检索结果-内蒙古大学图书馆

mobile edge computing-enabled blockchain: contract-guided computation offloading

Journal of Supercomputing 2023年第7期79卷 7970-7996页

作者： Li, Yijun Lin, Ziqiong Zhang, Wenjie Zheng, Yifeng Yang, Jingmin School of Computer Sciences Minnan Normal University Fujian Zhangzhou363000 China Key Laboratory of Data Science and Intelligence Application Fujian Province University Fujian Zhangzhou363000 China Department of Electronic Engineering National Taipei University of Technology Taipei106335 Taiwan

The core problem of blockchain is to solve the proof-of-work puzzle, which is a high energy-consumption task. To address the resource limit problem, the combination of blockchain and mobile edge computing (MEC) has attracted widespread concern. In this paper, we consider a resource trading problem for a MEC-enabled blockchain system with multiple miners and one edge computing service provider (ESP), in which ESP has no previous knowledge of miners’ private information. We focus on how to perform resource trading between miners and ESP to maximize ESP’s profit under incomplete information? To tackle this problem, the resource trading process is modeled as a monopoly market using contract theory. The ESP acts as a monopolist and needs to set a contract containing service time and price for the miners. The miners can be classified into multiple types based on the private information and select one contract item designed for its type. We first analyze the necessary and sufficient conditions for feasible contracts and derive the optimal contract that maximizes the ESP’s profit for complete information scenario. For incomplete information, the service demand and the number of transactions contained in the block are the private information of miners and not known by ESP, we explore the properties of a feasible contract to reduce the complexity and propose a Lagrange multiplier algorithm to obtain the optimal contract in this scenario. Finally, the feasibility and optimality of the contract have been shown through simulation results. In addition, our proposed method can achieve results close to that of complete information scenario and has a maximum performance improvement of 17.19% comparing with linear pricing strategy in incomplete information scenario. © 2022, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of User Review on Indonesian Food and Beverage Group using Machine Learning Techniques

Sentiment Analysis of User Review on Indonesian Food and Bev...

引用

2022 IEEE Creative Communication and Innovative technology, ICCIT 2022

作者： Yanfi, Yanfi Heryadi, Yaya Lukas, Lukas Suparta, Wayan Arifin, Yulyani Bina Nusantara University Binus Graduate Program Computer Science School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Computer Science Computer Science Department Jakarta11480 Indonesia Jakarta12930 Indonesia Faculty of Industrial Technology Institut Teknologi Nasional Yogyakarta Department of Electrical Engineering Yogyakarta55281 Indonesia

ISBN: (纸本)9781665468763

A vast number of technologies based on Artificial Intelligence (AI) have proliferated into various application domains. As part of its objectives to develop agents which can behave and think like humans, some branches of AI have focused on developing various algorithms that can learn from input data without explicitly being programmed. In the food industry, notably in restaurants, smartphone technology is typically used to collect data from customers efficiently such as orders or feedback toward the services provided. The use of smartphones by some restaurants is motivated by their convenience and efficiency. Furthermore, various promotions, discounts, and membership benefits offered by cellular service providers have attracted the use of smartphones as devices for improving restaurant services to their customers. This study aimed to conduct a sentiment analysis related to multi-brand restaurants in Indonesia based on customer feedback. The data retrieved from the Google Play Store consists of 756 reviews from Boga, Champs, Hangry, Ismaya, Kulo, and Union groups. In this study, TF-IDF was used as a vectorizer to represent customer feedback as numeric vectors. The polarity sentiment of customer feedback was recognized using classifier models based on machine learning such as Logistic Regression, Naive Bayes (NB), Random Forest, and Support Vector Machine (SVM) as the classifier. The empirical results showed that SVM has the best accuracy of 93.10 % average accuracy followed by Logistic Regression with 92.41 %, Random Forest with 84.14 % average accuracy, and Naive Bayes with 76.55 % average accuracy. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Cybersecurity Optimization in Internet of Things-Enabled Autonomous Vehicles 1

Machine Learning-Based Cybersecurity Optimization in Interne...

