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： Sunil, M.P. Pandey, Megha Garima Janakiraman, V. Maral, Vikas B. Das, Sidhant Department of Electronics and Communication Engineering Faculty of Engineering and Technology Karnataka Bangalore India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Prince Shri Venkateshwara Padmavathy Engineering College Department of Mechanical Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India

ISBN: (纸本)9798350319125

Fact mining has emerged as one of the most promising information discovery strategies in tremendous and complex databases. The tourism quarter advantages highly from records mining, as it can provide specific insights into how customers view and transact with the industry. In recent years, fact mining has grown exponentially within the tourism region, making it vital for researchers to apprehend how it can be implemented to discover meaningful information and inform strategic choice-making. This paper examines the potential of fact mining for know-how discovery in tourism, along with supervised and unsupervised learning techniques, artificial intelligence, predictive modeling, and information visualization. The authors talk about the results of technological improvements in information mining and the ability of tourism organizations to benefit from its use. They then speak of realistic examples of statistics mining programs inside the tourism area, from tracking client reviews to forecasting vacationer trends. An assessment of the prevailing literature is presented to assess knowledge discovery strategies inside the field of tourism. Ultimately, the authors recommend avenues for destiny studies in this location. © 2023 ieee.

关键词： conclusion forecasting knowledge presented technology

来源：评论

学校读者我要写书评

暂无评论

Research on Multimodal Knowledge Graph Construction Method Based on Conditional Random Field Model 7

Research on Multimodal Knowledge Graph Construction Method B...

引用

7th International Conference on Education, Network and Information Technology, ICENIT 2024

作者： Peng, Kanghua Qiao, Yifang Shi, Jincheng Information Engineering Institute Guangdong Engineering Polytechnic Guangzhou510520 China Guangdong Food and Drug Vocational College School of Nursing Guangzhou510520 China Jinan University Science and Technology Research Office Guangzhou510632 China

ISBN: (纸本)9798350374919

In an effort to enhance the efficiency and decision-making levels of higher education teaching management, and to address the fragmented, disorganized, and scattered state of online and offline educational resources, a new approach to constructing educational resources in emerging fields has been explored. The study proposes a method for entity extraction suitable for the software technology specialty domain, designs a Conditional Random Field (CRF) model, and employs new word discovery plus named entity recognition, along with dependency syntax analysis and entity relationship extraction algorithms for knowledge fusion. This leads to the visualization of knowledge graphs, building semantic associations within the entire discipline's knowledge points, and constructing a multimodal educational knowledge graph in the field of database technology. Using the software technology specialty group's platform course on database technology as a carrier, the method is implemented across three scenarios: offline textbooks, online MOOCs, and IT blogs. Among these, text recognition has achieved 100% accuracy, recall probability, and F-value on some pages, successfully completing the construction of subject and course knowledge graphs. The results show that the knowledge graph can visualize the relationships between course knowledge units, optimize course settings, meet the needs of intelligent search for teaching resources and personalized recommendation of course resources, solve the problem of resource information disorientation, make the use of educational resources more efficient, and achieve the construction goals of supporting teaching resources. © 2024 ieee.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Multi-Representation Convolutional Neural Network to Recognize Human Emotion 8

Multi-Representation Convolutional Neural Network to Recogni...

引用

8th International Conference on Information Technology and Digital Applications, ICITDA 2023

作者： Prabowo, Dwi Wahyu Setiawan, Noor Akhmad Debayle, Johan Nugroho, Hanung Adi Universitas Gadjah Mada Faculty of Engineering Department of Electrical and Information Engineering Yogyakarta Indonesia Universitas Darwan Ali Faculty of Computer Science Department of Information System Sampit Indonesia Centre Spin Mines Saint-Etienne Cnrs Umr 5307 Lgf Saint-Etienne France

