检索结果-内蒙古大学图书馆

An Efficient Data Protection Scheme Based on Hierarchical ID-Based Encryption for MQTT

ACM Transactions on Sensor Networks 2023年第3期19卷 61-61页

作者： Fan, Chun-I Shie, Cheng-Han Tseng, Yi-Fan Huang, Hui-Chun Department of Computer Science and Engineering National Sun Yat-sen University No. 70 Lien-hai RD. Kaohsiung804201 Taiwan Department of Computer Science National Chengchi University No. 64 Sec. 2 ZhiNan Rd. Wenshan District Taipei City11605 Taiwan

As Internet of Things (IoT) thrives over the whole world, more and more IoT devices and IoT-based protocols have been designed and proposed in order to meet people's needs. Among those protocols, message queueing telemetry transport (MQTT) is one of the most emerging and promising protocols, which provides many-to-many message transmissions based on the "publish/subscribe"mechanism. It has been widely used in industries such as the energy industry, chemical engineering, self-driving, and so on. While transporting important messages, MQTT specification recommends the use of TLS protocol. However, the computation cost of TLS is too heavy. Since topics in a broker are stored with a hierarchical structure, in this manuscript, we propose a novel data protection protocol for MQTT from hierarchical ID-based encryption. Our protocol adopts the intrinsic hierarchical structures of MQTT, and achieves constant-size keys, i.e., independent of the depth in hierarchical structures. Besides, the formal security model for the proposed protocol have been defined in the manuscript. The proposed protocol have been formally proven chosen-plaintext secure under the ĝ.,"-wBDHI assumption. © 2023 Association for Computing Machinery.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Classification of Cross-Layer Optimization Approaches in LoRaWAN for Internet of Things

A Classification of Cross-Layer Optimization Approaches in L...

引用

International Conference on Ubiquitous and Future Networks, ICUFN

作者： Carl Christian Chaguile Melchizedek Alipio Miroslav Bures Department of Electronics and Computer Engineering De La Salle University 2401 Taft Avenue Malate Manila Philippines Department of Computer Science FEE Czech Technical University in Prague Karlovo namesti 13 Prague 2 Czechia

The Internet of Things (IoT) uses Low-Power Wide Area Networks (LPWAN) for applications that require long-range, energy-efficient, and low-cost end devices. LoRaWAN is one of the most popular LPWAN technologies because of its key features and openness making it highly suitable for IoT. Despite its exceptional features, some challenges faced by this technology are optimizing the protocol used for scheduling, low data rate, and duty cycle restrictions. One possible way to address these challenges is by using cross-layer optimization. This optimization technique violates the restrictions of the traditional OSI protocol stack giving freedom to its protocol layers. However, there is currently no summary of cross-layer methods implemented in LoRaWAN. This paper presents a classification of state-of-the-art cross-layer approaches that were used in optimizing the LoRaWAN technology in IoT. The cross-layer techniques were classified based on the merging of adjacent layers, direct communication between layers, and completely new abstractions. In addition, this paper identified the issues and challenges featured in these state-of-the-art cross-layer approaches. Finally, this paper serves as an overview of the performance of cross-layer optimization in LoRaWAN technology for IoT applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

L-SeqSleepNet: Whole-cycle Long Sequence Modeling for Automatic Sleep Staging

引用

IEEE Journal of Biomedical and Health Informatics 2023年第10期27卷 4748-4757页

作者： Phan, Huy Lorenzen, Kristian P. Heremans, Elisabeth Chen, Oliver Y. Tran, Minh C. Koch, Philipp Mertins, Alfred Baumert, Mathias Mikkelsen, Kaare B. De Vos, Maarten Amazon Alexa CambridgeMA02142 United States Queen Mary University of London School of Electronic Engineering and Computer Science LondonE1 4NS United Kingdom Alan Turing Institute LondonNW1 2DB United Kingdom Aarhus University Department of Electrical and Computer Engineering Aarhus8200 Denmark KU Leuven Department of Electrical Engineering Leuven3001 Belgium Lausanne1015 Switzerland Lausanne1015 Switzerland University of Oxford Nuffield Department of Clinical Neurosciences OxfordOX3 9DU United Kingdom University of Lübeck Institute for Signal Processing Lübeck23562 Germany Lübeck23562 Germany The University of Adelaide School of Electrical and Mechanical Engineering AdelaideSA5005 Australia KU Leuven Department of Electrical Engineering and the Department of Development and Regeneration Leuven3001 Belgium KU Leuven Leuven.AI - KU Leuven Institute Leuven3001 Belgium

