检索结果-内蒙古大学图书馆

4th International Conference on Communication, Devices and Computing (ICCDC 2023)

作者： Sarkar, Puja Kalita, Psarag Jyoti Goswami, Mugdhatanu Dev Saha, Sanchita Nag, Amitava Department of Computer Science and Engineering Central Institute of Technology Assam Kokrajhar783370 India Department of Computer Science and Engineering Haldia Institute of Technology Haldia721657 India

ISBN: (纸本)9789819927098

Sharing students’ credentials is an essential process for any educational ecosystem that includes diverse stakeholders such as students, teachers, various committees of institutes, administrations, government agencies, and many more. All of these stakeholders take extensive measures to ensure the authenticity and confidentiality of students’ testimonials when those are being shared. In spite of these concerns, the distribution of students’ credentials is a vulnerable, potentially complex, and sometimes insecure process. The goal is to reduce the existing security-related issues when sharing the students’ credentials with the help of blockchain technology. The technology of blockchain can be used effectively to solve the issue of securely exchanging student credentials. We proposed a secure, immutable, authentic, tamper-proof, privacy-preserving, and easily shareable blockchain-based mechanism for securely exchanging students’ credentials. In order to make the process of sharing credentials scalable, we proposed a secure off-chain store mechanism. A decentralized application based on Ethereum technology is used for conducting an analysis of the architecture with regard to its performance as well as its potential feasibility. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Pulmonary Nodule Detection in Computed Tomography Images Using Deep Learning 1

Pulmonary Nodule Detection in Computed Tomography Images Usi...

引用

1st IEEE International Conference on Advances in Electronics, Communication, Computing and Intelligent Information Systems, ICAECIS 2023

作者： Longkumer, Akumlong Walling, Supongmen Kalita, Shobhanjana Icfai University Department of Computer Science Dimapur India National Institute of Technology Department of Computer Science and Engineering Dimapur India Tezpur University Department of Computer Science and Engineering Tezpur India

ISBN: (纸本)9798350348057

the well-being of individuals is seriously threatened by lung cancer, which has one of the highest fatality rates of all cancers. Therefore, to increase patient life expectancies, early diagnosis of lung nodules is essential. For many years, the science of machine vision and medical diagnostics has used convolution neural networks. Early diagnosis can significantly lower the patient's mortality, and computer-aided diagnosis has emerged as a vital tool for medical professionals. computer-aided diagnosis depends on the ability to identify pulmonary nodules in computed tomography images. In the Computed Tomography scans, it is difficult to find the lump inside the lungs. This project uses U-Net to implement automated lung nodule identification. Furthermore, the data sets used for pulmonary nodule recognition from CT scan images are from the freely accessible LIDC/IDRI database. © 2023 IEEE.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Improved Image Caption Generation With GPT-3 And Deep Learning Approach 11

Improved Image Caption Generation With GPT-3 And Deep Learni...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Manchala, Laxman Teja Kallem, Sheshanth Reddy Kunja, Hemanth Soundararajan, Surendhar Hariharan, Shanmugasundaram Kukreja, Vinay Vardhaman College of Engineering Department of Computer Science and Engineering Hyderabad India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9798350350357

Subtitling, a growing field of natural language processing (NLP) research, includes generating a caption representation of images. The major goal is to use the pre-trained convolutional neural network (CNN) to develop a mechanism to caption an image. Convolutional neural network helps in feature extraction in this study whereas the extracted features are utilized by Recurrent Neural Network (RNN) to subtitle the captions for images. To encode the image several convolutional neural network pre-trained models are used. The decoder, a GPT -3-based language model, constructs descriptive sentences. In addition, adding Bahdanau's attention model to GPT -3 improves performance by enabling targeted learning in specific image regions. In an empirical evaluation of the MSCOCO dataset, our approach shows competitive performance. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Cellular Automata Model and Frame Work for Tsunami Wave Propagation in Indian Coastal Region

Machine Learning-Based Cellular Automata Model and Frame Wor...

