检索结果-内蒙古大学图书馆

Profit Maximization of Delay-Sensitive, Differential Accuracy Inference Services in Mobile Edge Computing

IEEE Transactions on Mobile Computing 2025年第7期24卷 6209-6224页

作者： Zhang, Yuncan Liang, Weifa Xu, Zichuan Jia, Xiaohua Yang, Yuanyuan City University of Hong Kong Department of Computer Science Hong Kong Hong Kong Dalian University of Technology School of Software Dalian China Stony Brook University Department of Electrical and Computer Engineering Stony BrookNY United States

The integration of Artificial Itelligence (AI) and edge computing has sparked significant interest in edge inference services. In this paper, we consider delay-sensitive, differential accuracy inference services in a Mobile Edge Computing (MEC) network while meeting user stringent delay and accuracy requirements. We formulate two novel profit maximization problems under static and dynamic settings of service request arrivals, with the aim of maximizing the accumulative profit of admitted requests. We assign differential accuracy service requests to the corresponding resolution instances of their requested service models, assuming that each resolution instance can serve up to L≥ 1 the same type of service requests. Since the profit maximization problem is NP-hard, we first formulate an Integer Linear Program (ILP) solution if the problem size is small or medium;otherwise, we devise a constant randomized algorithm with high probability. Then, we consider dynamic service request admissions without the knowledge of future request arrivals for a given finite time horizon, for which we develop a simple yet effective prediction mechanism to accurately predict the number of different resolution instances of each model needed, and pre-deploy the predicted number of resolution instances into cloudlets to reduce instantiating delays. We then devise an online algorithm with a provable competitive ratio for the dynamic profit maximization problem by leveraging the primal-dual dynamic updating technique. Finally, we evaluate the performance of the proposed algorithms by simulations. The simulation results demonstrate that the proposed algorithms are promising. © 2002-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Mycology: Transfer Learning for Automated Mushroom Species Identification

AI-Driven Mycology: Transfer Learning for Automated Mushroom...

引用

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Ahmad, Md Hasan Rahman Sohag, Sohanur Rimon Bormon, Sajib Shishir, Hasanur Rahman Hossain Antar, Sabbir Daffodil International University Department of Computer Science and Engineering Ashulia Dhaka Bangladesh Noakhali Science and Technology University Department of Software Engineering Noakhali Bangladesh

ISBN: (纸本)9798331529765

Mushroom categorization is a difficult process since there are so many different species and they all have different aesthetic qualities. In this paper, we are to investigate the use of transfer learning techniques for precise mushroom classification. We have examined the performance of EfficientNetB0, ResNet50, InceptionV3, and MobileNet, four well-known transfer learning models. The mushroom dataset is first preprocessed to make sure that the images are properly scaled and normalized. After initializing and fine-tuning the pre-trained weights of the above-mentioned models on our mushroom dataset, we then apply transfer learning techniques. Each model is trained using a carefully chosen training set, and its performance is assessed using a different test set. Our findings reveal that all four transfer learning models successfully categorize mushrooms, achieving outstanding classification accuracies. With a 97% accuracy rate, EfficientNetB0 surpasses the other models when we compare them. Its sophisticated design, which combines compound scaling and AutoML approaches to attain the best accuracy and efficiency, is responsible for its exceptional performance. The results of this study demonstrate the value of transfer learning in tasks involving mushroom categorization. Additionally, they stress the benefit of using cutting-edge models like EfficientNetB0, which produce greater accuracy compared to conventional transfer learning architectures. The development of automated methods for mushroom identification and subsequent breakthroughs in the mycology field can be facilitated by the use of these findings by academics and professionals working on mushroom classification. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A reliable method for data aggregation on the industrial internet of things using a hybrid optimization algorithm and density correlation degree

引用

Cluster Computing 2024年第6期27卷 7521-7539页

作者： Heidari, Arash Shishehlou, Houshang Darbandi, Mehdi Navimipour, Nima Jafari Yalcin, Senay Department of Software Engineering Haliç University Istanbul34060 Turkey Department of Computer Engineering Tabriz Branch Islamic Azad University Tabriz Iran Pôle Universitaire Léonard de Vinci Paris France Department of Computer Engineering Kadir Has University Istanbul Turkiye and Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou64002 Taiwan Department of Energy System Engineering School of Engineering and Natural Sciences Bahçeşehir University Istanbul Turkey

The Internet of Things (IoT) is a new information technology sector in which each device may receive and distribute data across a network. Industrial IoT (IIoT) and related areas, such as Industrial Wireless Networks (IWNs), big data, and cloud computing, have made significant strides recently. Using IIoT requires a reliable and effective data collection system, such as a spanning tree. Many previous spanning tree algorithms ignore failure and mobility. In such cases, the spanning tree is broken, making data delivery to the base station difficult. This study proposes an algorithm to construct an optimal spanning tree by combining an artificial bee colony, genetic operators, and density correlation degree to make suitable trees. The trees’ fitness is measured using hop count distances of the devices from the base station, residual energy of the devices, and their mobility probabilities in this technique. The simulation outcomes highlight the enhanced data collection reliability achieved by the suggested algorithm when compared to established methods like the Reliable Spanning Tree (RST) construction algorithm in IIoT and the Hop Count Distance (HCD) based construction algorithm. This proposed algorithm shows improved reliability across diverse node numbers, considering key parameters including reliability, energy consumption, displacement probability, and distance. © The Author(s) 2024.