Human sleep is cyclical with a period of approximately 90 minutes, implying long temporal dependency in the sleep data. Yet, exploring this long-term dependency when developing sleep staging models has remained untouched. In this work, we show that while encoding the logic of a whole sleep cycle is crucial to improve sleep staging performance, the sequential modelling approach in existing state-of-the-art deep learning models are inefficient for that purpose. We thus introduce a method for efficient long sequence modelling and propose a new deep learning model, L-SeqSleepNet, which takes into account whole-cycle sleep information for sleep staging. Evaluating L-SeqSleepNet on four distinct databases of various sizes, we demonstrate state-of-the-art performance obtained by the model over three different EEG setups, including scalp EEG in conventional Polysomnography (PSG), in-ear EEG, and around-the-ear EEG (cEEGrid), even with a single EEG channel input. Our analyses also show that L-SeqSleepNet is able to alleviate the predominance of N2 sleep (the major class in terms of classification) to bring down errors in other sleep stages. Moreover the network becomes much more robust, meaning that for all subjects where the baseline method had exceptionally poor performance, their performance are improved significantly. Finally, the computation time only grows at a sub-linear rate when the sequence length increases. © 2013 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Detection Welding Performance of Industrial Robot Using Machine Learning

Detection Welding Performance of Industrial Robot Using Mach...

引用

2023 International Technical Conference on Circuits/Systems, computers, and Communications, ITC-CSCC 2023

作者： Duongthipthewa, Onjira Meesublak, Koonlachat Takahashi, Atsushi Mitsantisuk, Chowarit Kasetsart University Department of Electrical Engineering 50 Ngamwongwan Rd Chatuchak Bangkok10900 Thailand National Electronics and Computer Technology Center National Science and Technology Development Agency 112 Thailand Science Park Phahonyothin Road Khlong Nueng Khlong Luang Pathumthani12120 Thailand Tokyo Institute of Technology Department of Information and Communications Engineering 2-12-1 Ookayama Meguro-ku Tokyo152-8550 Japan

ISBN: (纸本)9798350326413

Automated welding robots have become an essential component in manufacturing industries due to their precision and increased productivity. Furthermore, they eliminate the need for human workers to be exposed to toxic fumes and bright light during welding processes, ensuring worker safety. However, any failure in welding robots can lead to poor product quality and impact a company's credibility. Therefore, it is critical to predict the welding performance of these machines to maintain product quality. This study proposes the use of spectrogram image classification to classify the quality of welding products. Using a TM-1400 WGIII welding robot, 180 welding datasets were collected to determine the conditions of the welding robot based on different welding wire lengths. Current and voltage signals of the welding robot were studied to identify suitable input parameters and machine learning algorithms were utilized to improve the accuracy of the predictive welding quality. The experiment resulted in an accuracy of 89% based on a 70% training sets and 30% testing sets of data, indicating that spectrogram image classification is an effective technique to monitor the condition of welding robots, improve welding quality, and increase product quality control. This method can be beneficial for both small- and large-scale industries such as automotive, energy, and construction. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Ultrasound-Coupled Electrocoagulation Based Azo Dye Fading Rate Prediction Using Deep Neural Networks

Ultrasound-Coupled Electrocoagulation Based Azo Dye Fading R...

引用

International KES Conference on Human Centred Intelligent Systems, KES HCIS 2023

作者： Akoulih, Meryem Tigani, Smail Wakrim, Asmaa Chehri, Abdellah Saadane, Rachid Ghachtouli, Sanae El IME Lab Faculty of Science Hassan 2 University Casablanca20250 Morocco AAIR Lab Digital Engineering and Artificial Intelligence Systems High Private School Casablanca20100 Morocco Electrical Engineering Department SIRC-LaGeS Hassania School of Public Labors Casablanca20250 Morocco Department of Mathematics and Computer Science Royal Military College KingstonONK7K 7B4 Canada

