2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT)最新文献_第2页

Enhanced Dyna-QPC model with Fuzzy logic to train gaming models 基于模糊逻辑的改进Dyna-QPC模型训练博弈模型

2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT) Pub Date : 2021-12-12 DOI: 10.1109/gcaiot53516.2021.9692963

H. Ignatious, H. El-Sayed, Manzoor Khan

引用次数: 0

A Probabilistic City Model Generation for Application in Internet of Vehicles Technology 基于车联网技术的概率城市模型生成

2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT) Pub Date : 2021-12-12 DOI: 10.1109/gcaiot53516.2021.9692922

Mohannad Barakat, Noha Magdy, M. Shimy, B. Mokhtar

引用次数: 0

Road Accident Severity Prediction — A Comparative Analysis of Machine Learning Algorithms 道路交通事故严重程度预测——机器学习算法的比较分析

2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT) Pub Date : 2021-12-12 DOI: 10.1109/gcaiot53516.2021.9693055

Sumbal Malik, Hesham El-Sayed, M. A. Khan, Muhammad Jalal Khan

{"title":"Road Accident Severity Prediction — A Comparative Analysis of Machine Learning Algorithms","authors":"Sumbal Malik, Hesham El-Sayed, M. A. Khan, Muhammad Jalal Khan","doi":"10.1109/gcaiot53516.2021.9693055","DOIUrl":"https://doi.org/10.1109/gcaiot53516.2021.9693055","url":null,"abstract":"Crash severity prediction models enable various agencies to predict the severity of a crash to gain insights into the factors that affect or are associated with crash severity. One of the potential ways to predict the crash severity is to leverage machine learning (ML) algorithms. With the help of accident data, ML algorithms find hidden patterns to predict whether the severity of the crash is fatal, serious, or slight. In this research, we develop a prediction framework and implemented six different machine learning algorithms, namely: Naïve Bayes, Logistic Regression, Decision Tree, Random Forest, Bagging, and AdaBoost to predict the severity of the crash. Experimental results procured for the crash dataset published by the UK shows that Random Forest, Decision Tree, and Bagging significantly outperformed other algorithms in terms of all performance metrics. Furthermore, we analyze the huge; traffic data and extract insightful crash patterns to figure out the significant factors that have a clear effect on road accidents and provide beneficial suggestions regarding this issue. We strongly believe that the proposed prediction framework and the extracted pattern analysis would be helpful in improving the traffic safety system and assist the road authorities to establish proactive strategies to prevent traffic accidents.","PeriodicalId":169247,"journal":{"name":"2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122462331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Unbalanced Encoding in Synchronous Weight Quantization-Compression for Low-Bit Quantized Neural Network 低比特量化神经网络同步权量化压缩中的不平衡编码

2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT) Pub Date : 2021-12-12 DOI: 10.1109/gcaiot53516.2021.9693045

Yuzhong Jiao, Sha Li, Peng Luo, Xiao Huo, Yiu Kei Li

{"title":"Unbalanced Encoding in Synchronous Weight Quantization-Compression for Low-Bit Quantized Neural Network","authors":"Yuzhong Jiao, Sha Li, Peng Luo, Xiao Huo, Yiu Kei Li","doi":"10.1109/gcaiot53516.2021.9693045","DOIUrl":"https://doi.org/10.1109/gcaiot53516.2021.9693045","url":null,"abstract":"Deep neural networks (DNNs) usually have thousands of trainable parameters to ensure high accuracy. Due to large amounts of computation and memory requirements, these networks are not suitable for real-time and resource-constrained systems. Various techniques such as network pruning, weight sharing, network quantization, and weight encoding have improved computational and memory efficiency. The synchronous weight quantization-compression (SWQC) technique applies both network quantization and weight encoding to realize weight compression in the process of network quantization. This technique generates a quantized neural network (QNN) model with a good trade-off between accuracy and compression rate by choosing the proper group size, retraining epoch number, and weight threshold. To further improve the compression rate of SWQC, a new strategy for weight encoding, unbalanced encoding, is proposed in this paper. This strategy is able to compress one or multiple quantized weights into one bit, thereby achieving a higher compression rate. Experiments are performed on a 4-bit QNN using the CIFAR10 dataset. The results show that unbalanced encoding achieves a higher compression rate for the layers with large-quantity parameters. By using mixed encoding which combines balanced and unbalanced encoding in different layers can achieve a higher compression rate than using one of them only. In the experiments with CIFAR10, unbalanced encoding gets the compression rate of over 13X in the fully connected layer. By comparison, the compression rate of SWQC with the incorporation of unbalanced encoding achieves more than 5X higher than using balanced encoding only.","PeriodicalId":169247,"journal":{"name":"2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126150610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Mobility-as-a-Service Challenges and Opportunities in the Post-Pandemic 大流行后流动性即服务的挑战与机遇

