检索结果-内蒙古大学图书馆

6th International Conference on Communications and Cyber-Physical Engineering, ICCCE 2023

作者： Krishna, J. Tejaswini, S. Viswa Sai Reddy, N. Susmitha, S. Sohail, S. Prasanna, G. Department of AI&ML AITS Rajampet India Department of Computer Science and Engineering AITS Rajampet India

ISBN: (纸本)9789819971367

Understanding digital media dishes is a fascinating issue, but it also involves a lot of challenge. The dish's complicated ingredient list presents a hurdle. Due to the growth of deep learning, a number of efficient tools can partially resolve the issue. The job of dish recognition in this work is thought about. Based on the EfficientNet architecture and transfer learning, a unique dish recognition algorithm is proposed. First, add a number of significant layers to the EfficientNet-B0. Next, employ transfer learning to retrain the model using the best parameters that were learned during the first pre-training on ImageNet on the UEH-VDR dataset, a fresh batch of dish pictures. The UEH-VDR dataset includes pictures of Vietnamese food gathered from a variety of sources. According to experimental findings, the suggested approach can identify a dish with an accuracy of 92.33%. Additionally, it performs better than models built on well-known Space Invariant Artificial Neural Networks (SIANN) like VGG and residual neural network. On the basis of the training data, a mobile application is also created to assist tourists who wish to learn about Vietnamese cuisine. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

AquaRescue: Intelligent Drowning Detection and Swift Rescue System Using Integrated Approach 4

AquaRescue: Intelligent Drowning Detection and Swift Rescue ...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Rakshitha Sowmya, P. Shettigar, Rashmitha Nishanth, N. Durgaprasad Kumar, Dhanush Department of Ai&ml Nitte574110 India Department of Computer Science and Engineering Nitte574110 India /CS East Mumbai400068 India

ISBN: (纸本)9798350387490

Drowning accidents, in pools continue to be a concern calling for creative solutions to improve safety standards. The research aims to establish a framework for identifying and saving drowning cases in pools. Cutting-edge technologies such as computer vision, Artificial Intelligence, and IoT are integrated into the system to quickly and precisely recognize incidents and trigger rescue operations. Utilizing cameras and advanced algorithms like YOLO v3 and CNN, the system continuously observes the pool environment. By assessing people's movements and locations in the water, it accurately detects drowning cases. Once an incident is identified, the system automatically starts rescue procedures by dispatching rescue tools and notifying lifeguards with alarms across the pool premises. Moreover, it enables emergency calls through GSM SIM900A module in case the lifeguard is not present nearby. This innovative detection and rescue system not only enhances swimmer safety but also reduces the workload on lifeguards, allowing them to react more effectively in emergencies. The ultimate goal of this system, driven by technological advancements, is to minimize drowning incidents in pools. The system's performance has been evaluated against other models like Faster R-CNN, YOLO v3, and SSD. YOLO v3 demonstrated superior accuracy of 90% with combined datasets (GF-1 & GF -2). © 2024 IEEE.

关键词： Guards (shields)

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Advancing Drowsiness Detection Using Head-Angle and Eye-Aspect Ratio 8

A Novel Approach to Advancing Drowsiness Detection Using Hea...

引用

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Shashidhar, V. Ahmed, Mueezuddin Razeena, M. Rajesh, K.S. Bharath, J. Bangalore India Rajarajeswari College of Engineering Department of Computer Science & Engineering Bangalore India Rajarajeswari College of Engineering Department of Ai&ml Bangalore India

ISBN: (纸本)9798331505462

Drowsiness is a significant risk factor for accidents, particularly in situations requiring sustained attention, such as driving or operating machinery. This research proposes an innovative methodology for detecting driver drowsiness using advanced computer vision algorithms and techniques. Our system employs a shapeshift predictor and face-tracking algorithms to monitor the driver's facial features and head movements. Specifically, it detects three distinct indicators of drowsiness: excessive head tilting to the right or left, significant drooping of the chin, and prolonged eye closure (defined as eyes remaining closed for more than 24 consecutive frames). When any of these conditions are met, an alarm is triggered, alerting the driver to their potentially hazardous state. The proposed system offers a robust and non-intrusive solution for real-time drowsiness monitoring, with potential applications in various fields where vigilance is critical for safety. © 2024 IEEE.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

Diffusion models for 3D generation: A survey

引用

Computational Visual Media 2025年第1期11卷 1-28页

作者： Chen Wang Hao-Yang Peng Ying-Tian Liu Jiatao Gu Shi-Min Hu Department of Computer and Information Science University of PennsylvaniaPhiladelphiaPennsylvania 19104USA Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China Machine Learning Research Apple AI/MLNew YorkUSA.E-mail:jiatao@***

