检索结果-内蒙古大学图书馆

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Yuvaraj, K. Yuvaraj, S. Dhabliya, Dharmesh Rengarajan, A. Jain, Narendra Kumar Agrawal, Trapty Karpagam Academy of Higher Education Department of Computer Science Coimbatore India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai India Vishwakarma Institute of Information Technology Department of Information Technology Maharashtra Pune India Department of Computer Science and Information Technology Karnataka Bangalore India Vivekananda Global University Department of Civil Engineering Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350319125

With the growing quantity of massive statistics, the need to correctly get entry to, mine, and analyse it has become ever more urgent. One approach to this project is to apply artificial intelligence (AI) methods to enhance the overall performance of massive information get entry to. AI strategies, such as neural networks and choice bushes, may be used to clear out huge quantities of information quick and as it should be. additionally, AI strategies may be tailor-made to precise applications, unlocking extra ability for progressed performance. This research will investigate the capacity of the usage of AI to enhance the overall performance of huge information get entry to. exclusive AI techniques might be tested and in comparison across various situations, to identify the handiest method. in the end, the blessings and downsides of using AI in large statistics get entry to might be mentioned, and guidelines on high-quality practices could be furnished. © 2023 IEEE.

关键词： approach blessings enhance precise unlocking

来源：评论

学校读者我要写书评

暂无评论

LiDAR Image-Based Earth Carbon Emission Analysis and Its Impact on Public Health: A Machine Learning Model

引用

Remote Sensing in Earth Systems Sciences 2025年第2期8卷 455-464页

作者： Meghana, S. Padmaja, Dhyaram Lakshmi Gundu, Krishna Sriharsha Kudari, Rajeev Somasekar, J. Chandran, Likha Department of Computer Science Engineering Neil Gogte Institute of Technology Hyderabad India Information Technology Anurag University Hyderabad India Enterprise Technology Arizona State University Tempe AZ United States Department of CSE Koneru Lakshmaiah Education Foundation Green Fields Vaddeswaram Andhra Pradesh Guntur 522502 India Department of Computer Science and Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Karnataka Bengaluru 562112 India Department of Chemistry VNR Vignana Jyothi Institute of Engineering and Technology Hyderabad India

Afforestation is a practical way to absorb carbon dioxide in contemporary context of carbon neutrality. In the assessment of forest emission reduction projects, stock can be utilized as a crucial indicator of biomass and carbon storage estimation in addition to serving as an economic value index for forest wood resources. We suggest a framework and technique for data-driven machine learning that uses satellite remote sensing and aerial LiDAR to forecast plantation stock. This research proposes a novel method in LiDAR image-based carbon emission analysis with their health impact using a machine learning method. Here, the input is collected as LiDAR image-based healthcare data for processing and smoothening. Then, this image has been segmented and classified using convolutional contour graph cut equalization with VGG-net transfer encoder Gaussian neural networks. The experimental analysis for LiDAR image dataset has been carried out for analysis of carbon emission, and healthcare data analysis has been carried out in terms of training accuracy, average precision, recall, F-1 score, and AUC. The proposed technique attained a training accuracy of 98%, an average precision of 93%, a recall of 96%, an F-1 score of 92%, and an AUC of 94%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Carbon emission analysis Health impact LiDAR image Machine learning model Transfer encoder

来源：评论

学校读者我要写书评

暂无评论

Drone-Based Intelligent System for Social Distancing Compliance Using YOLOv5 and YOLOv6 with Euclidean Distance Metric

引用

SN computer Science 2024年第8期5卷 972页

作者： Parkavi, A. Alex, Sini Anna Pushpalatha, M.N. Shukla, Prashant Kumar Pandey, Ankur Sharma, Sachin Department of Computer Science and Engineering M S Ramaiah Institute of Technology Bangalore India Department of Computer Science and Engineering (AI and ML) M S Ramaiah Institute of Technology Bangalore India Department of Information Science and Engineering M S Ramaiah Institute of Technology Bangalore India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram Guntur 522302 India Department of Computer Science and Engineering Manipal University Jaipur Rajasthan Jaipur India Manav Rachna International Institute of Research and Studies Faridabad India