2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT) Pub Date : 2021-12-12 DOI: 10.1109/gcaiot53516.2021.9693025

Sara Paiva, Filipa Mourão

{"title":"Mobility-as-a-Service Challenges and Opportunities in the Post-Pandemic","authors":"Sara Paiva, Filipa Mourão","doi":"10.1109/gcaiot53516.2021.9693025","DOIUrl":"https://doi.org/10.1109/gcaiot53516.2021.9693025","url":null,"abstract":"In December 2019, the world experienced a pandemic that called into question what we always took for granted, such as our freedom of movement. Tough restrictions imposed across the world were necessary to stem the transmission of the COVID-19 virus and have largely affected the mobility and transport sector. In a first phase, due to the mandatory confinement that forced people not to leave their houses; in a second phase, when the measures eased and people started to have the need to move again, it was necessary to look for alternative means of transport that avoided the gathering of people. In view of the advances that were being made in recent years towards a Mobility-as-a-Service paradigm that advocates multimodal and shared transport, the pandemic has raised many challenges. In this paper, a statistical analysis of the mobility data made available by Apple from January 2020 to March 2021 is presented, where the reduction in the use of public transport becomes evident, leading us to question what the future of Mobility-as-a-Service will be as its foundation advocates, among other aspects, the use of a shared transport model. Despite the challenges that the pandemic has brought to Mobility-as-a-Service, a set of opportunities are presented that can be used in the short and medium term to strengthen the paradigm and enhance its massive adoption.","PeriodicalId":169247,"journal":{"name":"2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126275986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Performance study on IOTA Chrysalis and Coordicide in the Industrial Internet of Things 工业物联网中IOTA蝶蛹和协蚊的性能研究

2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT) Pub Date : 2021-12-12 DOI: 10.1109/gcaiot53516.2021.9692985

Julia Rosenberger, Felix Rauterberg, Dieter Schramm

{"title":"Performance study on IOTA Chrysalis and Coordicide in the Industrial Internet of Things","authors":"Julia Rosenberger, Felix Rauterberg, Dieter Schramm","doi":"10.1109/gcaiot53516.2021.9692985","DOIUrl":"https://doi.org/10.1109/gcaiot53516.2021.9692985","url":null,"abstract":"Due to the big advantages like immutable, decentralized data record and smart contracts (SC), distributed ledger technologies (DLT) gain strongly in importance in a wide variety of areas. With the fourth industrial revolution and the industrial internet of things (IIoT), new business models and technology fields based on data-driven approaches evolve and lead to the demand for trustworthy data and secure data exchange in a decentralized system. While a comprehensive number of possible industrial use cases exists, there is a lack of experimental studies on their applicability on IIoT devices. Available performance tests mostly focus on the performance of the DLT but not on their influence on the resources of the IIoT device. Furthermore, one very important DLT, namely IOTA, which is explicitly designed for application in IoT environments, did not receive much attention yet. This was due to two major drawbacks, namely the need for a centralized instance and the lack of SC functionality in the first IOTA version compared to other DLTs such as Hyperledger. The recently published version IOTA Coordicide improved in both. This paper presents detailed results from two industrial use cases and experiments on a private DLT network based on IOTA in IIoT, focusing on the resource demands for the IIoT devices with different network setups. The results confirm the suitability of IOTA for IIoT devices. Furthermore, an overview of the required resources of the IIoT devices with different transaction rates and networks sizes is given.","PeriodicalId":169247,"journal":{"name":"2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121803379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Privacy-Preserving Multi-Party Machine Learning for Object Detection 保护隐私的对象检测多方机器学习

2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT) Pub Date : 2021-12-12 DOI: 10.1109/gcaiot53516.2021.9692980

