检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2872-2883页

作者： Bhardwaj, Nishit Pal, Anupriya Bhumika Das, Debasis Indian Institute of Technology Jodhpur Department of Computer Science and Engineering Rajasthan 343020 India Samsung Semiconductor India Research Karnataka560048 India Verint Systems Karnataka560005 India

Traffic accidents are common urban events that pose significant risks to human safety, traffic management, and economic stability;consequently, the research community is paying increasing attention toward accident risk prediction. However, accident risk prediction is a challenging problem because accident occurrences are sparse and influenced by multiple contextual factors (e.g., POI, road structure, road type, hour of the day, and month). Therefore, in this article, we propose a novel architecture named Topographic-Weighted Context Category (TWCCnet) that adapts heterogeneous contextual category weights based on spatial-temporal correlations across sectors. Specifically, the framework consists of two parallel components: one uses convolution and stacked bidirectional gated recurrent unit (Bi-GRU) to capture spatial-temporal relationships between neighborhood sectors, while the other uses multiple graph convolution network (GCN) over resemblance graphs to capture spatial-temporal relationships between semantic sectors. At last, temporal attention is utilized on top of parallel components to learn important spatiotemporal features that have a substantial impact on traffic accidents. The extensive experiments on two publicly available citywide datasets, i.e., New York City and Chicago demonstrate the effectiveness of the proposed approach and showed (7.21, 10.7) Root Mean Squared Error (RMSE), (34.09, 20.75) Mean Average Precision (MAP), and (0.19, 0.09) Recall approximately over both datasets, respectively, outperforming baseline as well as state-of-the-art models. © 2020 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Farmer's Crop Welfare System 15

Farmer's Crop Welfare System

引用

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

作者： Dhamodhar, G. Krishna, B. Vamsi Reddy, D. Sampath Reddy, A. Sameer Amutha, S. Ganesan, Kothai Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Tamilnadu Virudhnagar India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore Dist. Tamil Nadu India

ISBN: (纸本)9798331300579

The "Farmer's Crop Welfare System" is a technology that uses advanced data analytics and artificial intelligence to improve crop management and yield. It combines crop prediction, disease detection, and fertilizer recommendation. Crop prediction uses historical and real- time data, while disease detection uses image recognition and deep learning to identify early signs of diseases, promoting sustainable farming practices. © Grenze Scientific Society, 2024.

关键词： Livestock

来源：评论

学校读者我要写书评

暂无评论

Web-plugin to Detect Clickbait in News Articles using RNN and LSTM 5

Web-plugin to Detect Clickbait in News Articles using RNN an...

引用

5th International Conference on Inventive research in Computing Applications, ICIRCA 2023

作者： Krishneth, A. Dharaneesh, J.D. Jisnu, S. Sivaganesan, D. Psg Institute of Technology and Applied Research Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350321425

'Clickbaits' are either false or misleading headlines that aim to attract users' attention and entice them to click on a link or a news article that isn't really interesting as the title makes it up to be. A clickbait title can degrade the user experience and spread disinformation or misinformation on the Internet. In this study, a novel approach for Clickbait detection in news articles using machine learning technique of Recurrent Neural Network and Long-Short Term Memory is proposed. The clickbait detection process takes place in two distinct steps, first to identify the headlines in a website using a web plug-in, these headlines are then fed into a machine learning model which can predict if the headline is a clickbait or not. This a binary classification problem where the model is trying to predict which of the two categories the input belongs to. The algorithm is put into action using a web plugin which is triggered when popular news websites are visited and fetch the headlines using DOM method, the headlines are then sent to the server for prediction upon which the headlines get marked either red or green which indicates the headlines to be either clickbait or not respectively which, this makes the user aware if a headlineis clickbait or not with just a glance. The result obtained by the above method is an improvement over the existing methods and the user interface provided by the web plugin removes any manual labor from the user side and offers an engaging yetsimplistic user experience. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Where to Turn: Road Fork Detection in Sparse 3D Point Cloud 3rd

Where to Turn: Road Fork Detection in Sparse 3D Point Clou...

