检索结果-内蒙古大学图书馆

International Conference on Dependable Systems and Their Applications (DSA)

作者： Tse-Chuan Hsu Dong-Meau Chang Department of Computer Science & Information Management Soochow University Taipei Taiwan School of Computer Science and Intelligence Education Lingnan Normal University China

ISBN: (数字)9798331532390

ISBN: (纸本)9798331532406

Based on computer vision and machine learning, accurate hand behavior and gesture recognition are crucial, especially for missing or incomplete hand models. Finger joint point prediction technology is of great value for applications such as virtual reality and human posture recognition. However, hand joint point prediction models, such as Google’s MediaPipe, perform well in full-finger models but are ineffective in missing-finger situations. Missing fingers are familiar in clinical medicine, rehabilitation facilities, and unique scenarios such as hand injuries or congenital hand deformities. Accurate prediction of hand joints is critical for hand rehabilitation, prosthetic design, and human motion analysis and inspires the development of related technologies. Since traditional prediction models rely on complete hand data, and missing fingers can make the hand structure irregular, the complexity of prediction increases. This study proposes an improved prediction model focusing on hand joint point prediction in the case of missing fingers, hoping to improve prediction accuracy and provide valuable reference for future applications and research. Among the research results, we successfully integrated the new training image model with MediaPipe, significantly improving missing fingers’ prediction accuracy.

关键词： Hands Training Solid modeling Adaptation models Accuracy Computational modeling Gesture recognition Virtual reality Predictive models Data models

来源：评论

学校读者我要写书评

暂无评论

Enhancing Video Anomaly Detection Using Spatio-Temporal Autoencoders and Convolutional LSTM Networks

引用

SN computer science 2024年第1期5卷 190页

作者： Almahadin, Ghayth Subburaj, Maheswari Hiari, Mohammad Sathasivam Singaram, Saranya Kolla, Bhanu Prakash Dadheech, Pankaj Vibhute, Amol D. Sengan, Sudhakar Department of Networks and Cybersecurity Faculty of Information Technology Al Ahliyya Amman University Country Amman Jordan School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai 600127 India Department of Networks and Cybersecurity Information Technology Al Ahliyya Amman University Amman Jordan Department Computing Technology School of Computing SRM Institute of Science and Technology Kattankulathur Campus Tamil Nadu Chennai 603203 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur 522302 India Department of Computer Science and Engineering Swami Keshvanand Institute of Technology Management and Gramothan (SKIT) Rajasthan Jaipur 302017 India Symbiosis Institute of Computer Studies and Research (SICSR) Symbiosis International (Deemed University) MH Pune 411016 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli 627152 India

Identifying suspicious activities or behaviors is essential in the domain of Anomaly Detection (AD). In crowded scenes, the presence of inter-object occlusions often complicates the detection of such behaviors. Therefore, developing a robust method capable of accurately detecting and locating anomalous activities within video sequences becomes crucial, especially in densely populated environments. This research initiative aims to address this challenge by proposing a novel approach focusing on AD behaviors in crowded settings. By leveraging a spatio-temporal method, the proposed approach harnesses the power of both spatial and temporal dimensions. This enables the method to effectively capture and analyze the intricate motion patterns and spatial information embedded within the continuous frames of video data. The objective is to create a comprehensive model that can efficiently detect and precisely locate anomalies within complex video sequences, specifically those featuring human crowds. The efficacy of the proposed model will be rigorously evaluated using a benchmark dataset encompassing diverse scenarios involving crowded environments. The dataset is designed to simulate real-world conditions where millions of video footage need to be continuously monitored in real time. The focus is on identifying anomalies, which might occur within short time frames, sometimes as brief as five minutes or even less. Given the challenges posed by the massive volume of data and the requirement for rapid AD, the research emphasizes the limitations of traditional Supervised Learning (SL) methods in this context. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Anomaly detection Autoencoders LSTM Machine learning Spatio-temporal features Suspicious activities

