Qingsong Huang

A cloud-based framework for large-scale traditional Chinese medical record retrieval

INTRODUCTION Electronic medical records are increasingly common in medical practice. The secondary use of medical records has become increasingly important. It relies on the ability to retrieve the complete information about desired patient populations. How to effectively and accurately retrieve relevant medical records from large- scale medical big data is becoming a big challenge. Therefore, we propose an efficient and robust framework based on cloud for large-scale Traditional Chinese Medical Records (TCMRs) retrieval. METHODS We propose a parallel index building method and build a distributed search cluster, the former is used to improve the performance of index building, and the latter is used to provide high concurrent online TCMRs retrieval. Then, a real-time multi-indexing model is proposed to ensure the latest relevant TCMRs are indexed and retrieved in real-time, and a semantics-based query expansion method and a multi- factor ranking model are proposed to improve retrieval quality. Third, we implement a template-based visualization method for displaying medical reports. RESULTS The proposed parallel indexing method and distributed search cluster can improve the performance of index building and provide high concurrent online TCMRs retrieval. The multi-indexing model can ensure the latest relevant TCMRs are indexed and retrieved in real-time. The semantics expansion method and the multi-factor ranking model can enhance retrieval quality. The template-based visualization method can enhance the availability and universality, where the medical reports are displayed via friendly web interface. CONCLUSIONS In conclusion, compared with the current medical record retrieval systems, our system provides some advantages that are useful in improving the secondary use of large-scale traditional Chinese medical records in cloud environment. The proposed system is more easily integrated with existing clinical systems and be used in various scenarios.

Evaluating on online services based on social choice theory

Nowadays, there are a large number of online services in the open network environment. Due to the difference of subjective wills of users, such as consumption psychology and interests, their service preferences and evaluation standards differ. Since services are evaluated by users of inconsistent evaluation criteria, the scores would be possibly different even if the services same and that further led to online services not comparative. After exploring the way to provide highly satisfactory high-quality online services for users, a method is proposed in this paper for decision analysis. The method based on basic ideas of social choice theory, and according to information on each users preferences and evaluation to build the user preference matrix at first. Then, 0-1 integer programming models are built for Kemeny social choice functions through the matrixes. Finally, the optimal ranking of services is obtained by solving the models, so that it may be consistent with group preferences to the greatest extent. The experimental results show that the proposed method not only effective for solving problems concerning incomparability of online services, but also efficiently resists recommendation attacks and manipulation.

SmartWADO: an Extensible WADO Middleware for Regional Medical Image Sharing

Medical image sharing is an important problem in modern radiology, with wide applications in Internet and mobile devices. Some important features need to be added and optimized to medical image sharing. In this paper, we present an extensible Web Access to DICOM Persistent Objects (WADO) middleware based on image cache and real-time Web monitor technology for regional medical image sharing. We first develop the extension method of WADO standard and workflow of extended WADO service. Then, we design a medical image cache method to improve the performance of medical image on-demand transmission. Using the real-time monitor can discover the performance bottlenecks and optimized critical points. The experimental results show that the middleware effectively delivers medical images and reports to Web clients over the Internet, regardless of the platform used for access. It can be deployed in one hospital to provide WADO service to medical workers and also can be applied to regional picture archiving and communication systems (PACS) to transmit medical images and reports to Internet users in a way that is transparent to end-user applications.

Unsupervised segmentation and elm for fabric defect image classification

In order to solve the problem of low accuracy and efficiency for surface defects in common woven fabrics, a novel fabric defect classification method is proposed based on unsupervised segmentation and ELM. The classification method is divided into four steps including defect segmentation, feature extraction, ELM classifier training, and Bayesian probability fusion. Firstly, an unsupervised segmentation is presented for the Grayscale fabric defect image after preprocessing. Secondly, geometric and texture features were extracted by using the segmented image and the undivided Grayscale image. Then, features and labels in fabric defect images are considered as training sets to train the ELM classifier. Finally, the input fabric defect image is classified by the trained ELM classifier and the Bayesian probability fusion method. Experimental results show that the proposed method can classify the fabric defect image with high accuracy and efficiency that can better meet the requirements for practical applications.

Clothing Co-Segmentation Based on HOG Features and E-SVM Classifier

To improve the accuracy of clothing segmentation, a novel co-segmentation method is proposed in this paper based on HOG(Histogram of Oriented Gradients) features and E-SVM(Exemplar Support Vector Machine) classifier. The cosegmentation method uses an auxiliary dataset and is implemented with three steps: superpixel grouping, E-SVM classifier training, and segmentation propagation. Firstly, image input by user is segmented in superpixel, such that the images in auxiliary dataset can be divided into multi-regions. Secondly, some regions are selected to a positive segmentation and HOG information is used to train E-SVM classifiers. Finally, the cloth is segmented into user image with E-SVM classifiers and segmentation propagation. Experimental results show that the proposed method can segment clothing images with high accuracy.

A Probabilistic Approach to Analyzing the Stochastic QoS of Web Service Composition

Open and dynamic environments lead to inherent uncertainty of Web service QoS (Quality of Service). Thus, the Web service composition which consists of these services will be necessarily random of the QoS. The requirements of the QoS of Web service composition may not be certainly satisfied. We use a simulation approach named Importance Sampling to analyze the QoS probability of Web service composition in stochastic PERT network. In this paper, we propose a relatively simple distribution function and introduce a weighting function to ensure that the estimating of the target distribution function is an unbiased estimation. We conduct a comparison of Importance Sampling technique with Monte Carlo simulation about the rationality and the operation efficiency based on the actual QoS data of Web services by experiment. The experimental results prove that the Importance Sampling technique has better precision and higher efficiency than Monte Carlo simulation.

Setting optional number of Web services in Web service communities based on queue theory

Users always wait to be served by Web service in the community. The cost of Web service community is increased due to the users queue up in the community will consumes resources. In this paper we research on setting optional number of Web services in the community in order to make the cost of community be minimum. A solution was proposed based on both theory of queue and marginal analysis method. The queue model in the Web service community is M/M/n. In the M/M/n model, we combine the theory of queue to calculate the length of users in the community when the queue is in stable condition. Then we find out the cost function based on the cost factors of Web service community. The optional number of Web service is found after the community cost is counted based on the cost function and analyzing in marginal analysis theory. Our solution is proved to be effective to find out proper number of Web service in the community after the experiment.

Distributing profit of web services communities based on Shapley value

Community of Web Service is a society composed by a number of functionally identical Web Services. The communities are regarded as a whole for users in an opening environment and users would pay for services when they invoke Web Service successfully. Communities should distribute the whole profit to all of the providers of Web Services inside after a settlement period. Due to the cooperation among Web Services in a community we treat these Web Services as a cooperative game. In this paper we propose a method to distribute profit based on Shapley value which considers the contribution of each Web Service to community and we then implement an algorithm based on MC-nets to suit the actual situation which we always cannot get complete input for general algorithm of computing Shapley value. We also show our method is efficient and practicable.