检索结果-内蒙古大学图书馆

25th International Arab Conference on Information Technology, ACIT 2024

作者： Sourav, Md Sakib Ullah Mahmud, Mohammad Sultan Zheng, Hua Aljaidi, Mohammad Talukder, Md. Simul Hasan Bin Sulaiman, Rejwan Nur, Abdullah Hafez Al-Qerem, Ahmad Shandong University of Finance and Economics School of Management Science and Engineering Jinan China Shenzhen University College of Computer Science and Software Engineering Senzhen China Software Engineering Institute of Guangzhou Department of Software Engineering Guangzhou510990 China Zarqa University Department of Computer Science Zarqa Jordan University of Business and Technology College of Engineering Jeddah21448 Saudi Arabia Dhaka University of Engineering and Technology Department of Electrical and Electronic Engineering Dhaka Bangladesh Northumbria University Newcastle Tayne School of Computer Science & Technology Northumbria United Kingdom International Islamic University Chittagong Department of Electronic and Telecommunication Engineering Chittagong Bangladesh Zarqa University Faculty of Information Technology Department of Computer Science Zarqa Jordan

ISBN: (纸本)9798331540012

Due to its importance in studying people's thoughts on various Web 2.0 services, emotion classification is a critical undertaking. Most existing research is focused on the English language, with little work on low-resource languages. Though sentiment analysis, particularly emotion classification in English, has received increasing attention in recent years, little study has been done in the context of Bangla, one of the world's most widely spoken languages. In this research, we propose a complete set of approaches for identifying and extracting emotions from Bangla texts. We provide a Bangla emotion classifier for six classes, i.e., anger, disgust, fear, joy, sadness, and surprise, from Bangla words using transformer-based models, which exhibit phenomenal results in recent days, especially for high-resource languages. The Unified Bangla Multi-class Emotion Corpus (UBMEC) is used to assess the performance of our models. UBMEC is created by combining two previously released manually labelled datasets of Bangla comments on six emotion classes with fresh manually labelled Bangla comments created by us. The corpus dataset and code we used in this work are publicly available. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A New Cybersecurity Approach Enhanced by xAI-Derived Rules to Improve Network Intrusion Detection and SIEM

引用

computers, Materials & Continua 2025年第5期83卷 1607-1621页

作者： Federica Uccello Marek Pawlicki Salvatore D'Antonio RafałKozik MichałChoras Centro Direzionale Department of EngineeringUniversity of Naples‘Parthenope’Isola C4Napoli80133Italy Department of Computer and Information Science Software and SystemsLinköping UniversityLinköping58183Sweden ITTI Sp.z o.o. Pozna´n61-612Poland Faculty of Telecommunications Computer Science and Electrical EngineeringBydgoszcz University of Science and TechnologyBydgoszcz85-796Poland

The growing sophistication of cyberthreats,among others the Distributed Denial of Service attacks,has exposed limitations in traditional rule-based Security Information and Event Management *** machine learning–based intrusion detection systems can capture complex network behaviours,their“black-box”nature often limits trust and actionable insight for security *** study introduces a novel approach that integrates Explainable Artificial Intelligence—xAI—with the Random Forest classifier to derive human-interpretable rules,thereby enhancing the detection of Distributed Denial of Service(DDoS)*** proposed framework combines traditional static rule formulation with advanced xAI techniques—SHapley Additive exPlanations and Scoped Rules-to extract decision criteria from a fully trained *** methodology was validated on two benchmark datasets,CICIDS2017 and *** rules were evaluated against conventional Security Information and Event Management Systems rules with metrics such as precision,recall,accuracy,balanced accuracy,and Matthews Correlation *** results demonstrate that xAI-derived rules consistently outperform traditional static ***,the most refined xAI-generated rule achieved near-perfect performance with significantly improved detection of DDoS traffic while maintaining high accuracy in classifying benign traffic across both datasets.