引用

2024 International Conference on Advances in Modern Age Technologies for Health and engineering science, AMATHE 2024

作者： Syed Mohamed, E. Chithirai Pon Selvan, M. B. S. Abdur Rahman Crescent Institute Of Science And Technology Computer Science And Engineering Chennai India School Of Science And Engineering Curtin University Dubai United Arab Emirates

ISBN: (数字)9798350371567

ISBN: (纸本)9798350371567

Simulating the spread of tsunami waves quantitatively holds significant importance in devising swift risk management strategies and implementing efficient solutions for predicting the earliest arrival time. One effective method for dynamically simulating the spatiotemporal evolution of complex systems is through the use of cellular automata (CA), making it a suitable choice for modeling the intricate process of tsunami wave propagation. Nevertheless, the phenomenon of tsunami wave propagation is intricately linked with numerous interdependent factors, rendering it too intricate for analysis using traditional approaches. In answer to this challenge, we present a brand-new method for simulating the propagation of tsunami waves called LSSVM-CA. In this novel method, we integrate a three-dimensional tsunami wave CA framework with least squares support vector machines (LSSVM). We can now take into account and examine how neighboring waves affect the propagation patterns thanks to this integration. Using a dataset derived from historical data, LSSVM is trained to create sophisticated state transformation rules for tsunami wave propagation. We compared the LSSVM-CA-simulated tsunami wave spread areas with the real observed tsunami wave spread areas in order to evaluate the efficacy of the model. The outcomes unequivocally show how well LSSVM-CA simulates tsunami wave propagation accurately calculates a probability of the waves spreading. © 2024 IEEE.

关键词： Wave propagation

来源：评论

学校读者我要写书评

暂无评论

Skin Lesion Decode A CNN-SVM Convergence for Enhanced Diagnostic Accuracy

Skin Lesion Decode A CNN-SVM Convergence for Enhanced Diagno...

引用

2024 Asia Pacific Conference on Innovation in Technology, APCIT 2024

作者： Suryavanshi, Ankita Mehta, Shiva Rana, Samir Manwal, Manika Jain, Vishal Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Graphic Era Hill University Computer Science and Engineering Uttarakhand Dehradun India Graphic Era Deemed to Be University Computer Science and Engineering Uttarakhand Dehradun India Sharda University Computer Science and Engineering Sharda School of Engineering and Technology U.P. Greater Noida India

ISBN: (纸本)9798350361537

This research study investigates the development and evaluation of a merged CNN and SVM model for detecting and classifying skin lesions. The research systematically divides skin lesions into five categories that allow a thorough analysis of the model's diagnostic skills. The CNN-SVM model is developed and tested using a high-quality dataset, and its accuracy, recall, and F1 scores provide insights into specific performance aspects of the model. The results show a high level of precision for all the classes that vary from 92.95% for Class 1 to 95.95% for Class 5, which suggests that the model is good at making optimistic predictions. The recall measure, a sensitivity measure of the model, varies from 91.44% for Class 3 to 98.47% for Class 1, indicating the model's capability to recognize true positives correctly. The F1-score, which balances precision and recall, is always high, fluctuating from 93.00% for Class 3 to 96.28% for Class 5, reflecting the model's well-balanced categorization. Several types of averages are computed to assess the model's performance thoroughly. The macro average indicates accuracy of 94.70%, recall of 94.81%, and F1-score of 94.73%, with equal weight given to each class. With class distribution, the weighted average is as follows: accuracy - 94.74%, recall - 94.72%, F1-score - 94.71%. The micro average indicating the sum of contributions from all classes is 94.72% for all three parameters across the board. The model is entirely accurate, with an overall accuracy of 94.72397, showing the model's strong ability to generalize across different skin lesion types. The statistical measures confirm the CNN-SVM model as a practical approach to accurate and reliable classification of skin lesions, revealing high clinical potential. The paper's impressive experimental and statistical analyses demonstrate the power of the model and its ability to improve dermatological diagnostic procedures. © 2024 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced automated web scraping tool with proliferation of AI techniques

Enhanced automated web scraping tool with proliferation of A...

引用

2024 International Conference on Innovations and Challenges in Emerging Technologies, ICICET 2024

作者： Manikantam, Sadam Akhil, Patha Reddy, Komma Reddy Ashrith Prasada Reddy, G.S. Hariharan, Shanmugasundaram Kekreja, Vinay Vardhaman College of Engineering Department of Computer Science and Engineering Hyderabad India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9798350319019

