检索结果-内蒙古大学图书馆

Informatica (Slovenia) 2022年第2期46卷 223-233页

作者： Mechta, Djamila Harous, Saad Djoudi, Mahieddine Department of Computer Science LRSD Lab College of Sciences University of Ferhat ABBAS-Sétif-1 Algeria Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Laboratoire Techne-UR 20297 1 rue Raymond Cantel Bâtiment A3 TSA Poitiers Cedex 911102 86073 France

This work is part of a learning environment that has virtual laboratories that are designed for distant practical work (Tele-PW). In these environments, Tele-PW is performed in two modes: individual and/or collaborative. In this paper, we are concentrating on the tele-collaborative distant practical work model. The work, presented in this paper, proposes an artificial agent called Synchronizer Coordinator Agent (SCA) to synchronize and coordinate the activities of a cognitive process in order to build and maintain a shared conception of a distant practical work between a set of learners. This agent provides certain features such as managing groups of learners, coordinating tasks, shared workspace among members of the Working Group. It is also responsible for the synchronization of workspace agents when they want to manipulate shared virtual objects simultaneously. We have chosen Petri nets to illustrate the principle of granting access to shared objects in the case of simultaneous requests. Experimental results show the effectiveness, of the artificial agent within any tele-collaborative/tele-cooperative learning situation. Several situations describe the geographical/time dispersion of learners and tutors in our system are considered during the system design phase. © 2022 Slovene Society Informatika. All rights reserved.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

Image Based Feature Separation Using RBM Tech with ADBN Tech for Accurate Fruit Classification

Image Based Feature Separation Using RBM Tech with ADBN Tech...

引用

computing, Power and Communication Technologies (IC2PCT), IEEE International Conference on

作者： V Revathi Balasubramanian Prabhu Kavin Arunadevi Thirumalraj E. Gangadevi Balamurugan Balusamy Shilpa Gite Department of Applied Sciences - Physics New Horizon College of Engineering Ring Road Bellandur Post Bengaluru India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur Chengalpattu Tamil Nadu India Department of Computer Science Engineering K.Ramakrishnan College of Technology Trichy Tamil Nadu Department of Computer Science Loyola College Chennai Delhi-National Capital Region (NCR) Shiv Nadar University AIML department Symbiosis Institute of Technology Pune Symbiosis International (Deemed University) Pune India

One of the fastest-growing subfields of computer vision and picture categorization is fruit identification. The fruit industry could start using a standardised categorization system so that shoppers can easily distinguish between different types and quality levels of fruit. From a health perspective, fruit quality is essential. The task of classifying fruits is crucial in many commercial contexts. A supermarket cashier may use a fruit categorization system to better recognise the varieties of fruit and their associated costs. It might also be used to determine whether or not a given kind of fruit is suitable for a person’s diet. The rising use of intelligent imaging equipment may be directly attributed to the proliferation and development of AI software. Deep learning methods, such as CNN, are now being used by researchers for picture categorization. CNN’s superior performance may be achieved without using any manually-crafted characteristics, in contrast to the older methods. For automated categorization, it employs a plethora of filters that strip relevant visual information. Classifying fruits accurately is a challenge in the horticulture sector and calls for the knowledge of an expert. For accurately and quantitatively analysing fruits, the currently mentioned categorization techniques fall short. Therefore, it is beneficial to review the latest suggestions for categorizing fruits. To solve this problem, we need a computerised system that can automatically sort fruits into their respective categories. Deep learning models, such as the Restricted Boltzmann Machine (RBM) and the Adam based Deep Belief Network (DBN), are used in this assignment to categorise fruits according to the attributes that have been determined to be optimum and generated. The proposed approach has been shown to have effective accuracy and quantitative analysis outcomes, and this is just the beginning of this realisation. In addition, the suggested scheme’s relatively strong computational mo

