• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.8
• /
• pp.96-105
• /
• 1998

The aim of this paper is to propose the method of WDHMM(Weighted DHMM), using the MLP-VQ for the improvement of speaker-independent connect-digit recognition system. MLP neural-network output distribution shows a probability distribution that presents the degree of similarity between each pattern by the non-linear mapping among the input patterns and learning patterns. MLP-VQ is proposed in this paper. It generates codewords by using the output node index which can reach the highest level within MLP neural-network output distribution. Different from the old VQ, the true characteristics of this new MLP-VQ lie in that the degree of similarity between present input patterns and each learned class pattern could be reflected for the recognition model. WDHMM is also proposed. It can use the MLP neural-network output distribution as the way of weighing the symbol generation probability of DHMMs. This newly-suggested method could shorten the time of HMM parameter estimation and recognition. The reason is that it is not necessary to regard symbol generation probability as multi-dimensional normal distribution, as opposed to the old SCHMM. This could also improve the recognition ability by 14.7% higher than DHMM, owing to the increase of small caculation amount. Because it can reflect phone class relations to the recognition model. The result of my research shows that speaker-independent connected-digit recognition, using MLP-VQ and WDHMM, is 84.22%.

• Journal of Internet Computing and Services
• /
• v.18 no.1
• /
• pp.65-75
• /
• 2017

The Detection Model is the model to find the result of a certain purpose using artificial intelligent, data mining, intelligent algorithms In Cyber Security, it usually uses to detect intrusion, malwares, cyber incident, and attacks etc. There are an amount of unlabeled data that are collected in a real environment such as security data. Since the most of data are not defined the class labels, it is difficult to know type of data. Therefore, the label determination process is required to detect and analysis with accuracy. In this paper, we proposed a KDFL(K-means and D-S Fusion based Labeling) method using D-S inference and k-means(unsupervised) algorithms to decide label of data records by fusion, and a detection model architecture using a proposed labeling method. A proposed method has shown better performance on detection rate, accuracy, F1-measure index than other methods. In addition, since it has shown the improved results in error rate, we have verified good performance of our proposed method.

• 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 Broadcast Engineering
• /
• v.25 no.1
• /
• pp.1-12
• /
• 2020

In the medical field, numerical imbalance of data due to differences in disease prevalence is a common problem. It reduces the performance of a artificial intelligence network, leading to difficulties in learning a network with good performance. Recently, generative adversarial network (GAN) technology has been introduced as a way to address this problem, and its ability has been demonstrated by successful applications in various fields. However, it is still difficult to achieve good results in solving problems with performance degraded by numerical imbalances because the image resolution of the previous studies is not yet good enough and the structure in the image is modeled locally. In this paper, we propose a multi-scale conditional generative adversarial network based on attention mechanism, which can produce high resolution images to solve the numerical imbalance problem of chest X-ray image data. The network was able to produce images for various diseases by controlling condition variables with only one network. It's efficient and effective in that the network don't need to be learned independently for all disease classes and solves the problem of long distance dependency in image generation with self-attention mechanism.

• Investigative Magnetic Resonance Imaging
• /
• v.6 no.2
• /
• pp.137-146
• /
• 2002

Purpose : This paper introduces an improved classification approach which adopts a deterministic relaxation method and an agglomerative clustering technique for the classification of MRI using neural network. The proposed approach can solve the problems of convergency to local optima and computational burden caused by a large number of input patterns when a neural network is used for image classification. Materials and methods : Application of Hopfield neural network has been solving various optimization problems. However, major problem of mapping an image classification problem into a neural network is that network is opt to converge to local optima and its convergency toward the global solution with a standard stochastic relaxation spends much time. Therefore, to avoid local solutions and to achieve fast convergency toward a global optimization, we adopt MFA to a Hopfield network during the classification. MFA replaces the stochastic nature of simulated annealing method with a set of deterministic update rules that act on the average value of the variable. By minimizing averages, it is possible to converge to an equilibrium state considerably faster than standard simulated annealing method. Moreover, the proposed agglomerative clustering algorithm which determines the underlying clusters of the image provides initial input values of Hopfield neural network. Results : The proposed approach which uses agglomerative clustering and deterministic relaxation approach resolves the problem of local optimization and achieves fast convergency toward a global optimization when a neural network is used for MRI classification. Conclusion : In this paper, we introduce a new paradigm to classify MRI using clustering analysis and deterministic relaxation for neural network to improve the classification results.

