检索结果-内蒙古大学图书馆

3rd International Conference on Embedded Systems and Artificial Intelligence, ESAI 2024

作者： Sharan, Sudeep Thanh, Hung Do Nauth, Peter Dominguez-Jimenez, Juan Jose Frankfurt University of Applied Sciences Faculty of Computer Science and Engineering Frankfurt am Main Germany University of Cádiz UCASE Software Engineering Group School of Engineering Cádiz Spain

ISBN: (纸本)9798331522056

This paper presents an object detection and classification of the objects using Deep Learning (DL). The integration of object detection algorithms and depth camera developed is capable of providing robots, such as self developed assistive intelligent robot called 'ROSWITHA' (RObot System WITH Autonomy) with the ability to detect an object and interpret their surrounding environment. It also provides the real-world coordinates/position of the object in that environment, which helps the robot to perform some applications, such as grabbing and serving, etc. You Only Look Once (YOLO) is one of the most popular object detection algorithms which is treated as a single regression problem and is processed by a single neural network. In this work, the YOLOv5 (YOLO version 5) network is implemented on a depth camera 'RealSense' for processing object detection and estimating the position of the objects. The model is trained on reduced/filtered application-required objects (e.g. bottle and cup) from the available COCO dataset, and the training outcome alongside the performance of the overall system was evaluated. The results exhibited a satisfactory performance of the model in accurately detecting and classifying the objects with a high confidence score ranging from the least to7 2% to the highest of9 0%. The confidence score could also be adjusted by the user on the developed GUI to attain the most certain predictions. © 2024 IEEE.

关键词： Bottles

来源：评论

学校读者我要写书评

暂无评论

Improving Code Coverage for Structural Testing by using Parametric Inter-procedural Slicing

Improving Code Coverage for Structural Testing by using Para...

引用

2023 IEEE Conference on computer Applications, ICCA 2023

作者： Aung, Myint Myitzu Win, Kay Thi University of Computer Studies Software Engineering Lab Mandalay Mandalay Myanmar University of Computer Studies Faculty of Information Science Mandalay Mandalay Myanmar

ISBN: (纸本)9781665435994

Structural testing is one of the testing techniques in software testing. It is the testing process of internal structure in the given source code by comparing the expected result and real results and finding out faults. To complete the structural testing, it takes a long time and needs to improve code coverage. Thus, this paper focus on improving code coverage of structural testing by using parametric inter-procedural slicing with backward slicing technique. In program slicing, there are two types of slicing: forward and backward slicing depending on the slicing direction. In this paper, backward slicing is used and it starts at the criteria for the slice consideration. The parametric inter-procedural slicing is one of the program slicing techniques which is an algorithm that takes the slice criteria as a parameter and work to handle inter-procedural data flow by considering many possible dependence relations. By slicing the original input program before measuring code coverage, the input program is simplified and excluded unexecutable statements. Therefore, the proposed system in this paper can reduce the complexity of the source code and improve code coverage for structural testing. Moreover, the used dataset in experiment is benchmark dataset in C and it is converted to Java for the improvement of language oriented. © 2023 IEEE.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

Unveiling Interpretability: Analyzing Transfer Learning in Deep Learning Models for Traffic Sign Recognition

引用

SN computer Science 2024年第6期5卷 682页

作者： Waziry, Sadaf Rasheed, Jawad Ghabban, Fahad Mahmoud Alsubai, Shtwai Elkiran, Harun Alqahtani, Abdullah Department of Software Engineering Istanbul Aydin University Isanbul 34295 Turkey Department of Computer Engineering Istanbul Sabahattin Zaim University Istanbul 34303 Turkey Faculty of Computer Science and Engineering Taibah University Medina Saudi Arabia College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al Kharj 11942 Saudi Arabia

Since the advent of automobiles and driver assistance technologies, traffic sign recognition has been of the utmost importance for Industry 4.0. In the driving system, good data pre-processing is critical. For such objectives, sophisticated transformations or fundamentally computational image processing approaches are out of the question. Convolutional Neural Networks (CNN) have been used to perform more object identification challenges, thus, improving most computer vision applications, both existing and new, because of their excellent recognition rate and rapid execution. This study introduces a method for recognizing traffic signs by utilizing a CNN-based model and the transfer learning concept. The TensorFlow library is used for training the underlying neural network model. The offered approach makes use of the German Traffic Sign Recognition Benchmark (GTSRB) and images from the Traffic Sign Images from Turkey (TSIT) databases. These datasets are dependable and vibrant, and they have been used to train many algorithms. Furthermore, after training the model, the proposed scheme acquired a testing accuracy is 99.44%. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： CNN German traffic sign Image processing Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Deployment of Polar Codes for Mission-Critical Machine-Type Communication Over Wireless Networks

