检索结果-内蒙古大学图书馆

Date-Driven Approach for Identifying State of Hemodialysis Fistulas: Entropy-Complexity and Formal Concept Analysis

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Gromov, Vasilii A. Zvorykina, E.I. Beschastnov, Yurii N. Sohrabi, Majid School of Data Analysis and Artificial Intelligence Faculty of Computer Science HSE University Moscow109028 Russia Laboratory for Models and Methods of Computational Pragmatics HSE University Moscow Russia

The paper explores mathematical methods that differentiate regular and chaotic time series, specifically for identifying pathological fistulas. It proposes a noise-resistant method for classifying responding rows of normally and pathologically functioning fistulas. This approach is grounded in the hypothesis that laminar blood flow signifies normal function, while turbulent flow indicates pathology. The study explores two distinct methods for distinguishing chaotic from regular time series. The first method involves mapping the time series onto the entropy-complexity plane and subsequently comparing it to established clusters. The second method, introduced by the authors, constructs a concepts-objects graph using formal concept analysis. Both of these methods exhibit high efficiency in determining the state of the fistula. © 2023, CC BY-NC-ND.

关键词： Entropy

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

学校读者我要写书评

暂无评论

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

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

学校读者我要写书评

暂无评论

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

Engineering Educators’ Adoption and implementation of Project-Based Learning: Experiences from a South Indian University

学校读者我要写书评

暂无评论

Engineering Educators’ Adoption and implementation of Proje...

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

作者： Anjal P Dijo Anantha Krishnan K. P. N. P. Subheesh Aby John S M Anzar Sajin Sachidananthan Department of Computer Science and Engineering Federal Institute of Science and Technology India Department of Computer Science and Engineering College of Engineering Kerala India Teaching Learning Centre SRM University - AP Andhra Pradesh India Faculty of Philology RUDN University Moscow Russia Department of Electronics and Communication Engineering TKM College of Engineering Kollam India Curriculum Research and Development U-DNA Educational Foundation Anantapur Andhra Pradesh India

ISBN: (数字)9798350376234

ISBN: (纸本)9798350376241

This research investigates the attitudes and perceptions of engineering educators in Kerala, India, towards the implementation of Project-Based Learning (PjBL) within the framework of APJ Abdul Kalam Technological University (APJAKTU), Kerala. Despite the growing emphasis on experiential learning, only limited research studies focus on understanding the attitudes and perceptions of engineering faculty members towards PjBL. Against this backdrop, the present study aims to critically examine the readiness of engineering educators in adopting and identifying PjBL strategies for its effective integration into engineering curricula. The paper explores various dimensions of engineering educators’ engagement with PjBL, including faculty interest levels, satisfaction of implementation, perceived effectiveness, and career implications. The data were collected from engineering faculty members by distributing a comprehensive questionnaire titled Project-Based Learning in Engineering Education in Kerala (PLEEK), uniquely designed by the researchers. The research findings reveal that over 90% of the surveyed faculty members have shown keen interest in implementing PjBL, while the remaining respondents exhibited a neutral stance. This underscores a noteworthy receptivity to PjBL among engineering educators in Kerala. Suggestions from participants indicate that, if implemented correctly, PjBL would be highly effective, although time constraints pose a significant challenge. The results obtained are pivotal as they provide an explicit idea of the current status of the engineering education settings and the discrepancies between traditional theoretical instruction and project-based learning.

关键词： Engineering profession Time factors Engineering education

Structure-Aware DropEdge Towards Deep Graph Convolutional Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Han, Jiaqi Huang, Wenbing Rong, Yu Xu, Tingyang Sun, Fuchun Huang, Junzhou Department of Computer Science and Technology Tsinghua University Beijing China Gaoling School of Artificial Intelligence Renmin University of China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Tencent AI Lab Shenzhen China Department of Computer Science and Engineering The University of Texas Arlington United States

