• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.525-530
• /
• 2023

최근 소셜 네트워크 서비스(SNS) 및 모바일 서비스가 증가함에 따라 사용자들은 다양한 종류의 위험에 직면하고 있다. 특히 온라인 그루밍과 온라인 루머 같은 위험은 한 개인의 삶을 완전히 망가뜨릴 수 있을 정도로 심각한 문제로 자리 잡았다. 그러나 많은 경우 이러한 위험들을 판단하는 시점은 사건이 일어난 이후이고, 주로 법적인 증거채택을 위한 위험성 판별이 대다수이다. 따라서 본 논문은 이러한 문제를 사전에 예방하는 것에 초점을 맞추었고, 계속적으로 발생하는 대화와 같은 event를 실시간으로 감지하고, 위험을 사전에 탐지할 수 있는 Real-Time Early Risk Detection(RERD) 문제를 정의하고자 한다. 온라인 그루밍과 루머를 실시간 조기 위험 감지(RERD) 문제로 정의하고 해당 데이터셋과 평가지표를 소개한다. 또한 RERD 문제를 정확하고 신속하게 해결할 수 있는 강화학습 기반 새로운 방법론인 RT-ERD 모델을 소개한다. 해당 방법론은 RERD 문제를 이루고 있는 온라인 그루밍, 루머 도메인에 대한 실험에서 각각 기존의 모델들을 뛰어넘는 state-of-the-art의 성능을 달성하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.1B
• /
• pp.52-63
• /
• 2004

Packet loss process of cdma2000 mobile Internet channel deployed in Korea is modeled as a two state Markov process known as Gilbert model. This paper proposes the procedures to derive four parameters of the our modified Gilbert model from packet loss trace taken from two major cdma2000 networks in Korea. These four parameters are derived in various situations, that is, with fixed and moving terminals, in open field and urban areas. They can be used to produce synthetic packet loss patterns for study of the channel. Moreover, if they are calculated on-line during multimedia service, they can be used to make loss protection controls adaptive to network condition.

• Journal of Digital Convergence
• /
• v.11 no.5
• /
• pp.429-436
• /
• 2013

Context aware environment u-health service is to provide health service with recognition of a computer. The computer recognizes that a patient can contact real life in many context. Context aware environment service for recommend have to definition of context data and service recommendations related to factors shall be identified. In this paper, Context aware environment of u-health service will be provide context data related to identifies recommendations factors using multivariate analysis method and recommendations factors creation to decision tree, association rule based decision model. health service recommend for significantly context data can be distinguish through recommendation factors of identify. Also, context data of patient can know preference factors through preference decision model.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.35 no.1
• /
• pp.1-11
• /
• 2015

In this study, an online seed potato sorting system using a visible and near infrared (40 1100 nm) transmittance spectral technique and statistical model was evaluated for the nondestructive determination of infected and sound seed potatoes. Seed potatoes that had been artificially infected with Pectobacterium atrosepticum, which is known to cause a soil borne disease infection, were prepared for the experiments. After acquiring transmittance spectra from sound and infected seed potatoes, a determination algorithm for detecting infected seed potatoes was developed using the partial least square discriminant analysis method. The coefficient of determination($R^2_p$) of the prediction model was 0.943, and the classification accuracy was above 99% (n = 80) for discriminating diseased seed potatoes from sound ones. This online sorting system has good potential for developing a technique to detect agricultural products that are infected and contaminated by pathogens.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.8
• /
• pp.299-308
• /
• 2014

Various literatures related computing of information processing have been recently shown the researches inspired from the remarkably excellent human capabilities which recognize and categorize very complex visual patterns such as body motions and facial expressions. Applied from human's outstanding ability of perception, the classification function of visual sequences without context information is specially crucial task for computer vision to understand both the coding and the retrieval of spatio-temporal patterns. This paper presents a biological process based action recognition model of computer vision, which is inspired from visual information processing of human brain for action recognition of visual sequences. Proposed model employs the structure of neural fields of bio-inspired visual perception on detecting motion sequences and discriminating visual patterns in human brain. Experimental results show that proposed recognition model takes not only into account several biological properties of visual information processing, but also is tolerant of time-warping. Furthermore, the model allows robust temporal evolution of classification compared to researches of action recognition. Presented model contributes to implement bio-inspired visual processing system such as intelligent robot agent, etc.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.801-804
• /
• 2013