引用

3rd International Conference on Autonomous Unmanned Systems, ICAUS 2023

作者： Hu, Di Zhang, Kai Zhong, Yipan Xu, Jiachen Yuan, Xia Zhao, Chunxia School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Research Institute of Intelligence Southwest Research Institute of Information Control Chengdu611700 China

ISBN: (纸本)9789819711024

Intersection detection plays a crucial role in localizing and planning the path of autonomous vehicles in urban environments. This paper presents a novel approach, PVWO, for adaptive intersection detection in autonomous vehicles equipped with 3D LiDAR. Firstly, the algorithm removes ground and obstacles effectively, and eliminates noise points. Secondly, a polyarticular viewpoints beam model is applied to detect the type and location of intersections. Thirdly, a linear feature extraction approach in a rolling window is proposed to detect road width and optimize key parameters, enhancing model robustness across different scenes. Compared to parallel intersection detection algorithms, our method exhibits excellent performance under diverse road conditions. Experiments in sparse point clouds show an average precision exceeding 89% and an average processing time of approximately 88 ms/frame. These results demonstrate that our method can accurately detect intersections in real-time, across various road structures. © Beijing HIWING Scientific and Technological Information institute 2024.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Home Automation with Webserver Deployment with Raspberry Pi Pico 2

Home Automation with Webserver Deployment with Raspberry Pi ...

引用

2nd International Conference on Automation, Computing and Renewable Systems, ICACRS 2023

作者： Shabariram, C.P. Venkateshwaran, M. Abinesh, R. Manoranjith, R. Department of Computer Science and Engineering PSG Institute of Technology and Applied Research Coimbatore India

ISBN: (纸本)9798350340235

Home Automation system with web server deployment is developed using Raspberry Pi Pico and micropython, which turns ON the lights based on the count of persons inside that particular room. The system uses Infrared Red (IR) sensor, which detects the heat radiation in the environment. This heat radiation is not constant as it changes due to the movement of people in the sensing environment. This change is used as a measure to detect the changes in the environment which allows us to perform a particular action for the event. The data is sent to node which sends the data to the webserver running in the Raspberry pi pico. Based on the result, the light is turned ON or OFF. © 2023 IEEE.

关键词： Home Automation Infrared sensor Micropython Raspberry Pi Pico Webserver

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based AI Solutions for Personal Finance Management

Cloud-Based AI Solutions for Personal Finance Management

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Chhabra, Gurpreet Kaur Mishra, Ashutosh Kumar Tyagi, Varsha Mani, Chandra Tyagi, Vani Sagar, Pramod Kumar Management Education and Research Institute Department of Management Delhi India Srm Business School Department of Management UP Lucknow India Raj Kumar Goel Institute of Technology Computer Science & Engineering UP Ghaziabad India Mangalmay Institute of Engineering & Technology Computer Science & Engineering Greater Noida India

ISBN: (纸本)9798331508685

Cloud-based AI answers for private finance control are out-of-the-field tools that leverage synthetic intelligence and cloud computing technologies to manage people's money higher. In this article, I have described various solutions with features ranging from budgeting to personalized financial planning and investment suggestions. Utilizing superior system learning algorithms and cloud-based AI solutions can help understand an individual's fiscal information, including expenses, profits, or savings transactions, for generating personalized insights and advice. This lets people learn about their spending habits and make more informed financial choices. Through the power of the cloud, these solutions can securely store and access financial data from multiple devices, which helps individuals, manage their finances on the go easily. It also enables the client to get real-time updates and notifications, which offers him more comprehensive knowledge regarding his existing financial scenario. These offerings also come with more automation features like reminders to pay payments and computerized enough transfers for a price range, keeping customers from spending further effort and time on their funds. They also offer financial advisors, tax planning tools, and wealth management. © 2025 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Online Legal Literacy Platform 1

Online Legal Literacy Platform

引用

1st International Conference on Intelligent Technologies for Sustainable Electric and Communications Systems, iTech SECOM 2023

作者： Kala, I. Hariharan, K. Kavisri, S. Kaviyarasu, D. Psg Institute of Technology and Applied Research Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350371185

The Motor Vehicle Act is a complex legal framework that regulates various aspects of motor vehicle usage in India. However, many individuals lack knowledge and understanding of the Act, which can lead to unsafe driving practices, non-compliance with regulations, and legal violations. Furthermore, the Act is subject to frequent amendments, making it challenging for individuals to stay up to date on the latest regulations. To address these issues, this project proposes an Online Legal Information Platform for the Motor Vehicle Act. The platform utilizes advanced technologies such as BERT fine-tuning and natural language processing techniques to match user input scenarios with relevant sections of the Act. Users can input their scenarios and the platform suggests the ideal law that can be utilized in the given situation. The system displays matching laws with their title and description and generates a summary for the selected law to facilitate easy comprehension. Additionally, voice-to-text feature is incorporated in order to assist people with visual impairments. The platform aims to bridge the gap between legal language and everyday usage, promoting better compliance with road safety laws. The system will be user-friendly and accessible to individuals with limited legal knowledge, making it easier for them to navigate the legal system. Future work includes expanding the platform to include other regional languages as well to increase its availability to people all around the nation. © 2023 IEEE.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Fusion and Decomposition Network for Single Image Deraining