关键词：

来源：评论

学校读者我要写书评

暂无评论

Virtual Staging Technologies for the Metaverse

Virtual Staging Technologies for the Metaverse

引用

Intelligent Metaverse Technologies & Applications (iMETA), International Conference on

作者： Muhammad Tukur Yehia Boraey Sara Jashari Alberto Jaspe Villanueva Uzair Shah Mahmood Al-Zubaidi Giovanni Pintore Enrico Gobbetti Jens Schneider Marco Agus Noora Fetais College of Science and Engineering HBKU Doha Qatar Department of Computer Science Qatar University Doha Qatar VCCVIS High Perf. Visualization KAUST Jeddah Saudi Arabia Visual and Data-intensive Computing CRS4 Cagliari Italy

ISBN: (数字)9798350351514

ISBN: (纸本)9798350351521

We discuss virtual staging technologies, focusing on two primary pipelines for creating and exploring immersive indoor environments in the metavers: an AI-based image processing pipeline and a LIDAR-based pipeline. The AI-based image processing pipeline leverages advanced AI algorithms for tasks such as clutter removal, semantic style transfer, and super-resolution, enabling rapid generation of high-quality, photorealistic virtual environments from single panoramic images. The LIDAR-based pipeline captures measurable 3D models of indoor spaces, facilitating immersive editing and collaborative design through real-time interaction with high-fidelity virtual environments. A qualitative comparative analysis of these technologies highlights their strengths and limitations in various applications. The practical implications of these pipelines are discussed, particularly their potential to transform industries such as real estate, furniture retail, interior design, construction, remote collaboration, and immersive training. The paper concludes with suggestions for future research, including conducting user studies, integrating the two pipelines, and optimizing technologies for mobile and edge devices to enhance accessibility and usability.

关键词： Training Solid modeling Three-dimensional displays Image processing Pipelines Superresolution Semantics Collaboration Transforms Usability

来源：评论

学校读者我要写书评

暂无评论

An Improved Driver Drowsiness Detection using Haar Cascade Classifier

An Improved Driver Drowsiness Detection using Haar Cascade C...

引用

Innovative Data Communication Technologies and Application (ICIDCA), International Conference on

作者： S. S. Saranya Ravi Mytresh Mylavarapu Manideep Dept. Department of Computing Technologies College of Engineering & Technology Organization SRM Institute of Science and Technology Chennai India Dept. of Computer Science & Engineering Core Organization: SRM Institute of Science and Technology Chennai India

Driver drowsiness detection is a system that uses various sensors and algorithms to detect when a driver is becoming fatigued or drowsy. When a driver is drowsy, they are not operating in full alert mode rather, they are only somewhat tired. The majority of traffic accidents throughout the world are caused by fatigued and sleepy drivers. This can be done through monitoring eye movements, facial expressions, and head position, as well as analyzing driving patterns such as sudden lane changes or prolonged periods of inactivity on the steering wheel. The system can then alert the driver to take a break or pull over to rest, potentially preventing accidents caused by drowsy driving. It can also be used in commercial vehicles for safety of drivers and other people on the road. Accidents in the present day are increasingly being caused by this consisting of ocular fatigue. These characteristics show that the driver's condition is not right. For the purpose of detecting sleepiness, the ratio of distances between the horizontal and vertical eye landmarks is calculated using the EAR (Eye Aspect Ratio). The proposed method calculates the landmark since the landmarks are identified precisely enough to do so. This study determines the eye aspect ratio (EAR), a single scalar quantity that characterizes the opening of the eyes in each frame, and extracts it. Finally, an SVM classifier developed by Haar Cascade recognizes eye blinks as a pattern of EAR values. However, both driver fatigue and distraction may result in slower response times, reduced driving efficiency, and a higher risk of being involved in an accident. The output is delivered to the detection system, and the alert will be activated, if the driver's degree of fatigue and the estimated amount of sleepiness are determined. The true number of accidents brought on by driver fatigue is difficult to ascertain because it is frequently under reported. The driver typically doesn't notice the small change from being tired to

关键词： Support vector machines Sleep Wheels Ear Fatigue Sensor systems Sensors

来源：评论

学校读者我要写书评

暂无评论

Traffic Classification based on Incremental Learning Algorithms for the Software-Defined Networks

Traffic Classification based on Incremental Learning Algorit...

