• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.9
• /
• pp.811-819
• /
• 2014

Activity recognition is a key component in identifying the context of a user for providing services based on the application such as medical, entertainment and tactical scenarios. Instead of applying numerous sensor devices, as observed in many previous investigations, we are proposing the use of smartphone with its built-in multimodal sensors as an unobtrusive sensor device for recognition of six physical daily activities. As an improvement to previous works, accelerometer, gyroscope and magnetometer data are fused to recognize activities more reliably. The evaluation indicates that the IBK classifier using window size of 2s with 50% overlapping yields the highest accuracy (i.e., up to 99.33%). To achieve this peak accuracy, simple time-domain and frequency-domain features were extracted from raw sensor data of the smartphone.

• The Journal of Bigdata
• /
• v.3 no.1
• /
• pp.55-62
• /
• 2018

In this study, we have developed a model for predicting the number of patients (flu, pneumonia, and outbreak) using Big Data, which has been mainly performed overseas. Existing patient number system by government adopt procedures that collects the actual number and percentage of patients from several big hospital. However, prediction model in this study was developed combing a real-time collection of disease-related words and various other climate data provided in real time. Also, prediction number of patients were counted by machine learning algorithm method. The advantage of this model is that if the epidemic spreads rapidly, the propagation rate can be grasped in real time. Also, we used a variety types of data to complement the failures in Google Flu Trends.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.4
• /
• pp.717-724
• /
• 2020

Due to the important role played by emotion in human interaction, affective computing is dedicated in trying to understand and regulate emotion through human-aware artificial intelligence. By understanding, emotion mental diseases such as depression, autism, attention deficit hyperactivity disorder, and game addiction will be better managed as they are all associated with emotion. Various studies for emotion recognition have been conducted to solve these problems. In applying machine learning for the emotion recognition, the efforts to reduce the complexity of the algorithm and improve the accuracy are required. In this paper, we investigate emotion Electroencephalogram (EEG) feature reduction and classification using Stack AutoEncoder (SAE) and Long-Short-Term-Memory/Recurrent Neural Networks (LSTM/RNN) classification respectively. The proposed method reduced the complexity of the model and significantly enhance the performance of the classifiers.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.10
• /
• pp.503-510
• /
• 2016

FsGr model, which has been proposed recently, is an approach of accelerometer-based gesture recognition by applying DTW algorithm in two steps, which improved recognition success rate. In FsGr model, sets of similar gestures will be produced through training phase, in order to define the notion of a set of similar gestures. At the 1st attempt of gesture recognition, if the result turns out to belong to a set of similar gestures, it makes the 2nd recognition attempt to feature-strengthened parts extracted from the set of similar gestures. However, since a same gesture show drastically different characteristics according to physical traits such as body size, age, and sex, FsGr model may not be good enough to apply to multi-user environments. In this paper, we propose FsGrM model that extends FsGr model for multi-user environment and present a program which controls channel and volume of smart TV using FsGrM model.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.6
• /
• pp.594-600
• /
• 2017

The new design methodology of prediction model and pattern classification, which is based on the dimension reduction algorithm called principal component analysis, is introduced in this paper. Principal component analysis is one of dimension reduction techniques which are used to reduce the dimension of the input space and extract some good features from the original input variables. The extracted input variables are applied to the prediction model and pattern classifier as the input variables. The introduced prediction model and pattern classifier are based on the very simple regression which is the key point of the paper. The structural simplicity of the prediction model and pattern classifier leads to reducing the over-fitting problem. In order to validate the proposed prediction model and pattern classifier, several machine learning data sets are used.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.514-517
• /
• 2017

In solar photovoltaic systems, power generation is greatly affected by the weather conditions, so it is essential to predict solar energy for stable load operation. Therefore, data on weather conditions are needed as inputs to machine learning algorithms for solar energy prediction. In this paper, we use 15 kinds of weather data such as the precipitation accumulated during the 3 hours of the surface, upward and downward longwave radiation average, upward and downward shortwave radiation average, the temperature during the past 3 hours at 2 m above from the ground and temperature from the ground surface as input data to the algorithm. We analyzed the statistical characteristics and correlations of weather data and extracted the downward and upward shortwave radiation averages as a major elements of a feature vector with high correlation of 70% or more with solar energy.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.363-363
• /
• 2019