关键词： Cybersecurity explainable artificial intelligence intrusion detection system rule-based SIEM distributed denial of service

来源：评论

学校读者我要写书评

暂无评论

Task Consistent Prototype Learning for Incremental Few-Shot Semantic Segmentation 27th

Task Consistent Prototype Learning for Incremental Few-Shot...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Xu, Wenbo Wu, Yanan Jiang, Haoran Wang, Yang Wu, Qiang Zhang, Jian Faculty of Engineering and Information Technology University of Technology Sydney Sydney2007 Australia School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China Department of Computer Science and Software Engineering Concordia University MontrealH3G2J1 Canada

ISBN: (纸本)9783031783463

Incremental Few-Shot Semantic Segmentation (iFSS) tackles a task that requires a model to continually expand its segmentation capability on novel classes using only a few annotated examples. Typical incremental approaches encounter a challenge that the objective of the base training phase (fitting base classes with sufficient instances) does not align with the incremental learning phase (rapidly adapting to new classes with less forgetting). This disconnect can result in suboptimal performance in the incremental setting. This study introduces a meta-learning-based prototype approach that encourages the model to learn how to adapt quickly while preserving previous knowledge. Concretely, we mimic the incremental evaluation protocol during the base training session by sampling a sequence of pseudo-incremental tasks. Each task in the simulated sequence is trained using a meta-objective to enable rapid adaptation without forgetting. To enhance discrimination among class prototypes, we introduce prototype space redistribution learning, which dynamically updates class prototypes to establish optimal inter-prototype boundaries within the prototype space. Extensive experiments on iFSS datasets built upon PASCAL and COCO benchmarks show the advanced performance of the proposed approach, offering valuable insights for addressing iFSS challenges. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Weighted Multi-modal Sign Language Recognition

Weighted Multi-modal Sign Language Recognition

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Edmond Liu Jong Yoon Lim Bruce MacDonald Ho Seok Ahn Department of Electrical Computer and Software Engineering Faculty of Engineering University of Auckland New Zealand

ISBN: (数字)9798350375022

ISBN: (纸本)9798350375039

Multiple modalities can boost accuracy in the difficult task of Sign Language Recognition (SLR), however, each modality does not necessarily contribute the same quality of information. Current multi-modal approaches assign the same importance weightings to each modality, or set weightings based on unproven heuristics. This paper takes a systematic approach to find the optimal weights by performing grid search. Firstly, we create a multi-modal version of the RGB only WLASL100 data with additional hand crop and skeletal pose modalities. Secondly, we create a 3D CNN based weighted multi-modal sign language network (WMSLRnet). Finally, we run various grid searches to find the optimal weightings for each modality. We show that very minor adjustments in the weightings can have major effects on the final SLR accuracy. On WLASL100, we significantly outperform previous networks of similar design, and achieve high accuracy in SLR without highly complex pre-training schemes or extra data.

关键词： Sign language Accuracy Three-dimensional displays Systematics Crops Assistive technologies Robots

来源：评论

学校读者我要写书评

暂无评论

Collaborative learning-based inter-dependent task dispatching and co-location in an integrated edge computing system

引用

Digital Communications and Networks 2024年第6期10卷 1837-1850页

作者： Uchechukwu Awada Jiankang Zhang Sheng Chen Shuangzhi Li Shouyi Yang School of Software Henan Institute of Science and TechnologyXinxiang 453003China School of Electrical and Information Engineering Zhengzhou UniversityZhengzhou 450001China Department of Computing and Informatics Bournemouth UniversityPoole BH125BBUK School of Electronics and Computer Science University of SouthamptonSouthampton SO171BJUK Faculty of Information Science and Engineering Ocean University of ChinaQingdao 266100China

Recently,several edge deployment types,such as on-premise edge clusters,Unmanned Aerial Vehicles(UAV)-attached edge devices,telecommunication base stations installed with edge clusters,etc.,are being deployed to enable faster response time for latency-sensitive *** fundamental problem is where and how to offload and schedule multi-dependent tasks so as to minimize their collective execution time and to achieve high resource *** approaches randomly dispatch tasks naively to available edge nodes without considering the resource demands of tasks,inter-dependencies of tasks and edge resource *** approaches can result in the longer waiting time for tasks due to insufficient resource availability or dependency support,as well as provider ***,we present Edge Colla,which is based on the integration of edge resources running across multi-edge *** Colla leverages learning techniques to intelligently dispatch multidependent tasks,and a variant bin-packing optimization method to co-locate these tasks firmly on available nodes to optimally utilize *** experiments on real-world datasets from Alibaba on task dependencies show that our approach can achieve optimal performance than the baseline schemes.