• The KIPS Transactions:PartD
• /
• v.13D no.4 s.107
• /
• pp.549-556
• /
• 2006

In this paper, we propose a system for generating skeleton programs for directly transforming an XML document to another document, whose structure is defined in the target DTD with GUI environment. With the generated code, the users can easily update or insert their own codes into the program so that they can convert the document as the way that they want and can be connected with other classes or library files. Since most of the currently available code generation systems or methods for transforming XML documents use XSLT or XQuery, it is very difficult or impossible for users to manipulate the source code for further updates or refinements. As the generated code in this paper reveals the code along the XPaths of the target DTD, the result code is quite readable. The code generating procedure is simple; once the user maps the related elements represented as trees in the GUI interface, the source document is transformed into the target document and its corresponding Java source program is generated, where DTD is given or extracted from XML documents automatically by parsing it. The mapping is classified 1:1, 1:N, and N:1, according to the structure and semantics of elements of the DTD. The functions for changing the structure of elements designated by the user are amalgamated into the metadata interface. A real world example of transforming articles written in XML file into a bibliographical XML document is shown with the transformed result and its code.

• The KIPS Transactions:PartD
• /
• v.9D no.6
• /
• pp.1105-1112
• /
• 2002

Nowadays the information exchange based on XML such as B2B electronic commerce is spreading. Therefore a systematic and stable management mechanism for storing the exchanged information is needed. For this goal there are many research activities for concerning the connection between XML application and relational databases. But because XML data has hierarchical structure and relational databases can store only flat-structured data, we need to make a conversion rule which changes the hierarchical architecture to a 2-dimensional format. Accordingly the modeling methodology for storing such structured information in relational databases is needed. In order to build good quality application systems, modeling is an important first step. In 1997, the OMG adopted the UML as its standard modeling language. Since industry has warmly embraced UML, its popularity should become more important in the future. So a design methodology based on UML is needed to develop efficient XML applications. In this paper, we propose a unified design methodology for XML applications based on relational database using UML. To reach these goals, first we introduce a XML modeling methodology to design W3C XML schema using UML and second we propose data modeling methodology for relational database schema to store XML data efficiently in relational databases.

• The KIPS Transactions:PartD
• /
• v.10D no.1
• /
• pp.85-100
• /
• 2003

Today's computing system has expanded its application to business trade and distributed work transactions using the Internet. As the demand for more flexible, adaptable, extensible, and robust web-based enterprise, these application development has been gradually expanded based on reusable, independent, and portable components. Component Based Development (CBD) works by developing and evolving software from selected reusable software components and then assembling them within appropriate software architecture. However, it requires an increase in cost to build new components as well as the necessary effort to develop of the business requirement these components. Standardized component models are required as well from the perspective of systems in order to support rapid and exact component information transmission on the web. In this paper, we describe the e-Business Component Development with agent for rapid application development on the web that correspond to the demands of users in the business domain. We design and implement the specifications of e-business components by combining these demands. In order to improve the agent register and retrieval, we propose the intelligent search and register agents, which can conduct more precise searching and specializing for components. The system enables the locating of user's frequently used components through an agent involving register and retrieval, as well as rapid procedures for registers The e-BCOS (e-Business Component System) is the agent system for the user to register distributed components and to search for components Information. The e-BCOS increases reusability through the e-business component development of distributed components in the business domain. For the share and delivery, specification with XML is acceptable to user's variable order e-BCOS Includes the effective investment, timeliness, reliability, efficiency, and maintenance effort by with agent.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.4
• /
• pp.354-359
• /
• 2013

In this paper, we suggested the method for implementation of unsupervised nonlinear classification using Binary Harmony Search (BHS) algorithm, which is known as a optimization algorithm. Various algorithms have been suggested for classification of feature vectors from the process of machine learning for pattern recognition or EEG signal analysis processing. Supervised learning based support vector machine or fuzzy c-mean (FCM) based on unsupervised learning have been used for classification in the field. However, conventional methods were hard to apply nonlinear dataset classification or required prior information for supervised learning. We solved this problems with proposed classification method using heuristic approach which took the minimal Euclidean distance between vectors, then we assumed them as same class and the others were another class. For the comparison, we used FCM, self-organizing map (SOM) based on artificial neural network (ANN). KEEL machine learning datset was used for simulation. We concluded that proposed method was superior than other algorithms.

• Journal of Digital Convergence
• /
• v.18 no.10
• /
• pp.225-232
• /
• 2020

The underlaying communication scheme in 5G cellular network is a very promising resource sharing scheme, and it is an effective scheme for improving service performance of 5G and reducing communication load between a cellular link and a device to device (D2D) link. This paper proposes the algorithm to minimize the resource interference that occurs when performing 5G-based multi-class service on gNB(gNodeB) and the cooperative priority-based resource allocation scheduling scheme (CPRAS) to maximize 5G communication service according to the analyzed control conditions of interference. The proposed CPRAS optimizes communication resources for each device, and it optimizes resource allocation according to the service request required for 5G communication and the current state of the network. In addition, the proposed scheme provides a function to guarantee giga-class service by minimizing resource interference between a cellular link and a D2D link in gNB. The simulation results show that the proposed scheme is better system performance than the Pure cellular and Force cellular schemes. In particular, the higher the priority and the higher the cooperative relationship between UE(User Equipment), the proposed scheme shows the more effective control of the resource interference.