• Journal of the Institute of Electronics Engineers of Korea CI
• /
• 제44권1호
• /
• pp.56-63
• /
• 2007

In this paper, an eye tracking method is presented using a neural network (NN) and mean-shift algorithm that can accurately detect and track user's eyes under the cluttered background. In the proposed method, to deal with the rigid head motion, the facial region is first obtained using skin-color model and con-nected-component analysis. Thereafter the eye regions are localized using neural network (NN)-based tex-ture classifier that discriminates the facial region into eye class and non-eye class, which enables our method to accurately detect users' eyes even if they put on glasses. Once the eye region is localized, they are continuously and correctly tracking by mean-shift algorithm. To assess the validity of the proposed method, it is applied to the interface system using eye movement and is tested with a group of 25 users through playing a 'aligns games.' The results show that the system process more than 30 frames/sec on PC for the $320{\times}240$ size input image and supply a user-friendly and convenient access to a computer in real-time operation.

• Journal of KIISE:Computer Systems and Theory
• /
• 제33권10호
• /
• pp.709-721
• /
• 2006

The traditional broadcasting services over terrestrial, satellite and cable media have been unidirectional mass media regardless of TV viewer's preferences. Recently ich media streaming has become possible via the broadb and networks. Furthermore, since bidirectional communication is possible, personalcasting such as personalized streaming services has been emerging by taking into account the user's preference on content genres, viewing times and actors/actresses etc. Accordingly, personal media becomes an important means for content provision service in addition to the traditional broadcasting service as mass media. In this paper, we introduce a user profile reasoning method for target advertisement which is considered an important application in personalcasting service. The proposed user profile reasoning method predicts an unknown TV viewer's gender and ages by analyzing TV Viewing history data. Based on the estimated user's gender and ages, a target advertisement is provided with TV Anytime metadata. A proposed target advertisement system is developed based on the user profile reasoning and the target advertisement selection method. To show the effectiveness of our proposed methods, we present a plenty of experimental results by using realistic TV viewing history data.

• The Transactions of the Korea Information Processing Society
• /
• 제7권8호
• /
• pp.2349-2360
• /
• 2000

In medical image processing, if new technologies arc developed, they arc applied to real clinical cases. The results are to be analyzed by doctors to improve the new technologies. So, it is important for doctors to have a tool that helps the doctors in applying the new technologies to clinical cases and analyzing the clinical results. In this paper, we design and implement a visual programming environment where non-programming experts, such as medical doctors, can easily compose a medical image processing application program. A set of image processing functions are implemented and represented as icons. Thc user selects functions by clicking correslxmding icons. The users can easily find necessary' functions from the visualized library. A user selects a function from the visualized library and [Jut the function node into a canvas of Visual Programming Interface. The user connects nodes to compose a dataflow diagram. The connected dataflow diagram shows the now of the program. Hyperbolic Tree is helpful in visualizing a set of function icons in a single screen because it provides both the whole stmcture of the function Iihrary and the details of the focused functions at the same time. We also developed a CUI builder where the user interfaces of the medical image processing applications are composed. Therefore. non'programming experts such as physicians can apply new medical image processing algorithms to clinical cases without performing complex computer programming procedures.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• 제45권1호
• /
• pp.55-63
• /
• 2008

Ridge orientations of fingerprint image are crucial informations in many parts of fingerprint recognition such as enhancement, matching and classification. Therefore it is essential to extract the ridge orientations of image accurately because it directly affects the performance of the system. The two main properties of ridge orientation are 1) global characteristic(gradual change in whole part of fingerprint) and 2) local characteristic(abrupt change around core and delta points). When we only consider the local characteristic, estimated ridge orientations are well around singular points but not robust to noise. When the global characteristic is only considered, to estimate ridge orientation is robust to noise but cannot represent the orientation around singular points. In this paper, we propose a novel method for estimating ridge orientation which represents local characteristic specifically as well as be robust to noise. We reduce the noise caused by scar using iterative outlier rejection. We apply adaptive measurement resolution in each fingerprint area to estimate the ridge orientation around singular points accurately. We evaluate the performance of proposed method using synthetic fingerprint and FVC 2002 DB. We compare the accuracy of ridge orientation. The performance of fingerprint authentication system is evaluated using FVC 2002 DB.

• Journal of Platform Technology
• /
• 제9권3호
• /
• pp.52-62
• /
• 2021

Quality control is critical at manufacturing sites and is key to predicting the risk of quality defect before manufacturing. However, the reliability of manual quality control methods is affected by human and physical limitations because manufacturing processes vary across industries. These limitations become particularly obvious in domain areas with numerous manufacturing processes, such as the manufacture of major nuclear equipment. This study proposed a novel method for predicting the risk of quality defects by using natural language processing and machine learning. In this study, production data collected over 6 years at a factory that manufactures main equipment that is installed in nuclear power plants were used. In the preprocessing stage of text data, a mapping method was applied to the word dictionary so that domain knowledge could be appropriately reflected, and a hybrid algorithm, which combined n-gram, Term Frequency-Inverse Document Frequency, and Singular Value Decomposition, was constructed for sentence vectorization. Next, in the experiment to classify the risky processes resulting in poor quality, k-fold cross-validation was applied to categorize cases from Unigram to cumulative Trigram. Furthermore, for achieving objective experimental results, Naive Bayes and Support Vector Machine were used as classification algorithms and the maximum accuracy and F1-score of 0.7685 and 0.8641, respectively, were achieved. Thus, the proposed method is effective. The performance of the proposed method were compared and with votes of field engineers, and the results revealed that the proposed method outperformed field engineers. Thus, the method can be implemented for quality control at manufacturing sites.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• 제10권4호
• /
• pp.137-143
• /
• 2010