关键词： Edge computing Collaborative learning Resource utilization Execution time Edge federation Gang scheduling

来源：评论

学校读者我要写书评

暂无评论

A modified grey wolf optimizer with multi-solution crossover integration algorithm for feature selection

引用

Journal of Ambient Intelligence and Humanized Computing 2025年第1期16卷 329-345页

作者： Ihsan, Muhammad Din, Fakhrud Zamli, Kamal Z. Ghadi, Yazeed Yasin Alahmadi, Tahani Jaser Innab, Nisreen Faculty of IT Department of Computer Science and IT University of Malakand Khyber Pakhtunkhwa Chakdara18800 Pakistan Faculty of Computing College of Computing and Applied Sciences Universiti Malaysia Pahang Pahang Pekan26600 Malaysia Department of computer science and software engineering Al Ain University Abu Dhabi12555 United Arab Emirates Department of Information SystemsCollege of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh84428 Saudi Arabia Department of Computer Science and Information SystemsCollege of Applied Sciences Al-Maarefa University Diriyah Riyadh13713 Saudi Arabia

Feature selection helps eradicate redundant features which is essential to mitigate the curse of dimensionality when a machine-learning model deals with high-dimensional datasets. Grey Wolf Optimizer (GWO) is a swarm-based algorithm that simulates the wolves’ hunting behavior. Although very efficient, GWO faces some limitations which may cause premature convergence and/or local optima trapping. Moreover, GWO relies mainly on the three best wolves, limiting its potential for diverse exploration and exploitation. This work proposes an improved version of GWO namely, a modified grey wolf optimizer with multi-solution crossover integration (MGWO-MCI) algorithm. MGWO-MCI algorithm incorporates a multi-solution strategy that evolves new potential solutions in the optimization process. A crossover operation is performed between the new wolves and the existing hierarchy, reforming the position-updating process. MGWO-MCI utilizes this position-updating process using two different approaches. The first approach named MGWO-MCI-I expands the additional wolves’ role to both exploration and exploitation whereas the second approach named MGWO-MCI-II incorporates their role to exploration only. These approaches are evaluated and tested using 18 datasets and an Intrusion detection dataset NSL-KDD for feature selection. Statistically, the results are analyzed through the Wilcoxon test, which shows the superiority of MGWO-MCI-II. MGWO-MCI-II outperforms others with an accuracy of 98.6% on NSL-KDD and achieves 55.5% overall best outcomes on other datasets. Moreover, the MGWO-MCI was evaluated on two constrained optimization problems, the pressure vessel and welded beam design validating its effectiveness and adaptability in solving different optimization problems. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

On Understanding Sports-HAR: Hierarchical, Mobile, Multi-Sensor based Classification of Table-Tennis Strokes 1

On Understanding Sports-HAR: Hierarchical, Mobile, Multi-Sen...

引用

1st International Conference of Intelligent Methods, Systems and Applications, IMSA 2023

作者： Ezzeldin, Mustafa Ghoneim, Amr S. Abdelhamid, Laila Atia, Ayman Helwan University Faculty of Computers AI Software Engineering Cairo Egypt Helwan University Faculty of Computers and AI Computer Science Cairo Egypt Helwan University Faculty of Computers and AI Information Systems Cairo Egypt Helwan Univeristy HCI-LAB Faculty of Computers and AI Computer Science Cairo Egypt Faculty of Computer Science Giza Egypt

ISBN: (纸本)9798350335569

Table Tennis is a renowned competitive and recreational sport. An Olympic sport since 1988, table tennis in-cludes several movements, shots (i.e., strokes), and positions. Consequently, many factors can affect the strokes' accuracy and strength. This paper aims twofold: to classify the type of shot and to enhance the performance of the classification by improving the recognition accuracy and reducing the computational time. To track the movement of the body parts and extract table tennis stroke information, sensors (both Accelerometers and Gyroscopes) were utilized. The extracted data are processed and passed to a P-Dollar classifier to recognize six different table tennis strokes. This work utilizes two classification approaches to evaluate the performance, both linear and hierarchical. The presented results demonstrate that the hierarchical classification yields a better accuracy of 88%, achieved in 4 seconds, while traditional linear classification achieved 83% within 6 seconds. © 2023 IEEE.

关键词： Gyroscopes

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of Weapons in Surveillance Cameras Using Efficient-Net

引用

computers, Materials & Continua 2022年第9期72卷 4615-4630页

作者： Erssa Arif Syed Khuram Shahzad Muhammad Waseem Iqbal Muhammad Arfan Jaffar Abdullah S.Alshahrani Ahmed Alghamdi Department of Computer Science Superior UniversityLahore54000Pakistan Department of Informatics&Systems University of Management&TechnologyLahore54000Pakistan Department of Software Engineering Superior UniversityLahore54000Pakistan Faculty of Computer Science&Information Technology Superior UniversityLahore54000Pakistan Department of Computer Science&Artificial Intelligence College of Computer Science&EngineeringUniversity of JeddahJeddah21493Saudi Arabia Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddah21493Saudi Arabia