ISBN: (纸本)9789819934232

This research paper presents a deep learning based predictive model for predicting the azo dye fading rate during electrocoagulation coupled with ultrasound. Electrocoagulation is a commonly used method for the treatment of wastewater contaminated with azo dyes, but the efficiency of this process can be improved by incorporating ultrasound. The proposed deep learning model is trained on a dataset of electrocoagulation experiments with varying parameters such as current density, pH, and treatment time, as well as the presence or absence of ultrasound. The model is able to accurately predict the azo dye removal rate for new sets of electrocoagulation parameters, providing a valuable tool for optimizing the treatment process. The model’s performance is evaluated using standard metrics, and the results demonstrate its effectiveness in predicting azo dye removal rate. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Azo dyes

来源：评论

学校读者我要写书评

暂无评论

Exploring the use of AI in marine acoustic sensor management

Exploring the use of AI in marine acoustic sensor management

引用

2022 International Conference on Underwater Acoustics, ICUA 2022

作者： Clark, Edward Hunter, Alan Isupova, Olga Donnelly, Marcus Department of Mechanical Engineering University of Bath BathBA2 7AY United Kingdom Department of Computer Science University of Bath Bath United Kingdom Systems Engineering & Assesment Ltd Somerset BeckingtonBA116TA United Kingdom

ISBN: (纸本)9781713863311

Underwater passive acoustic source detection and tracking is important for various marine applications, including marine mammal monitoring and naval surveillance. The performance in these applications is dependent on the placement and operation of sensing assets, such as autonomous underwater vehicles. Conventionally, these decisions have been made by human operators aided by acoustic propagation modelling tools, situational and environmental data, and experience. However, this is time-consuming and computationally expensive. We consider a 'toy problem' of a single autonomous vehicle (agent) in search of a stationary source of low frequency within a reinforcement learning (RL) architecture. We initially choose the observation space to be the agent's current position. The agent is allowed to explore the environment with a limited action space, taking equal distance steps in one of $n$ directions. Rewards are received for positive detections of the source. Using OpenAI's PPO algorithm an increase in median episode reward of approximately 20 points in the RL environment developed is seen when the agent is given a history of it's previous moves and signal-to-noise ratio compared to the simple state. The future expansion of the RL framework is discussed in terms of the observation and action spaces, reward function and RL architecture. © 2022 Acoustical Society of America.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Camouflage-based location privacy preserving scheme in vehicular ad hoc networks

Camouflage-based location privacy preserving scheme in vehic...

引用

作者： Benarous, Leila Kadri, Benamar Boudjit, Saadi Department of Computer Science LIM Laboratory Faculty of Science University of Amar Telidji Laghouat Algeria LISSI-Tinc-NET Laboratory University of Paris-Est Creteil Vitry-sur-SeineF-94400 France Department of Biomedical Engineering Faculty of Technology University of Tlemcen Chetouane Algeria L2TI Laboratory University of Paris 13 Villetaneuse93430 France

The location privacy is critical and preserving it is essential. The tracking exposes the real time location, history of visited places and parsed trajectories. Metaphorically speaking, it is the cyber equivalent of the physical stalking and as dangerous as it is. In vehicular networks in particular, this issue is serious because the autonomous vehicles periodically and timely transmit their locations, headings, speed and identity to neighbour vehicles and/or service infrastructures. To preserve the location privacy, various pseudonymbased approaches exist, mainly focusing on unlinkable pseudonym change strategies. In this paper, we propose a camouflage-based solution that prevents the linkability of pseudonyms upon their update even within low density roads where the tracking chances are high. The solution is simulated using NS2 against a global passive attacker that executes the semantic and syntactic linking attacks. The results demonstrate the effectiveness of the solution in protecting the privacy. © 2023 Inderscience Enterprises Ltd.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

SERVICE LEVEL AGREEMENTS AND SECURITY SLA: A COMPREHENSIVE SURVEY

arXiv

引用

arXiv 2024年

作者： Nicolazzo, Serena Nocera, Antonino Pedrycz, Witold Department of Computer Science University of Milan Italy Department of Electrical Computer and Biomedical Engineering University of Pavia Italy Department of Electrical and Computer Engineering University of Alberta EdmontonABT6G 2R3 Canada Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland Research Center of Performance and Productivity Analysis Istinye University Istanbul Turkey