The proliferation of web technologies and artificial intelligence (AI) has paved the way for advanced web applications capable of intelligent behavior. This paper explores the integration of AI into web development to create a dynamic system that personalizes user experience and automates web interactions. We present a novel web-based AI framework developed using contemporary programming languages and libraries, detailed in the accompanying GitHub repository. Our methodology focuses on the use of machine learning algorithms to process and analyze user data in real-time, facilitating adaptive responses by the web application. The system's architecture is designed for scalability and efficiency, ensuring quick deployment and low latency in web interactions. Results from initial testing show promising improvements in user engagement and satisfaction. The discussion highlights the potential of this framework in revolutionizing user interaction across various web platforms, suggesting a significant step toward more intelligent and responsive web services. The paper concludes by suggesting future enhancements, including the integration of more robust AI models and expanding the framework's adaptability to different web environments. The research provides a foundational step for web developers and AI researchers interested in the convergence of these fields. © 2024 IEEE.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Impact of Ant Colony Optimization on Optimal Routing for Vehicular Ad Hoc Networks 5

Impact of Ant Colony Optimization on Optimal Routing for Veh...

引用

5th IEEE International Conference on Communication, Computing and Industry 6.0, C2I6 2024

作者： Ramamoorthy, Raghu Velu, Anitha Appala Naidu, R China Asha Kumari, A. Angel Donny, F. Harish Kumar, M. The Oxford College of Engineering Department of Computer Science and Engineering Bengaluru India Sri Sairam College of Engineering Department of Electronics and Communication Engineering Bengaluru India Ramaiah Institute of Technology Department of Computer Science and Engineering Bengaluru India Vemana Institute of Technology Department of Artificial Intelligence & Machine Learning Bengaluru India

ISBN: (纸本)9798350379884

Using biologically inspired approaches has bonus advantages in offering optimal message distribution for vehicular ad hoc networks (VANETs). Bio-motivated approaches are motivated by the natural behavior of biological entities such as bees and insects. Ant colony optimization (ACO) is the optimal bio-inspired style, suitable for offering optimal routing in VANETs. The communication pattern of ACO and VANETs is similar, such as ants of ACO apply indirect communication among ants for the exchange of information, and VANETs require cooperative routing techniques for message exchange. The goal of the Bio-motivated approach is to attain proficient and accessible communication in a VANET, where vehicles turn as nodes and animatedly form a system to interchange information. In this context, the proposed work discusses the effectiveness and benefits of using a bio-inspired approach such as ACO for VANETs. To demonstrate ACO, a healthcare scenario is considered. In the healthcare system, efficient communication is required between emergency vehicles and hospitals to offer optimal treatment for patients. This work applies ACO to find the optimal path for sending an alarm to the nearest hospital from the emergency vehicle to arrange necessary things to treat patients. Using ACO increases the efficiency of the routing mechanism in all aspects such as throughput, overhead, data delivery, low latency, route discovery time, route repair time, convergence speed, and stagnation issue. © 2024 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Detection of Harmful Snakes Using YOLO Algorithm

引用

SN computer science 2024年第1期5卷 1-10页

作者： Naresh, E. Babu, J. Ananda Darshan, S. L. Shiva Murthy, S.V.N. Srinidhi, N.N. Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Information Science and Engineering Malnad College of Engineering Karnataka Malnad India Department of Computer Science and Engineering National Institute of Technology Warangal Warangal India Department of CSE SJC Institute of Technology Chikkaballapur India Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

The spotlight of our discussion here is on developing a model for detecting snakes present in the agricultural fields using cameras and machine learning algorithms. The idea is to construct a machine learning model to identify the snakes, which will be trained on a vast set of images of snakes. These images will be carefully selected to include the snake patterns, skin color of different species of snakes (extraction of the unique features). This is done to train the model properly to identify different types of snakes that the farmer encounters in the fields. Most famers are unaware and have a need for a way to detect these snakes so that they can either avoid them or get rid of them. Hence, this system can be implemented to prevent thousands of deaths and can help famers alleviate the repercussions of snake bites. Mistakes in recognizing potentially harmful animal species based only on visual cues are major contributors to the high death toll from venomous animal attacks. Since they spend so much time in the fields, where rice and wheat are cultivated, farmers are at a higher risk of being bitten by a snake than the general population. Because of their ignorance, illiterate farmers are more inclined to believe in superstitions, which can lead to their untimely deaths from snakebites despite medical intervention. Animals that would normally pose no threat to humans are responsible for the deaths of thousands of people every year because of environmental factors. However, because it is hard for humans to recognize these dangers, a new design paradigm has been developed to make it simpler. Researchers in the field of animal biology can use it to search for endangered species. Predators may enter gardens and green areas like tea and coffee plantations. There is not yet a plan in place to implement automated sorting for discovering distinctions. By applying the suggested framework to photographs of potentially dangerous animals, several factors useful for studying anim

关键词： Classifier training Convolutional neural network Farmer deaths Feature extraction Snake detection YOLO algorithm

来源：评论

学校读者我要写书评

暂无评论

Congestion Control Routing Scheme for WSN using AI Technologies 3

Congestion Control Routing Scheme for WSN using AI Technolog...

