检索结果-内蒙古大学图书馆

Deep Learning and Holt-Trend Algorithms for Predicting Covid-19 Pandemic

computers, Materials & Continua 2021年第5期67卷 2141-2160页

作者： Theyazn H.H.Aldhyani Melfi Alrasheed Mosleh Hmoud Al-Adaileh Ahmed Abdullah Alqarni Mohammed Y.Alzahrani Ahmed H.Alahmadi Community College of Abqaiq King Faisal UniversityAl HofufSaudi Arabia Department of Quantitative Methods School of BusinessKing Faisal UniversityAl HofufSaudi Arabia Deanship of E-Learning and Distance Education King Faisal UniversityAl HofufSaudi Arabia Department of Computer Sciences and Information Technology Albaha UniversityAl BahahSaudi Arabia Department of Computer Science and Information Taibah UniversityMadinahKingdom of Saudi Arabia

The Covid-19 epidemic poses a serious public health threat to the world,where people with little or no pre-existing human immunity can be more vulnerable to its ***,developing surveillance systems for predicting the Covid-19 pandemic at an early stage could save millions of *** this study,a deep learning algorithm and a Holt-trend model are proposed to predict the *** Long-Short Term Memory(LSTM)and Holttrend algorithms were applied to predict confirmed numbers and death *** real time data used has been collected from theWorld Health Organization(WHO).In the proposed research,we have considered three countries to test the proposed model,namely Saudi Arabia,Spain and *** results suggest that the LSTM models show better performance in predicting the cases of coronavirus *** measure performance Mean squared Error(MSE),Root Mean Squared Error(RMSE),Mean error and correlation are employed to estimate the results of the proposed *** empirical results of the LSTM,using the correlation metrics,are 99.94%,99.94%and 99.91%in predicting the number of confirmed cases in the three *** far as the results of the LSTM model in predicting the number of death of Covid-19,they are 99.86%,98.876%and 99.16%with respect to Saudi Arabia,Italy and Spain ***,the experiment’s results of the Holt-Trend model in predicting the number of confirmed cases of Covid-19,using the correlation metrics,are 99.06%,99.96%and 99.94%,whereas the results of the Holt-Trend model in predicting the number of death cases are 99.80%,99.96%and 99.94%with respect to the Saudi Arabia,Italy and Spain *** empirical results indicate the efficient performance of the presented model in predicting the number of confirmed and death cases of Covid-19 in these *** findings provide better insights regarding the future of Covid-19 this pandemic in *** results were obtained by applying time series models,which

关键词： Deep learning algorithm holt-trend prediction Covid-19 machine learning

来源：评论

学校读者我要写书评

暂无评论

An extension method of sub-health intelligent prediction and transformation 9th

An extension method of sub-health intelligent prediction and...

引用

9th International Conference on Information Technology and Quantitative Management, ITQM 2022

作者： Sun, Junwen Li, Xingsen Zhu, Zhengxiang Zeng, Junlin Institute of Extenics and Innovation Methods Guangdong University of Technology Guangzhou510006 China School of Electromechanical Engineering Guangdong University of Technology Guangzhou510006 China Consumer Finance Center Bank of NanJing NanJing210002 China School of Computer Science and Technology Guangdong University of Technology Guangzhou510006 China

With the development of people's growing emphasis on health and the improving personal intelligent devices, wearable intelligent health monitoring devices have been popularized, and the data detected by them have great application potential in the prediction and improvement of sub-health. The current situation of wearable intelligent health monitoring devices is summarized, and the data of existing products and the data processing methods are listed. In order to study the relationship between physiological health data and sub-health, a construction method of decision tree and transformation tree based on extension theory is proposed, which enables it to intelligently acquire the rule knowledge of state transformation from the perspective of dynamic, and evaluate and analyze it through the superiority evaluation. © 2022 The Authors. Published by Elsevier B.V.

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

Anomaly Behavior Detection for the Web Application Based on LSTM

Anomaly Behavior Detection for the Web Application Based on ...