来源：评论

学校读者我要写书评

暂无评论

Ontogenetic shifts in leaf biomass allocation in crop plants

引用

National science Review 2024年第10期11卷 176-179页

作者： Renfei Chen Suping Xiao Chuancong Dong Shubin Xie Liang Zhang Fan Wu Chengyi Tu Quan-Xing Liu Shaopeng Wang ülo Niinemets Alan Hastings Karl J.Niklas Jianming Deng School of Life Science Shanxi Normal University School of Mathematics and Computer Science Shanxi Normal University State Key Laboratory of Herbage Improvement and Grassland Agro-Ecosystems College of Ecology Lanzhou University School of Economics and Management Zhejiang Sci-Tech University Department of Environmental Science Policy and Management University of California School of Mathematical Sciences Shanghai Jiao Tong University Institute of Ecology College of Urban and Environmental Science and Key Laboratory for Earth Surface Processes of the Ministry of Education Peking University Crop Science and Plant Biology Estonian University of Life Sciences Department of Environmental Science and Policy University of California Santa Fe Institute School of Integrative Plant Science Cornell University

Leaves are the primary photosynthetic organ of vascular land plants as they provide photosynthates that maintain plant growth and reproduction. The extent to which plants allocate biomass to their leaf construction strongly influences photosynthetic performance, net primary productivity [1] and thus ecosystem functions [2]. Consequently, biomass allocation patterns have been a central focus in ecology.

关键词： allocation leaf biomass crop ontogenetic plants shifts

来源：评论

学校读者我要写书评

暂无评论

Evaluating Factors Influencing University Ranking Based on QS Ranking 2023-2024 Using Machine Learning Algorithms

Evaluating Factors Influencing University Ranking Based on Q...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Sherin Hijazi Mahmoud Moshref Samer Mohammed Arqawi Department of Computer Science Palestine Technical University - Kadoorie Tulkarem Palestine Department of Computer Science Ministry of Education & Higher Education Tulkarem Palestine Department of Logistics Management Palestine Technical University - Kadoorie Tulkarem Palestine

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

This paper examines the use of machine learning algorithms to assess the factors influencing university rankings, with a focus on the QS World University Rankings for 2023-2024. The study employs multiple machine learning techniques, including Linear Regression, Multi-Layer Perceptron (MLP), Decision Trees, Random Forest, Gradient Boosted Trees, and H2O Deep Learning, to evaluate the relative importance of various ranking attributes. Key findings reveal that Gradient Boosted Trees and MLP models outperform other algorithms, achieving an R 2 of 0.978 and a Mean Absolute Percentage Error (MAPE) of 7.2% on test data. Academic Reputation, Citations per Faculty, and Sustainability emerged as the most significant factors, while attributes like Age Band and Size had minimal impact. These results provide actionable insights for universities aiming to enhance their global rankings. The study concludes that machine learning offers a robust framework for understanding and predicting university performance, enabling institutions to refine their strategies and improve their global competitiveness

关键词： Water Deep learning Machine learning algorithms Linear regression Data models Decision trees Sustainable development Random forests Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Advancements in Chatbot Technology for Enhanced Customer Support in Online Retail 9

Advancements in Chatbot Technology for Enhanced Customer Sup...

引用

9th International Conference on science, Technology, Engineering and Mathematics, ICONSTEM 2024

作者： Keerthi Kumar, N. Maheswari, K. Abinaya, A. Ramya, J. Ande, Pavan Kumar Ramaian, Christu Paul Bms Institute of Technology And Management Department of Mechanical Engineering Karnataka Bengaluru560064 India Cmr Technical Campus Department of Computer Science And Engineering Telangana Hyderabad501401 India Panimalar Engineering College Department of Computer Science And Engineering Tamil Nadu Chennai600123 India KoneruLakshmaiah Education Foundation Department OfComputer Science And Engineering Andhra Pradesh Guntur522502 India Hindustan Institute of Technology And Science Department of Automobile Engineering Tamil Nadu Chennai603103 India

ISBN: (纸本)9798350365092

In order to improve customer service and boost sales, this paper describes the creation of an ecommerce sales chatbot. In order to grasp natural language, the system employs machine learning. It is based on a chatbot that is modular. Framework. There are several parts to the system. A web-based framework for natural language teaching comes first. Chat bots are employed in a variety of industries, including e-commerce, healthcare, and education. The objective of this venture is to make Hebron, an online chatbot for the Contract College People group Shopping center. Python and Respond are both utilized in the chatbot's creation. Conventional customer service chatbots frequently copy human discussion, yet they have serious protection and data adaptability issues. Here, we present SuperAgent, a customer support chatbot that utilizes broad and promptly open internet business data. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

A More Efficient Way to Control Traffic Lights Through AI-Led Smart City management 3

A More Efficient Way to Control Traffic Lights Through AI-Le...