The COVID-19 pandemic forced rigorous social distancing measures to be put in place to halt the virus’s spread;compliance was extremely difficult. In response, we have designed a highly advanced intelligent drone system that maintains and controls distance measures following social distance principles through advanced machine learning skills. This paper describes an intelligent monitoring and compliance system in public places using drone technology with a focus on social distance requirements. Boosting the efficiency of human detection in real-time video streams acquired by drones, our solution employs the You Only Look Once version 5 (YOLOv5) and YOLO version 6 (YOLOv6) object detection algorithms which are the most potent computer vision tools today. The distances between the recognized individuals are computed based on the Euclidean distance measurement to distinguish cases of nonadherence to social distance measures. Our technique integrates the recently developed deep learning models with aerial imagery and monitoring to make it easily scalable for population health surveillance. Thus, we prove impressively that the underlying inventive method works well in different environmental conditions and can potentially contribute to people’s safety in the event of a pandemic. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： COVID-19 Drones Euclidean distance metric Social distancing YOLOv6

来源：评论

学校读者我要写书评

暂无评论

Defending Against Digital Threats: Machine Learning Techniques for Cyber Persecution Detection 5

Defending Against Digital Threats: Machine Learning Techniqu...

引用

5th International Conference on Artificial Intelligence and Data Sciences, AiDAS 2024

作者： Chinnasamy, P. Ayyasamy, Ramesh Kumar Krishnan, Kesavan Kumar, Vijay Jalil, Norazira Binti A Kiran, Ajmeera School of Computing Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamilnadu India Faculty of Information and Communication Technology Kampar Malaysia Universiti Malaya Faculty of Computer Science and Information Technology Kuala Lumpur Malaysia Graphic Era Hill University Department of Physics Dehardun India Graphic Era Deemed to be University Dehradun India Mlr Institute of Technology Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798331528553

Cyber persecution has become a widespread problem on the social media. It has resulted in omissions such as suicide and sadness. Content regulation on social media sites is becoming increasingly important. The following work employs natural language processing and Machine Learning techniques to construct a cyber harassment detection model utilizing data from cyberbullying, hate speech tweets from Twitter, and personal assaults from Wikipedia. The optimal approach is investigated by two feature extraction methods and six classifiers (SVM, Random Forest, XGBoost, MLP, and Logistic Regression). This study summarizes the general procedure for detecting cyberbullying and, more crucially, the technique. During experimentation, SVM, Random Forest, and Logistic Regression performed well with an average of 90%. Our model has been created to detect offensive comments on social media websites. © 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

Developing Novel Approaches for Implementing Machine Learning in Medicine 3

Developing Novel Approaches for Implementing Machine Learnin...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Mercilin Raajini, X. Inamdar, Fatima M. Kannagi, A. Agrawal, Trapty Vishnoi, Manish Yuvaraj, K. Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai India Vishwakarma Institute of Information Technology Department of Information Technology Pune India Department of Computer Science and Information Technology Karnataka Bangalore India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Civil Engineering Jaipur India Karpagam Academy of Higher Education Department of Computer Science Coimbatore India

ISBN: (纸本)9798350319125

Recent advances in computing hardware and software program have enabled the improvement and deployment of state-of-the-art system getting to know (ML) models in diverse scientific domain names. ML has the capacity to leverage large volumes of affected person facts to generate insights and actionable answers, allowing unique prognosis and treatment choices. In spite of promising ability, enforcing ML in medicine has been hard because of numerous realistic problems, inclusive of records bias and series technology, lack of robust evaluation frameworks, and ethical and privacy worries. To cope with these demanding situations, researchers have begun to expand novel methods to allow green and powerful ML deployment in medical practice. these tactics contain leveraging novel records resources such as wearable's and glide cytometry, the use of federated studying algorithms for privacy-preserving version development, and incorporating multi-level evaluation metrics which include explain ability and fairness. Together, these novel methods provide a roadmap for correctly and safely deploying ML in medication to higher help and enhance patient care. © 2023 IEEE.

关键词： computing generate improvement medication patient

来源：评论

学校读者我要写书评

暂无评论

IndoCL: Benchmarking Indonesian Language Development Assessment

IndoCL: Benchmarking Indonesian Language Development Assessm...