引用

1st International Conference on Innovative Engineering sciences and Technological Research, ICIESTR 2024

作者： Musa, Usman Ibrahim Musa, Aminu Ibrahim Galadima, Yakubu Ibrahim Kantunsung, Ramadan Osman Gupta, Sakshi Dua, Sakshi Lovely Professional University School of Computer Application Punjab India Esgt Benin University Department of Information Technology Cotonou Benin Al-Qalam University Department of Computer Science Katsina Nigeria University College of Engineering Osmania University Telangana India Amity University Amity Institute of Information Technology Uttar Pradesh Noida India

ISBN: (纸本)9798350348637

The swift proliferation of Internet of Things-Enabled Autonomous Vehicles, or IoT-AVs, caused serious apprehensions about potential security weaknesses. In response, we provide a unique solution that improves cybersecurity in IoT-AVs by applying machine learning (ML) approaches. Three critical areas are the focus of our research: intrusion detection optimization (IDOpt), network reliability and latency optimization (NetOpt), and user authentication optimization (AuthOpt). Through biometric approaches which include fingerprint recognition, we accomplish powerful user authentication with 99% accuracy by using convolutional neural networks (CNNs). For Network Reliability and Latency Optimization, the Random Forest Regressor algorithm minimizes downtime and latency issues, improving vehicle performance with 97% accuracy. Additionally, we use the K-Nearest Neighbors (KNN) technique in intrusion detection optimization to protect IoT-AVs against harmful assaults. We use this ML model and obtain a 99% accuracy rate, allowing us to quickly identify and stop intrusions. The entire security posture of IoT-AVs is strengthened greatly by this optimization. To validate the effectiveness of our proposed approach, we compare our results with existing models and algorithms. The outcomes demonstrate the superiority of our ML-based optimizations over the previous approaches. Our integrated methodology establishes new benchmarks for security enhancement in IoT-AVs. © 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

ABID: Attention-Based Bengali Image Description 3rd

ABID: Attention-Based Bengali Image Description

引用

3rd International Conference on Communication, Devices and Computing, ICCDC 2021

作者： Das, Bidyut Sekh, Arif Ahmed Majumder, Mukta Phadikar, Santanu Department of Information Technology Haldia Institute of Technology Haldia India School of Computer Science and Engineering XIM University Bhubaneswar India Department of Computer Science and Application University of North Bengal Darjeeling India Department of Computer Science and Engineering Maulana Abul Kalam Azad University of Technology West Bengal India

ISBN: (纸本)9789811691539

Image caption or description generation is a fundamental problem of artificial intelligence. It requires both knowledge, natural language processing, and computer vision together. It automatically produces description(s) from an image. The Bengali language is the fifth language spoken widely in the world. It is considered in many areas of research and development. Various established datasets are available in the literature for image caption generation in English since no such standard dataset exists for Bengali. This paper proposes a model for automatic image captioning in the Bengali language. This study uses a Bengali dataset to train the encoder–decoder neural network model. The proposed model trained with two descriptions per image and achieved a 0.67 BLEU-1 score. We expect that a far better result is obtained with a larger and more diverse dataset. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Domain Transfer Learning for Medical Image Segmentation Tasks 5th

Domain Transfer Learning for Medical Image Segmentation Task...

