http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Research on Image Retrieval Technology Based on Fast Wavelet Transform
보안공학연구지원센터(IJHIT) 보안공학연구지원센터 2015 International Journal of Hybrid Information Techno Vol.8 No.4
In present research, the image feature based on adaptive wavelet has been widely used in the content-based image retrieval field. However, there is a common problem in these methods, which is to describe different query images with the same wavelet basis. In order to improve the adaptability of the image retrieval technology, we design different image basis for different query images, to achieve characterizing the feature-changing of different image categories with the adjustable distance measure. We also use the approximate Taylor expansion to reduce the seeking time of the characterization image and the characterization derivative image. As the experimental results have shown that, the new image retrieval technology with high adaptability can improve the retrieval performance greatly.
CloudeMR : A Cloud Based Electronic Medical Record System
보안공학연구지원센터(IJHIT) 보안공학연구지원센터 2015 International Journal of Hybrid Information Techno Vol.8 No.4
The utilization of modern information technology in the delivery of healthcare is to enhance the availability and reliability of improved healthcare services to patients at a reduced cost. The alternative in this context is to outsource the computing storage resources with the help of cloud infrastructure. The drastic reduction in the cost of healthcare services, utilization of resources, maintainability and the adoption of new technologies are some of the benefits that healthcare centers in rural areas can get from cloud-based medical information system. Also, new prospects such as easy and ever-present access to medical records and the chances to make use of services of physicians that are not readily available in the rural areas are some of the opportunities offered by a cloud-based medical information system. This paper proposes and implements a cloud-based electronic medical record (CloudeMR) system to improve the delivery of healthcare system in the rural communities of Nigeria.
보안공학연구지원센터(IJHIT) 보안공학연구지원센터 2015 International Journal of Hybrid Information Techno Vol.8 No.4
In this study, we used three popular data mining techniques (decision trees, artificial neural networks and support vector machine) to analyze the risk factors of medical expense of patients with hepatitis A in Guangdong Province in 2008. We compared the three methods to find out an effective method to predict medical expense and extract main influence factors of the medical expense. The results showed that support vector machine is the most accurate predictor.
Design of Hybrid NC Control System for Automatic Line
보안공학연구지원센터(IJHIT) 보안공학연구지원센터 2015 International Journal of Hybrid Information Techno Vol.8 No.4
This paper presents a Hybrid NC Control System for Automatic line based on Cyber-Physical-System (CPS) technology. Firstly, this paper describes the overall system hierarchical structure, which uses a variety of techniques, such as sensors, smart computing, and heterogeneous network integration. In order to improve the practical value, we study and solve some technical problems, such as heterogeneous systems integration, data storage, and real-time simulation. Finally, the prototype system is developed, which has been applied in a large State-owned enterprise in Wuxi, China.
Implementation of AADL Interpreter Based on K
보안공학연구지원센터(IJHIT) 보안공학연구지원센터 2015 International Journal of Hybrid Information Techno Vol.8 No.4
By using model-driven architecture (MDA), most of errors can be discovered and solved at the early stage of system design. AADL lacks formal semantics which are essential for real-time embedded systems with high safety requirements. In this paper, we design and implementation the AADL Interpreter based on K semantics framework, and this lays a solid foundation for formal analysis and verification of AADL model.
Spectral-based Shadow Detection for Single Image
보안공학연구지원센터(IJHIT) 보안공학연구지원센터 2015 International Journal of Hybrid Information Techno Vol.8 No.4
Shadow detection for single image is difficult but has wide applications. This paper proposes a novel and fast shadow detection method based on the Tricolor Attenuation Model [1]. In this study, we analyze the spectral property of outdoor light sources to estimate the parameters of TAM. Then our shadow detection method is proposed by integrate the TAM feature and intensity information. Our method can extract shadows for a single and uncalibrated image without any prior knowledge, even for complex scenes. Experimental results show the effectiveness of the proposed method.
보안공학연구지원센터(IJHIT) 보안공학연구지원센터 2015 International Journal of Hybrid Information Techno Vol.8 No.4
In order to improve the problem of premature convergence and computational efficiency of traditional differential evolution algorithm in solving high-dimensional problems, an improved differential evolution (HMSDE) algorithm based on combing elite synergy strategy, multi-population strategy and dynamic adaptive strategy is proposed in this paper. In the proposed HMSDE algorithm, the population is dynamically divided into multi-populations in order to keep the diversity of the population, elite synergy strategy is used to achieve information exchange among different sub-populations, and dynamic adaptive strategy is used to dynamically control the parameter values of scaling factor and crossover factor in order to improve the stability and robustness of the HMSDE algorithm. In order to test the performance of the HMSDE algorithm, a set of 10 benchmark functions are selected in here. The results show that the HMSDE algorithm takes on remarkable optimized ability, faster convergence speed and higher search accuracy. And the HMSDE algorithm can avoid the premature convergence and outperforms several state-of-the-art performances.
보안공학연구지원센터(IJHIT) 보안공학연구지원센터 2015 International Journal of Hybrid Information Techno Vol.8 No.4
Energy efficient clustering is well known optimization problem which has been studied widely to extend lifetime of wireless sensor networks (WSNs). Grid computing, enable different entities to share computational, memory, and data resources using a flexible and secure framework. These resources enable users to run computational jobs that exceed the capabilities of available sensor at any single location. The algorithm presented here is to create a virtual cluster within established clusters in wireless sensor network to share individual sensor resources, which permits the wireless sensor network to gain extra cluster resources to run resource consuming applications with private resource control policies. According to the power issue and the unpredictable wireless network characteristics, it is possible that applications running on the sensor nodes might fail due to sensor energy termination, hence, using Cuckoo Search Optimization (CSO) algorithm is necessary as inspired nature technique to improve the availability of sensor nodes by electing the optimum sensor node from each cluster according to precise constrains applied by network specifications. The motivation for this virtual cluster is to create a virtual cluster environment with heterogeneous resources from clusters with homogeneous nodes when a critical event take place and need a service might requires several sensors resources which make it necessary to arrange these resources to achieve the required service.
보안공학연구지원센터(IJHIT) 보안공학연구지원센터 2015 International Journal of Hybrid Information Techno Vol.8 No.4
In this paper, we applied Sumudu decomposition method coupled with the Taylors series to solve linear and non-linear Advection problems. It is observed that the proposed method is highly suitable for such problems and overcomes some of the basic deficiencies of traditional decomposition method. Several examples are given to re-confirm the efficiency of the suggested algorithm.
The KNN based Uyghur Text Classification and its Performance Analysis
보안공학연구지원센터(IJHIT) 보안공학연구지원센터 2015 International Journal of Hybrid Information Techno Vol.8 No.3
This paper takes the automatic classification of the large-scale Uyghur text collected from the network as research background, designed the functional block structure of the Uyghur text classification system, and chose the KNN algorithm as the classification engine, and programmed the classification system using C sharp. In the preprocessing part, combining with the Uyghur language’s lexical characteristics, we introduced the stem extraction method into the procedure, and then have greatly reduced the whole feature dimensions. the classification experimental results on the basis of large-scale text corpus includes more than 3000 documents which are belongs to different 10 categories are given, and the results of the classification experiments for the different number of features selected by using x2 statistical method are also given. The results show that only 3% to 5% of the whole high dimensional features are crucial to higher classification accuracy, so it is possible how to determine what those best features are or further reducing the feature space dimensions which are the interesting issues to be further continued.