• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.1
• /
• pp.83-90
• /
• 2010

Cancelable biometrics is a robust and secure biometric recognition method using revocable biometric template in order to prevent possible compromisation of the original biometric data. In this paper, we present a new cancelable bits extraction method for the facial data. We use our previous cancelable feature template for the bits extraction. The adopted cancelable template is generated from two different original face feature vectors extracted from two different appearance-based approaches. Each element of feature vectors is re-ordered, and the scrambled features are added. With the added feature, biometric bits string is extracted using helper data based method. In this technique, helper data is generated using statistical property of the added feature vector, which can be easily replaced with straightforward revocation. Because, the helper data only utilizes partial information of the added feature, our proposed method is a more secure method than our previous one. The proposed method utilizes the helper data to reduce feature variance within the same individual and increase the distinctiveness of bit strings of different individuals for good recognition performance. For a security evaluation of our proposed method, a scenario in which the system is compromised by an adversary is also considered. In our experiments, we analyze the proposed method with respect to performance and security using the extended YALEB face database

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.11
• /
• pp.183-190
• /
• 2012

Conventional physical activity monitoring systems, which use accelerometers, global positioning system (GPS), heartbeats, or body temperature information, showed limited performances due to their own restrictions on measurement environment and measurable activity types. To overcome these limitations, we developed a portable exercise analysis system that can analyze aerobic exercises as well as isotonic exercises. For bioelectric signal acquisition during exercise, waist belt with two body contact electrodes was used. For exercise analysis, the measured signals were firstly divided into two signal groups with different frequency ranges which can represent respiration related signal and muscular motion related signal, respectively. After then, power values, differential of power values, and median frequency values were selected for feature values. Selected features were used as inputs of support vector machine (SVM) to classify the exercise types. For verification of statistical significance, ANOVA and multiple comparison test were performed. The experimental results showed 100% accuracy for classification of aerobic exercise and isotonic resistance exercise. Also, classification of aerobic exercise, isotonic resistance exercise, and hybrid types of exercise revealed 92.7% of accuracy.

• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.722-729
• /
• 2010

Prediction problems are widely used in medical domains. For example, computer aided diagnosis or prognosis is a key component in a CDSS (Clinical Decision Support System). SVMs with nonlinear kernels like RBF kernels, have shown superior accuracy in prediction problems. However, they are not preferred by physicians for medical prediction problems because nonlinear SVMs are difficult to visualize, thus it is hard to provide intuitive interpretation of prediction results to physicians. Nomogram was proposed to visualize SVM classification models. However, it cannot visualize nonlinear SVM models. Localized Radial Basis Function (LRBF) was proposed which shows comparable accuracy as the RBF kernel while the LRBF kernel is easier to interpret since it can be linearly decomposed. This paper presents a new tool named VRIFA, which integrates the nomogram and LRBF kernel to provide users with an interactive visualization of nonlinear SVM models, VRIFA visualizes the internal structure of nonlinear SVM models showing the effect of each feature, the magnitude of the effect, and the change at the prediction output. VRIFA also performs nomogram-based feature selection while training a model in order to remove noise or redundant features and improve the prediction accuracy. The area under the ROC curve (AUC) can be used to evaluate the prediction result when the data set is highly imbalanced. The tool can be used by biomedical researchers for computer-aided diagnosis and risk factor analysis for diseases.

• Journal of KIISE
• /
• v.43 no.10
• /
• pp.1085-1093
• /
• 2016

Community-based Question Answering system is a system which provides answers for each question from the documents uploaded on web communities. In order to enhance the capacity of question analysis, former methods have developed specific rules suitable for a target region or have applied machine learning to partial processes. However, these methods incur an excessive cost for expanding fields or lead to cases in which system is overfitted for a specific field. This paper proposes a multiple machine learning method which automates the overall process by adapting appropriate machine learning in each procedure for efficient processing of community-based Question Answering system. This system can be divided into question analysis part and answer selection part. The question analysis part consists of the question focus extractor, which analyzes the focused phrases in questions and uses conditional random fields, and the question type classifier, which classifies topics of questions and uses support vector machine. In the answer selection part, the we trains weights that are used by the similarity estimation models through an artificial neural network. Also these are a number of cases in which the results of morphological analysis are not reliable for the data uploaded on web communities. Therefore, we suggest a method that minimizes the impact of morphological analysis by using character features in the stage of question analysis. The proposed system outperforms the former system by showing a Mean Average Precision criteria of 0.765 and R-Precision criteria of 0.872.

