检索结果-内蒙古大学图书馆

International Conference on Software Engineering (ICSE)

作者： Hao Guan Ying Xiao Jiaying Li Yepang Liu Guangdong Bai The University of Queensland Brisbane Australia Southern University of Science and Technology Shenzhen China UQ-SUSTech Joint Program Microsoft Software Technology Center Asia Beijing China Department of Computer Science and Engineering Research Institute of Trustworthy Autonomous Systems

Due to the great advance in machine learning (ML) techniques, numerous ML models are expanding their application domains in recent years. To adapt for resource-constrained platforms such as mobile and Internet of Things (IoT) devices, pre-trained models are often processed to enhance their efficiency and compactness, using optimization techniques such as pruning and quantization. Similar to the optimization process in other complex systems, e.g., program compilers and databases, optimizations for ML models can contain bugs, leading to severe consequences such as system crashes and financial loss. While bugs in training, compiling and deployment stages have been extensively studied, there is still a lack of systematic understanding and characterization of model optimization bugs (MOBs). In this work, we conduct the first empirical study to identify and characterize MOBs. We collect a comprehensive dataset containing 371 MOBs from TensorFlow and PyTorch, the most extensively used open-source ML frameworks, covering the entire development time span of their optimizers (May 2019 to August 2022). We then investigate the collected bugs from various perspectives, including their symptoms, root causes, life cycles, detection and fixes. Our work unveils the status quo of MOBs in the wild, and reveals their features on which future detection techniques can be based. Our findings also serve as a warning to the developers and the users of ML frameworks, and an appeal to our research community to enact dedicated countermeasures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Enhanced System for Wrong-Way Driving Vehicle Detection with Road Boundary Detection Algorithm

An Enhanced System for Wrong-Way Driving Vehicle Detection w...

引用

2022 International Conference on Industry sciences and computer science Innovation, iSCSi 2022

作者： Suttiponpisarn, Pintusorn Charnsripinyo, Chalermpol Usanavasin, Sasiporn Nakahara, Hiro TAIST Tokyo Tech ICTES Program Sirindhorn International Institute of Technology Thammasat University Pathum Thani Thailand National Electronics and Computer Technology Center National Science and Technology Development Agency Pathum Thani Thailand School of ICT Sirindhorn International Institute of Technology Thammasat University Pathum Thani Thailand Dept. of Information and Communications Engineering Tokyo Institute of Technology Tokyo Japan

Driving in the wrong direction is one of the main reasons that cause road accidents in Thailand. To efficiently detect wrong direction driving vehicles, we proposed a system that can track those moving vehicles from CCTVs using deep learning and image processing techniques. Our proposed system is composed of two main algorithms: Road Lane Boundary detection from CCTV algorithm (RLB-CCTV) and Majority-Based Correct Direction Detection algorithm (MBCDD). In this paper, we introduced the RLB-CCTV algorithm and the enhanced version of MBCDD algorithms for detecting road boundaries and wrong-direction driving vehicles. Based on our experiments, our system can identify the road lane boundary and track vehicles driving in the wrong direction on each lane with an accuracy of 96.61%. © 2022 Elsevier B.V.. All rights reserved.

关键词： Hough transforms

来源：评论

学校读者我要写书评

暂无评论

SoC-Oriented Implementation of Machine Learning Based Breast Cancer Classification Algorithm

SoC-Oriented Implementation of Machine Learning Based Breast...

引用

Mediterranean Conference on Embedded Computing (MECO)

作者： Abdelrahman Saeed Ayman Tawfik Hassan Mostafa Ahmed Hussein Khalil Electronics and Communications Engineering Department Cairo University Giza Egypt Department of Electrical and Computer Engineering Ajman University United Arab Emirates (UAE) University of Science and Technology Nanotechnology and Nanoelectronics Program Zewail City of Science and Technology Giza Egypt