引用

2022 International Conference on Frontiers of Information Technology, FIT 2022

作者： Eldhai, Arwa M. Hamdan, Mosab Khan, Suleman Hamzah, Muzaffar Marsono, M.N. University of Science and Technology Faculty of Engineering Khartoum11115 Sudan Universiti Malaysia Sabah Faculty of Computing and Informatics Sabah Kota Kinabalu88450 Malaysia University of São Paulo Department of Computer Science São Paulo05508-090 Brazil University of Central Lancashire School of Psychology and Computer Science PrestonPR1 2HE United Kingdom Universiti Teknologi Malaysia Faculty of Electrical Engineering Johor81310 Malaysia

ISBN: (纸本)9798350345933

A new era of network administration has been ushered in by recent developments in software-defined networks (SDN) and traffic classification (TC) using machine learning (ML) techniques. All network devices are centrally managed and accessible through the SDN, which can simplify the TC process. The traditional data mining/ML approach that uses TC assumes that all of the task's data is always accessible and can be viewed simultaneously without processing time and memory restrictions. Therefore, these approaches are not effective in the case of stream learning since, in more realistic settings, the data is not available all at once and has a distinct distribution. Consequently, incremental learning algorithms (ILAs) can handle online data mining. This study's primary goal is to contrast various ILA approaches to enhance SDN's TC performance. In this study, we propose four ILAs: the self- adjusting memory coupled with the k Nearest Neighbor (kNN) classifier (SAMKNNC), the very fast decision rules classifier (VFDRC), the extremely fast decision tree classifier (EFDTC), and the streaming random patches ensemble classifier (SRPC). Both real and synthetic datasets are used for validation. Experimental findings reveal that the proposed techniques perform better in SDN traffic classification since they can effectively identify drift and use less memory and time. © 2022 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Secure Data Transmission in IoT Networks: A Machine Learning-Based Approach

Secure Data Transmission in IoT Networks: A Machine Learning...

引用

International Conference on science Technology Engineering and Management (ICONSTEM)

作者： K. Subathra Vignesh G R S B G Tilak Babu Dinesh Mendhe Ramesh kumar Yada Ramya Maranan Department of Mathematics Sri Sairam Engineering college Chennai-44 Tamil Nadu Department of Computer Science SSN College of Engineering Tamil Nadu Department of ECE Aditya Engineering College Surampalem Computer and Information Research Scientist Office of Research Computing Rutgers the State University of New Jersey New Brunswick FST Department ICFAI University Raipur Chhattisgarh Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai India

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365108

This research studies the application of machine learning to enhance the security of data transport for the. of Things (IoT). Conventional encryption methods might not be adequate in Internet of Things scenarios because of the fluidity and limited resources presented by these contexts. In the course of our research, we make use of fictional Internet of Things data in order to evaluate the effectiveness of machine learning models for anomaly detection, intrusion detection, and data encryption. When it comes to resolving difficulties related to the security of the internet of things (IoT), the findings suggest that machine learning is better to traditional cryptography methodologies. The Internet of Things (IoT) security is going to be strengthened by the introduction of new strategies, dynamic security frameworks, privacy-preserving methodologies, and practical implementations in the near future. It is possible that the implementation of machine learning will make the ecosystem of the Internet of Things (IoT) more safe and efficient, which would, in turn, foster innovation across a wide range of industries.

关键词： Industries Technological innovation Ecosystems Intrusion detection Machine learning Mathematics Data models

来源：评论

学校读者我要写书评

暂无评论

Optimizing Performance in Heterogeneous Wireless Networks: Insights from Adhoc and Sensor Technologies

Optimizing Performance in Heterogeneous Wireless Networks: I...