활성화 함수(activation function)는 기계학습(machine learning)의 학습과정에 비선형성을 도입하여 심층적인 학습을 용이하게 하고 예측의 정확도를 높이는 중요한 요소 중 하나이다(Roy et al., 2019). 일반적으로 기계학습에서 사용되고 있는 활성화 함수의 종류에는 계단 함수(step function), 시그모이드 함수(sigmoid 함수), 쌍곡 탄젠트 함수(hyperbolic tangent function), ReLU 함수(Rectified Linear Unit function) 등이 있으며, 예측의 정확도 향상을 위하여 다양한 형태의 활성화 함수가 제시되고 있다. 본 연구에서는 기계학습을 통하여 수위예측 시 정확도 향상을 위하여 Hybrid 활성화 함수를 제안하였다. 연구대상지는 조수간만의 영향을 받는 한강을 대상으로 선정하였으며, 2009년 ~ 2018년까지 10년간의 수문자료를 활용하였다. 수위예측 알고리즘은 Python 내 Tensorflow의 RNN (Recurrent Neural Networks) 모델을 이용하였으며, 강수량, 수위, 조위, 댐 방류량, 하천 유량의 수문자료를 학습시켜 3시간 및 6시간 후의 수위를 예측하였다. 예측정확도 향상을 위하여 입력 데이터는 정규화(Normalization)를 시켰으며, 민감도 분석을 통하여 신경망모델의 은닉층 개수, 학습률의 최적 값을 도출하였다. Hybrid 활성화 함수는 쌍곡 탄젠트 함수와 ReLU 함수를 혼합한 형태로 각각의 가중치($w_1,w_2,w_1+w_2=1$)를 변경하여 정확도를 평가하였다. 그 결과 가중치의 비($w_1/w_2$)에 따라서 예측 결과의 RMSE(Roote Mean Square Error)가 최소가 되고 NSE (Nash-Sutcliffe model Efficiency coefficient)가 최대가 되는 지점과 Peak 수위의 예측정확도가 최대가 되는 지점을 확인할 수 있었다. 본 연구는 현재 Data modeling을 통한 수위예측의 정확도 향상을 위해 기초가 되는 연구이나, 향후 다양한 형태의 활성화 함수를 제안하여 정확도를 향상시킨다면 예측 결과를 통하여 침수예보에 대한 의사결정이 가능할 것으로 기대된다.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.886-895
• /
• 2018

In this paper, we introduce a technique to detect the video forgery by using the regularity that occurs in the video compression process. The proposed method uses the hierarchical regularity lost by the video double compression and the frame deletion. In order to extract such irregularities, the depth information of CU and TU, which are basic units of HEVC, is used. For improving performance, we make a depth map of CU and TU using local information, and then create input data by grouping them in GoP units. We made a decision whether or not the video is double-compressed and forged by using a general three-dimensional convolutional neural network. Experimental results show that it is more effective to detect whether or not the video is forged compared with the results using the existing machine learning algorithm.

• Food Science of Animal Resources
• /
• v.41 no.2
• /
• pp.312-323
• /
• 2021

The purpose of this study was to use 1H nuclear magnetic resonance (1H NMR) to quantify taste-active and bioactive compounds in chicken breasts and thighs from Korean native chicken (KNC) [newly developed KNCs (KNC-A, -C, and -D) and commercial KNC-H] and white-semi broiler (WSB) used in Samgye. Further, each breed was differentiated using multivariate analyses, including a machine learning algorithm designed to use metabolic information from each type of chicken obtained using 1H-13C heteronuclear single quantum coherence (2D NMR). Breast meat from KNC-D chickens were superior to those of conventional KNC-H and WSB chickens in terms of both taste-active and bioactive compounds. In the multivariate analysis, meat portions (breast and thigh) and chicken breeds (KNCs and WSB) could be clearly distinguished based on the outcomes of the principal component analysis and partial least square-discriminant analysis (R2=0.945; Q2=0.901). Based on this, we determined the receiver operating characteristic (ROC) curve for each of these components. AUC analysis identified 10 features which could be consistently applied to distinguish between all KNCs and WSB chickens in both breast (0.988) and thigh (1.000) meat without error. Here, both 1H NMR and 2D NMR could successfully quantify various target metabolites which could be used to distinguish between different chicken breeds based on their metabolic profile.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.396-402
• /
• 2022

User interactions are being developed in various forms, and in particular, interactions using human gestures are being actively studied. Among them, hand gesture recognition is used as a human interface in the field of realistic media based on the 3D Hand Model. The use of interfaces based on hand gesture recognition helps users access media media more easily and conveniently. User interaction using hand gesture recognition should be able to view images by applying fast and accurate hand gesture recognition technology without restrictions on the computer environment. This paper developed a fast and accurate user hand gesture recognition algorithm using the open source media pipe framework and machine learning's k-NN (K-Nearest Neighbor). In addition, in order to minimize the restriction of the computer environment, a stereoscopic image control system based on user hand gesture recognition was designed and implemented using a web service environment capable of Internet service and a docker container, a virtual environment.