引用

computers, Materials & Continua 2022年第4期71卷 573-592页

作者： Najib Ahmed Mohammed Ali Mohammed Mansoor Rodina Binti Ahmad Saaidal Razalli Bin Azzuhri Department of Software Engineering Faculty of Computer Science and Information TechnologyUniversity of Malaya50603Kuala Lumpur Malaysia 2Department of Computer System&TechnologyFaculty of Computer Science and Information TechnologyUniversity of Malaya50603Kuala LumpurMalaysia

Mission critical Machine-type Communication(mcMTC),also referred to as Ultra-reliable Low Latency Communication(URLLC),has become a research *** is primarily characterized by communication that provides ultra-high reliability and very low latency to concurrently transmit short commands to a massive number of connected *** the reduction in physical(PHY)layer overhead and improvement in channel coding techniques are pivotal in reducing latency and improving reliability,the current wireless standards dedicated to support mcMTC rely heavily on adopting the bottom layers of general-purpose wireless standards and customizing only the upper *** mcMTC has a significant technical impact on the design of all layers of the communication protocol *** this paper,an innovative bottom-up approach has been proposed for mcMTC applications through PHY layer targeted at improving the transmission reliability by implementing ultra-reliable channel coding scheme in the PHY layer of IEEE 802.11a standard bearing in mind short packet transmission *** achieve this aim,we analyzed and compared the channel coding performance of convolutional codes(CCs),low-density parity-check(LDPC)codes,and polar codes in wireless network on the condition of short data packet *** Viterbi decoding algorithm(VA),logarithmic belief propagation(Log-BP)algorithm,and cyclic redundancy check(CRC)successive cancellation list(SCL)(CRC-SCL)decoding algorithm were adopted to CC,LDPC codes,and polar codes,***,a new PHY layer for mcMTC has been *** reliability of the proposed approach has been validated by simulation in terms of Bit error rate(BER)and packet error rate(PER)***-to-noise ratio(SNR).The simulation results demonstrate that the reliability of IEEE 802.11a standard has been significantly improved to be at PER=10−5 or even better with the implementation of polar *** results also show that the general-purpose wireless net

关键词： Machine-type communication mission-critical applications MTC URLLC M2M wireless networks polar codes

来源：评论

学校读者我要写书评

暂无评论

A Proposal for a New E-Waste Image Dataset Based on the UNU-KEYS Classification 23

A Proposal for a New E-Waste Image Dataset Based on the UNU-...

引用

23rd International Symposium on Electrical Apparatus and Technologies, SIELA 2024

作者： Iliev, Dimitar I. Marinov, Marin B. Ortmeier, Frank Technical University of Sofia Faculty of German Engineering and Industrial Management Sofia Bulgaria Technical University of Sofia Faculty of Electronic Engineering and Technologies Department of Electronics Sofia Bulgaria Otto-von-Guericke-University Magdeburg Faculty of Computer Science Software Engineering Magdeburg Germany

ISBN: (纸本)9798350382365

This paper introduces the largest and most diverse e-waste dataset to date, consisting of 19,613 pictures, 28,941 annotations, and 77 classes, where each class represents one visually distinctive type of electronic device. Furthermore, our dataset was structured using the United Nations University's UNU-KEYS classification, which ensures the compatibility of our dataset with the different e-waste classifications used worldwide and allowed us to choose more relevant dataset classes. The proposed methodology for image collection, annotation, and labeling is explained. The advantages and disadvantages of this dataset and how it can be improved in the future are presented. This dataset has been made open source with a permissive CC by 4.0 license so that it can be used to stimulate scientific progress in the field of automatic e-waste recognition, with the end goal of solving the global e-waste problem. The dataset is available online at https://***/electronic-waste-detection/e-waste-dataset-r0ojc. © 2024 IEEE.

