• Journal of the Korea Society of Computer and Information
• /
• v.15 no.2
• /
• pp.65-74
• /
• 2010

We propose a system that automatically recognizes the tense or relaxed condition of scrolling-shooting game subject that plays. Existing study compares the changed values of source of stimulation to the player by suggesting the source, and thus involves limitation in automatic classification. This study applies SOM of unsupervised learning for automatic classification and recognition of player's condition change. Application of SOM for automatic recognition of tense and relaxed condition is composed of two steps. First, ECG measurement and analysis, is to extract characteristic vector through HRV analysis by measuring ECG after having the player play the game. Secondly, SOM learning and recognition, is to classify and recognize the tense and relaxed conditions of player through SOM learning of the input vectors of heart beat signals that the characteristic extracted. Experiment results are divided into three groups. The first is HRV frequency change and the second the SOM learning results of heart beat signal. The third is the analysis of match rate to identify SOM learning performance. As a result of matching the LF/HF ratio of HRV frequency analysis to the distance of winner neuron of SOM based on 1.5, a match rate of 72% performance in average was shown.

• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4
• /
• pp.339-438
• /
• 2002

This paper presents a method to simulate noise propagation by a computer for outdoor environment. Sound propagated in 3 dimensional space generates reflected waves whenever it hits boundary surfaces. If a receiver is away from a sound source, it receives multiple sound waves which are reflected from various boundary surfaces in space. The algorithm being developed in this paper is based on a ray sound theory. If we get 3 dimensional geometry input as well as sound sources, we can compute sound effects all over the boundary surfaces. In this paper, we present two approaches to compute sound: the first approach, called forward tracing, traces sounds forwards from sound sources. while the second approach, called geometry based computation, computes possible propagation routes between sources and receivers. We compare two approaches and suggest the geometry based sound computation for outdoor simulation. Also this approach is very efficient in the sense we can save computational time compared to the forward sound tracing. Sound due to impulse-response is governed by physical environments. When a sound source waveform and numerically computed impulse in time is convoluted, the result generates a synthetic sound. This technique can be easily generalized to synthesize realistic stereo sounds for virtual reality, while the simulation result is visualized using VRML.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.3
• /
• pp.361-366
• /
• 2012

This paper presents speed control of an electric motorcycle using a fuzzy controller. The electric motorcycle required to meet not only fast throttle response but also stability, when it is on a cruise. However, a 1.5KW (50cc) electric motorcycles selling in the current market are difficult to cruise under the following conditions which are occupant's weight, load weight, wind resistance and road conditions (dirt roads, asphalt road). Because of these reasons, the rapid speed changing occurs in uphill and downhill road. To solve these problems, The input value for Improved fuzzy controller use the speed error and error variance. The output value for improved fuzzy controller uses Q-axis of the motor controlled variable. The D-axis of the motor output for improved fuzzy control uses D-axis controlled variable in proportional to Q-axis controlled variable. Improved fuzzy controller drives the electric motorcycle equipped with IPMSM. The control subject used in this paper is a 1.5KW electric motorcycle equipped with improved fuzzy controller that was used to control the motor speed. To control IPMSM Type of motor torque, D, Q-axis current controller was used. The Fuzzy controller using the proposed algorithm is demonstrated by experimental hardware simulator.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.2
• /
• pp.60-69
• /
• 1998

This paper proposes a speech synthesis method using Fuzzy VQ, and then study how to make choice of fuzziness value which optimizes (controls) the performance of FVQ in order to obtain the synthesized speech which is closer to the original speech. When FVQ is used to synthesize a speech, analysis stage generates membership function values which represents the degree to which an input speech pattern matches each speech patterns in codebook, and synthesis stage reproduces a synthesized speech, using membership function values which is obtained in analysis stage, fuzziness value, and fuzzy-c-means operation. By comparsion of the performance of the FVQ and VQ synthesizer with simmulation, we show that, although the FVQ codebook size is half of a VQ codebook size, the performance of FVQ is almost equal to that of VQ. This results imply that, when Fuzzy VQ is used to obtain the same performance with that of VQ in speech synthesis, we can reduce by half of memory size at a codebook storage. And then we have found that, for the optimized FVQ with maximum SQNR in synthesized speech, the fuzziness value should be small when the variance of analysis frame is relatively large, while fuzziness value should be large, when it is small. As a results of comparsion of the speeches synthesized by VQ and FVQ in their spectrogram of frequency domain, we have found that spectrum bands(formant frequency and pitch frequency) of FVQ synthesized speech are closer to the original speech than those using VQ.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.46 no.11
• /
• pp.66-76
• /
• 2009

