检索结果-内蒙古大学图书馆

Dynamic Graph Learning with Long and Short-Term for Multivariate Time Series Anomaly Detection 12

Dynamic Graph Learning with Long and Short-Term for Multivar...

12th IEEE International conference on Intelligent Data Acquisition and Advanced Computing Systems: technology and Applications, IDAACS 2023

作者： Tian, Yuyin Gao, Rong Yan, Lingyu Liu, Donghua Ye, Zhiwei School of Computer Science Hubei University of Technology Wuhan430068 China Nanjing University State Key Laboratory for Novel Software Technology Nanjing210023 China China Waterborne Transport Research Institue Information Center Beijing100080 China

ISBN: (纸本)9798350358056

Existing multivariate time series anomaly detection methods utilize graph neural networks to model inter-sensor dependencies and achieve satisfactory results. However, these methods often employ a predefined or self-learning static adjacency matrix for graph information aggregation, disregarding the dynamic characteristics of inter-sensor dependencies in the real world, which change over time and are observable at different time scales as dynamic changing graph structure information. Furthermore, existing techniques struggle to capture long-term temporal contextual relationships. To address these issues, we propose a Dynamic Graph Learning with Long and Short-term time model (DGL-LS) for multivariate time series anomaly detection. The network integrates a dynamic graph structure learning method among sensors in multi-time mode and long- and short-term temporal context information to enhance the prediction of multivariate time series anomalies. We propose a strategy for learning dynamic graphs that aggregates sensor node representations at various time intervals, and then uses an attention-based gating unit to evolve the node dynamic characterization and construct a series of adjacency matrices that describe the dynamic changes in graph structure over time. Moreover, we formulate a long-short time convolution to capture the long-term and short-term temporal dependencies within the time series. We demonstrate the superiority of our approach over other state-of-the-art methods by conducting extensive experiments on three publicly available datasets. © 2023 IEEE.

关键词： Anomaly Detection Graph Learning Multivariate Time Series Time Convolution

来源：评论

学校读者我要写书评

暂无评论

RPRB-Net: A Sign Language Recognition Based on Multi-dimension Attentions

RPRB-Net: A Sign Language Recognition Based on Multi-dimensi...

引用

2023 International conference on Machine Vision, Image Processing and Imaging technology, MVIPIT 2023

作者： Yang, Tian Shen, Cong Wang, Xinyue Ma, Xiaoyu Tianjin University of Technology Engineering Research Center of Learning-Based Intelligent System Ministry of Education School of Computer Science and Engineering Tianjin China

ISBN: (纸本)9798350306545

Sign Language Recognition (SLR) is the process of translating sign language into text or speech, which can also be viewed as a communication and expression tool between deaf individuals and hearing people. SLR using deep neural network has undergone significant development over the last decade. In this study, we design a feature-enhanced SLR technique based on serval spaces. To aid the network learning features from channel and spatial dimensions, we inject various attention mechanisms into the feature extractor backbone. As a result, we named our approach ResNet + Pyramid-Split-Attention + Recurrent-Criss-Cross-Attention + BiLSTM Network (RPRB-Net). Besides, we employ the BiLSTM architecture to encode high-level representations in temporal sequence. The network is ultimately trained using an end-to-end CTC alignment strategy. Extensive trials show that RPRB-Net achieves WERs of 3.5% and 23.6% on the USTC and RWTH-2014 datasets, respectively. Besides, it implies that RPRB-Net significantly surpasses the cutting-edge SLR approaches. Additionally, numerous ablation experiments have confirmed the efficiency of configuration. © 2023 IEEE.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

A multimodal feature fusion model for depression diagnosis based on BiLSTM+ViT

A multimodal feature fusion model for depression diagnosis b...

引用

2024 International conference on Image Processing and Artificial Intelligence, ICIPAl 2024

作者： Li, Muyao Xing, Yan He, Yitan Wang, Yuhe Yu, Zhouyang Wang, Xiaoyu Linghu, Pingchuan School of Mathematics Hefei University of Technology Hefei230009 China School of Management Hefei University of Technology Hefei230009 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China

ISBN: (纸本)9781510681514

A thorough diagnosis of depression, a mental illness that affects many people worldwide, must be made in light of the patient's medical background, present symptoms, and pertinent examination findings. In recent years, scholars have increasingly favored machine learning algorithms for depression diagnosis or prediction models. However, achieving higher prediction accuracy in prediction models remains challenging when relying solely on one modality. This research suggests a multi-modal feature fusion model for predicting depression tendency that is based on bi-directional LSTM and vision transformer (ViT). The model demonstrates an accuracy of 70.00%, surpassing that of single-modal depression tendency prediction models and presenting a novel approach to depression tendency prediction. © 2024 SPIE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

