• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.3
• /
• pp.357-362
• /
• 2004

Language models are essential in predicting the next word in a spoken sentence, thereby enhancing the speech recognition accuracy, among other things. However, spoken language domains are too numerous, and therefore developers suffer from the lack of corpora with sufficient sizes. This paper proposes a method of combining two n-gram language models, one constructed from a very small corpus of the right domain of interest, the other constructed from a large but less adequate corpus, resulting in a significantly enhanced language model. This method is based on the observation that a small corpus from the right domain has high quality n-grams but has serious sparseness problem, while a large corpus from a different domain has more n-gram statistics but incorrectly biased. With our approach, two n-gram statistics are combined by extending the idea of Katz's backoff and therefore is called a dual-source backoff. We ran experiments with 3-gram language models constructed from newspaper corpora of several million to tens of million words together with models from smaller broadcast news corpora. The target domain was broadcast news. We obtained significant improvement (30%) by incorporating a small corpus around one thirtieth size of the newspaper corpus.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.5
• /
• pp.522-538
• /
• 2001

This paper presents a cal center which is a subsystem of a web-based real time monitoring system of intensive care units. Based on Computer-Telephony Integration (CTI) technology, the call center attempts to efficiently and automatically send messages to patients\` families, doctors, and other staffs in hospital via communication media suitable to the occasion. The problem of determining appropriate media can be very complicated by the urgency of a message, calling time, and communication media available to the target person. We use the Dempster-Shafer theory, one of the uncertainty handling methods, to determine the most suitable communication media that will transmit a message rapidly and safely. In addition, we use agent technology to perform the calling process without requiring the intervention of the user of the call center. this call center enables message transfer through various communication media in an integrated environment, and relieves medical staff from the calling process, which in turn will make a contribution toward enhancing medical service.

• Polymer(Korea)
• /
• v.26 no.1
• /
• pp.105-112
• /
• 2002

The low actuation voltage and quick bending response of IPMC(ion-exchange polymer metal composite) are considered attractive for the construction of various types of actuators. In this study, in order to develop a new type actuators by using the IPMC platinum electrode of IPMC are fabricated by using electroless impregnation-reduction method plating. As the platinum-plating times are increased, IPMC performance was improved in terms of bending displacement and force due to the enhanced surface conductivity. In addition, we investigated the basic actuation characteristics of resonance frequency and actuator length as well as the effect of water uptake and ion mobility. Using the classical laminate theory(CLT), a modeling methodology was developed to predict the deformation, bending moment, and residual stress distribution of anisotropic IPMC thin plates. In this modeling methodology, the internal stress evolved by the unsymmetric distribution of water inside IPMC was quantitatively calculated and subsequently the bending moment and the curvature were estimated for various geometry of IPMC actuator.

• Journal of Digital Convergence
• /
• v.11 no.3
• /
• pp.165-173
• /
• 2013

The purpose of this study was to investigate the effects of customer's innovation and usefulness on the use intention of Service Robots by potential customers. Based on Davis(1989)'s Technology Acceptance Model, this study formulated three hypotheses, which were about relationships between customer's innovation, usefulness, and use intention of Service Robots. For this study, structured questionnaires were used and data were collected from the 171 people in Seoul and Cheonan. To test three hypotheses, collected data were analyzed using hierarchical regression technique. The results showed that customer's innovation has no influence on usefulness, whereas customer's innovation and usefulness have effects on use intention.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.1
• /
• pp.1-5
• /
• 2009

This paper suggests to apply mirror-reflected method based 2D emotion recognition database to 3D application. Also, it makes facial expression of fuzzy modeling using probability of emotion. Suggested facial expression function applies fuzzy theory to 3 basic movement for facial expressions. This method applies 3D application to feature vector for emotion recognition from 2D application using mirror-reflected multi-image. Thus, we can have model based on fuzzy nonlinear facial expression of a 2D model for a real model. We use average values about probability of 6 basic expressions such as happy, sad, disgust, angry, surprise and fear. Furthermore, dynimic facial expressions are made via fuzzy modelling. This paper compares and analyzes feature vectors of real model with 3D human-like avatar.

