检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Ouaari, Sofiane Ünal, Ali Burak Akgün, Mete Pfeifer, Nico Methods in Medical Informatics Department of Computer Science University of Tuebingen Germany University of Tuebingen Germany Medical Data Privacy and Privacy Preserving Machine Learning University of Tuebingen Germany

Several domains increasingly rely on machine learning in their applications. The resulting heavy dependence on data has led to the emergence of various laws and regulations around data ethics and privacy and growing awareness of the need for privacy-preserving machine learning (ppML). Current ppML techniques utilize methods that are either purely based on cryptography, such as homomorphic encryption, or that introduce noise into the input, such as differential privacy. The main criticism given to those techniques is the fact that they either are too slow or they trade off a model's performance for improved confidentiality. To address this performance reduction, we aim to leverage robust representation learning as a way of encoding our data while optimising the privacy-utility trade-off. Our method centers on training autoencoders in a multi-objective manner and then concatenating the latent and learned features from the encoding part as the encoded form of our data. Such a deep learning-powered encoding can then safely be sent to a third party for intensive training and hyperparameter tuning. With our proposed framework, we can share our data and use third party tools without being under the threat of revealing its original form. We empirically validate our results on unimodal and multimodal settings, the latter following a vertical splitting system and show improved performance over state-of-the-art. Copyright © 2023, The Authors. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Large Language Model-based Human-Agent Collaboration for Complex Task Solving

arXiv

引用

arXiv 2024年

作者： Feng, Xueyang Chen, Zhi-Yuan Qin, Yujia Lin, Yankai Chen, Xu Liu, Zhiyuan Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Department of Computer Science and Technology Tsinghua University Beijing China

In recent developments within the research community, the integration of Large Language Models (LLMs) in creating fully autonomous agents has garnered significant interest. Despite this, LLM-based agents frequently demonstrate notable shortcomings in adjusting to dynamic environments and fully grasping human needs. In this work, we introduce the problem of LLM-based human-agent collaboration for complex task-solving, exploring their synergistic potential. In addition, we propose a Reinforcement Learning-based HumanAgent Collaboration method, ReHAC. This approach includes a policy model designed to determine the most opportune stages for human intervention within the task-solving process. We construct a human-agent collaboration dataset to train this policy model in an offline reinforcement learning environment. Our validation tests confirm the model’s effectiveness. The results demonstrate that the synergistic efforts of humans and LLM-based agents significantly improve performance in complex tasks, primarily through well-planned, limited human intervention. Datasets and code are available at:https://***/XueyangFeng/ReHAC. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Prediction of Flight Arrival Delay Time Using U.S. Bureau of Transportation Statistics

Prediction of Flight Arrival Delay Time Using U.S. Bureau of...

引用

2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023

作者： Li, Jiarui Ji, Ran Li, Cheng'ao Yang, Xiaoying Li, Jiayi Li, Yiran Xiong, Xihan Fang, Yutong Ding, Shusheng Cui, Tianxiang School of Computer Science University of Nottingham Ningbo China Ningbo China School of Aerospace Engineering University of Nottingham Ningbo China Ningbo China Imperial College London Department of Computing London United Kingdom Ningbo Open University Teaching Research Center Ningbo China Business School Ningbo University Ningbo China

ISBN: (纸本)9781665430654

According to the data from the Bureau of Trans-portation Statistics (BTS), the number of passengers and flights has been increasing year by year. However, flight delay has become a pervasive problem in the United States in recent years due to various factors, including human factors such as security regulations, as well as natural factors such as bad weather. Flight delay not only affects the profits of airlines but also affects the satisfaction of passengers. Therefore, a model that can predict the arrival time of airplanes needs to be developed. Machine learning methods have been widely applied to prediction problems. In this paper, a variety of machine learning and computational intelligence methods, including linear regression, decision tree (DT), random forest (RF), gradient boosting (GB), gaussian regression models and genetic programming were trained on the U.S. department of Transportation's (DOT) BTS dataset. The results show that genetic programming performs best and can be used to predict the arrival time of the U.S. flights in advance, which is beneficial for airlines and passengers to make timely decisions. © 2023 IEEE.

