检索结果-内蒙古大学图书馆

2023 International Conference on IoT, Communication and Automation Technology, ICICAT 2023

作者： Soni, Tanishq Gupta, Deepali Uppal, Mudita Gupta, Gifty Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Mm Engineering College Maharishi Markandeshwar Deemed to Be University Department of Computer Science Haryana Mullana-Ambala133207 India

ISBN: (纸本)9798350302820

The Internet of Things and Artificial Intelligence are two quickly expanding disciplines that are coming together to provide everyone with exciting new prospects and help automate every industry. The Internet of Things (IoT) refers to a network of interconnected devices, sensors, and software that can communicate with each other and exchange data over the internet. Artificial Intelligence (AI) and Machine Learning (ML) algorithms are being used to analyze and predict the output. The IoT has gained significant attention in recent years due to its potential to transform various industries, including healthcare, transportation, and agriculture. The convergence of IoT and AI is opening up new possibilities in a wide range of industries and applications. Some common bibliometric measures used in IoT research include citation counts, co-citation analysis, and bibliographic coupling. Citation counts measure the number of times an article has been cited by other articles, while co-citation analysis examines the frequency of the articles. Bibliometric analysis is carried out using the most powerful tool, VOSviewer, which is widely used in the academic community for bibliometric analysis and visualization. © 2023 ieee.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Big data visualization Analysis of Rice Seedling Quantity Based on UAV 4

Big Data Visualization Analysis of Rice Seedling Quantity Ba...

引用

4th International Conference on Computer, Big data and Artificial Intelligence, ICCBD+AI 2023

作者： Zhu, Wen Jing Dai, Shi Yuan Feng, Zhan Kang Duan, Kai Wen Shao, Chang Feng Wei, Xin Hua Jiangsu University School of Food and Biological Engineering China

ISBN: (纸本)9798350373233

In order to reduce the labor cost and improve the efficiency of rice basic seedling statistics, a statistical method based on computer vision was designed. This paper introduced big data of rice spectrum and mixed pixels, established a basic seedling number inversion model, and drew a basic seedling density map, which effectively improved the statistical accuracy of the basic seedling number of rice, saved the labor cost, and intuitively experienced the basic seedling density of rice, and guided the fertilization and nitrogen application work in the later stage according to the requirements. To achieve the purpose of saving fertilizer and increasing yield in the process of rice planting. In this study, two methods were used to retrieve the number of basic rice seedlings. The first method was based on the pixel binary classification of Normalized Vegetation index (NDVI), visible Vegetation index (VDVI) and green Normalized Vegetation Index (GNDVI), with the coefficient of determination (R2) being 0.782, 0.767 and 0.744, respectively. The root mean square errors (RMSE) were 12.44, 12.85 and 13.48, respectively. The other method is a hybrid pixel decomposition method based on fully constrained least squares with an R2 of 0.897 and an RMSE of 8.53. Comprehensive analysis shows that the seedling number inversion model based on hybrid pixel decomposition has higher accuracy © 2023 ieee.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

visualization of Semantic Differential Questionnaire: A Case Study of Sofas and Stylish Products

Visualization of Semantic Differential Questionnaire: A Case...

引用

Joint 8th International Conference on Digital Arts, Media and Technology and 6th ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, ECTI DAMT and NCON 2023

作者： Li, Mei Lee, Suiang-Shyan Chen, Chong-Wen Huang, Yi-Jheng National Tsing Hua University Dept. of Arts and Design Hsinchu Taiwan E-SOFT Corp. Dept. of Research & Development Taipei Taiwan National Kaohsiung University of Science and Technology Dept. of Cultural and Creative Industries Kaohsiung Taiwan Yuan Ze University Dept. of Computer Science and Engineering Taoyuan Taiwan

ISBN: (纸本)9798350396546

Nowadays, consumers not only pay attention to the price of a product, but also to its design and taste. Designers try to design products that meet the feelings and needs of consumers. However, how can these feelings be translated into design elements? In the field of Kansei engineering, researchers try to find the answer. When studying the relationship between consumers' feelings and design elements, the semantic differential method is often used in Kansei engineering. This study built a visualization system to visualize the data from a semantic differential questionnaire. Our survey targets were sofas and stylish products. We classified design elements into six factors: style, shape, material, color, value, and emotion. Each factor contained two sets of scales with polar adjectives, meaning opposing adjective words. We then collected 68 semantic differential questionnaires based on these factors. Finally, we displayed our results in six types of charts: two tree charts, a comprehensive analysis chart, a heatmap, a donut radar chart, a line chart, and a bar chart. When the results of the semantic differential questionnaire are visualized in these charts, it helps designers to see patterns in the data and makes it easier to interpret the results © 2023 ieee.