This paper deals with the performance comparison of self adaptive equalizer by the weighting factor of MCMA cost function for the compensate the amplitude and phase distortion which occurs in the communication channel. The MCMA is improves the cost function of present CMA at the output of equalizer for the minimize of error function in the amplitude and phase, the value of weighting factor is used at this time. When the comparison of equalizer performance, we classified to initial state and steady state, then it represents the convergence time and convergence speed and steady state operation of equalizer to the predetermined level, it is determined by the weighting factor. We confirm to the different result to this 2 state by weighting factor values using computer simulation. By using the result of this paper, if we appropriately choose the weighting factor values in the environment of communication channel, it is expected that the high quality digital transmission is possible.

• Journal of Advanced Navigation Technology
• /
• 제23권6호
• /
• pp.561-569
• /
• 2019

Solar photovoltaic can provide electrical energy with only radiation, and its use is expanding rapidly as a new energy source. This study predicts the short and long-term PV power generation using actual converter output data of photovoltaic system. The prediction algorithm uses multiple linear regression, support vector machine (SVM), and deep learning such as deep neural network (DNN) and long short-term memory (LSTM). In addition, three models are used according to the input and output structure of the weather element. Long-term forecasts are made monthly, seasonally and annually, and short-term forecasts are made for 7 days. As a result, the deep learning network is better in prediction accuracy than multiple linear regression and SVM. In addition, LSTM, which is a better model for time series prediction than DNN, is somewhat superior in terms of prediction accuracy. The experiment results according to the input and output structure appear Model 2 has less error than Model 1, and Model 3 has less error than Model 2.

• Journal of Korean Society of Steel Construction
• /
• 제21권6호
• /
• pp.563-574
• /
• 2009

This paper briefly describes the fundamental strategies--path-tracing, pin-pointing, and path-switching--in the computational elastic bifurcation theory of geometrically non-linear single-load-parameter conservative elastic spatial structures. The stability points in the non-linear elasticity may be classified into limit points and bifurcation points. For the limit points, the path tracing scheme that successively computes the regular equilibrium points on the equilibrium path, and the pinpointing scheme that precisely locates the singular equilibrium points were sufficient for the computational stability analysis. For the bifurcation points, however, a specific procedure for path-switching was also necessary to detect the branching paths to be traced in the post-buckling region. After the introduction, a general theory of elastic stability based on the energy concept was given. Then path tracing, an indirect method of detecting multiple bifurcation points, and path switching strategies were described. Next, some numerical examples of bifurcation analysis were carried out for a trussed stardome, and a pin-supported plane circular arch was described. Finally, concluding remarks were given.

• Phonetics and Speech Sciences
• /
• 제14권4호
• /
• pp.35-43
• /
• 2022

This paper studies how to improve the identification rate of laryngeal disability speech data by convolutional neural network (CNN) and machine learning ensemble learning methods. In general, the number of laryngeal dysfunction speech data is small, so even if identifiers are constructed by statistical methods, the phenomenon caused by overfitting depending on the training method can lead to a decrease the identification rate when exposed to external data. In this work, we try to combine results derived from CNN models and machine learning models with various accuracy in a multi-voting manner to ensure improved classification efficiency compared to the original trained models. The Pusan National University Hospital (PNUH) dataset was used to train and validate algorithms. The dataset contains normal voice and voice data of benign and malignant tumors. In the experiment, an attempt was made to distinguish between normal and benign tumors and malignant tumors. As a result of the experiment, the random forest method was found to be the best ensemble method and showed an identification rate of 85%.

• The Journal of the Korea institute of electronic communication sciences
• /
• 제17권2호
• /
• pp.333-342
• /
• 2022

Cellular Automata (CA) is a discrete and abstract computational model that is being applied in various fields. Applicable as an excellent pseudo-random sequence generator, CA has recently developed into a basic element of cryptographic systems. Several studies on CA-based stream ciphers have been conducted and it has been observed that the encryption strength increases when the radius of a CA's neighbor is increased when appropriate CA rules are used. In this paper, among CAs that can be applied as a one-dimensional pseudo-random number sequence generator (PRNG), one-dimensional 5-neighbor CAs are classified according to the connection state of their neighbors, and the ignition relationship of the characteristic polynomial is obtained. Also this paper propose a synthesis algorithm for an asymmetric 1-D linear 5-neighbor MLCA in which the radius of the neighbor is increased by 2 using the one-dimensional 3-neighbor 90/150 CA state transition matrix.