检索结果-内蒙古大学图书馆

Dynamic Hand Gesture Recognition Based on Short-Term Sampling Neural Networks

IEEE/CAA Journal of Automatica Sinica 2021年第1期8卷 110-120页

作者： Wenjin Zhang Jiacun Wang Fangping Lan the Department of Computer Science and Software Engineering Monmouth UniversityNew Jersey 07740 USA

Hand gestures are a natural way for human-robot *** based dynamic hand gesture recognition has become a hot research topic due to its various *** paper presents a novel deep learning network for hand gesture *** network integrates several well-proved modules together to learn both short-term and long-term features from video inputs and meanwhile avoid intensive *** learn short-term features,each video input is segmented into a fixed number of frame groups.A frame is randomly selected from each group and represented as an RGB image as well as an optical flow *** two entities are fused and fed into a convolutional neural network(Conv Net)for feature *** Conv Nets for all groups share *** learn longterm features,outputs from all Conv Nets are fed into a long short-term memory(LSTM)network,by which a final classification result is *** new model has been tested with two popular hand gesture datasets,namely the Jester dataset and Nvidia *** with other models,our model produced very competitive *** robustness of the new model has also been proved with an augmented dataset with enhanced diversity of hand gestures.

关键词： Convolutional neural network(ConvNet) hand gesture recognition long short-term memory(LSTM)network short-term sampling transfer learning

来源：评论

学校读者我要写书评

暂无评论

PLAME: Piecewise-Linear Approximate Measure for Additive Kernel SVM (Extended abstract) 40

PLAME: Piecewise-Linear Approximate Measure for Additive Ker...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Chan, Tsz Nam Li, Zhe Leong Hou, U. Cheng, Reynold Shenzhen University Department of Computer Science and Software Engineering China Alibaba Cloud University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science China The University of Hong Kong Department of Computer Science and Musketeers Foundation Institute of Data Science Hong Kong

ISBN: (纸本)9798350317152

Additive Kernel SVM has been extensively used in many applications, including human activity detection and pedestrian detection. Since training an additive kernel SVM model is very time-consuming, which is not scalable to largescale datasets, many efficient solutions have been developed in the past few years. However, most of the existing methods normally fail to achieve one of these three important conditions which are (1) low classification error, (2) low memory space, and (3) low training time. In order to simultaneously fulfill these three conditions, we develop the new piecewise-linear approximate measure (PLAME) for training additive kernel SVM models. Experimental results verify that this approach can achieve the best trade-off between accuracy, memory space, and training time compared with different types of state-of-the-art methods. © 2024 IEEE.

关键词： Additives

来源：评论

学校读者我要写书评

暂无评论

NPBMT: A Novel and Proficient Buffer Management Technique for Internet of Vehicle-Based DTNs

引用

computers, Materials & Continua 2023年第10期77卷 1303-1323页

作者： Sikandar Khan Khalid Saeed Muhammad Faran Majeed Salman A.AlQahtani Khursheed Aurangzeb Muhammad Shahid Anwar Department of Computer Science Shaheed Benazir Bhutto University SheringalDir(U)Khyber Pakhtunkhwa18200Pakistan Department of Computer Science Kohsar University MurreePunjab47150Pakistan Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityP.O.Box 51178Riyadh11543Saudi Arabia Department of AI and Software Gachon UniversitySeongnam-si13120South Korea

Delay Tolerant Networks(DTNs)have the major problem of message delay in the network due to a lack of endto-end connectivity between the nodes,especially when the nodes are *** nodes in DTNs have limited buffer storage for storing delayed *** instantaneous sharing of data creates a low buffer/shortage ***,buffer congestion would occur and there would be no more space available in the buffer for the upcoming *** address this problem a buffer management policy is proposed named“A Novel and Proficient Buffer Management Technique(NPBMT)for the Internet of Vehicle-Based DTNs”.NPBMT combines appropriate-size messages with the lowest Time-to-Live(TTL)and then drops a combination of the appropriate messages to accommodate the newly arrived *** evaluate the performance of the proposed technique comparison is done with Drop Oldest(DOL),Size Aware Drop(SAD),and Drop Larges(DLA).The proposed technique is implemented in the Opportunistic Network Environment(ONE)*** shortest path mapbased movement model has been used as the movement path model for the nodes with the epidemic routing *** the simulation results,a significant change has been observed in the delivery probability as the proposed policy delivered 380 messages,DOL delivered 186 messages,SAD delivered 190 messages,and DLA delivered only 95 messages.A significant decrease has been observed in the overhead ratio,as the SAD overhead ratio is 324.37,DLA overhead ratio is 266.74,and DOL and NPBMT overhead ratios are 141.89 and 52.85,respectively,which reveals a significant reduction of overhead ratio in NPBMT as compared to existing *** network latency average of DOL is 7785.5,DLA is 5898.42,and SAD is 5789.43 whereas the NPBMT latency average is *** reveals that the proposed policy keeps the messages for a short time in the network,which reduces the overhead ratio.