Imen Chakroun, T. Aa, Roel Wuyts, Wilfried Verarcht

引用次数: 0

Multi-agent reinforcement learning for intelligent resource allocation in IIoT networks 工业物联网网络中智能资源分配的多智能体强化学习

2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT) Pub Date : 2021-12-12 DOI: 10.1109/gcaiot53516.2021.9692913

Julia Rosenberger, Michael Urlaub, D. Schramm

{"title":"Multi-agent reinforcement learning for intelligent resource allocation in IIoT networks","authors":"Julia Rosenberger, Michael Urlaub, D. Schramm","doi":"10.1109/gcaiot53516.2021.9692913","DOIUrl":"https://doi.org/10.1109/gcaiot53516.2021.9692913","url":null,"abstract":"In the industrial Internet of Things (IIoT), a high number of devices with limited resources, like computational power, memory, bandwidth and, in case of wireless sensor networks, also energy, communicate. At the same time, the amount of data as well as the demand for data processing in the edge is rapidly increasing. To enable Industry 4.0 (I4.0) and the IIoT, an intelligent resource allocation is required to make optimal use of the available resources. For this purpose, a multi-agent system (MAS) based on deep reinforcement learning (DRL) is proposed. Multi-agent reinforcement learning (MARL) is already taken into account in different communication networks, e.g. for intelligent routing. Despite its great potential, little attention is paid to these methods in industry so far. In this work, DRL is applied for resource allocation and load balancing for industrial edge computing. An optimal usage of the available resources of the IIoT devices should be achieved. Due to the structure of IIoT systems as well as for security reasons, a MAS is preferred for decentralized decision making. In subsequent steps, it is planned to add and remove devices during runtime, to change the number of tasks to be executed as well as evaluations on single- and multi-policy-approaches. The following aspects will be considered for evaluation: (1) improvement of the resource usage of the devices and (2) overhead due to the MAS.","PeriodicalId":169247,"journal":{"name":"2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120980251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Personalized Route Navigation System: Utilizing Available Static and Live Data for Preference-Based Recommendation 个性化路线导航系统:利用可用的静态和实时数据进行基于偏好的推荐

2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT) Pub Date : 2021-12-12 DOI: 10.1109/gcaiot53516.2021.9692993

Alec A. Souders, Mohammad S. Almalag, Christopher Kreider

引用次数: 1

Asynchronous Coarse-Grained Load Migration Scheme for IoT Applications in Fog Networks 雾网络中物联网应用的异步粗粒度负载迁移方案

2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT) Pub Date : 2021-12-12 DOI: 10.1109/gcaiot53516.2021.9693046

M. Jasim, N. Siasi, Mohammad S. Almalag, Vahraz Honary, A. Aldalbahi

{"title":"Asynchronous Coarse-Grained Load Migration Scheme for IoT Applications in Fog Networks","authors":"M. Jasim, N. Siasi, Mohammad S. Almalag, Vahraz Honary, A. Aldalbahi","doi":"10.1109/gcaiot53516.2021.9693046","DOIUrl":"https://doi.org/10.1109/gcaiot53516.2021.9693046","url":null,"abstract":"Fog computing provides distributed processing and storage solutions for real-time applications that demand low latency and fast response times. This makes fog solutions suitable for internet-of-things (IoT) devices that request various network functions. To offer multiple functions for IoT applications, fog nodes can leverage network function virtualization (NFV) for a scalable and elastic function modification, i.e., without the need for dedicated hardware. Despite the saliencies achieved from the synergistic combination between fog and NFV technologies, a key challenge here is the limited resources at the fog nodes. This makes the latter susceptible to rapid node saturation and network congestion at high traffic volumes. Along this, efficient resource utilization and load distribution mechanisms are necessary to enhance admission rates and quality-of-service (QoS). Hence, this paper proposes novel load migration schemes for NFV-based fog networks that aim to reduce the overhead of the migration process. Namely, a coarse-grained load diffusion scheme is adopted to reduce migration frequencies, incurred delay, and cost. Further, destination nodes are selected based on least-load (LL) or least-delay (LD) mechanisms to accommodate delay-sensitive, delay-tolerant, and computation-intensive IoT applications.","PeriodicalId":169247,"journal":{"name":"2021 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115893327","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2