检索结果-内蒙古大学图书馆

12th International Conference on Learning Representations, ICLR 2024

作者： Ye, Feiyang Lyu, Yueming Wang, Xuehao Zhang, Yu Tsang, Ivor W. Department of Computer Science and Engineering Southern University of Science and Technology China Australian Artificial Intelligence Institute University of Technology Sydney Australia Centre for Frontier AI Research Agency for Science Technology and Research Singapore Institute of High Performance Computing Agency for Science Technology and Research Singapore Shanghai Artificial Intelligence Laboratory China School of Computer Science and Engineering Nanyang Technological University Singapore

Multi-objective optimization (MOO) has become an influential framework for various machine learning problems, including reinforcement learning and multitask learning. In this paper, we study the black-box multi-objective optimization problem, where we aim to optimize multiple potentially conflicting objectives with function queries only. To address this challenging problem and find a Pareto optimal solution or the Pareto stationary solution, we propose a novel adaptive stochastic gradient algorithm for black-box MOO, called ASMG. Specifically, we use the stochastic gradient approximation method to obtain the gradient for the distribution parameters of the Gaussian smoothed MOO with function queries only. Subsequently, an adaptive weight is employed to aggregate all stochastic gradients to optimize all objective functions effectively. Theoretically, we explicitly provide the connection between the original MOO problem and the corresponding Gaussian smoothed MOO problem and prove the convergence rate for the proposed ASMG algorithm in both convex and non-convex scenarios. Empirically, the proposed ASMG method achieves competitive performance on multiple numerical benchmark problems. Additionally, the state-of-the-art performance on the black-box multi-task learning problem demonstrates the effectiveness of the proposed ASMG method. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

DNBP-CCA:A Novel Approach to Enhancing Heterogeneous Data Traffic and Reliable Data Transmission for Body Area Network

引用

computers, Materials & Continua 2024年第5期79卷 2851-2878页

作者： Abdulwadood Alawadhi Mohd.Hasbullah Omar Abdullah Almogahed Noradila Nordin Salman A.Alqahtani Atif M.Alamri InterNetWorks Research Laboratory School of ComputingUniversiti Utara MalaysiaSintok06010Malaysia Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn MalaysiaParit RajaJohor86400Malaysia School of Games&Creative Technology University for the Creative ArtsFarnhamGU97DSUK Computer Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia Software Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia

The increased adoption of Internet of Medical Things (IoMT) technologies has resulted in the widespread use ofBody Area Networks (BANs) in medical and non-medical domains. However, the performance of IEEE 802.15.4-based BANs is impacted by challenges related to heterogeneous data traffic requirements among nodes, includingcontention during finite backoff periods, association delays, and traffic channel access through clear channelassessment (CCA) algorithms. These challenges lead to increased packet collisions, queuing delays, retransmissions,and the neglect of critical traffic, thereby hindering performance indicators such as throughput, packet deliveryratio, packet drop rate, and packet delay. Therefore, we propose Dynamic Next Backoff Period and Clear ChannelAssessment (DNBP-CCA) schemes to address these issues. The DNBP-CCA schemes leverage a combination ofthe Dynamic Next Backoff Period (DNBP) scheme and the Dynamic Next Clear Channel Assessment (DNCCA)scheme. The DNBP scheme employs a fuzzy Takagi, Sugeno, and Kang (TSK) model’s inference system toquantitatively analyze backoff exponent, channel clearance, collision ratio, and data rate as input parameters. Onthe other hand, the DNCCA scheme dynamically adapts the CCA process based on requested data transmission tothe coordinator, considering input parameters such as buffer status ratio and acknowledgement ratio. As a result,simulations demonstrate that our proposed schemes are better than some existing representative approaches andenhance data transmission, reduce node collisions, improve average throughput, and packet delivery ratio, anddecrease average packet drop rate and packet delay.

关键词： Internet of Medical Things body area networks backoff period tsk fuzzy model clear channel assessment media access control

来源：评论

学校读者我要写书评

暂无评论

Gyroscope Aided Blur Kernel Estimation for IR Image Deblurring

Gyroscope Aided Blur Kernel Estimation for IR Image Deblurri...