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

Implementation and visualization of Path Finding Algorithms 5

Implementation and Visualization of Path Finding Algorithms

引用

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

作者： Bhatt, Chandradeep Sharma, Ritabh Chauhan, Rahul Vishvakarma, Ashish Manchanda, Mahesh Sharma, Sanjay Graphic Era Hill University Cse Department Dehradun India Graphic Era Hill University Computer Science and Engineering Dehradun India Institute of Technology & Management Department of Information Technology Uttarakhand India Sgrrits Computer Application Department Dehradun India

ISBN: (纸本)9798350321425

Learning computer science is tough for many students, especially the ones who don't have any knowledge about it previously. Just like other subjects, there are a lot of things that needs to be learned in Computer science. It is often to seen that students find it difficult to cope up with the extreme change in their learning environment. There are many reasons why students struggle in this field. 'Algorithms' is one such topic that students find the most confusing. Lecturers on the other hand, also face problems in describing the algorithms to students. Based on several researches, Algorithm visualization has been to have a positive impact on learning abilities of student. It is already known that a person can learn much more efficiently if it sees what is going on and how is it done. Pathfinding refers to the exploration of an optimal and shortest route, commencing from a designated initial point and concluding at a specified destination. Within the realm of artificial intelligence, pathfinding algorithms are specifically crafted to navigate through graph structures. These algorithms find utility in diverse domains like navigation systems, computer gaming, network architectures, and beyond. Their performance can be degraded by numerous factors such as the length of the path, size of the problem, obstacles and its distribution, data structures used and much more. Whenever a new path-finding algorithm is suggested, its performance is often investigated on the basis of the observations made when that algorithm is used. Proper design and analysis play an important role in giving an explanatory and precise evaluation. By conducting analysis of multiple research works, this study systematically categorized them based on their provisional designs, methodologies, and logical approaches. Throughout this process, this work discovered minor imperfections in these algorithms, which were frequently observed as well. © 2023 ieee.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

ChartEye: A Deep Learning Framework for Chart Information Extraction

ChartEye: A Deep Learning Framework for Chart Information Ex...

引用

2023 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2023

作者： Mustafa, Osama Ali, Muhammad Khizer Moetesum, Momina Siddiqi, Imran Bahria University Center of Excellence in Ai Islamabad Pakistan School of Electrical Engineering and Computer Science Islamabad Pakistan Xynoptik Pty Limited MelbourneVIC Australia

ISBN: (纸本)9798350382204

The widespread use of charts and infographics as a means of data visualization in various domains has inspired recent research in automated chart understanding. However, information extraction from chart images is a complex multi-tasked process due to style variations and, as a consequence, it is challenging to design an end-to-end system. In this study, we propose a deep learning-based framework that provides a solution for key steps in the chart information extraction pipeline. The proposed framework utilizes hierarchal vision transformers for the tasks of chart-type and text-role classification, while YOLOv7 for text detection. The detected text is then enhanced using Super Resolution Generative Adversarial Networks to improve the recognition output of the OCR. Experimental results on a benchmark dataset show that our proposed framework achieves excellent performance at every stage with F1-scores of 0.97 for chart-type classification, 0.91 for text-role classification, and a mean Average Precision of 0.95 for text detection. © 2023 ieee.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Observing Human Mobility Internationally During COVID-19