引用

2021 IEEE Conference on Telecommunications, Optics and computer science, TOCS 2021

作者： Ma, Hongxin Wang, Chunbo Qi, Hui Air Force Aviation University Teaching and Research Guarantee Center Changchun China Changchun Automobile Industry Institute School of Information Technology Changchun China Changchun University of Science and Technology School of Computer Science and Technology Changchun China

ISBN: (纸本)9781665424981

With the development of the Internet, more and more services are provided through various web applications. At the same time, the number of malicious behaviors of illegal access to the web application is also growing, which seriously threatens the security of the web application itself and user data. Anomaly detection is one of the primary methods to secure the web application and user data. Most of the traditional methods use statistical or machine learning algorithms to distinguish normal users and attackers according to the self-defined features. In this paper, we present an LSTM-based web application anomaly behavior detection method, which uses more comprehensive and raw web log data. First, the original request record is converted into an 8-dimension request vector and multiple requests of the same user are connected in chrono-logical order to form a user session vector. All session vectors are used as the input of LSTM. Then, LSTM network learns the behavior patterns hidden in the session vectors by itself, extracts behavior features and performs anomaly detection. Finally, we evaluate the proposed method on a real dataset. Experimental results show that our method can distinguish anomaly behavior well and outperforms the methods that use self-defined features, including K-means, PCA, KNN, NB and SVM. © 2021 IEEE.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Active Distance Learning: How Student Perceptions Affect Academic Performance

Active Distance Learning: How Student Perceptions Affect Aca...

引用

IEEE International Conference on teaching, Assessment and Learning for Engineering (TALE)

作者： Shamma Alwheibi Abdulhadi Shoufan Asli Hassan Department of Electrical Engineering and Computer Science Center for Cyber Physical Systems Khalifa University Abu Dhabi United Arab Emirates Center for Teaching and Learning Khalifa University United Arab Emirates

Active distance learning is an appealing approach that allows students to study at a distance by completing learning activities at their own pace without watching recorded or live lectures. This approach, however, raises some concerns due to the lack of teacher guidance, feedback, and scaffolding. Still, a thoughtful design of the learning activities can mitigate this issue. In this study, we aimed to investigate how students perceive distance learning activities and how their perceptions affect their performance on immediate short tests. Using regression analysis of 103 students’ data and 62 learning activities, we investigated the relationship between the grades and completion time of the learning activities and students’ ratings of the perceived level of interest, motivation, challenge, frustration, and boredom. We found out, for example, that student perceptions of interest and motivation are essentially affected by grades rather than the activity’s completion time. Furthermore, we investigated the relationship between the perceptions of the learning activities and students’ performance on immediate, short tests. The regression model showed that the perceived motivation, interest, and challenge have a remarkably strong impact on students’ performance. We conclude that active distance learning can benefit from a thoughtful design of learning activities that takes students’ perceptions seriously into consideration.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Web 3.0 and a Decentralized Approach to Education

arXiv

引用

arXiv 2023年

作者： Flanery, Sarah A. Mohanasundar, Kamalesh Chamon, Christiana Kotikela, Srujan D. Quek, Francis K. Department of Electrical and Computer Engineering Texas A&M University College StationTX United States Department of Computer Science and Engineering Texas A&M University College StationTX United States Department of Computer Science and Information Systems Texas A&M University-Commerce CommerceTX United States Department of Teaching Learning and Culture Texas A&M University College StationTX United States

With the natural evolution of the web, the need for decentralization has rendered the current centralized education system out of date. The student does not "own" their credentials, as the only way their accomplishments are directly linked to their person and considered valuable is by verification through a stamp of an expensive, prestigious institution. However, going to a university is no longer the only way to acquire an education;open-source learning material is widely available and accessible through the internet. However, our society does not deem these methods of education as verifiable if they do not include a degree or certificate. Additionally, a valid certificate for the vast majority of open-source courses costs a few hundred dollars to obtain. The centralized nature of education inadvertently places students in underprivileged communities at a disadvantage in comparison to students in economically advantaged communities, thus a decentralized approach to education would eliminate the vast majority of such discrepancies. In the present paper, we integrate Decentralized Identity (DID) with Web 3.0 to upload credentials linked directly to the user. Each credential is appended to an Ethereum blockchain that, by design, cannot be altered once uploaded. We include DID document based access controls to display the candidate's upload and verification history. Finally, we utilize TLS protocols to provide a secure connection to the internet for ensuring non-fungibility of credentials and authentication of users. © 2023, CC0.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Giving Shape to Words: Visual Knowledge Discovery for Textual Contents in Legal Scenarios

Giving Shape to Words: Visual Knowledge Discovery for Textua...