It has been discovered that Graph Convolutional Networks (GCNs) encounter a remarkable drop in performance when multiple layers are piled up. The main factor that accounts for why deep GCNs fail lies in over-smoothing, which isolates the network output from the input with the increase of network depth, weakening expressivity and trainability. In this paper, we start by investigating refined measures upon DropEdge—an existing simple yet effective technique to relieve over-smoothing. We term our method as DropEdge++ for its two structure-aware samplers in contrast to DropEdge: layer-dependent sampler and feature-dependent sampler. Regarding the layer-dependent sampler, we interestingly find that increasingly sampling edges from the bottom layer yields superior performance than the decreasing counterpart as well as DropEdge. We theoretically reveal this phenomenon with Mean-Edge-Number (MEN), a metric closely related to over-smoothing. For the feature-dependent sampler, we associate the edge sampling probability with the feature similarity of node pairs, and prove that it further correlates the convergence subspace of the output layer with the input features. Extensive experiments on several node classification benchmarks, including both full- and semi- supervised tasks, illustrate the efficacy of DropEdge++ and its compatibility with a variety of backbones by achieving generally better performance over DropEdge and the no-drop version. Copyright © 2023, The Authors. All rights reserved.

关键词： Drops

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

学校读者我要写书评

暂无评论

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

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

Lessons learned from Successful Online computer science PD Completers in the Midst of a Pandemic 6

学校读者我要写书评

暂无评论

Lessons learned from Successful Online Computer Science PD C...

6th International Conference on Research in Equitable and Sustained Participation in Engineering, Computing, and Technology, RESPECT 2022

作者： Arreguin, Maria G. Prasad, Priya V. Zawatski, Michael J. Wilde, Jina Wilde, Darean Fernandez, Amanda S. Kalinec-Craig, Crystal Bonner, Emily P. Monsibaiz, Edward Yuen, Timothy T. University of Texas at San Antonio Interdisciplinary Learning and Teaching San Antonio United States University of Texas at San Antonio Mathematics San Antonio United States University of Texas at San Antonio Computer Science San Antonio United States

ISBN: (纸本)9781665471145

The intended audience of this experience report include computer science coordinators, computer science teachers and computer science (CS) project leaders who seek to increase Latinx participation in computer science through preparing secondary teachers to teach CS. This report narrates the challenges faced and lessons learned while designing and implementing in-service teacher professional development, CS4SA-NOW, in an online format. While the pandemic affected the completion rate of most participants, CS4SA-NOW coordinators synthesized lessons learned based on two cases involving teachers who successfully completed a series of professional development CS modules. Traits identified in these teacher participants included pedagogical and ideological clarity as well as an asset-oriented mindset. Lessons learned from this project can inform future designs of in-service teacher professional development. © 2022 IEEE.

关键词： Professional aspects

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

学校读者我要写书评

暂无评论

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

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

Hierarchical Encryption in a Residual Number System

学校读者我要写书评

暂无评论

Hierarchical Encryption in a Residual Number System

International Conference on Advanced computer Information Technologies (ACIT)

作者： Igor Yakymenko Olesya Martyniuk Serhii Martyniuk Andrii Martyniuk Yurii Yakymenko Mykhailo Kasianchuk Department of Cyber Security West Ukrainian National University Ternopil Ukraine Department of Applied Mathematies West Ukrainian National University Ternopil Ukraine Department of Computer Science and Teaching Methods Ternopil Volodymyr Hnatiuk National Pedagogical University Ternopil Ukraine Faculty of Mechanics and Mathematics Taras Shevchenko National University of Kyiv Kyiv Ukraine

ISBN: (数字)9798350350043

ISBN: (纸本)9798350350050

Within this article, a method of symmetric encryption of information based on a hierarchical residue number system has been developed. The corresponding mathematical and algorithmic framework is presented. The proposed approach simplifies hardware implementation and enhances operational speed by reducing modulus sizes and consequently numerical operands at each subsequent level, as well as by parallelizing computational processes. Utilizing this encryption method enables the creation of reliable, efficient, and resistant-to-cryptanalysis systems for protecting information streams. A encryption/decryption scheme and an application example of the method are provided.

关键词： Hardware Encryption Reliability Information technology Streams