检索结果-内蒙古大学图书馆

2025 CHI Conference on Human Factors in Computing Systems, CHI EA 2025

作者： Bashar, Mohammad Raihanul Amini, Mohammadreza Stuerzlinger, Wolfgang Sarac, Mine Pfeuffer, Ken Machuca, Mayra Donaji Barrera Batmaz, Anil Ufuk Department of Computer Science & Software Engineering Concordia University MontrealQC Canada Simon Fraser University VancouverBC Canada Kadir Has University Istanbul Turkey Department of Computer Science Aarhus University Aarhus Denmark Faculty of Computer Science Dalhousie University HalifaxNS Canada

ISBN: (纸本)9798400713958

Due to the increasing availability and popularity of virtual reality (VR) systems, 3D sketching applications have also boomed. Most of these applications focus on peripersonal sketching, e.g., within arm’s reach. Yet, sketching in larger scenes requires users to walk around the virtual environment while sketching or to change the sketch scale repeatedly. This paper presents Depth3DSketch, a 3D sketching technique that allows users to sketch objects up to 2.5 m away with a freehand sketching technique. Users can select the sketching depth with three interaction methods: using the joystick on a single controller, the intersection from two controllers, or the intersection from the controller ray and the user’s gaze. We compared these interaction methods in a user study. Results show that users preferred the joystick to select visual depth, but there was no difference in user accuracy or sketching time between the three methods. © 2025 Copyright held by the owner/author(s).

关键词： Virtualization

来源：评论

学校读者我要写书评

暂无评论

HAMI: Hybrid Adaptive AutoML for IoT Intrusion Detection

HAMI: Hybrid Adaptive AutoML for IoT Intrusion Detection

引用

IEEE Communication Strategies in Digital Society Workshop (ComSDS)

作者： Mohamed Saber Natalia Gusarova Vladimir Bogatyrev Faculty of Software Engineering and Computer Systems ITMO University St. Petersburg Russia Faculty of Infocommunication Technologies ITMO University St. Petersburg Russia

ISBN: (数字)9798331536121

ISBN: (纸本)9798331536138

the growth of IoT devices presents significant security challenges due to their diverse and dynamic environments. To address this, we developed HAMI, a novel intrusion detection system. Our method leverages the GIFS algorithm, which combines feature rankings from ensemble models with genetic algorithms to uncover subtle inter-feature correlations, enhancing detection accuracy. Additionally, we introduce GridSearchSMOTE, a technique that optimizes data balancing by evaluating various SMOTE variants through a meticulous grid search, ensuring optimal performance for each dataset. Empirical evaluations of HAMI show superior accuracy, achieving a 99% detection rate and reduced false positives, outperforming existing systems. These results underscore HAMI’s potential to significantly improve IoT network security by exploring its scalability and real-time detection capabilities.

关键词： Adaptation models Adaptive learning Accuracy Biological system modeling Intrusion detection Feature extraction Automated machine learning Data models Real-time systems Internet of Things

来源：评论

学校读者我要写书评

暂无评论

An Efficient Detection Model for Brain Stroke Based on Transfer Learning

An Efficient Detection Model for Brain Stroke Based on Trans...

引用

Emerging Smart Technologies and Applications (eSmarTA), International Conference on

作者： Faroq H. M. Mohammed Abdulfattah Ba Alawi Ferhat Bozkurt M. Dilruba Geyikoğlu Electrical and Electronic Engineering Dept. Faculty of Engineering Ataturk University Erzurum Turkey Computer Engineering Dept. Faculty of Engineering Ataturk University Erzurum Turkey Software Engineering Dept. Faculty of Engineering & IT Taiz University Taiz Yemen