关键词： Delay tolerant networks buffer management message drop policy ONE simulator NPBMT

来源：评论

学校读者我要写书评

暂无评论

Adjusting Logit in Gaussian Form for Long-Tailed Visual Recognition

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 5026-5039页

作者： Li, Mengke Cheung, Yiu-Ming Lu, Yang Hu, Zhikai Lan, Weichao Huang, Hui Shenzhen518132 China Hong Kong Baptist University Department of Computer Science 999077 Hong Kong Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen361005 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

It is not uncommon that real-world data are distributed with a long tail. For such data, the learning of deep neural networks becomes challenging because it is hard to classify tail classes correctly. In the literature, several existing methods have addressed this problem by reducing classifier bias, provided that the features obtained with long-tailed data are representative enough. However, we find that training directly on long-tailed data leads to uneven embedding space. That is, the embedding space of head classes severely compresses that of tail classes, which is not conducive to subsequent classifier learning. This article therefore studies the problem of long-tailed visual recognition from the perspective of feature level. We introduce feature augmentation to balance the embedding distribution. The features of different classes are perturbed with varying amplitudes in Gaussian form. Based on these perturbed features, two novel logit adjustment methods are proposed to improve model performance at a modest computational overhead. Subsequently, the distorted embedding spaces of all classes can be calibrated. In such balanced-distributed embedding spaces, the biased classifier can be eliminated by simply retraining the classifier with class-balanced sampling data. Extensive experiments conducted on benchmark datasets demonstrate the superior performance of the proposed method over the state-of-the-art ones. © 2020 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Effort-aware cross-project just-in-time defect prediction framework for mobile apps

引用

Frontiers of computer science 2022年第6期16卷 15-29页

作者： Tian CHENG Kunsong ZHAO Song SUN Muhammad MATEEN Junhao WEN School of Big Data and Software Engineering Chongqing UniversityChongqing401331China School of Computer Science Wuhan UniversityWuhan430072China Department of Computer Science Air University Multan CampusMultan60000Pakistan

As the boom of mobile devices,Android mobile apps play an irreplaceable roles in people’s daily life,which have the characteristics of frequent updates involving in many code commits to meet new ***-in-Time(JIT)defect prediction aims to identify whether the commit instances will bring defects into the new release of apps and provides immediate feedback to developers,which is more suitable to mobile *** the within-app defect prediction needs sufficient historical data to label the commit instances,which is inadequate in practice,one alternative method is to use the cross-project *** this work,we propose a novel method,called KAL,for cross-project JIT defect prediction task in the context of Android mobile *** specifically,KAL first transforms the commit instances into a high-dimensional feature space using kernel-based principal component analysis technique to obtain the representative ***,the adversarial learning technique is used to extract the common feature embedding for the model *** conduct experiments on 14 Android mobile apps and employ four effort-aware indicators for performance *** results on 182 cross-project pairs demonstrate that our proposed KAL method obtains better performance than 20 comparative methods.

关键词： kernel-based principal component analysis adversarial learning just-in-time defect prediction cross-project model

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Query Generation Methods for IoT Middleware Evaluation 17

A Comparative Analysis of Query Generation Methods for IoT M...

引用

IEEE Congress on Cybermatics: 17th IEEE International Conference on Internet of Things, iThings 2024, 20th IEEE International Conference on Green Computing and Communications, GreenCom 2024, 17th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2024, 10th IEEE International Conference on Smart Data, SmartData 2024

作者： De Silva, Ravindi Zaslavsky, Arkady Loke, Seng W. Jayaraman, Prem Prakash Deakin University School of Information Technology Melbourne Australia Swinburne University of Technology Department of Computer Science and Software Engineering Melbourne Australia