The coded schoolhouse: Tablet computers and public education

引用

proceedings of the Association for Information science and technology 2015年第1期52卷 1-1页

作者： Crooks, Roderic N. UCLA Department of Information Studies United States

Using a South Los Angeles charter school of approximately 500 students operated by a non-proft charter management organization (CMO) as the primary field site, this two-year, ethnographic dissertation project examines the implementation of a one-to-one tablet computer program in a public high school. This poster examines the variety of ways that information and communication technology (ICT) functions in everyday life within the institution — including classroom instruction, school discipline, and evaluation — through qualitative methods, primarily class observations, photographs, and interviews with teachers, students, and administrators as the program evolved over two consecutive school years. This project contributes needed empirical context to questions of technological innovation in public education, providing the first-ever multi-year study of a one-to-one tablet computer program in a California public school. Copyright © 2015 by Association for Information science and technology

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Clavision: Visual automatic piano music transcription 15th

Clavision: Visual automatic piano music transcription

引用

15th International conference on New Interfaces for Musical Expression, NIME 2015

作者： Akbari, Mohammad Cheng, Howard School of Engineering Science Simon Fraser University 8888 University Drive BurnabyBCV5A 1S6 Canada Department of Mathematics and Computer Science University of Lethbridge 4401 University Drive LethbridgeABT1K 3M4 Canada

One important problem in Music Information Retrieval is Automatic Music Transcription, which is an automated conversion process from played music to a symbolic notation such as sheet music. Since the accuracy of previous audio-based transcription systems is not satisfactory, we propose an innovative visual-based automatic music transcription system named claVision to perform piano music transcription. Instead of processing the music audio, the system performs the transcription only from the video performance captured by a camera mounted over the piano keyboard. claVision can be used as a transcription tool, but it also has other applications such as music education. The claVision software has a very high accuracy (over 95%) and a very low latency in real-time music transcription, even under di↵erent illumination conditions. © 2015, Steering Committee of the International conference on New Interfaces for Musical Expression. All rights reserved.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

education on digital forensics for working people and graduate students in Japan 12

Education on digital forensics for working people and gradua...

引用

12th International conference on ICT, Society and Human Beings, ICT 2019, 5th International conference on Connected Smart Cities, CSC 2019 and the 16th International conference on Web Based Communities and Social Media, WBC 2019

作者： Sasaki, Ryoichi Tokyo Denki University 5 Senju- Asahi-Cho Adachi-Ku Tokyo120-8551 Japan

ISBN: (纸本)9789898533906

Security is becoming a very important technology for ICT, society and human beings. The importance of digital forensics, one of the security technologies has been recognized in Japan;however, in 2014, lectures on digital forensics were not offered at Japanese universities, and the shortage of experts in the field became a problem. Therefore, the authors planned to introduce digital forensics lectures at Tokyo Denki University for working people and graduate students. Lectures on digital forensics began in 2015 as part of a course called Cyber Security Studies Special Course for Working People and Graduate Students (CySec) with the support of the Ministry of education, Culture, Sports, science and technology. This paper describes the needs, objectives, syllabus and other aspects of the lectures. We also discuss the results and student satisfaction with the lectures 4 years after their introduction. © 2019 IADIS Press. All rights reserved.

关键词： Digital forensics

来源：评论

学校读者我要写书评

暂无评论

DBMS-KU at SemEval-2019 task 9: Exploring machine learning approaches in classifying text as suggestion or non-suggestion 13

DBMS-KU at SemEval-2019 task 9: Exploring machine learning a...

引用

13th International Workshop on Semantic Evaluation, SemEval 2019, co-located with the 17th Annual conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019

作者： Fatyanosa, Tirana Noor Siagian, Al Hafiz Akbar Maulana Aritsugi, Masayoshi Computer Science and Electrical Engineering Graduate School of Science and Technology Kumamoto University Japan Big Data Science and Technology Faculty of Advanced Science and Technology Kumamoto University Japan Indonesian Institute of Sciences Indonesia

ISBN: (纸本)9781950737062

This paper describes the participation of DBMS-KU team in the SemEval 2019 Task 9, that is, suggestion mining from online reviews and forums. To deal with this task, we explore several machine learning approaches, i.e., Random Forest (RF), Logistic Regression (LR), Multinomial Naive Bayes (MNB), Linear Support Vector Classification (LSVC), Sublinear Support Vector Classification (SSVC), Convolutional Neural Network (CNN), and Variable Length Chromosome Genetic Algorithm-Naive Bayes (VLCGA-NB). Our system obtains reasonable results of F1-Score 0.47 and 0.37 on the evaluation data in Subtask A and Subtask B, respectively. In particular, our obtained results outperform the baseline in Subtask A. Interestingly, the results seem to show that our system could perform well in classifying Non-suggestion class. © 2019 Association for Computational Linguistics

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Symposium on New Frontiers in Materials Processing and Manufacturing Engineering Teaching and Learning at the 24th University educational innovation Congress on Technical education, CUIEET 2016

Symposium on New Frontiers in Materials Processing and Manuf...