引用

2023 International Conference on computer, Electronics and Electrical Engineering and their Applications, IC2E3 2023

作者： Singh, Kaustubh Saurabh Diwakar, Manoj Singh, Prabhishek Arya, Chandrakala Deemed to Be University Cse Graphic Era Dehradun India Bennett University School of Computer Science Engineering and Technology Greater Noida India Graphic Era Hill University School of Computing Dehradun India

ISBN: (纸本)9798350338003

Stabilized Electro-Optical Systems are used in multiple domains, like target detection, tracking, and area surveillance. Cooled thermal imagers are used for long range surveillance. The requirement of a fast steering speed of the gimbal during surveillance induces blur in the captured IR video frames, which is required to be correct in real-time. Existing blind deblurring methods take a long time to execute. Deep learning methods are fast but cannot be generalised for all practical scenarios. In this work, we propose a noble blur kernel estimation method, using inertial sensor, and integrate it with existing non-blind deblurring methods and a sensor based deep learning method. Our method shows good results and is a suitable candidate for deblurring the image captured by gimbal-based imaging systems. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

The Evolvement of E-learning in the 21st Century-A Literature Review

The Evolvement of E-learning in the 21st Century-A Literatur...

引用

2021 IEEE International Conference on Artificial Intelligence and computer Applications, ICAICA 2021

作者： Sun, Geng Huang, Zhenghong Yue, Lin Lu, Jiangkun Xue, Zheng Zhai, Qishi Chen, Hongyang Feng, Qingrong School of Computer Engineering Zte Ict University Chongqing College of Humanities Science and Technology Chongqing China Australian Catholic University Peter Faber Business School North Sydney Australia University of Wollongong School of Computing and Information Technology Wollongong Australia

ISBN: (纸本)9781665418676

This literature review examines the literature on curation in e-learning and some of the common themes used in e-learning research. In more detail, this literature review focuses on the development of web-based learning, how e-learning is initiated, the characteristics, specifications, shortcomings, and how it will develop in the future. For educators engaged in e-learning, different levels of experience in the e-learning system, education level, communication skills, and experience in managing technical issues in the system will show different levels of performance. © 2021 IEEE.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent personalised learning system based on emotions in e-learning

引用

Personal and Ubiquitous computing 2023年第6期27卷 2211-2223页

作者： Karthika, R. Jesi, V. Elizabeth Christo, Mary Subaja Deborah, L. Jegatha Sivaraman, Audithan Kumar, Sanjeev Department of Computer Science and Engineering University College of Engineering Tindivanam Tamil Nadu Melpakkam604001 India Department of Networking and Communications School of Computing College of Engineering SRM Institute of Science and Technology Chennai Kattankulathur603203 India Department of Information Technology Netaji Subhas University of Technology New Delhi110078 India Department of Electronics and Communication Engineering Netaji Subhas University of Technology New Delhi110078 India

One of the greatest challenges in the success of a personalised e-learning system lies in the behaviour identification of the learners during the learning and evaluation phase. The content delivery in an e-learning system must be modified and updated periodically according to the preference and behaviour of the learners. Usually, the behaviour of the learners drastically changes according to their affective states during the learning phase. The accurate identification of the learner’s negative emotions and addressing such emotions carefully in a positive sense can greatly provide success to the learners. In this paper, the learner’s emotions especially frustration emotion are automatically and accurately estimated using the information received from learning management systems (LMS) using the Takagi sugeno fuzzy inference engine. Based on this estimation, several motivational messages are distributed according to the identified emotions which had greatly helped them to succeed during e-learning. The motivational messages that are used for sending to the learners are based on regulatory fit theory. Several kinds of statistical tests are used in this paper for deep analysis. Two sets of learners, namely, control and experimental sets, are identified from undergraduate students. Experimental results are shown for these two sets to reveal the increase in their emotional strength after receiving the motivational messages. Statistical analysis t-test is also applied to the two sets, and the experimental results have shown that there is a significant difference between the two groups which shows the dominance of the proposed system. © 2023, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Image-Based Extraction of Prescription Information using OCR-Tesseract