The conventional Close circuit television(CCTV)cameras-based surveillance and control systems require human resource *** all the criminal activities take place using weapons mostly a handheld gun,revolver,pistol,swords ***,automatic weapons detection is a vital requirement now a *** current research is concerned about the real-time detection of weapons for the surveillance cameras with an implementation of weapon detection using Efficient–*** time datasets,from local surveillance department’s test sessions are used for model training and *** consist of local environment images and videos from different type and resolution cameras that minimize the *** research also contributes in the making of Efficient-Net that is experimented and results in a positive *** results are also been represented in graphs and in calculations for the representation of results during training and results after training are also shown to represent our research ***-Net algorithm gives better results than existing *** using Efficient-Net algorithms the accuracy achieved 98.12%when epochs increase as compared to other algorithms.

关键词： Detection algorithms machine learning machine vision video surveillance

来源：评论

学校读者我要写书评

暂无评论

Innovative fusion of VGG16, MobileNet, EfficientNet, AlexNet, and ResNet50 for MRI-based brain tumor identification

引用

Iran Journal of computer Science 2024年第1期8卷 185-215页

作者： Kia, Marjan Sadeghi, Soroush Safarpour, Homayoun Kamsari, Mohammadreza Jafarzadeh Ghoushchi, Saeid Ranjbarzadeh, Ramin Department of Business Information System Business Analysis (ISBA) Park University Parkville United States School of Electrical and Computer Engineering University of Tehran Tehran Iran Department of Software Engineering University of Szeged Szeged Hungary Faculty of Electrical Engineering Malek-Ashtar University of Technology(MUT) Esfahan Iran Faculty of Industrial Engineering Urmia University of Technology Urmia Iran School of Computing Faculty of Engineering and Computing Dublin City University Dublin Ireland

This study presents a novel approach for brain MRI classification by integrating multiple state-of-the-art deep learning (DL) architectures, including VGG16, EfficientNet, MobileNet, AlexNet, and ResNet50, with an attention mechanism. The primary objective was to accurately detect the presence or absence of brain tumors—a critical challenge in medical diagnosis. The methodology was validated on a comprehensive dataset comprising 3264 brain MRI scans, systematically divided into training, validation, and testing subsets. Preprocessing techniques tailored for MRI data were employed to enhance input quality. Each model was initially developed and evaluated individually to establish a performance baseline before their integration. The proposed ensemble technique capitalized on the complementary strengths of these models to enhance classification accuracy and robustness. The inclusion of an attention mechanism further refined the models by emphasizing critical regions in the MRI scans, thereby boosting predictive performance. In addition, data augmentation techniques were applied to mitigate overfitting and increase dataset resilience. Performance metrics, including precision, accuracy, and recall, demonstrated significant improvements across all evaluations, particularly for the models incorporating the attention mechanism. These findings highlight the potential of combining advanced DL architectures with attention mechanisms as a promising strategy for precise and reliable brain tumor classification in MRI scans. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： AlexNet Attention mechanism Brain tumor classification MobileNet ResNet50

来源：评论

学校读者我要写书评

暂无评论

An Overview for Trustworthy and Explainable Artificial Intelligence in Healthcare

An Overview for Trustworthy and Explainable Artificial Intel...

引用

International Scientific-Professional Conference on Information Technology (IT)

作者： Kübra Arslanoğlu Mehmet Karaköse Department of Software Engineering The Faculty of Engineering The University of Firat Elazig Department of Computer Engineering The Faculty of Engineering The University of Firat Elazig

Recently, the increased use of artificial intelligence in healthcare has significantly changed the developments in the field of medicine. Medical centres have adopted AI applications and used it in many applications to predict disease diagnosis and reduce health risks in a predetermined way. In addition to Artificial Intelligence (AI) techniques for processing data and understanding the results of this data, Explainable Artificial Intelligence (XAI) techniques have also gained an important place in the healthcare sector. In this study, reliable and explainable artificial intelligence studies in the field of healthcare were investigated and the blockchain framework, one of the latest technologies in the field of reliability, was examined. Many researchers have used blockchain technology in the healthcare industry to exchange information between laboratories, hospitals, pharmacies, and doctors and to protect patient data. In our study, firstly, the studies whose keywords were XAI and Trustworthy Artificial Intelligence were examined, and then, among these studies, priority was given to current articles using Blockchain technology. Combining the existing methods and results of previous studies and organizing these studies, our study presented a general framework obtained from the reviewed articles. Obtaining this framework from current studies will be beneficial for future studies of both academics and scientists.

关键词：

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：