检索结果-内蒙古大学图书馆

ToSiM-IoT: Towards a Sustainable Optimisation of Machine Learning Tasks in Internet of Things

IEEE Internet of Things Journal 2025年第11期12卷 16829-16840页

作者： Kaushal, Ashish Almurshed, Osama Muftah, Asmail Auluck, Nitin Rana, Omer Indian Institute of Technology Department of Computer Science and Engineering Ropar India Cardiff University School of Computer Science and Informatics United Kingdom Azzaytuna University Libya

With the rise of digital infrastructure and Internet of Things (IoT), a substantial amount of data is continuously generated that needs to be processed efficiently. While modern artificial intelligence (AI) approaches have shown good capabilities in handling large volumes of data, their excessive demands for memory and processing power result in very high utilisation of resources. In this work, we propose ToSiM-IoT, an optimisation framework that introduces a layer selection approach to identify an ideal mix of active, and inactive layers, using a genetic algorithm for model training. Next, we design a pruning mechanism that identifies performance-critical features using heatmap visualisation, during model inference, and eliminates the remaining features. Two machine learning (ML) models - InceptionV3 and VGG16, have been evaluated on an agricultural weed detection scenario, using the DeepWeeds image classification dataset. Experimental results demonstrate that our framework can achieve a significant reduction in model size and training time, while maintaining high accuracy, for both models. Therefore, this approach provides the potential to be efficiently deployed on intelligent IoT systems where computational capabilities are limited. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based knowledge-aware semantic communications for remote driving image transmission

引用

Digital Communications and Networks 2025年第2期11卷 317-325页

作者： Yangfei Lin Tutomu Murase Yusheng Ji Wugedele Bao Lei Zhong Jie Li Department of Computer and Network Engineering University of Electro-Communications Information Technology Center Nagoya University National Institute of Informatics(NII) Hohhot Minzu College Toyota Motor Corporation Department of Computer Science and Engineering Shanghai Jiaotong University

Remote driving, an emergent technology enabling remote operations of vehicles, presents a significant challenge in transmitting large volumes of image data to a central server. This requirement outpaces the capacity of traditional communication methods. To tackle this, we propose a novel framework using semantic communications, through a region of interest semantic segmentation method, to reduce the communication costs by transmitting meaningful semantic information rather than bit-wise data. To solve the knowledge base inconsistencies inherent in semantic communications, we introduce a blockchain-based edge-assisted system for managing diverse and geographically varied semantic segmentation knowledge bases. This system not only ensures the security of data through the tamper-resistant nature of blockchain but also leverages edge computing for efficient management. Additionally, the implementation of blockchain sharding handles differentiated knowledge bases for various tasks, thus boosting overall blockchain efficiency. Experimental results show a great reduction in latency by sharding and an increase in model accuracy, confirming our framework's effectiveness.

关键词： Semantic communication Remote driving Semantic segmentation Blockchain Knowledge base management

来源：评论

学校读者我要写书评

暂无评论

Explainable Emotion Recognition in Social Networks with Transformers 24

Explainable Emotion Recognition in Social Networks with Tran...

引用

24th IEEE/ACIS International Conference on computer and Information Science, ICIS 2024

作者： Perikos, Isidoros Pylarinou, Chara University of Patras Computer Technology Institute and Press 'Diophantus' Computer Engineering and Informatics Department Patras Greece University of Patras Computer Engineering and Informatics Department Patras Greece

ISBN: (纸本)9798350376647

Emotion recognition in text has become an essential research area within artificial intelligence and natural language processing due to its applications in sentiment analysis, human-computer interaction, and social media analysis. This paper introduces an approach for emotion recognition in social networks using transformer models enhanced with explainability techniques. By leveraging the advanced capabilities of transformers to analyze and classify emotions in written content, our finetuned models achieves high accuracy in identifying emotions according to the Ekman emotional model. The integration of LIME and SHAP provides transparency and interpretability to our model, making it more trustworthy for practical applications. Our findings indicate that models like XLNET report an exceptional performance in emotion recognition tasks. The explainability techniques illustrate the transformer model decision-making processes and the way that they utilize words and their continual information in sentences. © 2024 IEEE.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Online Vehicle Routing with Pickups and Deliveries Under Time-Dependent Travel-Time Constraints 24

Online Vehicle Routing with Pickups and Deliveries Under Tim...