引用

COMPUTER 2023年第3期56卷 59-69页

作者： Allcroft, Shane Metwaly, Mohammed Berg, Zachery Ghodgaonkar, Isha Bordwell, Fischer Zhao, Xinxin Liu, Xinglei Xu, Jiahao Chakraborty, Subhankar Banna, Vishnu Chinnakotla, Akhil Goel, Abhinav Tung, Caleb Kao, Gore Zakharov, Wei Shoham, David A. A. Thiruvathukal, George K. K. Lu, Yung-Hsiang Brown Univ BrainGate lab Providence RI 02912 USA Purdue Univ W Lafayette IN 47907 USA Zebra Technol Lincolnshire IL 60069 USA MITRE San Diego CA 92106 USA Columbia Univ Comp Sci New York NY 10027 USA Univ Southern Calif Appl Data Sci Los Angeles CA 90089 USA AMD W Lafayette IN 47906 USA Graviton Res Capital Gurgaon 122002 Haryana India Apple San Francisco CA 94108 USA Capital One New York NY 10011 USA NVIDIA Santa Clara CA 95051 USA Carnegie Mellon Univ Elect & Comp Engn Pittsburgh PA 15213 USA Purdue Univ Lib W Lafayette IN 47907 USA Sch Informat Studies W Lafayette IN 47907 USA East Tennessee State Univ Coll Publ Hlth Johnson City TN 37615 USA Loyola Univ Chicago Dept chairperson Chicago IL USA Purdue Univ Elect & Comp Engn Univ Fac Scholar W Lafayette IN 47907 USA Indian Inst Technol Madras Chennai India

This article analyzes visual data captured from five countries and three U.S. states to evaluate the effectiveness of lockdown policies for reducing the spread of COVID-19. The main challenge is the scale: nearly six ... 详细信息

关键词： COVID-19 visualization

来源：评论

学校读者我要写书评

暂无评论

Perception and Navigation in Autonomous Systems in the Era of Learning: A Survey

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第12期34卷 9604-9624页

作者： Tang, Yang Zhao, Chaoqiang Wang, Jianrui Zhang, Chongzhen Sun, Qiyu Zheng, Wei Xing Du, Wenli Qian, Feng Kurths, Juergen East China Univ Sci & Technol Key Lab Smart Mfg Energy Chem Proc Minist Educ Shanghai 200237 Peoples R China Shanghai AI Lab Shanghai 200030 Peoples R China Western Sydney Univ Sch Comp Data & Math Sci Sydney NSW 2751 Australia Potsdam Inst Climate Impact Res D-14473 Potsdam Germany Humboldt Univ Inst Phys D-12489 Berlin Germany

Autonomous systems possess the features of inferring their own state, understanding their surroundings, and performing autonomous navigation. With the applications of learning systems, like deep learning and reinforcement learning, the visual-based self-state estimation, environment perception, and navigation capabilities of autonomous systems have been efficiently addressed, and many new learning-based algorithms have surfaced with respect to autonomous visual perception and navigation. In this review, we focus on the applications of learning-based monocular approaches in ego-motion perception, environment perception, and navigation in autonomous systems, which is different from previous reviews that discussed traditional methods. First, we delineate the shortcomings of existing classical visual simultaneous localization and mapping (vSLAM) solutions, which demonstrate the necessity to integrate deep learning techniques. Second, we review the visual-based environmental perception and understanding methods based on deep learning, including deep learning-based monocular depth estimation, monocular ego-motion prediction, image enhancement, object detection, semantic segmentation, and their combinations with traditional vSLAM frameworks. Then, we focus on the visual navigation based on learning systems, mainly including reinforcement learning and deep reinforcement learning. Finally, we examine several challenges and promising directions discussed and concluded in related research of learning systems in the era of computer science and robotics.

关键词： Autonomous systems Navigation Learning systems Deep learning visualization Simultaneous localization and mapping Sensors Autonomous system deep learning environment perception learning systems navigation reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Research on the Construction of Logistics Industry Knowledge Graph Based on Big data 7

Research on the Construction of Logistics Industry Knowledge...

引用

7th Asian Conference on Artificial Intelligence Technology, ACAIT 2023

作者： Yang, Fan Li, Juntao Shen, Yiting Liu, Min Beijing Wuzi University Beijing Key Laboratory of Intelligent Logistics Systems Beijing China

ISBN: (纸本)9798350359145

With the development of the national economy and society, the domestic logistics industry has also experienced unprecedented prosperity, at the same time data volume is also constantly increasing. How to accurately analyze the multi-source and heterogeneous data in the logistics system is an important problem facing the logistics industry at present. The emergence of knowledge graph provides new ideas for these issues. The knowledge graph is a new method of knowledge representation, which has the advantages of precision, structure, and clarity. It can help reflect the relationship between industries and industrial chains, assist in event driven, important industrial events, and so on. For the logistics field, building a knowledge graph of the logistics industry can help logistics enterprises achieve intelligent supply chain management, including upstream and downstream management, knowledge sharing, intelligent logistics, etc. It can provide strong decision-making support for government agencies, industry associations, logistics enterprises, etc. This paper proposes an entity recognition method based on the BERT-BiLSTM-CRF model and a relationship extraction method based on the BERT pre-training model. Research shows that both the BERT-BiLSTM-CRF model and the BERT pre-training model have high practicality in entity recognition and relationship extraction, which can effectively extract relevant entities and relationships from text, and then use the Neo4j graph database to store triplets, and use the constructed logistics industry knowledge graph visualization system to display, providing strong support for the logistics industry brain, upstream and downstream situations of the supply chain, and important industry events. © 2023 ieee.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A data logger for educational purposes of a laboratory chemical reactor: an IoT approach

A Data logger for educational purposes of a laboratory chemi...