Denoising diffusion models have demonstrated tremendous success in modeling data distributions and synthesizing high-quality *** the 2D image domain,they have become the state-of-the-art and are capable of generating photo-realistic images with high *** recently,researchers have begun to explore how to utilize diffusion models to generate 3D data,as doing so has more potential in real-world *** requires careful design choices in two key ways:identifying a suitable 3D representation and determining how to apply the diffusion *** this survey,we provide the first comprehensive review of diffusion models for manipulating 3D content,including 3D generation,reconstruction,and 3D-aware image *** classify existing methods into three major categories:2D space diffusion with pretrained models,2D space diffusion without pretrained models,and 3D space *** also summarize popular datasets used for 3D generation with diffusion *** with this survey,we maintain a repository https://***/cwchenwang/awesome-3d-diffusion to track the latest relevant papers and ***,we pose current challenges for diffusion models for 3D generation,and suggest future research directions.

关键词： diffusion models 3D generation generative models aiG

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient and Congestion Control Technique for IoT Enabled WSN for Video Routing Surveillance: A Survey 15

Energy Efficient and Congestion Control Technique for IoT En...

引用

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

作者： Prathibha, S.B. Supriya, M.C. Dept of computer science and engineering SSIT Sri Siddhartha Academy of Higher Education India Dept of DS and AI&ML SSIT Tumkur India

ISBN: (纸本)9798331300579

Cities all around the world have recently begun to build contemporary smart city infrastructure, which is typically only possible with the usage of cutting-edge *** smart city environments are made possible by intelligent video *** various angle cameras serve as smart sensors that gather visual information from the environment of smart cities and send it for additional visual *** are numerous ways to avoid network communication bottlenecks and enhance the routing *** the majority of the time, unknown attributes caused the network to become unstable and lower the Quality of *** using the right training model to anticipate the congestion properties, this can be *** research offered a unique prediction method by utilizing the matching identification of feature sets to address this *** Probabilistic Rapid March Searching (PRMS) algorithm can be used to do this. © Grenze Scientific Society, 2024.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Analysis on Detecting Cardiac Arrhythmia Using Advanced Technologies 8th

Analysis on Detecting Cardiac Arrhythmia Using Advanced Tech...

引用

8th International Conference on Information System Design and Intelligent Applications, ISDIA 2024

作者： Radhika, N. Sujatha, D. School of Computer Science & Engineering MRUH Telangana Hyderabad India CSE-AI&ML Department MRCET Telangana Hyderabad India Department of Computational Intelligence MRCET Telangana Hyderabad India

ISBN: (纸本)9789819786657

Essential features of the various cardiac diseases that affect the human heart are provided by the electrocardiogram (ECG). A significant portion of the diagnosis of heart illness comes from the categorization of arrhythmias. An arrhythmia is any alteration to the regular electrical impulse sequence. Conventional techniques for analyzing digital signals, machine learning, and the offshoots, including deep learning approaches are widely used for analyzing and classification of ECG signals and more importantly, for the timely diagnosis of cardiac disorders and arrhythmias. An extensive review of the literature regarding ECG analysis is presented in this document. Also address the computational barriers of machine learning techniques to wearable devices. The study started with a search for pertinent papers and then the gathered data was examined. Examining the assessed ECG features and the machine learning technique for identifying arrhythmias was the second step. The analysis shows that even though the MIT-BIH database requires a large amount of preprocessing work, it chose a sizable proportion of studies. We examine the substantial corpus of literature on pre-recorded ECG data, signal collection, ECG signal processing, and noise reduction, identifying ECG spectrographic states through function technology, classification of ECG signals, and relative perspectives among the examined modules. We reviewed the ultra-modern machine learning strategies for automated arrhythmia detection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Forecasting the Disease Using Discrete Deep Learning Algorithms

引用

SN computer science 2023年第4期4卷 356页

作者： Sri Nagesh, O. Laxmi Kanth, P. Raja Vikram, G. Ramakrishna Reddy, K. Department of CSE Vignan Institute of Technology and Science Hyderabad India Department of CSE (AI&ML) Vignan Institute of Technology and Science Hyderabad India

Predictive modelling is the foundation of the disease prediction system. Based on the symptoms that the client provides as input to the system, it forecasts the client’s illness. The system evaluates the client’s or patient’s reported symptoms as input and produces a likelihood of the disease or illness. Implementing the Decision Tree Classifier, RF Tree and Naive Bayes algorithm are used to predict diseases. The three algorithms determine the likelihood that the disease will manifest itself. Precision clinical information analysis aids in early disease discovery and patient consideration as a result of the significant information development in biomedical and medical services networks. Medical services businesses are one of the industries with the fastest growth rates. The medical fields have access to a wealth of data regarding patient characteristics, diagnoses, and drugs. Machine learning techniques are used in the medical care industry to transform this knowledge into useful examples and to forecast future trends. The machine learning (ml) sector has gained momentum in almost every area of analysis and, more recently, has developed into a reliable tool in the therapeutic field. The field of medical sciences has acquired more services for medical diagnosis and offers additional details about the patient’s medical background. New medications are constantly coming across clinical ventures. To achieve the great nature of administration, medical care organizations should provide better patient evaluation and care. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Artificial intelligence (ai) Decision tree ml Naïve bayes Quality of experience (QOE) Quality of service (QOS) Random forest

来源：评论

学校读者我要写书评

暂无评论

Agriculture Wastage Management System Using Android Application

Agriculture Wastage Management System Using Android Applicat...