ISBN: (纸本)9798350344691

Emotion recognition using brain-computer interfaces (BCIs) is an emerging field with the ongoing challenge of developing robust and efficient classification methods. This study introduces an original approach, the multi-representation convolutional neural network (MrCNN), designed to exploit the complementary features of recurrence plots (RP) and spectrograms. The efficacy of this new method was empirically evaluated and compared with the standalone RP and spectrogram methods in emotion classification tasks using electroencephalogram (EEG) signals. Two widely used datasets, DEAP and SEED, were used as the experimental platforms for this study. Employing a multifaceted analytical approach involving descriptive statistics, data visualization, and hypothesis tests, this study revealed that MrCNN significantly outperforms the standalone RP and spectrogram methods in terms of key performance metrics. Specifically, MrCNN achieved an accuracy of 0.9663, sensitivity of 0.9848, specificity of 0.9825, kappa score of 0.9511, and F1 score of 0.9656 for the DEAP dataset. For the SEED dataset, the accuracy was 0.9695, with sensitivity, specificity, kappa scores, and F1 score of 0.9844, 0.9842, 0.9543, and 0.9695, respectively. These results were statistically validated, and a comparative analysis with existing literature substantiated the robustness and superiority of the MrCNN method. This study sets new performance benchmarks and offers a reliable and effective approach for emotion classification using EEG signals. © 2023 ieee.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Automated Brain Tumor Classification of Different Types of Tumors Using Convolutional Neural Network of Multi Label MRI Scans

Automated Brain Tumor Classification of Different Types of T...

引用

2023 International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent Engineering, ICECONF 2023

作者： Raghav, Jaiwant Singh Das, Aditya Narayan Suresh, A. School of Computing SRM Institute of Science and Technology Department of Networking and Communications Srm Nagar Kattankulathur Chengalpattu Tamil Nadu Chennai603203 India

ISBN: (纸本)9798350334357

The conventional technique for defect detection in resonance brain pictures is human examination. This technique is impractical thanks to great amount of knowledge. Therefore, automated and reliable classification methods are very important to decrease human death rate. So, machine-driven growth detection ways square measure developed because it would save specialist time and acquire a tested accuracy. Computed Tomography scans, radiography, and magnetic resonance imaging scans square measure the usual visualization ways among magnetic resonance (M.R.I) that square measure the foremost dependable and assured. During this study, we have a tendency to performed pre-processing victimization the morphological gap for removal of the noises that square measure gift in Associate in Nursing mister data. Following this, Neural Network segmentation and binary threshold techniques were used to reliably identify tumor regions. Square measures used in training, test, and validation of datasets. If our machine is supported, we will predict if the topic contains brain tumor or not. We have a tendency to arrange to check and experiment completely different models for higher accuracy. We hope that the proposed project will produce superior compared to its counterpart. This will also be helpful for the modern medical technology and help those who have lost faith on the medical entities and renew their trust and help them overcome their fear. © 2023 ieee.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Environmental Mapping Automation by Quadruped Robot Using Lidar Technology 8

Environmental Mapping Automation by Quadruped Robot Using Li...

引用

8th International Conference on Electrical, Electronics and Information Engineering, ICEEIE 2023

作者： Siregar, Baihaqi Bagustiawan, Hagel Sitompul, Opim Salim Universitas Sumatera Utara Universitas Sumatera Utara Center of Excellence for Artificial Intelligence of Things Department of Data Science and Artificial Intelligence Indonesia Universitas Sumatera Utara Department of Information Technology Sumatera Utara Indonesia

ISBN: (纸本)9798350340501

Navigation as well as mapping using robots is currently widely used in various fields. Automated robot navigation and mapping allows robots to provide information about their surroundings to humans more effectively. LiDAR is one of the latest technologies used to carry out environmental mapping. The implementation of LiDAR technology coupled with legged robots is useful for autonomously mapping environments that have uneven trajectories, such as on the ground, rocky areas, and grass. Quadruped robot is a type of legged robot that is used in research and operations in the industrial world or in observing certain environmental areas. Determining the appropriate gait according to the observed characteristics of the robot and the environment, selecting the algorithm for mapping, and presenting the visualization of the map must be met for the success of the mapping process. This research applies Hector SLAM, crawl gait, trot gait, and the use of LiDAR technology to map the artificial environment which is carried out autonomously by a quadruped robot with the aim of obtaining information in the form of an environmental map which is visualized using RViz. The implementation of crawl gait to move forward is considered the most suitable for the quadruped robot in this research because the load being lifted is quite heavy, namely ±1.5kg, while the implementation of a dynamic trot gait is used to turn left or right. The result of this research is that the quadruped robot is able to walk through a well-defined environment and draw a complete map of the observed artificial environment with an accuracy rate of 97%. © 2023 ieee.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Signal Preprocessing Towards IoT Acoustic data for Farm Pest Detection 20

Signal Preprocessing Towards IoT Acoustic Data for Farm Pest...