引用

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

作者： Basha, S.K. Mahaboob Gurumoorthi, E. Beulah, E. Mercy Kesavan, R. Kalaiselvan, S.A. Kumar, Lenin Tkr College of Engineering and Technology Department of Computer Science and Engineering Telangana India Cmr College of Engineering & Technology Department of Computer Science and Engineering Telangana India Vel Tech Multi Tech Dr. Rangarajan Dr.Sakunthala Engineering College Department of Computer Science and Engineering Chennai Avadi India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Rajalakshmi Engineering College Department of Artificial Intelligence and Machine Learning Chennai India Vignan Institute of Technology and Sciences Department of Electronics Communication and Engineering Telangana India

ISBN: (纸本)9798350369083

An essential part of wireless sensor networks (WSN) is managing congestion, which occurs when the amount of traffic exceeds the combined or individual capacities of the underlying channel. As a result, developing more advanced methods to prevent, detect, and alleviate congestion requires particular considerations. In order to obtain the highest throughput, these strategies must take into account the limited resources of the WSN. Dedicated congestion control strategies and routing protocols that help in congestion detection as well as management are two of the many methods that have been created in recent years. As a means of avoiding congestion, the sink node in the previous designs would reset the topology and reduce bulk traffic. In this article, we lay the groundwork for WSNs and AI, the latter of which will try to prevent congestion in WSNs from the get-go and the former of which will try to minimize the spread of impending congestion by rerouting traffic. An integral part of modern life, Artificial Intelligence (AI) allows us to create self-governing systems. It is possible to enhance performance and reliability by making use of several sophisticated AI approaches. Better network management and routing in WSN may be the outcome of studying the AI algorithm used by WSN, leading to a more dependable network. Here we'll take a look at several AI algorithms that have found their way into WSNs, and we'll talk about how these algorithms might help WSNs overcome their challenges and become more reliable and efficient. Additionally, artificial intelligence has often been disregarded in these networks because of limitations on data processing as well as power consumptions. Thanks to AI, WSN is now lightning fast, error-free, as well as effective in almost every way. Using AI methods in nodes of wireless sensors for congestion aware routes is the goal of this work. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Combining Fuzzy Logic and Reinforcement Learning for Resource Management in Edge Computing 5

Combining Fuzzy Logic and Reinforcement Learning for Resourc...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Prasath, S. Ram Selvi, M. Krishnan, R. Santhana Nithila, Ezhil E. Malar, P. Stella Rose Sankar, G. Ram Scad College of Engineering and Technology Computer Science and Engineering Cheranmahadevi India Rajarajeswari College of Engineering Computer Science and Engineering Bangalore India Scad College of Engineering and Technology Electronics and Communication Engineering Chranmahadevi India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Electronics and Communication Engineering Chennai Avadi India J.P. College of Engineering Electronics and Communication Engineering Thenkasi India Velammal College of Engineering and Technology Department of Computer Science and Engineering Madurai India

ISBN: (纸本)9798350379945

With the wide spread of Internet of Things (loT) devices, edge computing plays a decisive part in meeting the computational demands of loT applications. Efficient resource allocation in such networks is essential to ensure optimal utilization of resources and meet the quality of service (QoS) necessities of loT applications. This research addresses the challenge of dynamic resource allocation in edge computing networks for loT applications through a novel hybrid AI approach, 'FledegeRL.' By integrating fuzzy logic and reinforcement learning, FledegeRL aims to optimize resource utilization and enhance system performance. The proposed framework is evaluated through simulation analysis and compared with existing algorithms, including Q-Iearning, Fuzzy Logic Control, and Ant Colony Optimization, using metrics such as resource allocation accuracy, average throughput, and network overhead. The results demonstrate that FledegeRL consistently outperforms these algorithms, achieving higher accuracy, greater throughput, and lower network overhead. This highlights the potential of FledegeRL as an effective solution for dynamic resource allocation in edge computing environments. © 2024 IEEE.

关键词： Quality of service

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：