引用

24th Symposium on Algorithmic Approaches for Transportation Modelling, Optimization, and Systems, ATMOS 2024

作者： Kontogiannis, Spyros Paraskevopoulos, Andreas Zaroliagis, Christos Computer Engineering and Informatics Department University of Patras Greece Computer Technology Institute and Press "Diophantus" Patras Greece Computer Technology Institute and Press "Diophantus" Greece

ISBN: (纸本)9783959773508

The Vehicle Routing Problem with pickups, deliveries and spatiotemporal service constraints (VRPPDSTC) is a quite challenging algorithmic problem that can be dealt with in either an offline or an online fashion. In this work, we focus on a generalization, called VRPPDSTCtd, in which the travel-time metric is time-dependent: the traversal-time per road segment (represented as a directed arc) is determined by some function of the departure-time from its tail towards its head. Time-dependence makes things much more complicated, even for the simpler problem of computing earliest-arrival-time paths which is a crucial subroutine to be solved (numerous times) by VRPPDSTCtd schedulers. We propose two online schedulers of requests to workers, one which is a time-dependent variant of the classical Plain-Insertion heuristic, and an extension of it trying to digest some sort of forecasts for future demands for service. We enrich these two online schedulers with two additional heuristics, one targeting for distance-balanced assignments of work loads to the workers and another that makes local-search-improvements to the produced solutions. We conduct a careful experimental evaluation of the proposed algorithms on a real-world instance, with or without these heuristics, and compare their quality with human-curated assignments provided by professional experts (human operators at actual pickup-and-delivery control centers), and also with feasible solutions constructed from a relaxed MILP formulation of VRPPDSTCtd, which is also introduced in this paper. Our findings are quite encouraging, demonstrating that the proposed algorithms produce solutions which (i) are significant improvements over the human-curated assignments, and (ii) have overall quality pretty close to that of the (extremely time-consuming) solutions provided by an exact solver for the MILP formulation. © Spyros Kontogiannis, Andreas Paraskevopoulos, and Christos Zaroliagis.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

Model-to-Circuit Cross-Approximation for Printed Machine Learning Classifiers

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2023年第11期42卷 3532-3544页

作者： Armeniakos, Giorgos Zervakis, Georgios Soudris, Dimitrios Tahoori, Mehdi B. Henkel, Jorg Karlsruhe Institute of Technology Karlsruhe76131 Germany National Technical University of Athens School of Electrical and Computer Engineering Athens15780 Greece University of Patras Computer Engineering and Informatics Department Patras26504 Greece Karlsruhe Institute of Technology Department of Computer Science Karlsruhe76131 Germany

Printed electronics (PEs) promises on-demand fabrication, low nonrecurring engineering costs, and subcent fabrication costs. It also allows for high customization that would be infeasible in silicon, and bespoke architectures prevail to improve the efficiency of emerging PE machine learning (ML) applications. Nevertheless, large feature sizes in PE prohibit the realization of complex ML models in PE, even with bespoke architectures. In this work, we present an automated, cross-layer approximation framework tailored to bespoke architectures that enable complex ML models, such as multilayer perceptrons (MLPs) and support vector machines (SVMs), in PE. Our framework adopts cooperatively a hardware-driven coefficient approximation of the ML model at algorithmic level, a netlist pruning at logic level, and a voltage overscaling at the circuit level. Extensive experimental evaluation on 12 MLPs and 12 SVMs and more than 6000 approximate and exact designs demonstrates that our model-to-circuit cross-approximation delivers power and area optimal designs that, compared to the state-of-the-art exact designs, feature on average 51% and 66% area and power reduction, respectively, for less than 5% accuracy loss. Finally, we demonstrate that our framework enables 80% of the examined classifiers to be battery-powered with almost identical accuracy with the exact designs, paving thus the way toward smart complex printed applications. © 1982-2012 IEEE.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Distributed computing and shared memory-based utility list buffer miner with parallel frameworks for high utility itemset mining

引用

International Journal of Business Intelligence and Data Mining 2023年第2期23卷 125-149页

作者： Atmaja, Eduardus Hardika Sandy Sonawane, Kavita Department of Computer Engineering St. Francis Institute of Technology Mumbai India Department of Informatics Sanata Dharma University Yogyakarta Indonesia

High utility itemset mining (HUIM) is a well-known pattern mining technique. It considers the utility of the items that leads to finding high profit patterns which are more useful for real conditions. Handling large and complex dataset are the major challenges in HUIM. The main problem here is the exponential time complexity. Literature review shows multi-core approaches to solve this problem by parallelising the tasks, but it is limited to single machine resources and also needs a novel strategy. To address this problem, we proposed new strategies namely distributed computing (DC-PLB) and shared memory (SM-PLB)-based utility list buffer miner with parallel frameworks (PLB). It utilises cluster nodes to parallelise and distribute the tasks efficiently. Thorough experiments with results proved that the proposed frameworks achieved better runtime (448 s) in dense datasets compared to the existing PLB (2,237 s). It has effectively addressed the challenges of handing large and complex datasets. © 2023 Inderscience Enterprises Ltd.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Optimized Price Prediction of Cryptocurrencies using Deep Learning on High-Volume Time Series Data 15

Optimized Price Prediction of Cryptocurrencies using Deep Le...