引用

20th International Conference on Smart Technologies, EUROCON 2023

作者： Amenyedzi, Destiny Kwabla Kazeneza, Micheline Vodacek, Anthony Maginga, Theofrida Julius Nzanywayingoma, Frederic Nsengiyumva, Philibert Bamurigire, Peace Ndashimye, Emmanuel University of Rwanda African Centre of Excellence in Internet of Things Kigali Rwanda Rochester Institute of Technology Chester F. Carlson Center for Imaging Science RochesterNY United States School of Ict University of Rwanda Kigali Rwanda University of Rwanda Electrical and Electronics Engineering Kigali Rwanda School of Ece Carnegie Mellon University Africa Kigali Rwanda

ISBN: (纸本)9781665463973

In Africa the realization of the Sustainable Development Goal 2 (SDG-2) of zero hunger by 2030 is threatened by agricultural pests. Acoustic technology offers one method for pest detection in agriculture. AudioMoth microphones were deployed in three farms in Rwanda. Band filters were applied to the files for listening to pest calls for labeling. The WAV files were processed using Scikit-maad package in Python to spectrograms, which allowed for visualization. The regions of interest were selected to be used for labeling. Results suggest that birds are the dominant pest during the morning sections of the day while frogs are active at night. The contribution of this work is to provide a roadmap towards labeling for detection of agricultural pests using machine learning at the edge. © 2023 ieee.

关键词： Agriculture

来源：评论

学校读者我要写书评

暂无评论

Postural Synergy Analysis of Continuous Hand Movements for Application to Prosthetic Hands 17

Postural Synergy Analysis of Continuous Hand Movements for A...

引用

17th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2024

作者： Jiang, Hai Yamanoi, Yusuke Chen, Peiji Yong, Xu Li, Guanglin Yokoi, Hiroshi Jing, Xiaobei Shenzhen518055 China The Univiersity of Electro-Communications Department of Mechanical Engineering and Intelligent Systems Tokyo 182-8585 Japan Tokyo University of Science Faculty of Engineering Department of Elecrical Engineering Tokyo 125-8585 Japan

ISBN: (纸本)9798331507398

This paper focuses on exploring the coordinated movements used to control dexterous myoelectric prosthetic hands by hand motion analysis inspired by the motor synergy theory of the human hand. Recently, prosthetic hands have become multi-degree-of-freedom, and simultaneous proportional control of each finger is the most required challenge. In response to this problem, motor synergy is expected to play a key role in constructing the control method because it reduces the amount of information on the control object. In the experiment, we used a Leap Motion Controller to measure 60 continuous hand movement data from four healthy individuals, analyzed based on principal component analysis methods, and extracted several principal component data used by humans to control various grasping movements. We produced a hand model with 19 degrees of freedom for visualizing the principal component data. The results of the visualization showed similarities in postural synergies among the four healthy individuals used to control continuous hand movements. Based on the acquired synergies, the number of learning data for the control method of myoelectric prosthetic hands will be greatly reduced. © 2024 ieee.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

Kernel Density visualization for Big Geospatial data: Algorithms and Applications

Kernel Density Visualization for Big Geospatial Data: Algori...

引用

International Conference on Mobile data Management

作者： Tsz Nam Chan Leong Hou U Byron Choi Jianliang Xu Reynold Cheng Department of Computer Science Hong Kong Baptist University Department of Computer and Information Science University of Macau Department of Computer Science The University of Hong Kong Guangdong–Hong Kong-Macau Joint Laboratory

The use of Kernel Density visualization (KDV) has become widespread in a number of disciplines, including geography, crime science, transportation science, and ecology, for analyzing geospatial data. However, the growing scale of massive geospatial data has rendered many commonly used software tools unable of generating high-resolution KDVs, leading to concerns about the inefficiency of KDV. This 90-minute tutorial aims to raise awareness among database researchers about this important, emerging, database-related, and interdisciplinary topic. It is structured into four parts: a thorough discussion of the background of KDV, a review of state-of-the-art methods for generating KDVs, a discussion of key variants of KDV, including network kernel density visualization (NKDV) and spatiotemporal kernel density visualization (STKDV), and an outline of future directions for this topic.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards an Intelligent Tutoring System for Virtual Reality Learning Environments 53

Towards an Intelligent Tutoring System for Virtual Reality L...

