• Architectural research
• /
• v.12 no.2
• /
• pp.15-22
• /
• 2010

Our prediction model is based on the development of "Semantic Location Model." It embodies geometrical and topological information which can increase the efficiency in prediction and make it easy to manipulate the prediction model. Data mining is being implemented to extract the inhabitant's location patterns generated day by day. As a result, the self-learning system will be able to semantically predict the inhabitant's location in advance. This context-aware system brings about the key component of the ubiquitous computing environment. First, we explain the semantic location model and data mining methods. Then the location prediction model for the ubiquitous computing system is described in details. Finally, the prototype system is introduced to demonstrate and evaluate our prediction model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.538-561
• /
• 2020

Recommender Systems (RecSys) have a major role in e-commerce for recommending products, which they may like for every user and thus improve their business aspects. Although many types of RecSyss are there in the research field, the state of the art RecSys has focused on finding the user similarity based on sequence (e.g. purchase history, movie-watching history) analyzing and prediction techniques like Recurrent Neural Network in Deep learning. That is RecSys has considered as a sequence prediction problem. However, evaluation of similarities among the customers is challenging while considering temporal aspects, context and multi-component ratings of the item-records in the customer sequences. For addressing this issue, we are proposing a Deep Learning based model which learns customer similarity directly from the sequence to sequence similarity as well as item to item similarity by considering all features of the item, contexts, and rating components using Dynamic Temporal Warping(DTW) distance measure for dynamic temporal matching and 2D-GRU (Two Dimensional-Gated Recurrent Unit) architecture. This will overcome the limitation of non-linearity in the time dimension while measuring the similarity, and the find patterns more accurately and speedily from temporal and spatial contexts. Experiment on the real world movie data set LDOS-CoMoDa demonstrates the efficacy and promising utility of the proposed personalized RecSys architecture.

• Journal of Information Technology Applications and Management
• /
• v.21 no.4
• /
• pp.203-223
• /
• 2014

This study proposes a novel context-aware recommender system, which is designed to recommend the items according to the customer's responses to the previously recommended item. In specific, our proposed system predicts the user's emotional state from his or her responses (such as facial expressions and movements) to the previous recommended item, and then it recommends the items that are similar to the previous one when his or her emotional state is estimated as positive. If the customer's emotional state on the previously recommended item is regarded as negative, the system recommends the items that have characteristics opposite to the previous item. Our proposed system consists of two sub modules-(1) emotion prediction module, and (2) responsive recommendation module. Emotion prediction module contains the emotion prediction model that predicts a customer's arousal level-a physiological and psychological state of being awake or reactive to stimuli-using the customer's reaction data including facial expressions and body movements, which can be measured using Microsoft's Kinect Sensor. Responsive recommendation module generates a recommendation list by using the results from the first module-emotion prediction module. If a customer shows a high level of arousal on the previously recommended item, the module recommends the items that are most similar to the previous item. Otherwise, it recommends the items that are most dissimilar to the previous one. In order to validate the performance and usefulness of the proposed recommender system, we conducted empirical validation. In total, 30 undergraduate students participated in the experiment. We used 100 trailers of Korean movies that had been released from 2009 to 2012 as the items for recommendation. For the experiment, we manually constructed Korean movie trailer DB which contains the fields such as release date, genre, director, writer, and actors. In order to check if the recommendation using customers' responses outperforms the recommendation using their demographic information, we compared them. The performance of the recommendation was measured using two metrics-satisfaction and arousal levels. Experimental results showed that the recommendation using customers' responses (i.e. our proposed system) outperformed the recommendation using their demographic information with statistical significance.

• The Journal of the Acoustical Society of Korea
• /
• v.17 no.4E
• /
• pp.11-16
• /
• 1998

For large vocabulary speech recognition using HMMs, context-dependent subword units have been often employed. However, when context-dependent phone models are used, they result in a system which has too may parameters to train. The problem of too many parameters and too little training data is absolutely crucial in the design of a statistical speech recognizer. Furthermore, when building large vocabulary speech recognition systems, unseen triphone problem is unavoidable. In this paper, we propose the modified phonetic decision tree algorithm for the automatic prediction of unseen triphones which has advantages solving these problems through following two experiments in Japanese contexts. The baseline experimental results show that the modified tree based clustering algorithm is effective for clustering and reducing the number of states without any degradation in performance. The task experimental results show that our proposed algorithm also has the advantage of providing a automatic prediction of unseen triphones.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.425-428
• /
• 2005