关键词： Air flight Airport Big data Computational intelligence Delay Machine learning Prediction Regression

来源：评论

学校读者我要写书评

暂无评论

RIGID PROTEIN-PROTEIN DOCKING VIA EQUIVARIANT ELLIPTIC-PARABOLOID INTERFACE PREDICTION

arXiv

引用

arXiv 2024年

作者： Yu, Ziyang Huang, Wenbing Liu, Yang Department of Computer Science Tsinghua University China Tsinghua University China Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

The study of rigid protein-protein docking plays an essential role in a variety of tasks such as drug design and protein engineering. Recently, several learning-based methods have been proposed for the task, exhibiting much faster docking speed than those computational methods. In this paper, we propose a novel learning-based method called ElliDock, which predicts an elliptic paraboloid to represent the protein-protein docking interface. To be specific, our model estimates elliptic paraboloid interfaces for the two input proteins respectively, and obtains the roto-translation transformation for docking by making two interfaces coincide. By its design, ElliDock is independently equivariant with respect to arbitrary rotations/translations of the proteins, which is an indispensable property to ensure the generalization of the docking process. Experimental evaluations show that ElliDock achieves the fastest inference time among all compared methods and is strongly competitive with current state-of-the-art learning-based models such as DiffDock-PP and Multimer particularly for antibody-antigen docking. Copyright © 2024, The Authors. All rights reserved.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Accurate Classroom Person Detection Based on Multi-Frame Feature Fusion with Attention 8

Accurate Classroom Person Detection Based on Multi-Frame Fea...

引用

8th International Conference on Image, Vision and Computing, ICIVC 2023

作者： Cheng, Guoan Ren, Jiandong Li, Yuping Wang, Shengke Ding, Yougang Wang, Hao School of Information & Electrical Engineering Qingdao Harbour Vocational & Technical College Qingdao China Qingdao Harbour Vocational & Technical College Student Work Department Qingdao China College of Computer Science and Engineering Ocean University of China Qingdao China Experimental School Affiliated to Shandong University Mathematics Teaching and Research Group Heze China

ISBN: (纸本)9798350335231

In recent years, object detection technology has developed rapidly and is widely used in the field of intelligent video monitoring, especially in the classroom scenes, where incorporating the intelligent object detection technique into the video monitoring systems for intelligent monitoring purpose has important practical significance. However, surveillance videos may encounter issues such as object occlusion, motion blur, posture changes, and video defocus, which poses great challenges to object detection in the surveillance video scenarios. Therefore, in this paper, we conduct in-depth research on human detection in classroom multi camera surveillance video scenes and propose a multi frame feature fusion network based on the attention mechanism. The algorithm first adds the dilated convolution layers to the ResNet50 backbone network to expand the receptive field and retain more feature information;Secondly, a multi frame feature fusion strategy based on the attention mechanism was proposed to enhance the feature representation ability of the deep detector by fusing the feature information of adjacent frames, thereby improving the accuracy of human detection in the classroom monitoring video. To verify the effectiveness of the proposed method, we have compiled and produced a large-scale classroom monitoring video dataset, named OUC-ClassVideo. The proposed object detection network, which is developed based on the attention mechanism and multi frame feature fusion strategy, has achieved satisfactory performance on both the public dataset ImageNet VID and the OUC-ClassVideo dataset collected by ourselves. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Prognosticating anthropomorphic chatbots' usage intention as an e-banking customer service gateway: cogitations from Zimbabwe

引用

PSU Research Review 2024年第2期8卷 356-372页

作者： Nyagadza, Brighton Muposhi, Asphat Mazuruse, Gideon Makoni, Tendai Chuchu, Tinashe Maziriri, Eugine T. Chare, Anyway Department of Marketing Faculty of Agribusiness and Entrepreneurship Marondera University of Agricultural Sciences and Technology Marondera Zimbabwe Department of Information and Marketing Sciences Faculty of Business Sciences Midlands State University Gweru Zimbabwe Teaching and Learning Institute (TLI) Marondera University of Agricultural Sciences and Technology Marondera Zimbabwe Department of Mathematics and Computer Science Great Zimbabwe University Masvingo Zimbabwe Marketing Division School of Business Sciences University of the Witwatersrand Johannesburg South Africa Department of Business Management Faculty of Economic and Management Sciences University of the Free State Bloemfontein South Africa