引用

Procedia computer science 2024年 235卷 1077-1086页

作者： Mahesh Ponnuru Sridevi Ponmalar P Likhitha A Tanu sree B Guna Chaitanya G School of Computing SRM Institute of Science and Technology Potheri 603203 India Department of Computational Intelligence School of ComputingFaculty of Engineering and Technology SRM Institute of Science and Technology Potheri 603203 India School of Computer Science Vellore institute of technology Amaravathi 522237 India

The paper presents advancements in healthcare data capture through the application of image-based extraction techniques, which include sophisticated image processing techniques such as resizing and adaptive thresholding, for prescription information. With the increasing digitization of medical records, automating the extraction of relevant data from prescription documents has become crucial. This research explores the utilization of image processing and optical character recognition (OCR) methodologies to extract prescription information accurately. By converting prescription documents into image format and employing OCR algorithms, the text content is extracted and parsed for critical details such as medication names, dosages, and patient instructions. Notably, our methodology excels in overcoming limitations associated with handwritten documents, achieving an impressive accuracy rate of 98%. This image-based approach offers a streamlined and efficient method for capturing prescription data, reducing manual data entry efforts, and minimizing potential errors. Experimental evaluations demonstrate the effectiveness and accuracy of the proposed approach, highlighting its potential to enhance healthcare data capture and improve patient care.

关键词： Health care Data capture Prescription information Medical records OpenCv Image processing OCR

来源：评论

学校读者我要写书评

暂无评论

ET5: A Novel End-to-end Framework for Conversational Machine Reading Comprehension 29

ET5: A Novel End-to-end Framework for Conversational Machine...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Zhang, Xiao Huang, Heyan Chi, Zewen Mao, Xian-Ling School of Computer Science and Technology Beijing Institute of Technology China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China Southeast Academy of Information Technology Beijing Institute of Technology China

Conversational machine reading comprehension (CMRC) aims to assist computers to understand an natural language text and thereafter engage in a multi-turn conversation to answer questions related to the text. Existing methods typically require three steps: (1) decision making based on entailment reasoning;(2) span extraction if required by the above decision;(3) question rephrasing based on the extracted span. However, for nearly all these methods, the span extraction and question rephrasing steps cannot fully exploit the fine-grained entailment reasoning information in decision making step because of their relative independence, which will further enlarge the information gap between decision making and question phrasing. Thus, to tackle this problem, we propose a novel end-to-end framework for conversational machine reading comprehension based on shared parameter mechanism, called entailment reasoning T5 (ET5). Despite the lightweight of our proposed framework, experimental results show that the proposed ET5 achieves new state-of-the-art results on the ShARC leaderboard with the BLEU-4 score of 55.2. Our model and code are publicly available © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

The packing problem of uncertain multicasts

The packing problem of uncertain multicasts

引用

作者： Ren, Bangbang Guo, Deke Xie, Junjie Li, Wenxin Yuan, Bo Liu, Yunfei Science and Technology on Information Systems Engineering Laboratory National University of Defense Technology Changsha China School of Computer Science and Technology Dalian University of Technology Dalian China Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guangxi Colleges and Universities Key Laboratory of Cloud Computing and Complex Systems Guilin University of Electronic Technology Guilin China

Multicast performs better than unicast in delivering the same content from a fixed single source to a set of destinations. Many efforts have been made to optimize such kind of deterministic multicast, such as minimizing the transmission cost of each multicast session. In practice, it is not necessary that the source of each multicast session has to be in a specific location, as long as certain constraints are satisfied. Accordingly, applications usually meet a novel multicast with uncertain sources, ie, uncertain multicast. That is, multiple nodes have the responsibility to act as the root node of a multicast session. Prior proposals have addressed an uncertain multicast by constructing the minimum cost forest. However, it is still unknown how to efficiently share the network resources, when a set of uncertain multicast occupies the network simultaneously. To tackle such a challenging issue, we present the packing problem of uncertain multicasts (MPU) to minimize the total transmission cost, under the constraint of link capacity. We prove that the MPU problem is NP-hard. An intrinsic solution is constructing the minimum cost forest for each uncertain multicast individually. This method, however, is inefficient and may be infeasible because of the constraint of link capacity. Thus, we design 2 dedicated greedy methods, named priority-based and adjusting congested link, to approximate the optimal solution. The comprehensive results indicate that both of our 2 methods can find a feasible solution for the MPU problem. Moreover, given a set of uncertain multicasts, the adjusting congested link method can generate a desired transmission structure for each uncertain multicast and achieve the least total cost when packing them. Copyright © 2016 John Wiley & Sons, Ltd.