引用

53rd ieee ASEE Frontiers in Education International Conference, FIE 2023

作者： Bezanson, Katherine Soberanis, Lara Thomas, Britain Brooks, Randy Rojas-Muñoz, Edgar Texas A&m University Department of Computer Science and Engineering College StationTX United States Texas A&m University Department of Multidisciplinary Engineering College StationTX United States School of Performance Visualization & Fine Arts Texas A&m University College StationTX United States College of Engineering Texas A&m University College StationTX United States

ISBN: (纸本)9798350336429

This Work-in-Progress Research paper explores the development of an Intelligent Tutoring System (ITS) inside a Virtual Reality Learning Environment (VRLE). As technology becomes more pervasive in teaching, platforms that afford immersive learning experiences, such as VRLEs, are receiving increased attention. VRLEs engage students in a virtual representation of a learning space;however, understanding how to use and interact with a VRLE usually represents a steep learning curve, particularly for the instructor. Our work addresses this problem by integrating an ITS into the VRLE. In doing so, timely guidance can be provided to the students, and the instructor can adapt the ITS support to best guide student learning across multiple skill levels. Our approach immerses students in an engineering-based VRLE that resembles a space launch mission control. Inside the environment, students interact with the system to acquire data, compute, and evaluate options to attempt the successful landing of a spacecraft. The VRLEs' ITS provides the students with feedback as they interact with the environment to address challenges. The feedback is provided in various modalities, such as virtual floating panels with general suggestions, hints on which parameters from the calculations should be changed, and visual demonstrations of the calculations' outputs. To perform an initial validation of our approach, we compare its effectiveness against a physical laboratory version of the same experiment. The results of the interviews validated the ITS as a successful approach in providing students with prompt feedback while they are immersed in the VRLE. Overall, the work strengthens the validity of VRLEs as platforms that support more engaging and immersive learning experiences, and informs how to effectively integrate ITS within them. © 2023 ieee.

关键词： Human-Computer Interaction Intelligent Tutoring Systems Learning Environments Virtual Reality

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning-Based Framework for Offensive Text Detection in Unstructured data for Heterogeneous Social Media

引用

ieee ACCESS 2023年 11卷 124484-124498页

作者： Bacha, Jamshid Ullah, Farman Khan, Jebran Sardar, Abdul Wasay Lee, Sungchang Tech Univ Berlin Sch Elect Engn & Comp Sci D-10623 Berlin Germany Korea Aerosp Univ Sch Elect & Informat Engn Goyang Si 10540 South Korea United Arab Emirates Univ UAEU Coll Informat Technol Abu Dhabi U Arab Emirates Ajou Univ Dept Artificial Intelligence Suwon 16499 Gyeonggi South Korea Univ Coll Dublin Smurfit Sch Business Nat Comp Res & Applicat Grp Dublin 4 Ireland Thingswell Inc Anyang Si 14056 Gyeonggi Do South Korea

Social media such as Facebook, Instagram, and Twitter are powerful and essential platforms where people express and share their ideas, knowledge, talents, and abilities with others. Users on social media also share harmful content, such as targeting gender, religion, race, and trolling. These posts may be in the form of tweets, videos, images, and memes. A meme is one of the mediums on social media which has an image and embedded text in it. These memes convey various views, including fun or offensiveness, that may be a personal attack, hate speech, or racial abuse. Such posts need to be filtered out immediately from social media. This paper presents a framework that detects offensive text in memes and prevents such nuisance from being posted on social media, using the collected KAU-Memes dataset 2582. The latter combines the "2016 U.S. Election" dataset with the newly generated memes from a series of offensive and non-offensive tweets datasets. In fact, this model uses the KAU-Memes dataset containing symbolic images and the corresponding text to validate the proposed model. We compare the performance of three proposed deep-learning algorithms to train and detect offensive text in memes. To the best of the authors knowledge and literature review, this is the first approach based on You Only Look Once (YOLO) for offensive text detection in memes. This framework uses YOLOv4, YOLOv5, and SSD MobileNetV2 to compare the model's performance on the newly labeled KAU-Memes dataset. The results show that the proposed model achieved 81.74%, 84.1%, mAP, and F1-score, respectively, for SSD-MobileNet V2, and 85.20%, 84.0%, mAP, and F1-score, respectively for YOLOv4. YOLOv5 had the best performance and achieved the highest possible mAP, F1-score, precision, and recall which are 88.50%, 88.8%, 90.2%, and 87.5%, respectively, for YOLOv5.

关键词： visualization Optical character recognition Feature extraction Cyberbullying Text detection Multimedia Web sites Deep learning Media Image processing YOLO Cyberbully unstructured data deep learning social media offensive MobileNet-SSD image processing

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：