ISBN: (数字)9798350354133

ISBN: (纸本)9798350354140

Brain stroke is one of the most common causes of death, ranking as the second leading cause worldwide. With the advancements of deep learning, the detection of brain strokes from CT images becomes possible. In this study, we propose a method for classifying brain stroke images and predicting the presence of a stroke using convolutional neural networks (CNNs), which are particularly effective in image classification tasks. These techniques involve training different CNN models (EfficientNetB0-B7, InceptionResNetV2, ResNet50, ResNet152, and VGG19) on a dataset of labeled brain strokes and normal brain images. Through this process, the model learns to identify patterns and features that are indicative of a stroke. The results show that the different CNN models were able to classify stroke images with high accuracy and predict the presence of stroke with an overall accuracy of 99.95%, which is a significant improvement compared to similar studies. This demonstrates the potential of deep learning-based approaches using CNNs in assisting the diagnosis of strokes and aiding in early-stage treatment. Finally, we provide an analysis of model performance, highlighting each CNN model used, and providing insights for future research.

关键词： Training Analytical models Accuracy Transfer learning Stroke (medical condition) Brain modeling Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Service Migration for Delay-Sensitive IoT Applications in Edge Networks

引用

IEEE Transactions on Services Computing 2025年第3期18卷 1782-1797页

作者： Li, Xiaocui Zhou, Zhangbing Wang, Yasha Deng, Shuiguang Hung, Patrick C. K. School of Information Engineering Beijing100083 China Peking University National Research & Engineering Center of Software Engineering Beijing100871 China Peking University New Generation Information Technology Research Institute Tianjin300380 China School of Information Engineering Frontiers Science Center for Deep-Time Digital Earth Beijing100083 China Institut Polytechnique de Paris Télécom SudParis Palaiseau91120 France Zhejiang University College of Computer Science and Technology Hangzhou310012 China Ontario Tech University Faculty of Business and Information Technology Oshawa Canada

The proliferation of Internet of Things (IoT) applications prompts extraordinary demands for the collaboration of large amounts of computational resources provided by IoT devices in edge networks, and these applications are mostly delay-sensitive. Generally, these resources are encapsulated as IoT services. Thereafter, IoT applications can be performed, such that the collaboration of their sub-tasks is achieved through the composition of functionally complementary and geographically contiguous IoT services. The status of computational resources in IoT devices may change continuously along with their occupancy and release by IoT services. Considering the resource-scarceness of IoT devices, when the workload of IoT devices increases due to more services to be processed, certain IoT devices may hardly have enough remaining resources to co-host more instances of certain IoT services prescribed by forthcoming IoT applications with strict constraints. As a result, the delay satisfaction of both on-running and forthcoming IoT applications may be negatively impacted, or even hardly be satisfied any longer. To solve this issue, this paper proposes a rEsource-Efficient service Configuration (E2rC) mechanism, which aims to optimize the configuration of computational resources provided by IoT devices with respect to complex requirements prescribed by IoT applications, through service migration techniques. This service migration problem is formulated as markov multi-phases decisions, which is solved through our enhanced Deep Reinforcement Learning (DRL) approach with a two-layer Q-network. Extensive experiments have been conducted upon the dataset of our testbed system. Evaluation results show that our E2rC is more efficient than the state-of-art counterparts in satisfying delay constraints of IoT applications, while reducing the energy consumption and improving the resource utilization efficiency of IoT devices. © 2025 IEEE. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

An Approach for Early Detection of Schizophrenia

An Approach for Early Detection of Schizophrenia

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Sachin Paranagama Isiwara Uditha Pamodya Daundasekara Shehani Hettiarachchi Lokesha Weerasinghe Dharshana Kasthurirathna Department of Computer Science and Software Engineering Faculty Of Computing Sri Lanka Institue Of Information Technology Malabe Sri Lanka

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Schizophrenia is a chronic mental disorder with distorted thinking, hallucinations, and social difficulties. Early diagnosis is vital, but current methods are limited. This research proposes a web-based application integrating machine learning, emotion recognition, and game-based elements to track symptoms and aid in early diagnosis. Interactive exercises focus on specific symptoms like cognitive evaluation, emotional analysis, and memory assessment. By combining computer science, psychology, and machine learning, the project aims to improve early detection and ultimately enhance the quality of life for affected individuals. Key components include using Deep Convolutional Neural Network (DCNN) architecture for recognizing facial and physical expressions associated with schizophrenia with an 87% accuracy rate, and utilizing Vector Regressor (SVR) with a 93% accuracy rate, along with Vision Transformer (ViT) and Custom CNN models for cognitive assessment, achieving accuracy rates of 99% and 98%, respectively.