关键词： Reliability

来源：评论

学校读者我要写书评

暂无评论

A Metamodel for a DSL to Design Decision Support Systems in Smart Tourism

A Metamodel for a DSL to Design Decision Support Systems in ...

引用

2024 International Conference on Decision Aid Sciences and Applications, DASA 2024

作者： Ouaddi, Charaf Benaddi, Lamya Souha, Adnane Naimi, Lahbib Bouziane, El Mahi Jakimi, Abdeslam Moulay Ismail University Software Engineering and Information Systems Engineering Team Faculty of Science and Technology Errachidia Department of Computer Sciences Morocco

ISBN: (纸本)9798350369106

The development of Decision Support Systems (DSS) for several companies operating in sectors such as tourism, healthcare, or others, presents significant challenges due to the nature of their multi-component architecture. A typical DSS consists of a data component, a model component incorporating machine learning and deep learning techniques, and a user interface component, each one requires diverse technologies. This complexity increases development time and effort, hindering the efficient design of DSS tailored to specific domains like tourism, where real-time decision-making is essential. One promising approach to overcome these challenges is the use of Domain-Specific Languages (DSLs). DSLs allow developers to model and generate code more efficiently by providing high-level abstractions suited to the domain. By leveraging DSLs, it is possible to simplify the design process and automate the generation of code or parts of the DSS, thereby reducing the overall complexity and time required for development. This paper proposes a metamodel for designing DSS, specifically for the Smart Tourism sector. The metamodel serves as a foundation for the creation of DSL. The goal is to provide a solution to facilitate the development of DSS for the demands of tourism. The paper outlines the key concepts, approach, and results, presenting the first element of the proposed DSL which is the metamodel capturing the essential components and relationships for DSS in Smart Tourism. © 2024 IEEE.

关键词： Digital subscriber lines

来源：评论

学校读者我要写书评

暂无评论

Triplet MAML for Few-Shot Classification Problems 2nd

Triplet MAML for Few-Shot Classification Problems

引用

2nd International Conference on Advanced engineering, Technology and Applications, ICAETA 2023

作者： Gülcü, Ayla Özkan, İsmail Taha Samed Kuş, Zeki Karakuş, Osman Furkan Department of Software Engineering Bahçeşehir University Istanbul Turkey Department of Computer Engineering Bahçeşehir University Istanbul Turkey Department of Computer Engineering Fatih Sultan Mehmet Vakif University Istanbul Turkey Department of Computer Engineering Yıldız Technical University Istanbul Turkey

ISBN: (纸本)9783031509193

In this study, we propose a TripletMAML algorithm as an extension to Model-Agnostic Meta-Learning (MAML) which is the most widely-used optimization-based meta-learning algorithm. We approach MAML from a metric-learning perspective and train it using meta-learning tasks composed of triplets of images. The idea of meta-learning is preserved while generating the meta-learning tasks and training our novel meta-model. The experimental results obtained on four few-shot classification datasets show that TripletMAML that is trained using a combined loss yields in high quality results. We compared the performance of TripletMAML to several metric learning-based methods and a baseline method, in addition to MAML. For fair comparison, we used the reported results of those algorithms that were obtained using the same shallow backbone. The results show that TripletMAML improves MAML by a large margin, and yields better results than most of the compared algorithms in both 1-shot and 5-shot settings. Moreover, when we consider the classification performance of other meta-learning algorithms that use much deeper backbones, we conclude that TripletMAML is not only competitive in terms of the classification performance but also very efficient in terms of the complexity. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Few-Shot Image Classification MAML Meta-learning Metric Learning Triplet Networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning with a Novel Concoction Loss Function for Identification of Ophthalmic Disease

引用

computers, Materials & Continua 2023年第9期76卷 3763-3781页

作者： Sayyid Kamran Hussain Ali Haider Khan Malek Alrashidi Sajid Iqbal Qazi Mudassar Ilyas Kamran Shah Department of Computer Science TIMES InstituteMultan60000Pakistan Department of Software Engineering Faculty of Computer ScienceLahore Garrison UniversityLahore54000Pakistan Department of Computer Science Applied CollegeUniversity of TabukTabukSaudi Arabia Department of Information Systems College of Computer Sciences and Information TechnologyKing Faisal UniversityAl Hofuf31982Saudi Arabia Department of Mechanical Engineering College of EngineeringKing Faisal UniversityAl HofufSaudi Arabia