引用

3rd International Conference on Technological Advancements in Computational sciences, ICTACS 2023

作者： Choudhary, Shilpa Ali, Shaik Shabbir Babu, N. Ramesh Sharma, Harshita Kaliraman, Bhawna Dhankhar, Yash Hyderabad India Koneru Lakshmaiah Education Foundation Department of Electronics and Communication Engineering Vaddeswaram India Koneru Lakshmaiah Education Foundation Department of Mathematics Vaddeswaram India Dpg Institute of Technology and Management Department of Computer Science and Engineering Gurugram India

ISBN: (纸本)9798350342338

Urban regions are nevertheless plagued by traffic congestion, which increases travel times, fuel use, and greenhouse gas emissions. To lessen traffic congestion and enhance the performance of traffic systems, effective traffic control is crucial. The ideal flow of traffic is not achieved by traditional traffic light control technologies, which are based on planned signal plans or fixed timings that do not adjust to real-time traffic circumstances. By dynamically changing signal timing based on real-time traffic data, artificial intelligence (AI) has emerged as a viable method to optimize traffic signal regulation. This paper suggests a real-time traffic signal timing optimization system that is powered by AI and leverages machine learning methods. This suggested work is a traffic light control system that uses artificial intelligence and offers a number of *** instance, a shorter trip distance, improved fuel economy, and lower pollutants. Additionally, the system is easily upgradeable with new data sources or algorithms and may be incorporated with current traffic management systems. It suggested using an artificial intelligence-based traffic light control system (TLCS) to greatly enhance traffic flow and relieve congestion in metropolitan areas. Real-time data and machine learning algorithms combined to enable dynamic and adaptive signal control, resulting in more effective traffic management and improved quality of life for city dwellers. This clarifies their potential to enhance urban transportation and lessen congestion. © 2023 IEEE.

关键词： Fog Haze OpenCv radars Sensors YOLOv3

来源：评论

学校读者我要写书评

暂无评论

Effective Side-Channel Attacks for Cryptographic Keys 15

Effective Side-Channel Attacks for Cryptographic Keys

引用

15th International Conference on Computing Communication and Networking technologies, ICCCNT 2024

作者： Nishanthi, R. Khurana, Shivam Mithun Kumar, S. Deshpande, Leena A. Thangarasu, N. Khanna, Lalit Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Chennai127 India Chitkara University Chitkara Centre for Research and Development Himachal Pradesh 174103 India School of Mangement - Ug Management Karnataka Bangalore India Vishwakarma Institute of Technology Department of Computer Engineering Pune India Karpagam Academy of Higher Education Department of Computer Science Coimbatore641021 India Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140417 India

ISBN: (纸本)9798350370249

This technical summary examines effective aspect-channel assaults for cryptographic keys. Facet-channel assaults involve acquiring cryptographic keys or other personal statistics by observing patterns in the target gadget's conduct or the environment it operates. Generally speaking, side-channel assaults awareness on measuring or analyzing the goal device's bodily or electrical traits, which include power consumption, electromagnetic radiation, or statistics transfers. Such techniques are normally used to acquire the keys used to encrypt or decrypt information on an at-ease gadget, as well as many other sensitive secrets. This technical summary affords an overview of the most commonplace types of facet-channel attacks, as well as how they can be averted and strategically mitigated. It highlights recent studies on the subject, including new strategies for attack resilience and the growing sophistication of attackers. © 2024 IEEE.

关键词： Consumption Cryptographic Decrypt Electrical Facet Measuring Sophistication Strategies

来源：评论

学校读者我要写书评

暂无评论

Innovative Trends in the Field of Modern Artificial Intelligence Methodology 15

Innovative Trends in the Field of Modern Artificial Intellig...

引用

15th International Scientific and Practical Conference on Environment. Technology. Resources, ETR 2024

作者： Yarovyi, Anatolii M. Yarovyi, Andrii A. Kizim, Svitlana S. Ozeranskyi, Volodymyr S. Department of Public Management and Administration Vinnytsia Mykhailo Kotsiubynskyi State Pedagogical University Vinnytsia Ukraine Department of Computer Sciences Vinnytsia National Technical University Vinnytsia Ukraine Department of Innovative and Information Technologies in Education Vinnytsia Mykhailo Kotsiubynskyi State Pedagogical University Vinnytsia Ukraine