• Molecules and Cells
• /
• v.41 no.9
• /
• pp.868-880
• /
• 2018

Pancreatic cancer (PC) is one of the most aggressive cancers presenting with high rates of invasion and metastasis, and unfavorable prognoses. The current study aims to investigate whether EZH2/miR-139-5p axis affects epithelial-mesenchymal transition (EMT) and lymph node metastasis (LNM) in PC, and the mechanism how EZH2 regulates miR-139-5p. Human PC and adjacent normal tissues were collected to determine expression of EZH2 and miR-139-5p, and their relationship with clinicopathological features of PC. Human PC cell line was selected, and treated with miR-139-5p mimics/inhibitors, EZH2 vector or shEZH2 in order to validate the regulation of EZH2-mediated miR-139-5p in PC cells. Dual-luciferase report gene assay and chromatin immunoprecipitation assay were employed to identify the relationship between miR-139-5p and EZH2. RT-qPCR and Western blot analysis were conducted to determine the expression of miR-139-5p, EZH2 and EMT-related markers and ZEB1/2. Tumor formation ability and in vitro cell activity were also analyzed. Highly-expressed EZH2 and poorly-expressed miR-139-5p were detected in PC tissues, and miR-139-5p and EZH2 expressions were associated with patients at Stage III/IV, with LNM and highly-differentiated tumors. EZH2 suppressed the expression of miR-139-5p through up-regulating Histone 3 Lysine 27 Trimethylation (H3K27me3). EMT, cell proliferation, migration and invasion were impeded, and tumor formation and LNM were reduced in PC cells transfected with miR-139-5p mimics and shEZH2. MiR-139-5p transcription is inhibited by EZH2 through up-regulating H3K27me3, thereby down-regulation of EZH2 and up-regulation of miR-139-5p impede EMT and LNM in PC. In addition, the EZH2/miR-139-5p axis presents as a promising therapeutic strategy for the treatment of PC.

• Journal of KIISE:Computing Practices and Letters
• /
• v.12 no.1
• /
• pp.9-20
• /
• 2006

Web Map Service on mobile environment, provided with cost effective mobile GIS contents and user preferred POIs(Points of interests), is strongly required at this moment when mobile and portable Internet is rapidly spreaded on mobile user community as information technology and mobile HW are evolved in its speed, bandwidth and features. As the mobile and portable Internet becomes popular in mobile services, LBS(Location Based Service) is positioned on a mobile client as one of the best information infra services. Recently mobile GIS (Geographic Information System) comes in service to support LBS, but it is constrained and limited on its system configuration and its presentation methodology of a map, and also it depends on its run time environment. In this paper, we made an effort to design and implement a GIS computing platform with server based thin client for mobile WMS(Web Map Service). For its cost effective Platform which could be easily building up POIs and GIS contents, we're not using commercial GIS solution but NGII's (National Geographic Information Institute's) DXF numerical map, and representing the maps, GIS contents and POIs by SVG(Scalable Vector Graphics) recommended by OGC(OpenGis Consortium). We're also adapting de facto standard of XML web service technology such as WSDL, SOAP to provide real time mobile GIS service on PDA as well as mobile terminal by applying a GPS receiver for a user's location information on mobile environment.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.2 s.302
• /
• pp.11-18
• /
• 2005

To detect vehicles in image, first the image is transformed with the steerable pyramid which has independent directions and levels. Feature vectors are the collection of filter responses at different scales of a steerable image pyramid. For the detection of vehicles in image, feature vectors in feature points of the vehicle image is used. First the feature points are selected with the grid points in vehicle image that are evenly spaced, and second, the feature points are comer points which m selected by human, and last the feature points are corner Points which are selected in grid points. Next the feature vectors of the model vehicle image we compared the patch of the test images, and if the distance of the model and the patch of the test images is lower than the predefined threshold, the input patch is decided to a vehicle. In experiment, the total 11,191 vehicle images are captured at day(10,576) and night(624) in the two local roads. And the $92.0\%$ at day and $87.3\%$ at night detection rate is achieved.