引用

5th International Conference on Data science, Machine Learning and applications, ICDSMLA 2023

作者： Kharbas, Vikas Kumar Srivastava, Pulkit Bargavi, Manju Pandeya, Megha Department of Computer Science and Application Vivekananda Global University Jaipur India Department of Mechanical Engineering Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bangalore India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India

ISBN: (纸本)9789819780426

Domain transfer learning is a powerful device for clinical image Segmentation duties. It involves transferring information from a source domain to a goal area so that related tasks on those domains can be advantageous from every difference. This era allows improving and robust clinical photo segmentation models by exploiting the prevailing area information and facts from a source area. This approach has been used to enhance the performance of sure segmentation responsibilities in medical imaging together with the segmentation of pathologies from imaging, segmentation of anatomic structures, and system getting to know-based total segmentation. The most critical domain version strategies encompass domain-adversarial neural networks, generative fashions, and meta-getting to know. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Efficiency of Key Management Techniques Used in Information Security Models for Networked applications 5th

Analyzing the Efficiency of Key Management Techniques Used i...

引用

5th International Conference on Data science, Machine Learning and applications, ICDSMLA 2023

作者： Beemkumar, N. Singh, Vaishali Shree, Ritu Batra, Raman Karnataka Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science & Application Vivekananda Global University Jaipur India Department of Mechanical Engineering Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India

ISBN: (纸本)9789819780426

This study aims to investigate the performance of numerous key manipulation strategies utilized in modern statistics protection models. Especially, this painting examines the use of public key infrastructures (PKI), symmetric key infrastructures (SKI), and identity-based totally encryption (IBE) for securing application conversation in networked environments. By way of analyzing the strengths and weaknesses of each gadget, potential improvements are diagnosed. Moreover, a comparison among the unique fashions is done to pinpoint feasible weaknesses and endorse feasible mitigation strategies. The research results will enable the improvement of greater comfortable and green key management structures for networked programs, which can offer effective protection against malicious assaults. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Infrastructures Pinpoint Protection Symmetric Weaknesses

来源：评论

学校读者我要写书评

暂无评论

DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation

arXiv

引用

arXiv 2025年

作者： Guo, Hanghui Zhu, Jia Di, Shimin Shi, Weijie Chen, Zhangze Xu, Jiajie School of Computer Science and Technology Zhejiang Normal University China The Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University China School of Computer Science and Engineering Southeast University China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong School of Computer Science and Technology Soochow University China

Dynamic Retrieval-augmented Generation (RAG) has shown great success in mitigating hallucinations in large language models (LLMs) during generation. However, existing dynamic RAG methods face significant limitations in two key aspects: 1) Lack of an effective mechanism to control retrieval triggers, and 2) Lack of effective scrutiny of retrieval content. To address these limitations, we propose an innovative dynamic RAG method, DioR (Adaptive Cognitive Detection and Contextual Retrieval Optimization), which consists of two main components: adaptive cognitive detection and contextual retrieval optimization, specifically designed to determine when retrieval is needed and what to retrieve for LLMs is useful. Experimental results demonstrate that DioR achieves superior performance on all tasks, demonstrating the effectiveness of our work. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Coordinate-Oriented Clustered Chain Based Routing Protocol (COCCBRP) for Wireless Sensor Network 3

Coordinate-Oriented Clustered Chain Based Routing Protocol (...

引用

3rd International Conference on Technological Advancements in Computational sciences, ICTACS 2023

作者： Deep, Kamal Rani, Sonia Jain, Payal Yaduvanshi, Ankit Dronacharya Group of Institutions Department of Electronics and Communication Engineering Greater Noida India School of Computing Science & Engineering Galgotias University Greater Noida India Dpg Institute of Technology & Management Department of Computer Science & Application Gurugram India

ISBN: (纸本)9798350342338

Wireless sensor networks employ a variety of techniques such as data recycling, power management, and energy-aware routing protocols to reduce power consumption. Clustering is a well-known approach for extending the life of a network. It is an approach to divide the network into small groups and high-powered nodes are elected as Cluster Heads (CHs)for each group. This paper presents Coordinate-Oriented Clustered Chain Based Routing Protocol (COCCBRP), where the cluster is created along with X and Y-coordinates into equal size. Three phases make up the COCCBRP protocol's operation: chain construction, chain head selection, and head rotation mechanism. According to the distance and energy level, the criteria value of each node is determined and the node with the highest criteria value is chosen as the Chain Head. The performance of implemented work is compared with the existing CCBRP protocol. According to the findings of the simulation, the purposed strategy COCCBRP increases lifetime and reduces energy consumption as compared to the CCBRP protocol. © 2023 IEEE.