关键词： computer science Emotion recognition computer vision Accuracy Face recognition Psychology Machine learning Transformers Vectors Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on AI-Powered Employee Feedback Tools

Research on AI-Powered Employee Feedback Tools

引用

International Russian Smart Industry Conference (SmartIndustryCon)

作者： Konstantin Babushkin Nikolai Timofeev Ivan Filianin Faculty of Infocommunication Technologies ITMO University St. Petersburg Russia Faculty of Software Engineering and Computer Systems ITMO University St. Petersburg Russia

ISBN: (数字)9798331511241

ISBN: (纸本)9798331511258

This paper explores methods for employee feedback (EF) collection and introduces a new framework to improve the process. Current feedback collection process often suffers from slow workflow, bias, and poor Artificial Intelligence (AI) integration. Large Language Models (LLM) combined with human oversight may provide a more agile, objective, and user-friendly way for collecting and analyzing feedback. Existing EF tools were evaluated based on criteria such as AI capabilities, usability, and costs. Building on these findings, an open-source and self-hosted EF tool was developed. The tool integrates AI at every stage of the process and offers real-time AI assistance in writing, summarizing, and interpreting feedback. Pilot testing in two tech companies demonstrated user satisfaction.

关键词： Surveys Performance evaluation Industries Costs Large language models Companies Writing Real-time systems Usability Testing

来源：评论

学校读者我要写书评

暂无评论

Research on AI-Powered Employee Feedback Tools

Research on AI-Powered Employee Feedback Tools

引用

2025 International Russian Smart Industry Conference, SmartIndustryCon 2025

作者： Babushkin, Konstantin Timofeev, Nikolai Filianin, Ivan ITMO University Faculty of Infocommunication Technologies St. Petersburg Russia ITMO University Faculty of Software Engineering and Computer Systems St. Petersburg Russia

ISBN: (纸本)9798331511241

关键词： Job satisfaction

来源：评论

学校读者我要写书评

暂无评论

Offline Handwriting Signature Verification: A Transfer Learning and Feature Selection Approach

arXiv

引用

arXiv 2024年

作者： Özyurt, Fatih Majidpour, Jafar Rashid, Tarik A. Koç, Canan Department of Software Engineering Faculty of Engineering Firat University Elazig23119 Turkey Department of Software and Informatics Engineering University of Raparin Kurdistan Region Rania Iraq Department of Computer Science Faculty of Science Soran University Kurdistan Region Soran Iraq Computer Science and Engineering Department University of Kurdistan Hewlêr Erbil Iraq

Handwritten signature verification poses a formidable challenge in biometrics and document authenticity. The objective is to ascertain the authenticity of a provided handwritten signature, distinguishing between genuine and forged ones. This issue has many applications in sectors such as finance, legal documentation, and security. Currently, the field of computer vision and machine learning has made significant progress in the domain of handwritten signature verification. The outcomes, however, may be enhanced depending on the acquired findings, the structure of the datasets, and the used models. Four stages make up our suggested strategy. First, we collected a large dataset of 12600 images from 420 distinct individuals, and each individual has 30 signatures of a certain kind (All authors' signatures are genuine). In the subsequent stage, the best features from each image were extracted using a deep learning model named MobileNetV2. During the feature selection step, three selectors—neighborhood component analysis (NCA), Chi2, and mutual_info (MI)—were used to pull out 200, 300, 400, and 500 features, giving a total of 12 feature vectors. Finally, 12 results have been obtained by applying machine learning techniques such as SVM with kernels (rbf, poly, and linear), KNN, DT, Linear Discriminant Analysis, and Naïve Bayes. Without employing feature selection techniques, our suggested offline signature verification achieved a classification accuracy of 91.3%, whereas using the NCA feature selection approach with just 300 features it achieved a classification accuracy of 97.7%. High classification accuracy was achieved using the designed and suggested model, which also has the benefit of being a self-organized framework. Consequently, using the optimum minimally chosen features, the proposed method could identify the best model performance and result validation prediction vectors. © 2024, CC BY.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Privacy Enhanced Mobile User Authentication Method Using Motion Sensors

