• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.654-670
• /
• 2020

Workers at construction sites are easily exposed to many dangers and accidents involving falls, tripping, and missteps on stairs. However, researches on construction site monitoring system to prevent work-related injuries are still insufficient. The purpose of this study was to develop a wearable textile pressure insole sensor and examine its effectiveness in managing the real-time safety of construction workers. The sensor was designed based on the principles of parallel capacitance measurement using conductive textile and the monitoring system was developed by C# language. Three separate experiments were carried out for performance evaluation of the proposed sensor: (1) varying the distance between two capacitance plates to examine changes in capacitance charges, (2) repeatedly applying 1 N of pressure for 5,000 times to evaluate consistency, and (3) gradually increasing force by 1 N (from 1 N to 46 N) to test the linearity of the sensor value. Five subjects participated in our pilot test, which examined whether ascending and descending the stairs can be distinguished by our sensor and by weka assessment tool using k-NN algorithm. The 10-fold cross-validation method was used for analysis and the results of accuracy in identifying stair ascending and descending were 87.2% and 90.9%, respectively. By applying our sensor, the type of activity, weight-shifting patterns for balance control, and plantar pressure distribution for postural changes of the construction workers can be detected. The results of this study can be the basis for future sensor-based monitoring device development studies and fall prediction researches for construction workers.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2005.09a
• /
• pp.319-324
• /
• 2005

An integrated approach for prostate cancer detection using proteomic data is presented. Due to the high-dimensional feature of proteomic data, the discrete wavelet transform (DWT) is used in the first-stage for data reduction as well as noise removal. After the process of DWT, the dimensionality is reduced from 43,556 to 1,599. Thus, each sample of proteomic data can be represented by 1599 wavelet coefficients. In the second stage, a voting method is used to select a common set of wavelet coefficients for all samples together. This produces a 987-dimension subspace of wavelet coefficients. In the third stage, the Autoassociator algorithm reduces the dimensionality from 987 to 400. Finally, the artificial neural network (ANN) is applied on the 400-dimension space for prostate cancer detection. The integrated approach is examined on 9 categories of 2-class experiments, and also 3- and 4-class experiments. All of the experiments were run 10 times of ten-fold cross-validation (i. e. 10 partitions with 100 runs). For 9 categories of 2-class experiments, the average testing accuracies are between 81% and 96%, and the average testing accuracies of 3- and 4-way classifications are 85% and 84%, respectively. The integrated approach achieves exciting results for the early detection and diagnosis of prostate cancer.

• Journal of Information Technology Services
• /
• v.13 no.3
• /
• pp.221-233
• /
• 2014

Because people's interest of the stock market has been increased with the development of economy, a lot of studies have been going to predict fluctuation of stock prices. Latterly many studies have been made using scientific and technological method among the various forecasting method, and also data using for study are becoming diverse. So, in this paper we propose stock prices prediction models using sentiment analysis and machine learning based on news articles and SNS data to improve the accuracy of prediction of stock prices. Stock prices prediction models that we propose are generated through the four-step process that contain data collection, sentiment dictionary construction, sentiment analysis, and machine learning. The data have been collected to target newspapers related to economy in the case of news article and to target twitter in the case of SNS data. Sentiment dictionary was built using news articles among the collected data, and we utilize it to process sentiment analysis. In machine learning phase, we generate prediction models using various techniques of classification and the data that was made through sentiment analysis. After generating prediction models, we conducted 10-fold cross-validation to measure the performance of they. The experimental result showed that accuracy is over 80% in a number of ways and F1 score is closer to 0.8. The result can be seen as significantly enhanced result compared with conventional researches utilizing opinion mining or data mining techniques.

• Journal of Biomedical Engineering Research
• /
• v.41 no.5
• /
• pp.185-194
• /
• 2020

Arrhythmia is basically diagnosed with the electrocardiogram (ECG) signal, however, ECG is difficult to measure and it requires expert help in analyzing the signal. On the other hand, the radial pulse can be measured with easy and uncomplicated way in daily life, and could be suitable bio-signal for the recent untact paradigm and extensible signal for diagnosis of Korean medicine based on pulse pattern. In this study, we developed an irregular radial pulse detection algorithm based on a learning model and considered its applicability as arrhythmia screening. A total of 1432 pulse waves including irregular pulse data were used in the experiment. Three data sets were prepared with minimal preprocessing to avoid the heuristic feature extraction. As classification algorithms, elastic net logistic regression, random forest, and extreme gradient boosting were applied to each data set and the irregular pulse detection performances were estimated using area under the receiver operating characteristic curve based on a 10-fold cross-validation. The extreme gradient boosting method showed the superior performance than others and found that the classification accuracy reached 99.7%. The results confirmed that the proposed algorithm could be used for arrhythmia screening. To make a fusion technology integrating western and Korean medicine, arrhythmia subtype classification from the perspective of Korean medicine will be needed for future research.

