Shuai Ding

Combining QoS prediction and customer satisfaction estimation to solve cloud service trustworthiness evaluation problems

The collection and combination of assessment data in trustworthiness evaluation of cloud service is challenging, notably because QoS value may be missing in offline evaluation situation due to the time-consuming and costly cloud service invocation. Considering the fact that many trustworthiness evaluation problems require not only objective measurement but also subjective perception, this paper designs a novel framework named CSTrust for conducting cloud service trustworthiness evaluation by combining QoS prediction and customer satisfaction estimation. The proposed framework considers how to improve the accuracy of QoS value prediction on quantitative trustworthy attributes, as well as how to estimate the customer satisfaction of target cloud service by taking advantages of the perception ratings on qualitative attributes. The proposed methods are validated through simulations, demonstrating that CSTrust can effectively predict assessment data and release evaluation results of trustworthiness.

Decision support for personalized cloud service selection through multi-attribute trustworthiness evaluation.

Facing a customer market with rising demands for cloud service dependability and security, trustworthiness evaluation techniques are becoming essential to cloud service selection. But these methods are out of the reach to most customers as they require considerable expertise. Additionally, since the cloud service evaluation is often a costly and time-consuming process, it is not practical to measure trustworthy attributes of all candidates for each customer. Many existing models cannot easily deal with cloud services which have very few historical records. In this paper, we propose a novel service selection approach in which the missing value prediction and the multi-attribute trustworthiness evaluation are commonly taken into account. By simply collecting limited historical records, the current approach is able to support the personalized trustworthy service selection. The experimental results also show that our approach performs much better than other competing ones with respect to the customer preference and expectation in trustworthiness assessment.

QoS-aware resource matching and recommendation for cloud computing systems

Resource matching and recommendation is an important topic in the field of cloud computing. While a lot of cloud resource discovery and negotiation models have been proposed, resource matching and recommendation issues have often been neglected, such as the utilization of attribute weights and the collaborative application of empirical data, price utility and so on. To cope with this challenge, we focus on designing a novel resource recommendation method which can regulate multi-attribute matching between provider solutions and customer demands in this paper. At first, we describe a resource matching algorithm that considers both functional requirements and QoS attributes. Then, we propose a resource recommendation method for cloud computing system that integrates price utility, multi-attribute matching metric and group customer evaluation. Finally, the extensive simulation results demonstrate that our proposed method is effective in various simulated scenarios. Current results are of high significance to design an efficient resource matching and recommendation with guaranteed QoS requirements under the realistic cloud computing circumstances.

Utilizing customer satisfaction in ranking prediction for personalized cloud service selection

Abstract With the rapid development of cloud computing, cloud service has become an indispensable component of modern information systems where quality of service (QoS) has a direct impact on the systems performance and stability. While scholars have concentrated their efforts on the monitoring and evaluation of QoS in cloud computing, other service selection characteristics have been neglected, such as the scarcity of evaluation data and various customer needs. In this paper, we present a ranking-oriented prediction method that will assist in the process of discovering the cloud service candidates that have the highest customer satisfaction. This approach encompasses two basic functions: ranking similarity estimation and cloud service ranking prediction that takes into account customers preference and expectation. The comparative experimental results show that the proposed method outperforms other competing methods.

Online pricing with bundling and coupon discounts

We propose an online pricing strategy by utilising product bundling and coupon discounts. Given customer’s purchase behaviour and preference for bundling and coupon, we propose a nonlinear mixed-integer programming model to determine the most appropriate bundle discount and instant coupon so as to maximise e-tailer’s profit. A fast heuristic algorithm is designed to implement the proposed model online in real time. We investigate the robustness of the proposed method by examining how uncertainties in system parameters affect performance. Through collaborative optimisation, we offer important insights and managerial implications, and show how marketers can attract more purchase and maximise profit by properly integrating marketing tools such as bundling and coupon.