As ocular computer-aided diagnostic(CAD)tools become more widely accessible,many researchers are developing deep learning(DL)methods to aid in ocular disease(OHD)*** eye diseases like cataracts(CATR),glaucoma(GLU),and age-related macular degeneration(AMD)are the focus of this study,which uses DL to examine their *** imbalance and outliers are widespread in fundus images,which can make it difficult to apply manyDL algorithms to accomplish this analytical *** creation of efficient and reliable DL algorithms is seen to be the key to further enhancing detection *** the analysis of images of the color of the retinal fundus,this study offers a DL model that is combined with a one-of-a-kind concoction loss function(CLF)for the automated identification of *** study presents a combination of focal loss(FL)and correntropy-induced loss functions(CILF)in the proposed DL model to improve the recognition performance of classifiers for biomedical *** is done because of the good generalization and robustness of these two types of losses in addressing complex datasets with class imbalance and *** classification performance of the DL model with our proposed loss function is compared to that of the baseline models using accuracy(ACU),recall(REC),specificity(SPF),Kappa,and area under the receiver operating characteristic curve(AUC)as the evaluation *** testing shows that the method is reliable and efficient.

关键词： Deep learning multi-classification focal loss CNN eye disease

来源：评论

学校读者我要写书评

暂无评论

Intelligent Systems and Photovoltaic Cells Empowered Topologically by Sudoku Networks

引用

computers, Materials & Continua 2023年第2期74卷 4221-4238页

作者： Khalid Hamid Muhammad Waseem Iqbal MUsman Ashraf Akber Abid Gardezi Shafiq Ahmad Mejdal Alqahtani Muhammad Shafiq Department of Computer Science Superior UniversityLahore54000Pakistan Department of Software Engineering Superior UniversityLahore54000Pakistan Department of Computer Science GC Women UniversitySialkot51310Pakistan Department of Computer Science COMSATS University IslamabadIslamabad45550Pakistan Industrial Engineering Department College of EngineeringKing Saud UniversityP.O.Box 800Riyadh11421Saudi Arabia Department of Information and Communication Engineering Yeungnam UniversityGyeongsan38541Korea

A graph invariant is a number that can be easily and uniquely calculated through a ***,part of mathematical graph invariants has been portrayed and utilized for relationship ***,no reliable appraisal has been embraced to pick,how much these invariants are associated with a network graph in interconnection networks of various fields of computer science,physics,and *** this paper,the study talks about sudoku networks will be networks of fractal nature having some applications in computer science like sudoku puzzle game,intelligent systems,Local area network(LAN)development and parallel processors interconnections,music composition creation,physics like power generation interconnections,Photovoltaic(PV)cells and chemistry,synthesis of chemical *** networks are generally utilized in disorder,fractals,recursive groupings,and complex *** outcomes are the normal speculations of currently accessible outcomes for specific classes of such kinds of networks of two unmistakable sorts with two invariants K-banhatti sombor(KBSO)invariants,Irregularity sombor(ISO)index,Contraharmonic-quadratic invariants(CQIs)and dharwad invariants with their reduced *** study solved the Sudoku network used in mentioned systems to improve the performance and find irregularities present in *** calculated outcomes can be utilized for the modeling,scalability,introduction of new architectures of sudoku puzzle games,intelligent systems,PV cells,interconnection networks,chemical compounds,and extremely huge scope in very large-scale integrated circuits(VLSI)of processors.

关键词： Sudoku dharwad KBSO indices CQIs network graph intelligent system photovoltaic cells

来源：评论

学校读者我要写书评

暂无评论

A Novel Blockchain-Based Deepfake Detection Method Using Federated and Deep Learning Models

引用

Cognitive Computation 2024年第3期16卷 1073-1091页

作者： Heidari, Arash Navimipour, Nima Jafari Dag, Hasan Talebi, Samira Unal, Mehmet Department of Software Engineering Haliç University Istanbul34060 Turkey Department of Computer Engineering Kadir Has University Istanbul Turkey Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou64002 Taiwan Department of Information Technology Kadir Has University Istanbul Turkey Department of Computer Science University of Texas at San Antonio San AntonioTX United States Department of Computer Engineering Nisantasi University Istanbul Turkey