ISBN: (纸本)9798350351637

The rapid expansion of Internet of Things (IoT) applications necessitates the demand for efficient IoT middleware platforms, especially Context Management Platforms (CMPs) for accessing real-time contextual information. Current IoT middleware evaluation methods lack accessibility, posing a significant challenge for standardized performance analysis of CMPs. This paper introduces a novel scenario-based context query generation approach for assessing the data retrieval performance of a CMP. The proposed approach enables scene creation using either IoT data or real-world images, employing both data-driven and image-driven scene generation methods. This paper presents the challenges, limitations, and applicability of each approach in scene generation through a qualitative evaluation. The scenes are transformed into scene graphs, enabling inference to identify situations. Both approaches generate queries reflecting dynamic real-world situations, allowing for random query loads to evaluate CMPs fairly. This paper validates the proposed approach using real-world IoT datasets and camera images with a focus on bicycle riding safety use cases. The evaluation provides insights into the contextual completeness of scene graph representations crucial for accurately capturing real-world situations. The proposed approach generates queries of varying complexity, with the only difference being the underlying mechanism of scenario generation, providing a streamlined and user-friendly method for evaluating the data retrieval performance of CMPs. © 2024 IEEE.

关键词： Middleware

来源：评论

学校读者我要写书评

暂无评论

Application of Support Vector Machine to Lassa Fever Diagnosis

Lecture Notes on Data Engineering and Communications Technol...

引用

Lecture Notes on Data engineering and Communications Technologies 2023年 180卷 165-177页

作者： Nwankwo, Wilson Adigwe, Wilfred Umezuruike, Chinecherem Acheme, Ijegwa D. Nwankwo, Chukwuemeka Pascal Ojei, Emmanuel Oghorodi, Duke Department of Computer Science Edo State University Uzairue Nigeria Department of Computer Science Delta State University of Science and Technology Ozoro Nigeria College of Computing and Communication Studies Bowen University Iwo Nigeria Department of Software Engineering Delta State University of Science and Technology Ozoro Nigeria Department of Cyber Security Delta State University of Science and Technology Ozoro Nigeria

Lassa fever is a type of viral hemorrhagic fever with high fatality rate. Precise and prompt diagnosis and successful treatment of this disease is very important in the control and prevention of the spread as unrestricted spread can easily erupt into an epidemic. An insightful decision support system can help make quick and more exact findings on this disease. In this paper, an intelligent model is proposed for predicting Lassa fever is proposed. The Lassa fever dataset was extracted from the clinical records of patients from a known Specialist Teaching Hospital in Southern Nigeria. The relevant feature variables were identified and encoded in a manner appropriate for use in algorithmic analysis. The support vector classifier was used to develop a characterization model for the disease. Assessment and evaluation were based on exactness, accuracy, and affectability. Findings showed that the proposed system could improve and encourage quick decision-making as it utilizes real historical data to effectively characterize Lassa fever spread as well as promote the timely treatment and management of patients. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Parallel Hybrid Testing Technique for Tri-Programming Model-Based software Systems

引用

computers, Materials & Continua 2023年第2期74卷 4501-4530页

作者： Huda Basloom Mohamed Dahab Abdullah Saad AL-Ghamdi Fathy Eassa Ahmed Mohammed Alghamdi Seif Haridi Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddah21493Saudi Arabia KTH Royal Institute of Technology StockholmSweden

Recently,researchers have shown increasing interest in combining more than one programming model into systems running on high performance computing systems(HPCs)to achieve exascale by applying parallelism at multiple *** different programming paradigms,such as Message Passing Interface(MPI),Open Multiple Processing(OpenMP),and Open Accelerators(OpenACC),can increase computation speed and improve *** the integration of multiple models,the probability of runtime errors increases,making their detection difficult,especially in the absence of testing techniques that can detect these *** studies have been conducted to identify these errors,but no technique exists for detecting errors in three-level programming *** the increasing research that integrates the three programming models,MPI,OpenMP,and OpenACC,a testing technology to detect runtime errors,such as deadlocks and race conditions,which can arise from this integration has not been ***,this paper begins with a definition and explanation of runtime errors that result fromintegrating the three programming models that compilers cannot *** the first time,this paper presents a classification of operational errors that can result from the integration of the three *** paper also proposes a parallel hybrid testing technique for detecting runtime errors in systems built in the C++programming language that uses the triple programming models MPI,OpenMP,and *** hybrid technology combines static technology and dynamic technology,given that some errors can be detected using static techniques,whereas others can be detected using dynamic *** hybrid technique can detect more errors because it combines two distinct *** proposed static technology detects a wide range of error types in less time,whereas a portion of the potential errors that may or may not occur depending on the 4502 CMC,2023,vol.74,no.2 operating environme