Time-aware cloud service recommendation using similarity-enhanced collaborative filtering and ARIMA model

Abstract The quality of service (QoS) of cloud services change frequently over time. Existing service recommendation approaches either ignore this property or address it inadequately, leading to ineffective service recommendation. In this paper, we propose a time-aware service recommendation (taSR) approach to address this issue. We first develop a novel similarity-enhanced collaborative filtering (CF) approach to capture the time feature of user similarity and address the data sparsity in the existing PITs (point in time). We then apply autoregressive integrated moving average model (ARIMA) to predict the QoS values in the future PIT under QoS instantaneity. We evaluate the proposed approach and compare it to the state-of-the-art. Our experimental results show that taSR achieves significant performance improvements over existing approaches.

Trust-Enhanced Cloud Service Selection Model Based on QoS Analysis

Cloud computing technology plays a very important role in many areas, such as in the construction and development of the smart city. Meanwhile, numerous cloud services appear on the cloud-based platform. Therefore how to how to select trustworthy cloud services remains a significant problem in such platforms, and extensively investigated owing to the ever-growing needs of users. However, trust relationship in social network has not been taken into account in existing methods of cloud service selection and recommendation. In this paper, we propose a cloud service selection model based on the trust-enhanced similarity. Firstly, the direct, indirect, and hybrid trust degrees are measured based on the interaction frequencies among users. Secondly, we estimate the overall similarity by combining the experience usability measured based on Jaccard’s Coefficient and the numerical distance computed by Pearson Correlation Coefficient. Then through using the trust degree to modify the basic similarity, we obtain a trust-enhanced similarity. Finally, we utilize the trust-enhanced similarity to find similar trusted neighbors and predict the missing QoS values as the basis of cloud service selection and recommendation. The experimental results show that our approach is able to obtain optimal results via adjusting parameters and exhibits high effectiveness. The cloud services ranking by our model also have better QoS properties than other methods in the comparison experiments.

Multi-objective optimization based ranking prediction for cloud service recommendation

Abstract Performing effective ranking prediction for cloud services can help customers make prompt decisions when they are confronted by a large number of choices. This can also enhance web service user satisfaction levels. Improving ranking prediction of QoS-based services continues to be an active topic of research in cloud service recommendation. Most service recommendation algorithms focus on prediction accuracy, ignoring diversity, which also may be an important consideration. In this paper we view service recommendation as a multi-objective optimization problem, and give two modified ranking prediction and recommendation algorithms that simultaneously consider accuracy and diversity. Existing algorithm recommendations can be made much more diverse by adjusting weights on service origin and substantially reducing the risk of inappropriate recommendations. Our experiments show that the algorithms we propose can yield greater diversity without greatly sacrificing prediction accuracy.

Smart connected electronic gastroscope system for gastric cancer screening using multi-column convolutional neural networks

Gastroscopy is a widely adopted method for gastric cancer screening and early diagnosis. Clinical studies show that it can effectively prolong patient life and maximise therapeutic effect. However, it is difficult for doctors to identify and detect lesions in real time, which manifests as the major challenge in gastroscopy. In this paper, we propose SCEG, a smart connected electronic gastroscopy system that performs dynamic cancer screening in gastroscopy. By integrating electronic gastroscopy with cloud-based medical image analysis service, we develop an AdaBoost-based multi-column convolutional neural network (MCNN) for enhancing gastric cancer screening. Experimental results show that the proposed MCNN approach significantly outperforms other competing approaches.

Exploring diffusion strategies for mHealth promotion using evolutionary game model

Abstract Mobile health (mHealth) is an emerging healthcare practice that provides public health information and medical care services using mobile communication devices, such as smartphones and tablet computers. Given the service convenience and the great potential in reducing medical expense, the promotion of mHealth has become an indispensable component of healthcare reform in China. While Chinese government has shown strong support in promoting mHealth, the behaviors of different participants in mHealth have not been well studied, which prevents its fast diffusion in China. In this paper, by analyzing the current status of mHealth in China, we leverage the evolutionary game theory to build a novel model to capture the behaviors of two key participants, e.g., hospitals and patients, in mHealth. We analyze the payoff matrix between hospitals and patients such that a replicator dynamic system can be built. We validate the proposed model with detailed simulations. Our observations benefit not only the mHealth participants but also the government policy makers.