引用

International Conference on Information Visualisation (IV)

作者： Nicola Lettieri Alfonso Guarino Delfina Malandrino Rocco Zaccagnino Salvatore Del Piano National Institute for Public Policy Analysis Rome Italy Department of Law Economics Management and Quantitative Methods University of Sannio Benevento BN Italy Computer Science Department University of Salerno Fisciano SA Italy

Visual Knowledge Discovery (VKD), the emerging research field exploring the integration between Artificial Intelligence and Visual Analytics is impacting a growing number of contexts. This paper dwells on the potential intersections between the VKD perspective and the legal world, a scenario for many reasons drawn by the idea of combining empirical insights offered by computation with intuitive, visually-enhanced forms of data mining. We will focus on criminal justice, taking the cue from an ongoing experimental research project that investigates novel applications of computational social science methods - complex network analysis - to analyze criminal organizations for both scientific and investigative purposes. The work will describe the VKD solutions devised to allow public prosecutors to visually browse the content of phone calls and environmental tapping gathered during preliminary inquiries. We will discuss how given visualizations - graph-based visualizations in the first place - can enhance text mining techniques helping to capture in-a-glance communication flows, discussions' topics and both structural and functional features of criminal networks at hand.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Preliminary Study on Analysing Mandarin Tone Values of Romance L2 Mandarin Learners

A Preliminary Study on Analysing Mandarin Tone Values of Rom...

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Wu-Hao Li Te-hsin Liu Chen-Yu Chiang College of Electrical Engineering and Computer Science National Taipei University Taiwan Graduate Program of Teaching Chinese as the Second Language National Taiwan University Dept. of Communication Engineering National Taipei University New Taipei City Taiwan

ISBN: (数字)9798350367331

ISBN: (纸本)9798350367348

The 5-level tone value labeling system helps characterize pitch contours of syllables for L2 Mandarin learners and teachers to facilitate tone acquisition and tone error analysis, respectively. In the past, linguistic experts did the tone value labeling and initially used it to represent or analyze the pitch contours of monosyllables. Some L2 Mandarin teachers also used the tone value labeling system to analyze pitch contours of continuous speech and illustrate pitch realizations for L2 Mandarin learners. However, the pitch contours of the labeled tone values of continuous speech were rarely objectively measured or analyzed. This paper presents a preliminary analysis of tone values of a continuous read speech corpus uttered by six Romance L2 Mandarin learners. The pitch contours of the tone value classes were explored, and some experiments related to the automatic recognition of tone and tone value classes were reported. We expect the results reported by this study to shed light on the development of an automatic tone value classification mechanism, which will be used in computer-assisted pronunciation training for L2 learners in the future.

关键词： Training Error analysis Asia Information processing Linguistics Labeling

来源：评论

学校读者我要写书评

暂无评论

Teachers' Perception and Experiences of computer science Education in K-8 Schools

Teachers' Perception and Experiences of Computer Science Edu...

引用

Intermountain Engineering, Technology and Computing (IETC)

作者： Vaibhav Anu Sumi Hagiwara Katherine Herbert Kazi Zakia Sultana Minsun Shin Rebecca Goldstein Patricia Virella Department of Computer Science Montclair State University Montclair USA Department of Teaching and Learning Montclair State University Montclair USA Department of Educational Leadership Montclair State University Montclair USA