引用

2024 Findings of the Association for Computational Linguistics, EMNLP 2024

作者： Lin, Nankai Wu, Hongyan Zheng, Weixiong Liao, Xingming Jiang, Shengyi Yang, Aimin Xiao, Lixian School of Computer Science and Technology Guangdong University of Technology China College of Computer National University of Defense Technology China School of Information Technology and Engineering Guangzhou College of Commerce China School of Computer Science and Intelligence Education Lingnan Normal University China Faculty of Asian Languages and Cultures Guangdong University of Foreign Studies China

ISBN: (纸本)9798891761681

Recently, the field of language acquisition (LA) has significantly benefited from natural language processing technologies. A crucial task in LA involves tracking the evolution of language learners' competence, namely language development assessment (LDA). However, the majority of LDA research focuses on high-resource languages, with limited attention directed toward low-resource languages. Moreover, existing methodologies primarily depend on linguistic rules and language characteristics, with a limited exploration of exploiting pre-trained language models (PLMs) for LDA. In this paper, we construct the IndoCL corpus (Indonesian Corpus of L2 Learners), which comprises compositions written by undergraduate students majoring in Indonesian language. Moreover, we propose a model for LDA tasks, which automatically extracts language-independent features, relieving laborious computation and reliance on specific language. The proposed model uses sequential information attention and similarity representation learning to capture the differences and common information from the first-written and second-written essays, respectively. It has demonstrated remarkable performance on both our self-constructed corpus and publicly available corpora. Our work could serve as a novel benchmark for Indonesian LDA tasks. We also explore the feasibility of using existing large-scale language models (LLMs) for LDA tasks. The results show significant potential for improving LLM performance in LDA tasks. © 2024 Association for Computational Linguistics.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Advanced Text Matching for Improved information Capture and Retrieval 3

AI-Driven Advanced Text Matching for Improved Information Ca...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Agrawal, Trapty Kulhar, Kuldeep Singh Singh, K. Ranjith Indira, G. Shelke, Priya M. Kannagi, A. Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Civil Engineering Jaipur India Karpagam Academy of Higher Education Department of Computer Science Coimbatore India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electrical and Electronics Engineering Chennai India Vishwakarma Institute of Information Technology Department of Information Technology Pune India Department of Computer Science and Information Technology Karnataka Bangalore India

ISBN: (纸本)9798350319125

This paper presents an AI-pushed advanced text matching technique to improve facts capture and retrieval. The proposed approach makes use of deep getting to know and natural language processing algorithms to successfully compare texts and discover similarities and dissimilarities among them. The deep gaining knowledge of algorithm is trained on a textual content corpus that serves as enter statistics for the model. This corpus may be made from diverse styles of textual information depending at the goal of the assessment. To make certain accuracy, the model is outfitted with parameters consisting of word embedding, semantic similarity, and fuzzy string matching. Once skilled, the version is tested to discover false positives and fake negatives. Finally, the model is carried out to a hard and fast of statistics to quantify fits among texts and retrieve useful statistics. Consequences show a discount in false positives and a higher precision of the version in retrieving applicable statistics from given facts. © 2023 IEEE.

关键词： dissimilarities presents similarities statistics version

来源：评论

学校读者我要写书评

暂无评论

Correlation and Workload-Based Transaction Allocation Algorithm for Blockchain Sharding 22

Correlation and Workload-Based Transaction Allocation Algori...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Xiao, Guixia Samian, Normalia Binti Seah, Winston K. G. Hafez Bin Ninggal, Mohd Izuan Binti Hussin, Masnida Sahni, Jyoti Universiti Putra Malaysia Faculty of Computer Science and Information Technology Selangor Serdang Malaysia Changde Vocational Technical College Modern Education Technology Center Changde China Victoria University of Wellington School of Engineering and Computer Sciences Wellington New Zealand