引用

IEEE Transactions on Image Processing 2024年 33卷 191-204页

作者： Wang, Qiong Jiang, Kui Wang, Zheng Ren, Wenqi Zhang, Jianhui Lin, Chia-Wen Wuhan University National Engineering Research Center for Multimedia Software School of Computer Science Wuhan430072 China Sun Yat-sen University School of Cyber Science and Technology Guangzhou510275 China Hangzhou Dianzi University College of Computer Science and Technology Hangzhou310018 China National Tsing Hua University Department of Electrical Engineering The Institute of Communications Engineering Hsinchu30013 Taiwan

Convolutional neural networks (CNNs) and self-attention (SA) have demonstrated remarkable success in low-level vision tasks, such as image super-resolution, deraining, and dehazing. The former excels in acquiring local connections with translation equivariance, while the latter is better at capturing long-range dependencies. However, both CNNs and Transformers suffer from individual limitations, such as limited receptive field and weak diversity representation of CNNs during low efficiency and weak local relation learning of SA. To this end, we propose a multi-scale fusion and decomposition network (MFDNet) for rain perturbation removal, which unifies the merits of these two architectures while maintaining both effectiveness and efficiency. To achieve the decomposition and association of rain and rain-free features, we introduce an asymmetrical scheme designed as a dual-path mutual representation network that enables iterative refinement. Additionally, we incorporate high-efficiency convolutions throughout the network and use resolution rescaling to balance computational complexity with performance. Comprehensive evaluations show that the proposed approach outperforms most of the latest SOTA deraining methods and is versatile and robust in various image restoration tasks, including underwater image enhancement, image dehazing, and low-light image enhancement. The source codes and pretrained models are available at https://***/qwangg/MFDNet. © 1992-2012 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Fake Product Identification using Blockchain 14

Fake Product Identification using Blockchain

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Hemkiran, S. Prakash Ramanathan, R.M. War, Mohammad Mudasir Aadhithiyan, K.S. Psg Institute of Technology and Applied Research Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350335095

Manufacture and sale of counterfeit goods has been plaguing several business sectors for many years. The production of counterfeit goods are increasing, this has an impact on the sales and earnings of the businesses. By stifling revenues, economic growth, and consumer health, it has an impact on governments, global trade, businesses, and consumers. The current technology used for combating counterfeit goods rely on a centralised authority. Issues with this design include single point processing, failure, and storage. Blockchain technology has can be used as an alternative to address all these issues for these *** code can be used along with a blockchain hash code to uniquely identify every single product that ever enters the supply chain, hence no fake product can flood the supply chain. Ethereum blockchain is utilized and smart contracts are deployed to store the data about each and every product. Each products whole history can be tracked by using its QR code. © 2023 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Toddler Activity Analysis Using Machine Learning

Toddler Activity Analysis Using Machine Learning

引用

2023 International Conference on Intelligent Systems for Communication, IoT and Security, ICISCoIS 2023

作者： Kala, I. Bhuvaneswari, P. Dharun, R. Dharshini, S. PSG Institute of Technology and Applied Research Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350335835

Toddler activity recognition aims in finding out the activities of toddler and also toddlers based on the video captured by camera. The purpose of activity recognition is to monitor a new employee of the company (maybe a software or even a restaurant) whether employees are working properly or do we need to give more training. This system can also be used by the parents to monitor the activity of the kids who are alone at home. This system can also be implemented in hospitals to monitor the patients and to check their improvement. Toddler activity recognition system is developed using CNN and LSTM. To predict the activity the path of the video file is given as input. The predicted result by the model is checked for accuracy. To make the result available for the end user (who needs to monitor the activity) and can access the result through two ways. In the First method user can directly view on the system where the model is predicting the result. In the second method user is out of station, so the predicted result will be updated on the cloud on fixed time intervals and user can view the result from the working place itself. © 2023 IEEE.

关键词： Personnel training

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：