The motion estimation in video encoding system occupies the biggest part. So, we require the motion estimator with efficient structure for real-time operation. And for motion estimator's implementation, it is desired to design hardware module of an exclusive use that perform the encoding process at high speed. This paper proposes motion estimation detection block(MED), 41 SADs(Sum of Absolute Difference) calculation block, minimum SAD calculation and motion vector generation block based on parallel processing. The parallel processing can reduce effectively the amount of the operation. The minimum SAD calculation and MED block uses the pre-computation technique for reducing switching activity of the input signal. It results in high-speed operation. The MED and 41 SADs calculation blocks are composed of adder tree which causes the problem of critical path. So, the structure of adder tree has changed the most commonly used ripple carry adder(RCA) with carry skip adder(CSA). It enables adder tree to operate at high speed. In addition, as we enabled to easily control key variables such as control signal of search range from the outside, the efficiency of hardware structure increased. Simulation and FPGA verification results show that the delay of MED block generating the critical path at the motion estimator is reduced about 19.89% than the conventional strukcture.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.3
• /
• pp.65-74
• /
• 2021

3D reconstruction means that reconstructing the 3D shape of the object in an image and a video. We proposed a progressive occupancy network architecture that can recover not only the overall shape of the object but also the local details. Unlike the original occupancy network, which uses a feature vector embedding information of the whole image, we extract and utilize the different levels of image features depending on the receptive field size. We also propose a novel network architecture that applies the image features sequentially to the decoder blocks in the decoder and improves the quality of the reconstructed 3D shape progressively. In addition, we design a novel decoder block structure that combines the different levels of image features properly and uses them for updating the input point feature. We trained our progressive occupancy network with ShapeNet. We compare its representation power with two prior methods, including prior occupancy network(ONet) and the recent work(DISN) that used different levels of image features like ours. From the perspective of evaluation metrics, our network shows better performance than ONet for all the metrics, and it achieved a little better or a compatible score with DISN. For visualization results, we found that our method successfully reconstructs the local details that ONet misses. Also, compare with DISN that fails to reconstruct the thin parts or occluded parts of the object, our progressive occupancy network successfully catches the parts. These results validate the usefulness of the proposed network architecture.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.119-137
• /
• 2022

Recent recommendation system studies apply various deep learning models to represent user and item interactions better. One of the noteworthy studies is ONCF(Outer product-based Neural Collaborative Filtering) which builds a two-dimensional interaction map via outer product and employs CNN (Convolutional Neural Networks) to learn high-order correlations from the map. However, ONCF has limitations in recommendation performance due to the problems with CNN and the absence of side information. ONCF using CNN has an inductive bias problem that causes poor performances for data with a distribution that does not appear in the training data. This paper proposes to employ a Vision Transformer (ViT) instead of the vanilla CNN used in ONCF. The reason is that ViT showed better results than state-of-the-art CNN in many image classification cases. In addition, we propose a new architecture to reflect side information that ONCF did not consider. Unlike previous studies that reflect side information in a neural network using simple input combination methods, this study uses an independent auxiliary classifier to reflect side information more effectively in the recommender system. ONCF used a single latent vector for user and item, but in this study, a channel is constructed using multiple vectors to enable the model to learn more diverse expressions and to obtain an ensemble effect. The experiments showed our deep learning model improved performance in recommendation compared to ONCF.