关键词： Routing algorithms

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of web-based dynamic geometry drawing technology

引用

The Journal of China Universities of Posts and Telecommunications 2019年第6期26卷 43-53页

作者： Guan Hao Rao Yongsheng Xu Zhangtao Chengdu Institute of Computer Application Chinese Academy of SciencesChengdu 610041China University of Chinese Academy of Sciences Beijing 100049China Institute of Computing Science and Technology Guangzhou UniversityGuangzhou 510006China School of Mathematics and Statistics Central China Normal UniversityWuhan 430079China

Dynamic geometry software, as a piece of computer-assisted instruction(CAI) software, is closely and deeply associated with mathematics, and is widely applied to mathematics teaching activities in primary and secondary schools. Meanwhile, web technology also has become an important technology for assisting education and teaching. This paper expounds a web-based dynamic geometry software development process, and analyses specific requirements regarding graphical application programming interface(API) required by dynamic geometry software. With experiments and comparison on the two different hypertext markup language(HTML)5 graphical API technologies, i.e., scalable vector graphics(SVG) and Canvas, on different apparatuses and browsers, we draw the conclusion that it is more suitable to adopt Canvas as the graphical API technology for the web-based dynamic geometry software, thus further proposed the principles and methods for an object-oriented Canvas design. The dynamic geometry software based on the newly-designed Canvas has technical advantages and educational value, well incorporating aesthetic education into mathematics education.

关键词： web Canvas dynamic geometry subject tools

来源：评论

学校读者我要写书评

暂无评论

LBBGEMM: A Load-balanced Batch GEMM Framework on ARM CPU s 24

LBBGEMM: A Load-balanced Batch GEMM Framework on ARM CPU s

引用

24th IEEE International Conference on High Performance computing and Communications, 8th IEEE International Conference on Data science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Wei, Cunyang Jia, Haipeng Zhang, Yunquan Li, Kun Wang, Luhan Institute of Computing Technology Chinese Academy of Sciences State Key Lab of Processors Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Microsoft Research China

ISBN: (纸本)9798350319934

The trend in modern high performance computing is to decompose a large linear algebraic problem into many small problems that can be solved independently. Although there are many studies to obtain near-peak performance for large-scale dense matrix operations, it is not sufficient for batch operations with small matrices. The study of small GEMM kernel optimization and load balanced scheduling of batch operations on ARM processors is not enough. In this paper, we present LBBGEMM, a load-balanced batch GEMM framework for optimizing large groups of variable-size small GEMM to boost near-optimal performance based on ARMv8 architecture. The LBBGEMM is divided into the install-time stage and the run-time stage. At the install-time stage, we analyze the characteristics of each transposition mode to design the high-performance small GEMM kernel without data packing. This strategy greatly reduces the memory access overhead. In addition, we optimize instruction scheduling and instruction selection carefully to achieve optimal performance. The run-time stage provides a comprehensive auto-tuning process for batch GEMM by using a tiling designer and a pre-grouped dynamic scheduling algorithm. The tiling designer generates high-performance execution plans for each group of matrices with different sizes. Then we divide the large group of GEMM operations into small task groups. These task groups are assigned to threads for execution in the form of command queues through our proposed dynamic mapping between threads and tasks. This pre-grouped multi-thread task scheduling algorithm greatly improves the speedup of multi-thread. The experiments show that LBBGEMM could achieve significant performance improvements in batch GEMM compared with other mainstream BLAS libraries. © 2022 IEEE.

关键词： Matrix algebra

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：