We propose a new tongue examination model according to the taste division of tongue. The proposed sytem consists of image acquisition, region segmentation, color distribution analysis and abnormality decision of tongue. Tongue DB which is classified into abnormality is constructed with tongue images captured from oriental medicine hospital inpatients. We divided 4 basic taste(bitter, sweet, salty and sour) regions and performed color distribution analysis targeting each region under HSI(Hue Saturation Intensity) color model. To minimize the influence of illumination, the histograms of H and S components only except I are utilized. The abnormality of taste regions each by comparing the proposed diagnosis model with diagnosis results by a doctor of oriental medicine. We confirmed the 87.5% of classification results of abnormality by proposed algorithm is coincide with the doctor's results.

• Journal of Korea Society of Industrial Information Systems
• /
• v.8 no.1
• /
• pp.18-25
• /
• 2003

In this Paper, we propose a dissolve detection method based on video editing model. Our method consists of two steps In the first step, the candidate regions are found by using the first md second derivative of a variance curve. In a variance curve, a dissolve presents a parabola that is downward convex. Therefore the parabola is found as a candidate region for a dissolve. In the second step, the candidate region is verified for a dissolve region. In each candidate region, a variance at a valley of the parabola corresponding to dissolve is estimated and then the candidate region is verified by using estimated valley's variance. The valley's variance is determined by neighbor scene variances, so proposed method is adaptive to detect dissolve with various variances. Experiment results on video of various content types are reported and validated.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.17 no.2
• /
• pp.89-96
• /
• 2011

A three dimensional ecological model(EMT-3D) was applied to Ulsan Bay for the simulation of Dioxins. The simulated results of dissolved Dioxins were in agreement with the observed values, with a correlation coefficient(R) of 0.7951 and a coefficient of determination($R^2$) of 0.6265. The results of sensitivity analysis showed that partition rate, adsorption rate and bioconcentration factor were important factors. Therefore, the parameters must be carefully considered in the modeling. In the case of 50% and 80% total loads reduction, concentration of dissolved Dioxins was shown to be lower than 0.150 and 0.250 pg WHD-TEQ/L, respectively.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.6
• /
• pp.759-765
• /
• 2006

In this paper, it is proposed an effective face expression recognition LDA mixed mode using a triangularity membership fuzzy function and wavelet basis. The proposal algorithm gets performs the optimal image, fuzzy wavelet algorithm and Expression recognition is consisted of face characteristic detection step and face Expression recognition step. This paper could applied to the PCA and LDA in using some simple strategies and also compares and analyzes the performance of the LDA mixed model which is combined and the facial expression recognition based on PCA and LDA. The LDA mixed model is represented by the PCA and the LDA approaches. And then we calculate the distance of vectors dPCA, dLDA from all fates in the database. Last, the two vectors are combined according to a given combination rule and the final decision is made by NNPC. In a result, we could showed the superior the LDA mixed model can be than the conventional algorithm.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.5
• /
• pp.259-266
• /
• 2022

In this study, we developed a deep learning and vision sensor-based assembly performance evaluation method isfor prefabricated steel structures. The assembly parts were segmented using a modified version of the receptive field block convolution module inspired by the eccentric function of the human visual system. The quality of the assembly was evaluated by detecting the bolt holes in the segmented assembly part and calculating the bolt hole positions. To validate the performance of the evaluation, models of standard and defective assembly parts were produced using a 3D printer. The assembly part segmentation network was trained based on the 3D model images captured from a vision sensor. The sbolt hole positions in the segmented assembly image were calculated using image processing techniques, and the assembly performance evaluation using the k-nearest neighbor algorithm was verified. The experimental results show that the assembly parts were segmented with high precision, and the assembly performance based on the positions of the bolt holes in the detected assembly part was evaluated with a classification error of less than 5%.