ISBN: (纸本)9781713899570

The article justifies the necessity of introducing methodological innovations in the modern field of artificial intelligence (AI), which precede and actively determine technological innovations. The authors of the article analyse the existing AI conceptual structure and point out its insufficiency and introduce significant improvements, including the figurative component. This addition was not made arbitrarily but in accordance with the structure of human natural intelligence, where the rational (symbolic) is directly related to the figurative and interacts with it. The figurative is not identical to the rational (symbolic);there are significant differences in their epistemological content. This difference results from the epistemological differences in their basic (primary) structures - the concept and the image. This, accordingly, means that the figurative (image) is always a reflection of the singular (individual), which is always brought to the sensory-specific, while the rational (concept) is always a reflection of the general (typical), which reaches the level of the systematic. This analysis of the peculiarities of the epistemological and methodological content of figurative and rational thinking becomes important not only in terms of studying the essence of an individual's natural thinking. These features are of great methodological importance in the modeling of artificial intelligence, especially when the question is raised about the creation of a new generation of artificial intelligent systems. Considering all of the above, artificial intelligence combines rational (logical) and figurative components, with priority given to the figurative structure as more information-intensive and heuristically powerful. It is the figurative component of artificial intelligence that defines and ensures the object's multidimensional representation, while the rational component chooses one of the dimensions provided by the figurative one and fills it with logical content.

关键词： Rational functions

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Power of Big Data: A Comprehensive Analysis and Future Directions 6

Unleashing the Power of Big Data: A Comprehensive Analysis a...

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Sharma, Annu Kumar, Gaurav Farooq, Mansoor Gupta, Manish Kumar Raj, Saranya Rai, Ashok Kumar RajaRajeshwari College of Engineering Department of Computer Science & Application Karnataka Bengaluru India Indian Institute of Science Education and Research Bhopal Department of Computer Science & Engineering Madhya Pradesh Bhopal India University of Kashmir Department of Management Studies Jammu & Kashmir India Madan Mohan Malaviya University of Technology Department of Information Technology & Computer Application UP Gorakhpur India Dronacharya Group of Institutions Department of Data Science & Engineering Uttar Pradesh Greater Noida India Madan Mohan Malaviya University of Technology Department of Computer Science & Engineering UP Gorakhpur India

ISBN: (纸本)9798350304480

Big Data (BD) has emerged as a transformative force, offering unprecedented opportunities for organizations to extract valuable insights and drive informed decision-making. This research paper presents a comprehensive analysis of the current state of BD, explores its potential applications across industries, and outlines future directions for maximizing its benefits. This paper examines the key components of BD, including data collection, storage, processing, and analytics. It investigates the technologies and methodologies that enable efficient handling of large volumes of structured and unstructured data. Additionally, it explores the impact of cloud computing, artificial intelligence (AI), and the Internet of Things (IoT) on the growth and utilization of BD. Overall, this research paper provides a comprehensive analysis of BD, its current applications, challenges, and future directions. It serves as a valuable resource for researchers, practitioners, and policymakers seeking to unlock the full power of BD and harness its benefits across diverse domains. © 2023 IEEE.

关键词： Analytics artificial intelligence Big data Internet of Things Processing

来源：评论

学校读者我要写书评

暂无评论

Automated Classification of Diabetic Retinopathy Using Deep Learning Architecture 4th

Automated Classification of Diabetic Retinopathy Using Deep ...

引用

4th International Conference on Advanced Computational and Communication Paradigms, ICACCP 2023

作者： D’Souza, Noel Siddalingaswamy, P.C. Reddy, N. V. Subba Language Technologies Institute Carnegie Mellon University Pittsburgh United States Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal India

ISBN: (纸本)9789819942831

Diabetic Retinopathy (DR) is an eye disease that can lead to blindness. It is one of the leading causes of vision loss in the world. Early detection of DR is critical to prevent permanent vision loss. DR is diagnosed by a trained ophthalmologist. In many developing countries, access to ophthalmologists for regular screening is often difficult. Using Machine Learning to overcome the need for skilled personnel to diagnose DR is a viable alternative. To automate the diagnosis of DR, we preprocessed our images to obtain 6 channels before training a modified Inception-v3 model on retinal fundus images obtained from Kaggle. We then trained a second model, combining data from both eyes, obtained as outputs from Inception-v3 to diagnose the stage of DR. Using this architecture, we were able to obtain a Kappa score of 0.821 on the dataset provided by Kaggle. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Diagnosis

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：