关键词： dataset e-waste object detection UNU-KEYS WEEE

来源：评论

学校读者我要写书评

暂无评论

Cleaning Uncertain Time Series Based on Random Walk Sampling 4

Cleaning Uncertain Time Series Based on Random Walk Sampling

引用

4th International Conference on High Performance Big Data and Intelligent Systems, HDIS 2022

作者： Zhou, Delin Sun, Jizhou Jiang, Bo Hudoyberdi, Toshboev Lin, Jianchu Huaiyin Institute of Technology Faculty of Computer and Software Engineering Huai'an China

ISBN: (数字)9781665491440

ISBN: (纸本)9781665491440

In the era of big data, there are many different data types, and time series data makes up a large portion of observational data. However, when using sensors to collect time series data, the observation values are not very accurate due to the quality of the sensors and the observation errors. So how to estimate true data from multiple uncertain sensors' observations has becoming a hot research topic in IoT and big data fields. Several data cleaning methods for time series have been proposed, but many of them have strong constraints. Intuitively, if two observations are close, their contributions to true data estimation should be similar. According to this idea, in this paper we propose a novel data cleaning and truth discovery method named RWTD for time series based on random walk sampling. Distances between observations are calculated to build a state graph, and random walk sampling is used to estimate the weights of data sources. True data is estimated as the weighted sum of observations. Experimental results demonstrate the effectiveness of our method. © 2022 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

YOLO-BTM: A Novel Shuttlecock Detection Method for Embedded Badminton Robots

YOLO-BTM: A Novel Shuttlecock Detection Method for Embedded ...

引用

2022 International Conference on Automation, Robotics and computer engineering, ICARCE 2022

作者： Zhang, Yimin Chen, Chuxuan Hu, Ronglin Huaiyin Institute of Technology Faculty of Computer & Software Engineering Huai'an China

ISBN: (纸本)9781665475488

Employing robots in badminton training contributes to a more accurate analysis of an athlete's movements and helps avoid injuries. Shuttlecock detection during the flying stage is a critical component of the badminton robot design. However, previous shuttlecock localization methods were unable to detect shuttlecock quickly and accurately in embedded device-based badminton robots, given scale variations, few extractable features, occlusion, and device limitation. In this paper, a deep learning-based shuttlecock localization method is proposed. First, an indoor shuttlecock dataset including 9548 shuttlecock images of various angles and scenes was constructed. Then a shuttlecock detection method YOLO-BTM is proposed, which is based on YOLOv4-Tiny. We proposed a new convolution block to replace the cross-stage partially block in the backbone, to improve the detection speed. To improve the network's ability to detect small objects, the efficient channel attention block is introduced in feature fusion. Finally, a comparative experiment on the accuracy of the method and the detection speed was conducted. The results show that the proposed YOLO-BTM has better performance in detection speed and accuracy compared to the existing state-of-the-art object detection methods on our own shuttlecock dataset. Our method enables real-time, accurate localization of shuttlecock and has the potential to be used in other embedded device based sports robots. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Comprehensive analysis of multiple machine learning techniques for rock slope failure prediction

引用

Journal of Rock Mechanics and Geotechnical engineering 2024年第11期16卷 4386-4398页

作者： Arsalan Mahmoodzadeh Abed Alanazi Adil Hussein Mohammed Hawkar Hashim Ibrahim Abdullah Alqahtani Shtwai Alsubai Ahmed Babeker Elhag Department of Civil Engineering University of HalabjaHalabjaKurdistan Region46018Iraq Department of Computer Science College of Computer Engineering and Sciences in Al-KharjPrince Sattam bin Abdulaziz UniversityP.O.Box 151Al-Kharj11942Saudi Arabia Department of Communication and Computer Engineering Faculty of EngineeringCihan University-ErbilKurdistan RegionIraq Department of Civil Engineering College of EngineeringSalahaddin University-Erbil44002ErbilKurdistan RegionIraq Software Engineering Department College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityP.O.Box 151Al-Kharj11942Saudi Arabia Department of Civil Engineering College of EngineeringKing Khalid UniversityAbha61413Saudi Arabia