This paper is made up Advanced Image Coding(AIC) that combines algorithms from next generation image coding standard, H.264/MPEG-4 Part 10 advanced video coding(AVC) and still image compression standard, JPEG(Joint Photographic Experts Group). AIC combines intra frame block prediction from H.264 with a JPEG style discrete cosine transform and quantization, followed by Context-based Adaptive Binary Arithmetic Coding(CABAC) as used in H.264. In this paper, we analyzes the efficiency of the AIC algorithm and JPEG and JPEG-2000, and it presents of result.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.12
• /
• pp.2647-2654
• /
• 2009

In this paper, we propose H.264 Encoder integrating Intra Prediction, Deblocking Filter, Context-Based Adaptive Variable Length Coding, and Motion Estimation encoder module. This designed module can be operated in 440 cycle for one-macroblock. To verify the Encoder architecture, we developed the reference C from JM 9.4 and verified the our developed hardware using test vector generated by reference C. The designed circuit can be operated in 166MHz clock system, and has 1800K gate counts using Charterd 0.18 um process including SRAM memory. Manufactured chip has the size of $6{\times}6mm$ and 208 pins package.

• The Journal of the Korea Contents Association
• /
• v.9 no.6
• /
• pp.9-16
• /
• 2009

According to the construction of infrastructure for the water resource management services, the importance of the eco-friendly reservoir tank management is being spotlighted. In this paper, we proposed the eco-friendly reservoir tank management using prediction for improving the water quality and on-line managing efforts of reservoir tanks. The proposed method defined the context and environment of the reservoir tank and predicted the profited service according to the pump motion, the solar battery, the chemicals, the water level, the telephone line, and the modem using collaborative filtering. To evaluate the performance of the eco-friendly reservoir tank management system using prediction, we conducted sample T-tests so as to verify usefulness. This evaluation found that the difference of satisfaction by service was statistically meaningful, and showed high satisfaction. Accordingly, the satisfaction and the quality of services will be improved the efficient prediction by supporting the context information as well as the environment information.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.791-792
• /
• 2008

We present a new algorithm for VLC table prediction in H.264 context-based adaptive variable length coding (CAVLC). Using both the correlation of coding modes and the statistics of the mode distribution in intra and inter frames, we can predict an appropriate VLC table of the given $4{\times}4$ block. Experimental results demonstrate that the proposed algorithm reduces the bit rate about 0.97% on average, compared to the H.264/AVC standard.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.11
• /
• pp.5459-5473
• /
• 2017

Recently, a tracking algorithm called the spatial-temporal context model has been proposed to locate a target by using the contextual information around the target. This model has achieved excellent results when the target undergoes slight occlusion and appearance changes. However, the target location in the current frame is based on the location in the previous frame, which will lead to failure in the presence of fast motion because of the lack of a prediction mechanism. In addition, the spatial context model is updated frame by frame, which will undoubtedly result in drift once the target is occluded continuously. This paper proposes two improvements to solve the above two problems: First, four possible positions of the target in the current frame are predicted based on the displacement between the previous two frames, and then, we calculate four confidence maps at these four positions; the target position is located at the position that corresponds to the maximum value. Second, we propose a target reliability criterion and design an adaptive threshold to regulate the updating speed of the model. Specifically, we stop updating the model when the reliability is lower than the threshold. Experimental results show that the proposed algorithm achieves better tracking results than traditional STC and other algorithms.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.2
• /
• pp.185-190
• /
• 2006

Most systems in ubiquitous computing analyze context information of users which have similar propensity with demographics methods and collaborative filtering to provide personalized recommendation services. The systems have mostly used static context information such as sex, age, job, and purchase history. However the systems have limitation to analyze users' propensity accurately and to provide personalized recommendation services in real-time, because they have difficulty in considering users situation as moving path. In this paper we use users' moving path of dynamic context to consider users situation. For the prediction accuracy we complete with a path completion algorithm to moving path which is inputted to RSOM. We train the moving path to be completed by RSOM, analyze users' moving pattern and predict a future moving path. Then we recommend the nearest product on the prediction path with users' high preference in real-time. As the experimental result, MAE is lower than 0.5 averagely and we confirmed our method can predict users moving path correctly.