Purpose: The purpose of this article is to investigate the factors that explain the reasons why customers may be willing to use chatbots in Zimbabwe as an e-banking customer service gateway, an area that remains under researched. Design/methodology/approach: The research study applied a cross-sectional survey of 430 customers from five selected commercial banks conducted in Harare, the capital city of Zimbabwe. Hypotheses were tested using structural equation modelling. Findings: The research study showed that a counterintuitive intention to use chatbots is directly affected by chatbots' expected performance, the habit of using them and other factors. Research limitations/implications: To better appreciate the current research concept, there is a need to replicate the same study in other contexts to enhance generalisability. Practical implications: Chatbots are a trending new technology and are starting to be increasingly adopted by banks and they have to consider that customers need to get used to them. Originality/value: This study contributes to bridging the knowledge gap as it investigates the factors that explain why bank customers may be willing to use chatbots in five selected commercial Zimbabwean banks. This is a pioneering study in the context of a developing economy such as Zimbabwe. © 2022, Brighton Nyagadza, Asphat Muposhi, Gideon Mazuruse, Tendai Makoni, Tinashe Chuchu, Eugine T. Maziriri and Anyway Chare.

关键词： Anthropomorphism Chatbots Customer experience (CX) Digital marketing E-Banking E-Customer service New digital technologies User experience (UX)

来源：评论

学校读者我要写书评

暂无评论

Experience Report: Exploring the Use of CTF-based Co-Curricular Instruction to Increase Student Comfort and Success in Computing 21

Experience Report: Exploring the Use of CTF-based Co-Curricu...

引用

26th ACM Conference on Innovation and Technology in computer science Education, ITiCSE 2021

作者： Ellis, Margaret Baum, Liesl Filer, Kimberly Edwards, Stephen H. Virginia Tech Department of Computer Science BlacksburgVA United States Virginia Tech Center for Excellence in Teaching and Learning BlacksburgVA United States

ISBN: (纸本)9781450382144

Very little research exists on the incorporation of co-curricular opportunities, specifically capture-the-flag (CTF) activities, and the impact on computer science students. However, some literature on underrepresented groups in the field of computer science indicates that co-curricular experiences, such as CTF activities, have a significant impact on efficacy and sense of belonging. This experience report seeks to identify and share teaching strategies that impact student learning, efficacy, and sense of self/belonging in the field of computer science, for all students. In an effort to design learning opportunities to help bridge the gap between the haves and have nots, and maximize learning for all students, this strategy uses CTF-based instruction as a way to generate and support culture-based, computer science experiences. The aim is to identify instructional strategies that build students' computing skills and improve their comfort participating in computing activities thus broadening participation in computing and cybersecurity. As students' comfort is related to their self-efficacy and sense of belonging, we explore the integration of co-curricular opportunities, specifically a capture-the-flag (CTF) approach to computer science instruction, as means of increasing student success, with regard to learning, efficacy, and sense of belonging/identity. This report involves a description of the class activities as well as data from a series of pre- and post- surveys of the student experience, attitudes, and gain in knowledge. Initial analysis indicates that low-stakes, entry-level exposure to computer science concepts has a positive effect on student comfort and skill acquisition in computing domains external to coursework. © 2021 ACM.

关键词： Students

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

An intelligent hybrid approach for hepatitis disease diagnosis: Combining enhanced k-means clustering and improved ensemble learning

An intelligent hybrid approach for hepatitis disease diagnos...

引用

作者： Singh, Aman Mehta, Jaydip Chandrakant Anand, Divya Nath, Pinku Pandey, Babita Khamparia, Aditya Department of Computer Science and Engineering Lovely Professional University JalandharPunjab India Master in International Teaching Department Namseoul University Korea Republic of Department of Chemistry Lovely Professional University Jalandhar India Department of Computer Science and Information Technology BabaSaheb Bhimrao Ambedkar University Satellite Campus AmethiLucknow India

In real world, the automatic detection of liver disease is a challenging problem among medical practitioners. The intent of this work is to propose an intelligent hybrid approach for the diagnosis of hepatitis disease. The diagnosis is performed with the combination of k-means clustering and improved ensemble-driven learning. To avoid clinical experience and to reduce the evaluation time, ensemble learning is deployed, which constructs a set of hypotheses by using multiple learners to solve a liver disease problem. The performance analysis of the proposed integrated hybrid system is compared in terms of accuracy, true positive rate, precision, f-measure, kappa statistic, mean absolute error, and root mean squared error. Simulation results showed that the enhanced k-means clustering and improved ensemble learning with enhanced adaptive boosting, bagged decision tree, and J48 decision tree-based intelligent hybrid approach achieved better prediction outcomes than other existing individual and integrated methods. © 2020 John Wiley & Sons, Ltd

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

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：