• Journal of Digital Contents Society
• /
• v.2 no.1
• /
• pp.41-50
• /
• 2001

According to the rapid changing of modern Society, the portion and influence of the industries which are related to IT(Information Technology) have being Increased. Therefore, we need to recognize and learn to the new technologies such as ITS (Intelligent Transport Systems) because they are very closely related to our living environments. Unfortunately, people who are not expertized to the ITS have had hard time to understand these systems. In this paper, we introduce a multimedia courseware which requires only simple operations of mouse and keyboard for education of ITS. This courseware includes not only the areas of services for user but also scopes and components, and applications of ITS, which make possible to understand what the ITS are When we apply this courseware to the people who we not specialized to ITS, they can understand the ITS more easily.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.9 no.5
• /
• pp.555-565
• /
• 1999

The optimal identification algorithm of fuzzy systems is presented for rule-based fuzzy modeling of nonlinear complex systems. Nonlinear systems are expressed using the identification of structure such as input variables and fuzzy input subspaces, and parameters of a fuzzy model. In this paper, the rule-based fuzzy modeling implements system structure and parameter identification using the fuzzy inference methods and hybrid structure combined with two types of optimization theories for nonlinear systems. Two types of inference methods of a fuzzy model are the simplified inference and linear inference. The proposed hybrid optimal identification algorithm is carried out using both a genetic algorithm and the improved complex method. Here, a genetic algorithm is utilized for determining initial parameters of membership function of premise fuzzy rules, and the improved complex method which is a powerful auto-tuning algorithm is carried out to obtain fine parameters of membership function. Accordingly, in order to optimize fuzzy model, we use the optimal algorithm with a hybrid type for the identification of premise parameters and standard least square method for the identification of consequence parameters of a fuzzy model. Also, an aggregate performance index with weighting factor is proposed to achieve a balance between performance results of fuzzy model produced for the training and testing data. Two numerical examples are used to evaluate the performance of the proposed model.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.4
• /
• pp.501-506
• /
• 2008

Statistical POS tagging is prone to error, because of the inherent limitations of statistical data, especially single source of data. Therefore it is widely agreed that the possibility of further enhancement lies in exploiting various knowledge sources. However these data sources are bound to be inconsistent to each other. This paper shows the possibility of using maximum entropy model to Korean language POS tagging. We use as the knowledge sources n-gram data and trigger pair data. We show how perplexity measure varies when two knowledge sources are combined using maximum entropy method. The experiment used a trigram model which produced 94.9% accuracy using Hidden Markov Model, and showed increase to 95.6% when combined with trigger pair data using Maximum Entropy method. This clearly shows possibility of further enhancement when various knowledge sources are developed and combined using ME method.

• Journal of Intelligence and Information Systems
• /
• v.16 no.2
• /
• pp.95-108
• /
• 2010

In this paper, we present a hybrid neural network model for dynamic hand gesture recognition. The model consists of two modules, feature extraction module and pattern classification module. We first propose a modified CNN(convolutional Neural Network) a pattern recognition model for the feature extraction module. Then we introduce a weighted fuzzy min-max(WFMM) neural network for the pattern classification module. The data representation proposed in this research is a spatiotemporal template which is based on the motion information of the target object. To minimize the influence caused by the spatial and temporal variation of the feature points, we extend the receptive field of the CNN model to a three-dimensional structure. We discuss the learning capability of the WFMM neural networks in which the weight concept is added to represent the frequency factor in training pattern set. The model can overcome the performance degradation which may be caused by the hyperbox contraction process of conventional FMM neural networks. From the experimental results of human action recognition and dynamic hand gesture recognition for remote-control electric home appliances, the validity of the proposed models is discussed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.6
• /
• pp.431-437
• /
• 2017

In this study, based on the RPS algorithm, the application results to an electrically controlled suspension system using previewed road information are presented. Reducing the excessive vibration induced by a disturbance transmitted to the system and secure its stability is a major issue. In particular, in the automotive industry, the demand is constantly being raised. A typical external disturbance causing vibration and instability of a vehicle is an irregular roadway surface that contacts a running vehicle tire. Therefore, obtaining such profile information is an important process. The RPS algorithm using a multi sensor system was constructed and implemented in a real car. Through experimental work using the RPS system included non-contact type optical sensors, it could robustly reconstruct the road input profiles from the intermixed data onto the vehicle's dynamic motion while traveling at an uneven roadway surface. A controller with a preview control was designed in the framework of a semi-active suspension system based on the 7 degrees of freedom full vehicle model. The control performance of the system was evaluated through simulations and the results were compared with the passive vehicle condition. These results highlight the feasibility of the presented control frame.