引用

Technological Advancements in Computational sciences (ICTACS), International Conference on

作者： Shashank Pareek Ahmed Saleh Al-Samalek Sandeep Singh Mohammed Al-Farouni Sharanpreet Kaur Jayant Jagtap Department of Computer Science and Engineering Chandigarh University Mohali India Department of Medical Laboratory Technics Al-Zahrawi University College Karbala Iraq Department of Civil Engineering School of Engineering and Technology Bahra University Solan HP India Department of Computers Techniques Engineering College of Technical Engineering The Islamic university Najaf Iraq Department of Computer Science Engineering Chandigarh Engineering College Chandigarh Group of Colleges Jhanjeri Mohali Punjab India NIMS School of Computing Science and Artificial Intelligence NIMS University Rajasthan Jaipur India

ISBN: (数字)9798350387490

ISBN: (纸本)9798350387506

In this paper, we explore the implications of cloud- based platforms for agricultural data management and decision support systems, including the benefits, drawbacks, and potential developments. Cloud computing has thus played a very big role in promoting efficiency and productivity in agriculture through providing better data storage, data processing, and better decision making tools. From the review of the various platforms it was realized that the cloud solutions enhance the data management and decision support that can lead to better and faster decisions in the agricultural sector. However, there are some drawbacks, for example, data protection issues, issues of compatibility with other platforms, relatively high costs of the implementation, and the need for standardization of the data. These limitations can be considered as the factors which do not allow using the full potential of cloud-based solutions in agriculture. The study therefore recommends more research to deal with these challenges especially on the improvements in security, the integration of AI and machine learning in the system and the improvement on the costs for the smallholder farmers. Also, the problem of integrating data standards across the cloud and enhancing the compatibility of systems is of great importance to enhance the overall efficiency of cloud services. Further work in these directions is important to overcome present drawbacks and to enhance the prospects of cloud technologies in agriculture. This paper has discussed the challenges facing the agricultural sector to adopt the cloud-based platforms, thus, if these challenges are to be solved, the agricultural sector can be in a better position to improve the management of resources, sustainability and overall agricultural performance.

关键词： Cloud computing Costs Wireless networks Scalability Throughput Agriculture Security Sustainable development Standards Radio spectrum management

来源：评论

学校读者我要写书评

暂无评论

Detection of EDoS attacks in SDN-based Cloud Model using Deep Learning based SDPN Technique

Detection of EDoS attacks in SDN-based Cloud Model using Dee...

引用

Smart Technologies in computing, Electrical and Electronics (ICSTCEE), International Conference on

作者： Suguna M Mohan M Srikanth J M Suresh P G Banupriya Logeshwari Dhavamani Department of Computer Science and Engineering SNS College of Engineering Coimbatore India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India Department of Computer Science and Technology SNS College of Engineering Coimbatore India Department of Computer science and Engineering School of Computing Science QIS College of Engineering and Technology Ongole Andhra Pradhesh India Department of Computer Science and Engineering Karpagam Institute of Technology Coimbatore India Department of Information Technology St. Joseph's College of Engineering Chennai India

Offering IT services to businesses and consumers via the cloud is increasingly seen as the most cost-effective model. But it is vulnerable to emerging flaws. In particular, a recently identified form of attack known as an economic-denial-of-sustainability (EDoS) takes advantage of the pay-per-use model to gradually increase the utilisation of the cloud's resources, forcing the customer to fork over further money. Therefore, in this learning, we present a novel method for detection and mitigating EDoS assaults in the SDN-based cloud computing setting utilising a Stack Deep Polynomial Network (SDPN). First, the SDPN learns precise representations of multivariate time sequence in order to imitate the typical patterns. Then, the reconstructed input data is compared to the original. Finally, the probabilities derived from the reconstruction process may serve as both a tool for detecting outliers and a source of insight into what those outliers could mean. Existing systems often utilise a hard threshold to examine the anomalies, which leads to growing mistake rates; in contrast, the suggested scheme introduces a threshold value utilising SDPN to lower error rates. When likened to other solutions and our past work, the findings of this extensive analysis indicate remarkable performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generalized Kullback-Leibler Divergence Loss