In this study,twelve machine learning(ML)techniques are used to accurately estimate the safety factor of rock slopes(SFRS).The dataset used for developing these models consists of 344 rock slopes from various open-pit mines around Iran,evenly distributed between the training(80%)and testing(20%)*** models are evaluated for accuracy using Janbu's limit equilibrium method(LEM)and commercial tool GeoStudio *** assessment metrics show that the random forest model is the most accurate in estimating the SFRS(MSE=0.0182,R2=0.8319)and shows high agreement with the results from the LEM *** results from the long-short-term memory(LSTM)model are the least accurate(MSE=0.037,R2=0.6618)of all the models ***,only the null space support vector regression(NuSVR)model performs accurately compared to the practice mode by altering the value of one parameter while maintaining the other parameters *** is suggested that this model would be the best one to use to calculate the SFRS.A graphical user interface for the proposed models is developed to further assist in the calculation of the SFRS for engineering *** this study,we attempt to bridge the gap between modern slope stability evaluation techniques and more conventional analysis methods.

关键词： Rock slope stability Open-pit mines Machine learning(ML) Limit equilibrium method(LEM)

来源：评论

学校读者我要写书评

暂无评论

Human Pose Estimation for Boxing Based on Model Transfer Learning 4

Human Pose Estimation for Boxing Based on Model Transfer Lea...

引用

4th International Conference on High Performance Big Data and Intelligent Systems, HDIS 2022

作者： Lin, Jianchu Xie, Xiaolong Wu, Wangping Xu, Shengpeng Liu, Chunyan Hudoyberdi, Toshboev Huaiyin Institue of Technology Faculty of Computer and Software Engineering Huai'an China

ISBN: (数字)9781665491440

ISBN: (纸本)9781665491440

The boxing as a competitive sport is now walking into Chinese campus and daily fitness exercises. The rapid growth of boxing sports has resulted in a coaching shortage. The pose of boxing can be estimated by using human pose estimation technology in artificial intelligence, to teach interns and relieve the coach shortage. However, the large number of training datasets and the lack of consistency of camera views in training limit the technology's practical application. Therefore, the model transfer methodology was implemented to address these limitations, three basic models of OpenPose (OP), High Resolution (HR), and stacked Hourglass (HG) networks were employed for model transfer learning and analyzing of boxing application. The results show the model transfer can efficiently improve the average accuracy of pose key points from 1% to 19%, model transfer can practically help address the issue of dependence on dataset collection. The HR network achieves the best performance among these three networks, but the HG network still gets better estimation on some key points. © 2022 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Cross Attention Transformer-Mixed Feedback Video Recommendation Algorithm Based on DIEN

引用

computers, Materials & Continua 2025年第1期82卷 977-996页

作者： Jianwei Zhang Zhishang Zhao Zengyu Cai Yuan Feng Liang Zhu Yahui Sun College of Software Engineering Zhengzhou University of Light IndustryZhengzhou450000China Faculty of Information Engineering Xuchang Vocational Technical CollegeXuchang461000China College of Computer Science and Technology Zhengzhou University of Light IndustryZhengzhou450000China College of Electronics and Information Zhengzhou University of Light IndustryZhengzhou450000China

The rapid development of short video platforms poses new challenges for traditional recommendation *** systems typically depend on two types of user behavior feedback to construct user interest profiles:explicit feedback(interactive behavior),which significantly influences users’short-term interests,and implicit feedback(viewing time),which substantially affects their long-term ***,the previous model fails to distinguish between these two feedback methods,leading it to predict only the overall preferences of users based on extensive historical behavior ***,it cannot differentiate between users’long-term and shortterm interests,resulting in low accuracy in describing users’interest states and predicting the evolution of their *** paper introduces a video recommendationmodel calledCAT-MFRec(CrossAttention Transformer-Mixed Feedback Recommendation)designed to differentiate between explicit and implicit user feedback within the DIEN(Deep Interest Evolution Network)*** study emphasizes the separate learning of the two types of behavioral feedback,effectively integrating them through the cross-attention ***,it leverages the long sequence dependence capabilities of Transformer technology to accurately construct user interest profiles and predict the evolution of user *** results indicate that CAT-MF Rec significantly outperforms existing recommendation methods across various performance *** advancement offers new theoretical and practical insights for the development of video recommendations,particularly in addressing complex and dynamic user behavior patterns.

关键词： Video recommendation user interest cross-attention transformer

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：