A Cloud-Edge Computing Framework for Cyber-Physical-Social Services

Wang, Xiaokang; Yang, Laurence T.; Xie, Xia; Jin, Jirong; Deen, M. Jamal

doi:10.1109/mcom.2017.1700360

Cited by 274 publications

(111 citation statements)

References 14 publications

Supporting

Mentioning

111

Contrasting

Order By: Relevance

“…Some of the interesting problems are how to adjust subsequence length/ step length and regularize a network and how to use LSTM-FCN, ALSTM-FCN [9], hierarchies of feature [19], or time aware [20,21] to improve the performance of time series classification. In addition, we will try to apply the method of classification service in distributed cloud/fog environment [22][23][24][25][26][27][28][29][30][31][32] in the future.…”

Section: Discussionmentioning

confidence: 99%

Time series classification based on statistical features

Lei

2020

J Wireless Com Network

View full text Add to dashboard Cite

This paper presents a statistical feature approach in fully convolutional time series classification (TSC), which is aimed at improving the accuracy and efficiency of TSC. This method is based on fully convolutional neural networks (FCN), and there are the following two properties: statistical features in data preprocessing and finetuning strategies in network training. The key steps are described as follows: firstly, by the window slicing principle, dividing the original time series into multiple equal-length subsequences; secondly, by extracting statistical features on each subsequence, in order to form a new sequence as the input of the neural network, and training neural network by the fine-tuning idea; thirdly, by evaluating the classification performance about test sets; and finally, by comparing the sample sequence complexity and network classification loss accuracy with the FCN using the original sequence. Our experimental results show that the proposed method improved the classification effects of FCN and the residual network (ResNet), which means that it has a generalization ability to the network structures.

show abstract

Section: Discussionmentioning

confidence: 99%

Time series classification based on statistical features

Lei

2020

J Wireless Com Network

View full text Add to dashboard Cite

show abstract

“…With the development of IoT and data computing technologies [16][17][18], researchers have access to achieve more data with various types and large amount. However, imbalanced data problem leads to artificial intelligence models built on these data which behave extremely poor in performance.…”

Section: Smote Methodsmentioning

confidence: 99%

SMOTE-Boost-based sparse Bayesian model for flood prediction

Ding

Feng

2020

J Wireless Com Network

View full text Add to dashboard Cite

With a significant development of big data analysis and cloud-fog-edge computing, human-centered computing (HCC) has been a hot research topic worldwide. Essentially, HCC is a cross-disciplinary research domain, in which the core idea is to build an efficient interaction among persons, cyber space, and real world. Inspired by the improvement of HCC on big data analysis, we intend to involve related core and technologies to help solve one of the most important issues in the real world, i.e., flood prediction. To minimize the negative impacts brought by floods, researchers pay special attention to improve the accuracy of flood forecasting with quantity of technologies including HCC. However, historical flood data is essentially imbalanced. Imbalanced data causes machine learning classifiers to be more biased towards patterns with majority samples, resulting in poor classification of pattern with minority samples. In this paper, we propose a novel Synthetic Minority Over-sampling Technique (SMOTE)-Boost-based sparse Bayesian model to perform flood prediction with both high accuracy and robustness. The proposed model consists of three modules, namely, SMOTE-based data enhancement, AdaBoost training strategy, and sparse Bayes model construction. In SMOTE-based data enhancement, we adopt a SMOTE algorithm to effectively cover diverse data modes and generate more samples for prediction pattern with minority samples, which greatly alleviates the problem of imbalanced data by involving experts' analysis and users' intentions. During AdaBoost training strategy, we propose a specifically designed AdaBoost training strategy for sparse Bayesian model, which not only adaptively and inclemently increases prediction ability of Bayesian model, but also prevents its over-fitting performance. Essentially, the design of AdaBoost strategy helps keep balance between prediction ability and model complexity, which offers different but effective models over diverse rivers and users. Finally, we construct a sparse Bayesian model based on AdaBoost training strategy, which could offer flood prediction results with high rationality and robustness. We demonstrate the accuracy and effectiveness of the proposed model for flood prediction by conducting experiments on a collected dataset with several comparative methods.

show abstract

“…Encryption hash link and distributed consistency mechanism ensure that the data stored on the immutable blockchain will not be changed or deleted, but the blockchain mechanism does not guarantee the reliability of the data in the source. Wang et al [31] puts forward a cloud-edge computing framework for Cyber-Physical-Social Services. Therefore, some recent researches focus on integrating trust mechanism and performance optimization into blockchain-based IIoT applications.…”

Section: Blockchain-based Iiot Technology Analysismentioning

confidence: 99%

A Novel Blockchain Framework for Industrial IoT Edge Computing

Zeng

Yang

et al. 2020

Sensors

View full text Add to dashboard Cite

With the rapid development of industrial internet of thing (IIoT), the distributed topology of IIoT and resource constraints of edge computing conduct new challenges to traditional data storage, transmission, and security protection. A distributed trust and allocated ledger of blockchain technology are suitable for the distributed IIoT, which also becomes an effective method for edge computing applications. This paper proposes a resource constrained Layered Lightweight Blockchain Framework (LLBF) and implementation mechanism. The framework consists of a resource constrained layer (RCL) and a resource extended layer (REL) blockchain used in IIoT. We redesign the block structure and size to suit to IIoT edge computing devices. A lightweight consensus algorithm and a dynamic trust right algorithm is developed to improve the throughput of blockchain and reduce the number of transactions validated in new blocks respectively. Through a high throughput management to guarantee the transaction load balance of blockchain. Finally, we conducted kinds of blockchain simulation and performance experiments, the outcome indicated that the method have a good performance in IIoT edge application.

show abstract

A Cloud-Edge Computing Framework for Cyber-Physical-Social Services

Cited by 274 publications

References 14 publications

Time series classification based on statistical features

Time series classification based on statistical features

SMOTE-Boost-based sparse Bayesian model for flood prediction

A Novel Blockchain Framework for Industrial IoT Edge Computing

Contact Info

Product

Resources

About