A Service Level Agreement (SLA) is a formal contract between a service provider and a consumer, representing a crucial instrument to define, manage, and maintain relationships between these two parties. The SLA’s ability to define the Quality of Service (QoS) expectations, standards, and accountability helps to deliver high-quality services and increase client confidence in disparate application domains, such as Cloud computing and the Internet of Things. An open research direction in this context is related to the possible integration of new metrics to address the security and privacy aspects of services, thus providing protection of sensitive information, mitigating risks, and building trust. This survey paper identifies state of the art covering concepts, approaches, and open problems of SLA management with a distinctive and original focus on the recent development of Security SLA (SecSLA). It contributes by carrying out a comprehensive review and covering the gap between the analyses proposed in existing surveys and the most recent literature on this topic, spanning from 2017 to 2023. Moreover, it proposes a novel classification criterium to organize the analysis based on SLA life cycle phases. This original point of view can help both academics and industrial practitioners to understand and properly locate existing contributions in the advancement of the different aspects of SLA technology. The present work highlights the importance of the covered topics and the need for new research improvements to tackle present and demanding challenges. © 2024, CC BY.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

TiO_(2)-based photocatalysts for CO_(2) reduction and solar fuel generation

引用

Chinese Journal of Catalysis 2022年第10期43卷 2500-2529页

作者： Tao Zhang Xiaochi Han Nhat Truong Nguyen Lei Yang Xuemei Zhou School of Chemical Engineering Sichuan UniversityChengdu 610065SichuanChina Department of Chemical and Materials Engineering Gina Cody School of Engineering and Computer ScienceConcordia UniversityMontrealQC H3G 2W1Canada

Solar-driven CO_(2) reduction is an efficient way to convert sustainable solar energy and massive CO_(2) to renewable solar fuels,such as CH_(4),HCOOH,HCHO,and CH_(3)OH,*** to now,significant research efforts have been devoted to exploring the reaction path and developing the *** heterogeneous photocatalysis,among the semiconductor-based photocatalysts,titania(TiO_(2)),as an inexpensive and practically sustainable metal oxides,remains the most extensively studied photocatalyst over the past *** this review,we summarize the most recent advances in the solar-driven CO_(2) reduction using TiO_(2)-based photocatalysts,which include the fabrication of heterojunction,surface functional modification,band structure engineering,and morphology design,aiming to improve the CO_(2) conversion efficiency and selectivity to the desired ***,photoelectrochemical and photothermal approaches are introduced and the fundamental principles to activate and enhance the performance of TiO_(2) for the specific reaction are *** exploration of the solar-driven approaches and discussion on the underlying mechanism allow the comprehensive understanding of CO_(2) photoreduction,that can lead to a rational design and synthesis of TiO_(2)-based photocatalysts.

关键词： TiO_(2) Heterogeneous catalysis CO_(2)reduction Solar fuel

来源：评论

学校读者我要写书评

暂无评论

A Novel Structure-Agnostic Multi-Objective Approach for Weight-Sharing Compression in Deep Neural Networks

arXiv

引用

arXiv 2025年

作者： Khosrowshahli, Rasa Rahnamayan, Shahryar Ombuki-Berman, Beatrice Department of Computer Science Faculty of Mathematics and Science Brock University St. CatharinesONL2S 3A1 Canada lab Department of Engineering Brock University St. CatharinesONL2S 3A1 Canada

Deep neural networks suffer from storing millions and billions of weights in memory post-training, making challenging memory-intensive models to deploy on embedded devices. The weight-sharing technique is one of the popular compression approaches that use fewer weight values and share across specific connections in the network. In this paper, we propose a multi-objective evolutionary algorithm (MOEA) based compression framework independent of neural network architecture, dimension, task, and dataset. We use uniformly sized bins to quantize network weights into a single codebook (lookup table) for efficient weight representation. Using MOEA, we search for Pareto optimal k bins by optimizing two objectives. Then, we apply the iterative merge technique to non-dominated Pareto frontier solutions by combining neighboring bins without degrading performance to decrease the number of bins and increase the compression ratio. Our approach is model- and layer-independent, meaning the weights are mixed in the clusters from any layer, and the uniform quantization method used in this work has O(N) complexity instead of non-uniform quantization methods such as k-means with O(Nkt) complexity. In addition, we use the center of clusters as the shared weight values instead of retraining shared weights, which is computationally expensive. The advantage of using evolutionary multi-objective optimization is that it can obtain non-dominated Pareto frontier solutions with respect to performance and shared weights. The experimental results show that we can reduce the neural network memory by 13.72 ∼ 14.98× on CIFAR-10, 11.61 ∼ 12.99× on CIFAR-100, and 7.44 ∼ 8.58× on ImageNet showcasing the effectiveness of the proposed deep neural network compression framework. © 2025, CC BY.

关键词： Bins

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：