引用

Soft Computing for Security Applications (ICSCSA), International Conference on

作者： P. M. Naidu M. Anjali K. Sri Vaishnavi S. Chandralekha K. Tejaswini Reddy Department of Computer Science and Engineering (AI&ML) Vignan Institute of Technology and Science

ISBN: (数字)9798331515720

ISBN: (纸本)9798331515737

While numerous Agri-tech start-ups primarily focus on supply chain optimization and farm yield management, there is a growing need to address the unexplored challenge of managing agricultural stubble left after grain segregation. This project seeks to develop a solution for automating the stubble collection process, its transportation to designated sites, sending notifications about pickup and delivery, and facilitating the tracking of stubble disposal in an eco-friendly manner. The proposed Android application is versatile and can be utilized by various stakeholders, including farmers, transportation services, and small-scale industries. The application consists of modules to the specific needs of each user group, facilitating seamless interaction and problem resolution. The Agriculture Waste Management System Android application represents an innovative solution to efficiently and sustainably manage agricultural wastage. This system addresses the unique requirements of farmers, transporters, and industries, creating an interconnected ecosystem for responsible handling of surplus agricultural produce. Users can register, manage agricultural wastage, vehicles, and receive messages, enabling efficient information and resource flow within the agricultural supply chain. By digitizing and streamlining wastage management processes, this project aims to minimize waste, improve collaboration, and contribute to a more sustainable and interconnected agriculture. The Agriculture Waste Management System is not just a technological innovation but also a catalyst for positive change, promoting a greener, more efficient, and sustainable future for agriculture.

关键词： Waste management Technological innovation Supply chains Transportation Agriculture Registers Stakeholders Security Machinery Optimization

来源：评论

学校读者我要写书评

暂无评论

Exploring Vision-Based Models Using Kolmogorov-Arnold Networks: A Comparative Study

Exploring Vision-Based Models Using Kolmogorov-Arnold Networ...

引用

Advanced Computing Technologies (ICoACT), International Conference on

作者： Priyansh Gupta NS Pushkar Adit Acharya Aditya Hriday Rath Priyansh Surana Sucheta R Shinganmakki Computer Science (AI&ML) PES University Bengaluru India

ISBN: (数字)9798331509859

ISBN: (纸本)9798331509866

This study aims to integrate Kolmogorov Arnold Networks with vision based deep learning tasks. We hope to provide a comparative analysis between vision based deep learning models implemented using traditional methods and using Kolmogorov Arnold Networks. We have attempted this task specifically for two models: Image Classification and Image captioning. Our goal is to create these alternative KAN models and determine if they stand as a viable alternative. Our findings shed light on the scenarios where KAN's are applicable and adds to their capability in processing image data compared to pre-existing models further highlighting their value as an addition to the deep learning toolkit.

关键词： Training Adaptation models Accuracy Computational modeling Transfer learning Data models Natural language processing Standards Knowledge transfer Image classification

来源：评论

学校读者我要写书评

暂无评论

Enhancing Healthcare Data Security through Blockchain-Enhanced IDPS and Multi-Layered Firewall System

Enhancing Healthcare Data Security through Blockchain-Enhanc...

引用

Advancement in Technology (ICONAT), International Conference for

作者： Vishnu Kurnala Department of Computer Science and Engineering(AI&ML) Vardhaman College of Engineering

ISBN: (数字)9798350354171

ISBN: (纸本)9798350354188

This paper introduces a novel security framework to fortify healthcare data against cyber threats, incorporating blockchain technology and ledger tokenization within an integrated Intrusion Detection and Protection System (IDPS). Faced with escalating cybersecurity challenges, our approach merges traditional protection mechanisms with cutting-edge technologies to offer unparalleled data integrity and security. By leveraging blockchain for immutable data trails and enhancing IDPS with advanced machine learning techniques, our solution provides a robust defense against a range of cyber threats, including ransomware and data breaches. Extensive testing in simulated environments confirms the effectiveness of our system, suggesting it as a viable blueprint for future developments in healthcare cybersecurity. This study not only demonstrates the application of blockchain in enhancing data security but also sets the stage for further innovative practices in protecting sensitive healthcare information.

关键词： Firewalls (computing) Data integrity Intrusion detection Medical services Machine learning Tokenization Blockchains Ransomware Protection Testing

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：