantized system and the boundedness of the quantification error in the closed-loop control system are proved by means of some lemmas. On this basis, the stability of the designed system with state and input quantization is proved. Finally, the effectiveness and feasibility of the proposed algorithm are verified by simulation experiments. © 2023 IEEE.

关键词： Unmanned surface vehicles

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：