Supported by a state grant, our team of researchers (consisting of both computer science faculty and Teacher Education faculty) is offering a series of Professional Development sessions to K-8 teachers. These Professional Development (or PD) sessions are meant to help K-8 teachers develop their understanding of core computing concepts (such as algorithms, programming, data analysis, and networks) and thereby develop strong computer science programs for their students. In order to offer effective and meaningful Professional Development (PD) sessions, our research team first intended to understand the perceptions and experiences of K-8 teachers about computer science (CS) and Computational Thinking (CT) education. This paper presents the results of a K-8 teacher survey that we conducted as a pre-cursor to our PD series. The results of this survey provided valuable insights about elementary and middle-school teachers' perceptions of computer science education, self-perception of their ability to teach and learn CS, and understanding of CS discipline and those who typically engage in CS activities. The impact of teachers' perceptions impact how leaders in education and the CS industry can meet the needs of teachers, who in turn can meet the growing demand of CS education in K-8 schools.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging Artificial Intelligence (AI) to Enhance computer science Instruction

Leveraging Artificial Intelligence (AI) to Enhance Computer ...

引用

Frontiers in Education (FIE) Conference

作者： HyeonJin Yoon Xin Zhong Agnibh Dasgupta Gwen Nugent Guy Trainin Nebraska Center for Research on Children Youth Families and Schools University of Nebraska-Lincoln Lincoln USA Department of Computer Science University of Nebraska Omaha Omaha USA Teaching Learning and Teacher Education University of Nebraska-Lincoln Lincoln USA

ISBN: (数字)9798350351507

ISBN: (纸本)9798350363067

Measuring and understanding instructional processes in classrooms is essential for enhancing teaching and learning outcomes. Classroom observations provide educators with integral opportunity for professional development, fostering reflective practice and continuous improvement. However, traditional observation and coaching procedures are time-consuming, cumbersome, and expensive, requiring travel or video coding. Artificial intelligence (AI) technologies present a promising solution, enabling streamlined, efficient, and nuanced analysis of classroom observation data. This study aims to develop AI-based computer vision and multi-modal models to measure computer science (CS) instructional processes in video data and validate their accuracy. Using two K-8 CS classroom instruction videos, we tested two deep-learning approaches: 1) Convolutional Neural Network (CNN) for analyzing visual imagery, and 2) a multimodal deep learning approach that analyzed both visual and auditory information. Results showed that the multimodal approach achieved the highest accuracy. Our findings support the broader application of these methods for analyzing more intricate teaching and learning processes. We discuss the implications of the results for CS education practice and research.

关键词： computer science Video coding Deep learning Visualization Accuracy Education Data models Convolutional neural networks Continuous improvement Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Study of Qualitative Correlations Between Crucial Bio-markers and the Optimal Drug Regimen of Type-I Lepra Reaction: A Deterministic Approach

arXiv

引用

arXiv 2023年

作者： Nayak, Dinesh Sangeetha, A.V. Vamsi, D.K.K. Department of Mathematics and Computer Science Sri Sathya Sai Institute of Higher Learning Andhra Paresh 515134 India Central Leprosy Teaching and Research Institute Tamil Nadu Chengalpattu603003 India

Mycobacterium leprae is a bacteria that causes the disease Leprosy (Hansen’s disease), which is a neglected tropical disease. More than 200000 cases are being reported per year world wide. This disease leads to a chronic stage known as Lepra reaction that majorly causes nerve damage of peripheral nervous system leading to loss of organs. The early detection of this Lepra reaction through the level of bio-markers can prevent this reaction occurring and the further disabilities. Motivated by this, we frame a mathematical model considering the pathogenesis of leprosy and the chemical pathways involved in Lepra reactions. The model incorporates the dynamics of the susceptible schwann cells, infected schwann cells and the bacterial load and the concentration levels of the bio markers IFN-γ, TNF-α, IL-10, IL-12, IL-15 and IL-17. We consider a nine compartment optimal control problem considering the drugs used in Multi Drug Therapy (MDT) as controls. We validate the model using 2D - heat plots. We study the correlation between the bio-markers levels and drugs in MDT and propose a optimal drug regimen through these optimal control studies. We use the Newton’s Gradient Method for the optimal control studies. © 2023, CC BY.

关键词： Gradient methods

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：