关键词： software testing hybrid testing technique OpenACC OpenMP MPI tri-programming model exascale computing

来源：评论

学校读者我要写书评

暂无评论

Xtractor: A Two-Step Tweet Extractor for Sentiment Analysis 5

Xtractor: A Two-Step Tweet Extractor for Sentiment Analysis

引用

5th International Conference on Advancements in Computational sciences, ICACS 2024

作者： Alvi, Muhammad Bux Mahoto, Naeem Ahmed Unar, Mukhtiar Ali Shaikh, Muhammad Akram The Islamia University of Bahawalpur Computer Systems Engineering Bahawalpur Pakistan Mehran Uet Software Engineering Department Jamshoro Pakistan Mehran Uet Computer Systems Engineering Department Jamshoro Pakistan Pastic Pakistan Science Foundation Islamabad Pakistan

ISBN: (纸本)9798350394764

Twitter (now X) has been gaining popularity with each passing day since its inception in 2006. People have been using Twitter as an instant repository to collect data and gain insight into folks' minds on trending issues. Although Twitter allows access to its data through streaming and rest APIs, extracting the required data is difficult. The data (tweet) returned by Twitter is in json format, having at least 26 fields. Each field is bundled in the dictionary form data structure. tweet metadata such as tweet 'likes' and 'retweets' increase the volume and complexity of a tweet, making data extraction in a cleaner format more difficult. This work aims to develop an effective two-step tweet extractor (Xtractor: an online-offline keyword-based Twitter data extractor). In the first step, Xtractor collects publicly available topical tweets using keywords, hashtags, or their list on the fly, parses all the tweet fields, and filters them to retain potential field contents without additional payload. The second step of the Xtractor evicts partially matching tweets using the regular expression method to acquire the targeted domain-specific tweets. Using the proposed two-step Twitter data extraction method, datasets concerning the people of Pakistan have been collected, which can be leveraged to get insight for decision-making, specially in the context of sentiment analysis. We found this method efficient, capacitive, and productive. © 2024 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Opposition-Based White Shark Optimizer for Optimizing Modified EfficientNetV2 in Road Crack Classification

IEEE Open Journal of the Computer Society

引用

IEEE Open Journal of the computer Society 2025年第1期6卷 762-775页

作者： Al-Shalabi, Mohammed Mahdi, Mohammed A. Braik, Malik Al-Betar, Mohammed Azmi Ahamad, Shahanawaj Saad, Sawsan A. University of Ha'il Department of Information and Computer Science Ha'il Saudi Arabia Al-Balqa Applied University Department of Computer Science Jordan Ajman United Arab Emirates Al-Ahliyya Amman University Hourani Center for Applied Scientific Research Amman11942 Jordan University of Ha'il Department of Software Engineering Ha'il Saudi Arabia University of Ha'il Department of Computer Engineering Ha'il Saudi Arabia

Maintaining reliable and long-lasting road infrastructure requires accurate identification and management of pavement cracks, as these cracks can significantly weaken asphalt and concrete surfaces over time. Although Convolutional Neural Networks (CNNs) and meta-heuristic algorithms have proven effective in solving real-world problems, their use in low-contrast pavement crack images is worth investigating. This study proposes an automated crack detection framework that integrates three key components: (1) a new variant of a pre-trained CNN architecture, referred to as Modified EfficientNetV2 (MEfficientNetV2) for pavement crack classification;(2) a combination of opposition-based learning with White Shark Optimizer (WSO), known as Opposition WSO (OWSO), to improve the balance between exploration and exploitation;and (3) Principal Component Analysis (PCA) for efficient dimensionality reduction and feature selection. This method is validated on various publicly available asphalt crack datasets that contain low-contrast natural images. Preprocessing techniques are first applied to eliminate noise and enhance image quality. The OWSO algorithm is then integrated to optimize the classification performance of MEfficientNetV2, while PCA accelerates the learning process by retaining critical features in the thresholds of the varying components. Comparative evaluations with state-of-the-art methods demonstrate that the proposed model excels in terms of precision, robustness, and generalizability. The outcome emphasizes its ability to identify the most effective solution for crack detection in practical scenarios, where PCA-based feature selection improves computational efficiency without compromising performance. This study focuses on the potential of hybrid deep learning and bio-inspired optimization strategies to improve automated pavement maintenance systems. © 2020 IEEE.

关键词： Convolutional neural networks

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：