引用

15th International Conference on Information, Intelligence, Systems and Applications, IISA 2024

作者： Vonitsanos, Gerasimos Kanavos, Andreas Grivokostopoulou, Foteini Sioutas, Spyros University of Patras Computer Engineering and Informatics Department Patras Greece Ionian University Department of Informatics Corfu Greece Computer Technology Institute and Press 'Diophantus' Patras Greece

ISBN: (纸本)9798350368833

Statistical models, enhanced by deep learning techniques, have become pivotal in various predictive tasks, including financial forecasting. This paper addresses the challenge of predicting cryptocurrency prices, utilizing a dataset comprising various cryptocurrencies treated as time series. We employ several deep neural network architectures-including Multilayer Perceptrons (MLP), Recurrent Neural Networks (RNN), Long Short-Term Memory networks (LSTM), and Bidirectional LSTM networks-to forecast future prices. Our methodology involves a detailed analysis of cryptocurrency time series to inform the design of these networks. The performance of each model is rigorously compared, highlighting their predictive capabilities in the context of cryptocurrency markets. This study not only contributes to the empirical literature by applying advanced neural networks to high-volume financial data but also provides a comparative analysis that may guide future applications of deep learning in economic forecasting. © 2024 IEEE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Text Analysis and Recognition of Emotional Content Using Deep Learning Methods and BERT 23

Text Analysis and Recognition of Emotional Content Using Dee...

引用

23rd IEEE/ACIS International Conference on computer and Information Science, ICIS 2023

作者： Andrikakis, Efthymios Perikos, Isidoros Paraskevas, Michael Hatzilygeroudis, Ioannis University of Patras Department of Computer Engineering & Informatics Patras Greece University of Patras Computer Technology Institute and Press Diophantus Department of Computer Engineering & Informatics Patras Greece Department of Electrical and Computer Engineering University of Peloponnese Computer Technology Institute and Press Diophantus Patras Greece

ISBN: (纸本)9798350345841

Recognizing the emotional content of Natural Language sentences can improve the way humans communicate with a computer system by enabling them to recognize and imitate emotional expressions. In this paper, deep learning, deep neural networks as well as Transformers were examined. Specifically, we designed and developed deep learning methods and BERT-based implementations for recognizing emotional content in user-generated data. Extensive experiments were conducted using these models on a variety of textual data and all the designed methods were evaluated. The results of the study show that BERT achieved the best overall performance, getting an F1-score of 0.86 on the Twitter Data dataset. Also, the Bi-LSTM with Attention Mechanism and Bi-LSTM using Word2vec performed quite well, achieving F1-scores of 0.83 and 0.82, respectively. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Introduction to Heterogeneous Robotic Systems in 5G and Beyond Networks

引用

IEEE WIRELESS COMMUNICATIONS 2023年第2期30卷 64-65页

作者： Lu, Huimin Ho, Pin-Han Khalfi, Bassem Verikoukis, Christos Kyushu Institute of Technology Japan Department of Electrical and Computer Engineering The University of Waterloo Canada Oregon State University CorvallisOR United States University of Patras Department of Computer Engineering & Informatics Greece

Remote intelligence in the application of robotics and the autonomous system relies heavily on seamless wireless connections. The 5G mobile network technology meets traditional manufacturing enterprises' application requirements for wireless networks based on robot transformation and upgrading, robot interconnection, and remote interactive applications in production. However, there exists many challenging 5G communication issues, such as different communication protocols in the system varies with different robots and no dis-ruptive changes to the physical layer.

关键词： Special issues and sections Robots 5G mobile communication Physical layer Autonomous systems Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

Sensitive Content Detection in Social Networks Using Deep Learning Models and Explainability Techniques 9

Sensitive Content Detection in Social Networks Using Deep Le...

引用

9th IEEE/ACIS International Conference on Big Data, Cloud Computing, and Data Science, BCD 2024

作者： Perikos, Isidoros University of Patras Computer Engineering and Informatics Department Patras Greece University of Peloponnese Computer Technology Institute and Press 'Diophantus' Electrical and Computer Engineering Dept. Patras Greece

ISBN: (纸本)9798350394191

In the dynamic landscape of online social networks, recognizing sensitive content is essential for safeguarding user privacy, fostering inclusivity, and enhancing diversity awareness. Building on prior research, this study explores new dimensions and methodologies for detecting sensitive content. We examine the temporal evolution of sensitive content, revealing how patterns shift over time, and address cross-linguistic challenges, emphasizing cultural and contextual nuances in detection. We employ advanced machine learning techniques, including deep learning models and BERT that improve the accuracy and robustness of the detection procedure. In the experimental study, BERT transformer reported the best performance in detecting sensitive content in text. Additionally, we incorporate explainability techniques such as LIME and SHAP to provide deeper insights into the model's decision-making processes, ensuring predictions are interpretable and reliable. Our work enhances the theoretical framework of sensitive content detection in social networks and provide methods that are accurate and scalable and can facilitate the creation of user-centric interaction that prioritize privacy and user experience. © 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

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：