• The KIPS Transactions:PartD
• /
• v.8D no.5
• /
• pp.507-512
• /
• 2001

Feature-based similarity has become an important research issue in multimedia database systems. The features of multimedia data are useful for discriminating between multimedia objects. the performance of conventional multidimensional data structures tends to deteriorate as the number of dimensions of feature vectors increase. The $R^{*}-Tree$ is the most successful variant of the R-Tree. In this paper, we propose a SOM-based $R^{*}-Tree$ as a new indexing method for high-dimensional feature vectors. The SOM-based $R^{*}-Tree$ combines SOM and $R^{*}-Tree$ to achieve search performance more scalable to high-dimensionalties. Self-Organizingf Maps (SOMs) provide mapping from high-dimensional feature vectors onto a two-dimensional space. The map is called a topological feature map, and preserves the mutual relationships (similarity) in the feature spaces of input data, clustering mutually similar feature vectors in neighboring nodes. Each node of the topological feature map holds a codebook vector. We experimentally compare the retrieval time cost of a SOM-based $R^{*}-Tree$ with of an SOM and $R^{*}-Tree$ using color feature vectors extracted from 40,000 images. The results show that the SOM-based $R^{*}-Tree$ outperform both the SOM and $R^{*}-Tree$ due to reduction of the number of nodes to build $R^{*}-Tree$ and retrieval time cost.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.4
• /
• pp.456-462
• /
• 2008

The classification is that a new data is classified into one of given classes and is one of the most generally used data mining techniques. Memory-Based Reasoning (MBR) is a reasoning method for classification problem. MBR simply keeps many patterns which are represented by original vector form of features in memory without rules for reasoning, and uses a distance function to classify a test pattern. If training patterns grows in MBR, as well as size of memory great the calculation amount for reasoning much have. NGE, FPA, and RPA methods are well-known MBR algorithms, which are proven to show satisfactory performance, but those have serious problems for memory usage and lengthy computation. In this paper, we propose DPA (Dynamic Partition Averaging) algorithm. it chooses partition points by calculating GINI-Index in the entire pattern space, and partitions the entire pattern space dynamically. If classes that are included to a partition are unique, it generates a representative pattern from partition, unless partitions relevant partitions repeatedly by same method. The proposed method has been successfully shown to exhibit comparable performance to k-NN with a lot less number of patterns and better result than EACH system which implements the NGE theory and FPA, and RPA.

• Journal of Intelligence and Information Systems
• /
• v.15 no.2
• /
• pp.49-59
• /
• 2009

Contents-based image retrieval methods are in general more objective and effective than text-based image retrieval algorithms since they use color and texture in search and avoid annotating all images for search. SIM(Self-organizing Image browsing Map) is one of contents-based image retrieval algorithms that uses only browsable mapping results obtained by SOM(Self Organizing Map). However, SOM may have an error in selecting the right BMU in learning phase if there are similar nodes with distorted color information due to the intensity of light or objects' movements in the image. Such images may be mapped into other grouping nodes thus the search rate could be decreased by this effect. In this paper, we propose an improved SIM that uses HSV color model in extracting image features with color quantization. In order to avoid unexpected learning error mentioned above, our SOM consists of two layers. In learning phase, SOM layer 1 has the color feature vectors as input. After learning SOM Layer 1, the connection weights of this layer become the input of SOM Layer 2 and re-learning occurs. With this multi-layered SOM learning, we can avoid mapping errors among similar nodes of different color information. In search, we put the query image vector into SOM layer 2 and select nodes of SOM layer 1 that connects with chosen BMU of SOM layer 2. In experiment, we verified that the proposed SIM was better than the original SIM and avoid mapping error effectively.