引用

2023 International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2023

作者： Lima, José Brito, Thadeu Ferreira, Olga Afonso, Maria J. Pinto, Vítor H. Carvalho, José A. Costa, Paulo Instituto Politécnico de Bragança Campus de Santa Apolónia Bragança5300-253 Portugal Campus de Santa Apolónia Bragança5300-253 Portugal Porto Portugal CeDRI SusTEC INESC-TEC Porto4200-465 Portugal SusTEC Portugal Instituto Politécnico de Bragança ESTiG Bragança5300-253 Portugal Arise Ece Dept. Portugal CeDRI SusTEC Portugal Feup INESC-TEC Portugal

ISBN: (纸本)9798350322972

This paper presents the development of an acquisition system and data logger from an existing set of three continuous stirred-tank reactors in series. The reactors are currently used in chemical engineering educational laboratories to perform kinetic and tracer experiments. In this sense, to accomplish the store data process, the volumetric flow rate and the concentration of tracer, reactants and/or products of the reaction must be acquired as a function of time. In the original experimental setup, only the signal conditioning system was operational, while the acquisition, visualization, and control systems were obsolete and damaged. Thus, a new system composed of an interface and real-time acquisition data is proposed alongside preserving the main reactor structure. A graphical user interface and the automation of the various actuators were developed based on worldwide usage and low cost, respectively. This system, based on a common 8-bit microcontroller and an application developed in Lazarus, allows the storage of the acquired data in a time-series database. In this way, students can analyze the results later or in real time. Moreover, remote access allows controlling the reactor and getting data by the Internet of Things (IoT) resources. Additionally, the proposed system using IoT allows data to be shared with the community as a dataset. © 2023 ieee.

关键词： Chemical reactors

来源：评论

学校读者我要写书评

暂无评论

Contrastive Positive Sample Propagation Along the Audio-Visual Event Line

引用

ieee TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第6期45卷 7239-7257页

作者： Zhou, Jinxing Guo, Dan Wang, Meng Hefei Univ Technol HFUT Sch Comp Sci & Informat Engn Sch Artificial Intelligence Key Lab Knowledge Engn Big Data HFUTMinist Educ Hefei 230601 Peoples R China Hefei Univ Technol HFUT Intelligent Interconnected Syst Lab Anhui Prov Hefei 230601 Peoples R China Hefei Comprehens Natl Sci Ctr Inst Artificial Intelligence Hefei 230601 Peoples R China

Visual and audio signals often coexist in natural environments, forming audio-visual events (AVEs). Given a video, we aim to localize video segments containing an AVE and identify its category. It is pivotal to learn the discriminative features for each video segment. Unlike existing work focusing on audio-visual feature fusion, in this paper, we propose a new contrastive positive sample propagation (CPSP) method for better deep feature representation learning. The contribution of CPSP is to introduce the available full or weak label as a prior that constructs the exact positive-negative samples for contrastive learning. Specifically, the CPSP involves comprehensive contrastive constraints: pair-level positive sample propagation (PSP), segment-level and video-level positive sample activation (PSAS and PSAV). Three new contrastive objectives are proposed (i.e., L-avpsp, L-spsa, and L-vpsa) and introduced into both the fully and weakly supervised AVE localization. To draw a complete picture of the contrastive learning in AVE localization, we also study the self-supervised positive sample propagation (SSPSP). As a result, CPSP is more helpful to obtain the refined audio-visual features that are distinguishable from the negatives, thus benefiting the classifier prediction. Extensive experiments on the AVE and the newly collected VGGSound-AVEL100k datasets verify the effectiveness and generalization ability of our method.

关键词： visualization Task analysis Image segmentation Synchronization Roads Aggregates Representation learning Audio-visual event audio-visual learning contrastive learning positive sample propagation

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：