arXiv

引用

arXiv 2025年

作者： Cui, Jiequan Zhu, Beier Xu, Qingshan Tian, Zhuotao Qi, Xiaojuan Yu, Bei Zhang, Hanwang Hong, Richang College of Computing & Data Science Nanyang Technological University Singapore Department of Computer Science & Engineering The Chinese University of Hong Kong Sha Tin Hong Kong The University of Hong Kong Hong Kong Harbin Institution of Technology China Hefei University of Technology China

In this paper, we delve deeper into the Kullback–Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss that consists of 1) a weighted Mean Square Error (wMSE) loss and 2) a Cross-Entropy loss incorporating soft labels. Thanks to the decoupled structure of DKL loss, we have identified two areas for improvement. Firstly, we address the limitation of KL loss in scenarios like knowledge distillation by breaking its asymmetric optimization property along with a smoother weight function. This modification effectively alleviates convergence challenges in optimization, particularly for classes with high predicted scores in soft labels. Secondly, we introduce class-wise global information into KL/DKL to reduce bias arising from individual samples. With these two enhancements, we derive the Generalized Kullback–Leibler (GKL) Divergence loss and evaluate its effectiveness by conducting experiments on CIFAR-10/100, ImageNet, and vision-language datasets, focusing on adversarial training, and knowledge distillation tasks. Specifically, we achieve new state-of-the-art adversarial robustness on the public leaderboard — RobustBench and competitive knowledge distillation performance across CIFAR/ImageNet models and CLIP models, demonstrating the substantial practical merits. Our code is available at https://***/jiequancui/DKL. © 2025, CC BY-NC-SA.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Model Ownership Protection for Healthcare Consumer Electronics in Federated Edge Learning

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Wang, Rong Liang, Junchuan Feng, Chaosheng Chakraborty, Chinmay Alqahtani, Fayez Yu, Keping Sichuan Normal University College of Computer Science Chengdu610101 China Sichuan Normal University Visual Computing and Virtual Reality Key Laboratory of Sichuan Chengdu610068 China Birla Institute of Technology Mesra India King Saud University College of Computer and Information Sciences Software Engineering Department Riyadh12372 Saudi Arabia Hosei University Graduate School of Science and Engineering Tokyo184-8584 Japan

With the rising demand for intelligent services and privacy protection in consumer artificial intelligence (AI), federated edge learning has emerged as a beacon for privacy-preserving distributed machine learning. This non-centralized approach offers distinct data privacy advantages, making it especially suitable for applications with strict privacy policies, such as consumer-centric healthcare systems. However, consumer electronics/devices in federated edge learning might unlawfully violate model ownership by duplicating or distributing models. Another concern is that a central server, if compromised, can become a conduit for model leakage, whether for profit motives or due to external intrusions, thus exacerbating the model ownership violation. To our knowledge, few works have focused on model ownership protection for federated edge learning in the consumer-centric healthcare domain. In this paper, we introduce a federated model ownership protection (FedMOP) approach. FedMOP is a model ownership safeguard and a formidable fortress built upon two core innovations. First, FedMOP can swiftly embed and replace watermarks during local training, allowing for the accurate identification and subsequent flagging of deceitful consumer devices. Second, FedMOP ensures that the server only accesses encrypted versions of the federated model, keeping the model a secret. Extensive evaluations demonstrate the robustness and effectiveness of FedMOP. We hope that FedMOP can light the way for surmounting similar ethical challenges in the broader realm of consumer-edge AI. © 1975-2011 IEEE.

关键词： ethical AI Federated edge learning healthcare consumer electronicss model ownership protection

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：