In recent years, the proliferation of deep learning (DL) techniques has given rise to a significant challenge in the form of deepfake videos, posing a grave threat to the authenticity of media content. With the rapid advancement of DL technology, the creation of convincingly realistic deepfake videos has become increasingly prevalent, raising serious concerns about the potential misuse of such content. Deepfakes have the potential to undermine trust in visual media, with implications for fields as diverse as journalism, entertainment, and security. This study presents an innovative solution by harnessing blockchain-based federated learning (FL) to address this issue, focusing on preserving data source anonymity. The approach combines the strengths of SegCaps and convolutional neural network (CNN) methods for improved image feature extraction, followed by capsule network (CN) training to enhance generalization. A novel data normalization technique is introduced to tackle data heterogeneity stemming from diverse global data sources. Moreover, transfer learning (TL) and preprocessing methods are deployed to elevate DL performance. These efforts culminate in collaborative global model training zfacilitated by blockchain and FL while maintaining the utmost confidentiality of data sources. The effectiveness of our methodology is rigorously tested and validated through extensive experiments. These experiments reveal a substantial improvement in accuracy, with an impressive average increase of 6.6% compared to six benchmark models. Furthermore, our approach demonstrates a 5.1% enhancement in the area under the curve (AUC) metric, underscoring its ability to outperform existing detection methods. These results substantiate the effectiveness of our proposed solution in countering the proliferation of deepfake content. In conclusion, our innovative approach represents a promising avenue for advancing deepfake detection. By leveraging existing data resources and the power of FL

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Dysarthric Speech Recognition using Depthwise Separable Convolutions: Preliminary Study 12

Dysarthric Speech Recognition using Depthwise Separable Conv...

引用

12th International Conference on Speech Technology and Human-computer Dialogue, SpeD 2023

作者： Shahamiri, Seyed Reza Mandal, Krishnendu Sarkar, Sudeshna The University of Auckland Faulty of Engineering Department of Electrical Computer and Software Engineering Auckland New Zealand Indian Institute of Technology Computer Science & Engineering Department Kharagpur India

ISBN: (纸本)9798350327977

As a neurological disability that affects muscles involved in articulation, dysarthria is a speech impairment that leads to reduced speech intelligibility. In severe cases, these individuals could also be handicapped and unable to interact with digital devices. For such individuals, Automatic Speech Recognition (ASR) technologies could be life changing by enabling them to communicate with others as well as computing devices via voice commands. Nonetheless, ASR systems designed to recognize healthy speech have shown very poor performance to transcribe dysarthric speech, signaling the need to design ASR specifically tailored for dysarthria. Dysarthric Speech Recognition (DRS) research has progressed gradually because of the challenges the research community faces such as the scarcity of dysarthric speech that does not allow the researchers to design deeper acoustic models needed to better learn dysarthric speech variations. In this paper we report on our preliminary findings to improve our previous DSR called Speech Vision and study the effects of Separable Convolutional neurons to improve its acoustic model. Speech Vision is a novel Dysarthric Speech Recognition system that learns to recognize the shape of the words uttered by dysarthric speakers instead of recognizing phone sequences and then mapping them to words. Experiments conducted on the utterances provided by all UA-Speech dysarthric speakers indicate the proposed Depthwise separable architecture provided better word recognition accuracies compared to the original Speech Vision's architecture across all dysarthric speech intelligibility classes. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Incentive-Driven Approach for Misbehavior Avoidance in Vehicular Networks

引用

computers, Materials & Continua 2022年第3期70卷 6089-6106页

作者： Shahid Sultan Qaisar Javaid Eid Rehman Ahmad Aziz Alahmadi Nasim Ullah Wakeel Khan Department of Computer Science and Software Engineering International Islamic UniversityIslamabad44000Pakistan Department of Software Engineering Foundation University Islamabad44000Pakistan Department of Electrical Engineering Taif University KSA Taif21944Saudi Arabia Department of Electrical Engineering Foundation University Islamabad44000Pakistan

For efficient and robust information exchange in the vehicular adhoc network,a secure and trusted incentive reward is needed to avoid and reduce the intensity of misbehaving nodes and congestion especially in the case where the periodic beacons exploit the *** addition,we cannot be sure that all vehicular nodes eagerly share their communication assets to the system for message dissemination without any ***,there may be some misbehaving nodes and due to their selfish and greedy approach,these nodes may not help others on the *** deal with this challenge,trust-based misbehavior avoidance schemes are generally reflected as the capable *** this paper,we employed a fair incentive mechanism for cooperation aware vehicular communication *** order to deploy a comprehensive credit based rewarding scheme,the proposed rewardbased scheme fully depends on secure and reliable cryptographic *** order to achieve the security goals,we used the cryptographic scheme to generate a certified public key for the authenticity of every message exchange over the *** evaluated the friction of misbehaving vehicles and the effect of rewarding schemes in context with honest messages dissemination over the network.

关键词： VANET misbehavior reputation rewards congestion avoidance certified public key

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：