关键词： CH (Cluster Head) Clusters chain Sensor nodes Sink node WSN

来源：评论

学校读者我要写书评

暂无评论

引用

7th International Conference of computer and Informatics Engineering, IC2IE 2024

作者： Wandy, Wandy Adi, Kusworo Ayu, Media Anugerah Diponegoro University Doctoral Program of Information Systems School of Postgraduate Studies Semarang Indonesia Diponegoro University Faculty of Science and Mathematics Department of Physics Semarang Indonesia Sampoerna University Faculty of Engineering and Technology Department of Computer Science South Jakarta Indonesia

ISBN: (纸本)9798331505530

Full-marathon and Half-marathon distances are categorized as road running. Full-marathon running is becoming increasingly popular, and Half-marathon is increasing worldwide in both sexes and all age groups. Some aspects might relate to Full-marathon and Half-marathon running performance during training and races. technology also plays an essential role in supporting runners and running races. technology like artificial intelligence (AI) now supports the running athlete, not only predicting performance and results. It can also be used later to help the coach generate training programs for the athlete. This research aimed to find many aspects of marathons and performance and analyze them to see if artificial intelligence could later support them. It used secondary data and a systematic literature review proposed by Kitchenham. Out of the 58 articles, 21 of them (36.21%) received a score of 1 from Q1. Additionally, 19 articles (32.76%) received a score of 1 from both Q2 and Q3. Among the 58 articles, 9 (15.52%) received a total score of 3, with all three Q1, Q2, and Q3 scores being 1. This indicates that artificial intelligence will likely support the content of these nine articles. Several factors were also discovered to be connected to marathons and athletic performance. These findings suggested that additional investigation into marathons and performance, later backed by artificial intelligence, remained pertinent and essential. © 2024 IEEE.

关键词： artificial intelligence aspects marathon performance

来源：评论

学校读者我要写书评

暂无评论

Microgrid Recent Innovations & Uses 15

Microgrid Recent Innovations & Uses

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Kaushik, Neeraj Goswami, Shubhashis Sachan, Keerti Vijayalakshmi, V.J. Gajendran, P. Mishra, V.A. Tmu Department of Ece India Dev Bhoomi Uttarakhand University School of Engineering and Computer Uttarakhand India Iimt University School of computer science and application Meerut India Karpagam Academy of Higher Education Department of Electrical and Electronics Engineering Coimbatore India Karpagam College of Engineering Department of Electrical and Electronics Engineering Coimbatore India Vishwakarma Institute of Information Technology Computer Engg Pune India

ISBN: (纸本)9798350370249

Concerns about global warming brought on by increasing carbon dioxide levels in the environment have sped up technological development in the sustainable energy sector over the past few years. The advancement in science while the shift to less polluting materials sources possesses increased the appeal for DG, subsequent generations distributed generation, using renewable supplies. Nevertheless, it has become widely recognized that increasing DG entry can negatively affect the matrix's layout and operations. A suggestion made to reduce the effect about DG while improve the suitability of traditional grids over massive DG installation involves the Located concept. encompassing a variety of electrical devices', the elements and Micro-grids and related power gadgets fields are now very well-liked research areas. This essay examines the history and theory behind microgrids, as well as the present situation regarding the writing, active research initiatives, and pertinent requirements. It additionally provides a more thorough analysis of the numerous Located pilot initiatives which have been implemented surrounding the globe and addresses possible directions for future study. © 2024 IEEE.

关键词： Distributed generation IEEE Standard 1547 Microgrid control Microgrid management system Protection Renewable energy

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：