引用

computer Modeling in engineering & Sciences 2024年第3期138卷 3013-3032页

作者： Chunlin Xiong Zhengqiu Weng Jia Liu Liang Gu Fayez Alqahtani Amr Gafar Pradip Kumar Sharma Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhen518052China Sangfor Technologies Inc. Shenzhen518055China School of Data Science and Artificial Intelligence Wenzhou University of TechnologyWenzhou325035China College of Computer Science&Technology Zhejiang University of TechnologyHangzhou310023China Software Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh12372Saudi Arabia Math&Computer Science Department Faculty of ScienceMenofia UniversityShebin El-KomEgypt Computing Science Department University of AberdeenAberdeenUK

With the development of hardware devices and the upgrading of smartphones,a large number of users save privacy-related information in mobile devices,mainly smartphones,which puts forward higher demands on the protection of mobile users’privacy *** present,mobile user authenticationmethods based on humancomputer interaction have been extensively studied due to their advantages of high precision and non-perception,but there are still shortcomings such as low data collection efficiency,untrustworthy participating nodes,and lack of *** this end,this paper proposes a privacy-enhanced mobile user authentication method with motion sensors,which mainly includes:(1)Construct a smart contract-based private chain and federated learning to improve the data collection efficiency of mobile user authentication,reduce the probability of the model being bypassed by attackers,and reduce the overhead of data centralized processing and the risk of privacy leakage;(2)Use certificateless encryption to realize the authentication of the device to ensure the credibility of the client nodes participating in the calculation;(3)Combine Variational Mode Decomposition(VMD)and Long Short-TermMemory(LSTM)to analyze and model the motion sensor data of mobile devices to improve the accuracy of model *** experimental results on the real environment dataset of 1513 people show that themethod proposed in this paper can effectively resist poisoning attacks while ensuring the accuracy and efficiency of mobile user authentication.

关键词： Mobile authentication blockchain federated learning smart contract certificateless encryption VMD LSTM

来源：评论

学校读者我要写书评

暂无评论

HAMI: Hybrid Adaptive AutoML for IoT Intrusion Detection

HAMI: Hybrid Adaptive AutoML for IoT Intrusion Detection

引用

2025 Communication Strategies in Digital Society Seminar, ComSDS 2025

作者： Saber, Mohamed Gusarova, Natalia Bogatyrev, Vladimir Faculty of Software Engineering and Computer Systems ITMO University St. Petersburg Russia Faculty of Infocommunication Technologies ITMO University St. Petersburg Russia

ISBN: (纸本)9798331536121

the growth of IoT devices presents significant security challenges due to their diverse and dynamic environments. To address this, we developed HAMI, a novel intrusion detection system. Our method leverages the GIFS algorithm, which combines feature rankings from ensemble models with genetic algorithms to uncover subtle inter-feature correlations, enhancing detection accuracy. Additionally, we introduce GridSearchSMOTE, a technique that optimizes data balancing by evaluating various SMOTE variants through a meticulous grid search, ensuring optimal performance for each dataset. Empirical evaluations of HAMI show superior accuracy, achieving a 99% detection rate and reduced false positives, outperforming existing systems. These results underscore HAMI's potential to significantly improve IoT network security by exploring its scalability and real-time detection capabilities. © 2025 IEEE.

关键词： Network intrusion

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：