引用

Symposium on New Frontiers in Materials Processing and Manufacturing Engineering Teaching and Learning at the 24th University educational innovation Congress on Technical education, CUIEET 2016

ISBN: (纸本)9783035711820

The proceedings contain 16 papers. The special focus in this conference is on New Frontiers in Materials Processing and Manufacturing Engineering Teaching and Learning. The topics include: Design and implementation of a practical learning methodology for the control and programming of a flexible manufacturing cell;learning chip type strategies in turning processes by viewing with high-speed video cameras;development of a computer tool to support the teaching of materials technology;some examples for the automatic generation of self-assessment queries in manufacturing processes engineering subjects;proposal of an educational methodology to analyze cutting temperature in turning operations by infrared themography;acquisition of practical skills of manufacturing engineering - the case of the chair FERSA-university of zaragoza;aeronautics advanced manufacturing center, the bet to surpass the valley of death between university and company;development of interactive learning materials in engineering of manufacturing processes;learning activities through academic papers focused on forming processes;valuation of strategies for the incorporation of 3D printing contents in the teaching of subjects linked to productive processes from different approaches;innovations in learning and teaching for manufacturing engineering under ubiquitous computing and distributed on mobile devices smartphones and tablets;study of the continuous evaluation activities on UNED and accelerating the adoption of industry 4.0 supporting technologies in manufacturing engineering courses.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mature to Doubt: Using Ethical Theories for Role Modeling in Computing education

Mature to Doubt: Using Ethical Theories for Role Modeling in...

引用

2020 IEEE Frontiers in education conference, FIE 2020

作者： Grande, Virginia Hausswolff, Kristina Von Uppsala University Department of Information Technology Uppsala Sweden

ISBN: (纸本)9781728189611

This full research paper uses ethical theories to discuss role models in computing education. Role models are beneficial for students but there is little work on how role modeling works and how teachers can reflect on their role modeling for their students. To address this we connect different theories to role modeling and their use to analyze role modeling as a teacher in engineering. We present theories with ethical implications from Aristotle, Wittgenstein and Biesta, then the themes related to these theories found in our interview study on computing teachers' experiences of role *** aim is to show how these theories could help deepen teachers' understanding of role modeling in the concrete classroom situations from an ethical perspective. According to these theories, students first see the teacher as a whole as a potential role model. Gradually and through guidance, students mature to doubt: to being able to question which aspects and achievements of their teachers are desirable to emulate and which to avoid imitating. We discuss the teacher's responsibility to make ethical judgements that include the scaffolding of this process. © 2020 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Infusing Data science into Mechanical Engineering Curriculum with Course-Specific Machine Learning Modules

Infusing Data Science into Mechanical Engineering Curriculum...

引用

2023 ASEE Annual conference and Exposition - The Harbor of Engineering: education for 130 Years, ASEE 2023

作者： Xu, Yuhao Zhao, Bo Tung, Steve Hu, Han Department of Mechanical Engineering Prairie View A&M University Prairie ViewTX77446 United States Department of Mechanical Engineering University of Houston HoustonTX77204 United States Department of Mechanical Engineering University of Arkansas FayettevilleAR72701 United States

Recent advances in data science algorithms and libraries have impacted approaches and strategies for research and development in the industrial sector, which necessitates the integration of data science into engineering education. Data science courses offered by programs such as mathematics, computer science, and data science in academic institutions normally lack the implementation in solving engineering problems. To fill this gap, we have developed a project-based technical elective course "Machine Learning for Mechanical Engineers" and offered it to undergraduate and graduate students at the University of Arkansas. While this course is received very well by the students and has led to fruitful presentations and publications, it has a low enrollment volume from undergraduate students due to its relatively high programming requirements. A more sophisticated strategy is required to equip mechanical engineering students with data science skills without disturbing the existing curriculum. Inspired by the success of computer-aided design education at the University of Arkansas and the Data science InFusion into Undergraduate STEM education (DIFUSE) program at Dartmouth College, we have developed course-specific machine learning modules to be integrated into mechanical engineering core courses rather than dedicated data science courses. This effort includes a nonparametric regression module for computer Methods in Mechanical Engineering, a generative design module for computer-Aided Design, and a genetic algorithms module for Thermal Systems Analysis and Design, among others. Through this practice, students will practice programming and machine learning skills every semester from their sophomore year and will be ready for the project-based technical elective machine learning course. © American Society for Engineering education, 2023.

关键词： computer aided analysis

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：