ISBN: (纸本)9798331509712

Most existing transaction sharding technologies allocate transactions randomly or based on transaction addresses, leading to imbalanced workloads and high ratio of cross-shard transactions (CST). The uneven workload makes it impossible for blockchain to fully utilize resources for transaction processing, which degrades system throughput. CST incur additional overheads in communication, verification, and processing, increasing block confirmation latency. This paper proposes a blockchain sharding transaction allocation algorithm known as correlation and workload-based transaction allocation (CWTA) to address the above issues. CWTA regularly pumps a certain number of pending transactions from the transactions pool to establish a multiple-directed transaction graph (MDTG) and achieves faster allocation efficiency by quickly gathering the out-edges of each account based on MDTG. This process has successfully changed the distribution mode of transactions from one-by-one to group-by-group which depends on the correlation between the groups for current and upcoming workloads of each shard. CWTA has demonstrated its effectiveness through abundant transaction allocation results with 2-16 shards. Compared to similar existing work, CWTA can achieve a much more balanced transaction workload and less allocation time without increasing the CST ratio which denotes better scalability, and achieve better throughput. © 2024 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

A Sequential-based Deep Learning Model for Dry Beans Classification

A Sequential-based Deep Learning Model for Dry Beans Classif...

引用

2023 International Conference on Smart Computing and Application, ICSCA 2023

作者： Sujatha, R. Chatterjee, Jyotir Moy Rohith, A. Ramadan, Rabie A. Vellore Institute of Technology Software and Systems Engineering Vellore India Information Technology Lord Buddha Education Foundation Kathmandu Nepal Cairo University Computer Engineering Giza Egypt College of Computer Science and Engineering Hail University Hail Saudi Arabia

ISBN: (纸本)9798350347050

People take various types of cereals every day in their regular meals, but most people do not know their importance while consuming them. Each cereal has its benefit. One such cereal content is dry beans. Dry beans are a variety of beans that are produced in pods. These dry beans can be cooked and eaten, and it has numerous proteins and vitamins and are highly beneficial for our health. It also provides excellent immunity. Each bean has its characteristics, which can be identified with its unique features. These can be oval or kidney-shaped or even without a proper shape. According to their shape and features, they are classified separately. These nutrient-rich beans have to be classified based on their shapes. Human eyes sometimes may oversee or misclassify these tiny cereals for classification. This work involves the classification of 7 such dry bean varieties utilizing a deep learning context. The dataset utilized in this paper includes 13611 dry bean data for seven different UCI Machine learning repositories. In this work, we have taken seven different categorical labels: the dry bean varieties. The classification is done using deep learning techniques, and here we have utilized the Keras Sequential Algorithm for the classification. It is a supervised learning concept of machine learning used to predict two or more categorical labels. With the help of the deep learning approach, these dry beans are classified and obtained an accuracy of 94.88%. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Simulation of Message Injection Attacks on Control Area Networks 3

Simulation of Message Injection Attacks on Control Area Netw...

引用

3rd IEEE Mysore Sub Section International Conference, MysuruCon 2023

作者： Vanajakshi, J. Renuka, A. Adesh, N.D. Manipal Institute of Technology Manipal Academy of Higher Education Department of Computer Science and Engineering Karnataka Manipal India Manipal Institute of Technology Manipal Academy of Higher Education Department of Information and Communication Technology Karnataka Manipal India

ISBN: (纸本)9798350340358

The automobile industry is gradually incorporating new technologies into vehicles, making them increasingly connected, autonomous, and data-driven. It makes use of Control Area Network (CAN), a vital communication protocol for networking multiple Electronic Control Units (ECUs) within automobiles. Given its critical role in facilitating communication, CAN is vulnerable to a variety of cyber security threats. The objective of this work is to analyze the security elements of the CAN protocol while simulating attacks on CAN communication data to identify attack vectors targeting the CAN communication protocol and to preserve vehicle security. The proposed method involves analyzing and decoding CAN bus communication messages, which will aid in diagnostics, debugging, and security assessments by revealing insights into vehicle communication and behavior. This technique enables the vehicle to be secured with the required security measures, by investigating attack surfaces and attack vectors. As an effect, existing Python and CAN tools are being utilized to simulate message injection attacks and decode CAN messages in order to identify vulnerabilities, assess risks, and implement appropriate security solutions. The findings show that message injection simulation is carried out using Python and CAN tools, and CAN bus communication messages are captured. This results in disruption of the normal functioning of the vehicle. The captured data is inspected to decode and identify the components of the vehicle. Finally, an overview of best practices for countering cyber-Attacks is provided for the security of in-vehicle network communication. © 2023 IEEE.

关键词： Cybersecurity

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：