Convolutional Neural Networks (CNN) have drawn the attention of researchers in the medical imaging field. Many researchers have exploited CNN for breast cancer detection. This study provides an Internet of Things (IoT) friendly implementation of CNN for breast cancer detection. To achieve faster time to Market, Deep-learning Processing Unit (DPU) on Field programmable Gate Array (FPGA) is adopted for the CNN hardware implementation. CNN inference on the proposed system achieves a 1.6x speed-up factor and 91.5% reduction in energy consumption compared to the conventional general-purpose multi-core Central Processing Unit (CPU).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring Environmentally Friendly Corrosion Inhibitors: Insights from Natural and Biomass Residue-Derived Compounds

SSRN

引用

SSRN 2024年

作者： Othman, Norinsan Kamil Mohammed, Naba Jasim Yusop, Muhammed Rahimi Al-Gburi, Ahmed Jamal Abdullah Materials Science Program Department of Applied Physics Faculty of Science and Technology University Kebangsaan Malaysia Selangor Bangi43600 Malaysia Faculty of Science and Technology School of Chemical Sciences and Food Technology University Kepangsaan Malaysia Selangor Bangi43600 Malaysia Faculty of Electronics and Computer Engineering Universiti Teknikal Malaysia Melaka Hang Tuah Jaya Melaka Durian Tunggal76100 Malaysia

In this investigation, we explored the corrosive effects of date palm seed extracted from natural sources and biomass residues on mild steel in a solution of 0.5 M hydrochloric acid (HCl), employing a combination of experimental and theoretical approaches. Our objective was to scrutinize the interaction of the inhibitor with the metal surface, analyze experimental data, and elucidate how the structural characteristics of the inhibitors influence the corrosion process. The experimental results indicated that as the immersion time and temperature increased, the inhibitory effectiveness declined. Notably, the highest level of inhibition occurred when the concentration of date palm seed extract (DPSE) reached 1100 ppm, showcasing peak inhibitory effects of 95.8% and 97.8% through potentiodynamic polarization and electrochemical impedance spectroscopy techniques, respectively. Additionally, an analysis using X-ray diffraction (XRD) was conducted to scrutinize the chemical composition of the mild steel's surface. The adsorption data were evaluated using adsorption isotherms, revealing that DPSE adhered to the Langmuir adsorption isotherm on the mild steel surface. The Langmuir model exhibited the highest linear regression coefficient value and a slope close to unity. The Gibbs free energy () values suggested that the protection afforded by DPSE involved physical and spontaneous absorption. Examination of the results pertaining to the highest occupied molecular orbital (HOMO) and lowest unoccupied molecular orbital (LUMO) indicated that the carboxyl (COOH) group and the C=C bond were the principal regions exhibiting elevated electron acceptance activity. These components were found to be crucial in the adsorption process on the surface of iron (Fe). © 2024, The Authors. All rights reserved.

关键词： Electrochemical impedance spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Arabic text sentiment analysis and emotion classification using transformers

Arabic text sentiment analysis and emotion classification us...

引用

Electronics, Communications, and Computations (JAC-ECC), International Japan-Africa Conference on

作者： Nada Mossad Youssef Mohamed A Fares Ahmed B. Zaky Egypt-Japan University of Science and Technology (E-JUST) Alexandria Egypt The Department of Electrical Engineering The Computer Systems Engineering Program Faculty of Engineering at Shoubra Benha University

Sentiment analysis and emotion classification are two crucial components of natural language processing (NLP), which have been widely explored in recent years due to their broad applications. Sentiment analysis aims to identify the polarity of written texts, ranging from positive to negative. Meanwhile, emotion classification is focused on recognizing and categorizing the emotional states expressed in the text. To achieve a deeper understanding of sentiments and emotions, it's essential to utilize models like BERT transformers that can effectively interpret the context. The process begins with data preprocessing, including tokenization and noise removal, followed by fine-tuning techniques to adapt the BERT model to the proposed tasks. We employed the BERT model on four datasets obtained from various sources, including Twitter, news websites, and restaurant reviews, where each dataset represents a distinct Arabic dialect. Our proposed model outperforms commonly used techniques like LSTM and CNN, yielding superior results. Despite the progress made, there are still challenges to overcome, such as dealing with Arabic diacritics, the new Arabic Arabizi, which uses Latin characters, and handling Arabic idioms. Further research is required to address these challenges adequately.

关键词：

来源：评论

学校读者我要写书评

暂无评论

引用

International Conference of computer and Informatics Engineering (IC2IE)

作者： Wandy Wandy Kusworo Adi Media Anugerah Ayu Doctoral Program of Information Systems School of Postgraduate Studies Diponegoro University Semarang Indonesia Department of Physics Faculty of Science and Mathematics Diponegoro University Semarang Indonesia Department of Computer Science Faculty of Engineering and Technology Sampoerna University South Jakarta Indonesia

ISBN: (数字)9798331505530

ISBN: (纸本)9798331505547

Full-marathon and Half-marathon distances are categorized as road running. Full-marathon running is becoming increasingly popular, and Half-marathon is increasing worldwide in both sexes and all age groups. Some aspects might relate to Full-marathon and Half-marathon running performance during training and races. technology also plays an essential role in supporting runners and running races. technology like artificial intelligence (AI) now supports the running athlete, not only predicting performance and results. It can also be used later to help the coach generate training programs for the athlete. This research aimed to find many aspects of marathons and performance and analyze them to see if artificial intelligence could later support them. It used secondary data and a systematic literature review proposed by Kitchenham. Out of the 58 articles, 21 of them (36.21%) received a score of 1 from Q1. Additionally, 19 articles (32.76%) received a score of 1 from both Q2 and Q3. Among the 58 articles, 9 (15.52%) received a total score of 3, with all three Q1, Q2, and Q3 scores being 1. This indicates that artificial intelligence will likely support the content of these nine articles. Several factors were also discovered to be connected to marathons and athletic performance. These findings suggested that additional investigation into marathons and performance, later backed by artificial intelligence, remained pertinent and essential.

关键词： Training Roads Artificial intelligence Informatics

来源：评论

学校读者我要写书评

暂无评论

The effect of real-time pose recognition on badminton learning performance

引用

Interactive Learning Environments 2023年第8期31卷 4772-4786页

作者： Lin, Kuo-Chin Ko, Cheng-Wen Hung, Hui-Chun Chen, Nian-Shing Center for Physical and Health Education National Sun Yat-sen University Kaohsiung Taiwan Department of Computer Science and Engineering National Sun Yat-sen University Kaohsiung Taiwan Graduate Institute of Network Learning Technology National Central University Chung-Li Taiwan Institute for Research Excellence in Learning Sciences and Program of Learning Sciences National Taiwan Normal University Taipei Taiwan

Badminton is a very popular subject in Physical Education (PE). Many students enroll badminton courses in every semester which pose a tremendous teaching load to the instructors. The one-on-one guiding/feedback time provided by the instructor to each student is also greatly reduced. To overcome this challenge, some studies have tried to adopt pose recognition technique in teaching badminton. However, the lack of mobility and recognition accuracy problems hinder its applicability. To address this issue, a new pose recognition technique, OpenPose, was employed to develop a real-time pose recognition badminton teaching APP in this study. The APP was then installed on a mobile device to enhance badminton smash skill learning performance. The scores distribution of the experimental group shows majority of students achieved satisfactory performance, this implies the badminton teaching APP is helpful to all students no matter what their initial skill levels are. © 2021 Informa UK Limited, trading as Taylor & Francis Group.

关键词： badminton teaching motor skill learning physical education Pose recognition real-time feedback

来源：评论

学校读者我要写书评

暂无评论

Ant Colony Optimization Algorithm Enhancement for Better Performance

Ant Colony Optimization Algorithm Enhancement for Better Per...

引用

AI IoT Congress (AIIoT), World

作者： Mohammed Faisal Fahad Albogamy Center of AI & Robotics (CAIR) Kuwait College of Science and Technology (KCST) Kuwait Computer Sciences Program Turabah University College Taif University Taif Saudi Arabia

The scientific field of swarm intelligence is related to swarms existing in natural systems. Numerous systems and Algorithms built on swarm intelligence have appeared addressing optimization problems, including: Firefly Algorithm (FA), Ant System (AS), Particle Swarm Optimization (PSO), Intelligent Water Drops (IWD), Ant Colony Optimization (ACO), Artificial Bee Colony (ABC), and many others. The foraging behavior of the ant’s system inspired the researchers to generate the ACO and use it to solve optimization problems. In this research, we introduce the ACOStar algorithm to improve the performance of ACO by including the evaluation function of A* algorithm on the transition-probability function of ACO. To demonstrate the success of the proposed algorithm, we applied the suggested algorithm to the shortest path problem. All experiments demonstrate the success and the accuracy of the proposed algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of Agile Scrum Methodology in P4AI Application Development 8

Implementation of Agile Scrum Methodology in P4AI Applicatio...

引用

8th International HCI and UX Conference in Indonesia, CHIuXiD 2022

作者： Sasmoko Indrianti, Yasinta Manalu, Sonya Rapinta Bina Nusantara University Faculty of Humanities Primary Teacher Education Department Jakarta11480 Indonesia Podomoro University Entrepreneurship Department Jakarta Indonesia School of Computer Science Bina Nusantara University Mobile Application and Technology Program Jakarta11480 Indonesia

ISBN: (纸本)9781665476645

The profiling for Aptitude Inventory (P4AI) application is an application developed to help students carry out self-Assessments so they can understand the interests of the appropriate majors and careers. The application was developed using the agile scrum methodology, which is a software engineering method that applies the principles of the AGILE approach so that it relies on the strength of team collaboration, incremental product, and iterative processes to realize the product with the best final result. The Scrum. The purpose of this study was to evaluate whether the scrum methodology applies to the requirements of application development. The results of the research are several outputs from the Agile Scrum Methodology process which is implemented in the development of the artificial intelligence based P4AI Application aptitude test website. © 2022 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Towards the Improvement of the Cognitive Process of the Synthesized Speech of Mathematical Expression in MathML: An Eye-Tracking 2

Towards the Improvement of the Cognitive Process of the Synt...

引用

2nd International Conference on Interactive Media, Smart Systems and Emerging Technologies, IMET 2022

作者： Souza, Adriana Freitas, Diamantino Bahia Federal Institute of Education Science and Technology Bahia Brazil Doctoral Program in Digital Media Faculty of Engineering of the University of Porto Porto Portugal Faculty of Engineering of the University of Porto Speech Processing Laboratory Electrical and Computer Engineering Department Porto Portugal

ISBN: (数字)9781665470162

ISBN: (纸本)9781665470162

Being one essential part of the solutions we are developing to provide accessibility for blind persons, synthesized speech of mathematical content, although having evolved in naturalness in recent years, still keeps a characteristic of generating very long outputs, which makes it difficult for a person who uses a screen reader to memorize. Eye-gaze tracking has been useful for studying cognitive processes and student's effort in performing tasks therefore it seems attractive as a means to understand how people analyze, process, and break down extensive math expressions into smaller ones. This understanding can help to build a similar model of auditory rendering of MathML capable of avoiding cognitive overload. Therefore, we carried out an experiment to do a gaze-based analysis of reading and memorizing mathematical expressions. Our sample consisted of fourteen participants, and seven mathematical expressions were used in the experiment. The results showed that the computed complexity of the expressions and the average duration of eye-gaze fixations have a strong and significant relationship. Therefore, we conclude that the complexity variable must always be considered in the speech synthesis process of mathematical expressions. However, when considering why participants requested the repetition of an expression with not larger complexity during the memorization process, a tentative interpretation based on the number of MathML tree nodes and the computed complexity of the expressions was not enough to explain it, indicating that other factors need to be investigated. Although some answers to the research questions were not yet conclusive, we consider this research relevant because it points to directions for the work in order to minimize the cognitive processing and mental load of the synthesized speech rendering of mathematical expressions. © 2022 IEEE.

关键词： Eye tracking

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：