• Advances in environmental research
• /
• v.5 no.3
• /
• pp.153-167
• /
• 2016

We applied multilayer perceptron (MLP) and radial basis function (RBF) neural network in upstream and downstream water quality stations of the Karaj Reservoir in Iran. For both neural networks, inputs were pH, turbidity, temperature, chlorophyll-a, biochemical oxygen demand (BOD) and nitrate, and the output was dissolved oxygen (DO). We used an MLP neural network with two hidden layers, for upstream station 15 and 33 neurons in the first and second layers respectively, and for the downstream station, 16 and 21 neurons in the first and second hidden layer were used which had minimum amount of errors. For learning process 6-fold cross validation were applied to avoid over fitting. The best results acquired from RBF model, in which the mean bias error (MBE) and root mean squared error (RMSE) were 0.063 and 0.10 for the upstream station. The MBE and RSME were 0.0126 and 0.099 for the downstream station. The coefficient of determination ($R^2$) between the observed data and the predicted data for upstream and downstream stations in the MLP was 0.801 and 0.904, respectively, and in the RBF network were 0.962 and 0.97, respectively. The MLP neural network had acceptable results; however, the results of RBF network were more accurate. A sensitivity analysis for the MLP neural network indicated that temperature was the first parameter, pH the second and nitrate was the last factor affecting the prediction of DO concentrations. The results proved the workability and accuracy of the RBF model in the prediction of the DO.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.51-51
• /
• 2017

지역빈도해석은 짧은 기간의 자료를 보유하고 있는 계측 지점이나 자료가 없는 미계측 지점에서의 확률수문량을 산정하기 위하여 많이 쓰여 진다. 지역빈도해석을 실시하기 위한 조건으로는 우선 수집된 하천유역들을 대상으로 수문학적 동질 지역을 구분하는 것이 중요하다. 그리고 구분되어진 지역에 포함되는 모든 지점들의 자료를 빈도해석 함으로써 관심 지점의 신뢰할 만한 확률수문량을 산정하는 것이다. 그동안의 지역빈도해석은 주로 비건조지역을 중심으로 홍수와 같은 재난재해 대비 그리고 수자원 관리를 위한 연구들을 실시해왔다. 본 연구의 주 목적은 건조지역의 수자원 관리를 위해 건조지역 하천유역을 중심으로 지역빈도해석을 실시하여 신뢰할만한 확률수문량을 산정하는 것이다. 확률수문량 산정값의 정확도를 향상시키기 위해 지역빈도해석 모델에 쓰여 지는 새로운 지형학적 변수들을 제공하였고 수문학적 동질 지역을 구분 위해 수집된 각 하천유역의 형상들을 확인하여 동질 지역을 정의하였다. 예를 들면, 수지형 유역, 부채형 유역, 격자형 유역과 같은 다른 형상들을 구분하여 각 유역 형상 종류별로 동질 지역을 만들었다. 건조지역의 지역빈도해석을 위해 미국 건조지역의 105개 하천유역 유량자료들을 수집 및 이용하였다. 확률수문량 산정을 위하여 앙상블 인경신경망 (Ensemble Artificial Neural Network)과 정준 상관 계수(Canonical Correlation Analysis)를 이용한 지역빈도해석 모델을 만들었다. 제안된 모델의 수행평가와 정확성 평가를 위해 리샘플링 기법인 10-겹 교차 검증 (10-fold cross-validation), 잭나이프 (Jackknife) 기법들을 이용하였고 모델로부터 산정된 확률수문량값을 편향 (Bias), 상대 편향(rBias), 평균 제곱근 오차 (RMSE), 상대 평균 제곱근 오차 (rRMSE)를 통하여 산정 값과 실제 관측 값의 차이를 분석하였다. 그 결과 건조지역의 지역빈도해석을 위해 새롭게 제시된 지형학적 변수들을 사용하였을 때 모델의 수행능력이 향상되었음을 확인하였다. 또한 하천유역 형상에 따라 동질 지역을 구분하였을 때 향상된 확률수문량이 산정되었다. 향상된 지역빈도해석 모델을 통해 건조지역의 신뢰할만한 확률수문량을 산정함으로써 건조지역의 효과적인 수자원 관리를 위한 수공시설물 설계에 중요한 정보들을 제공할 것이다.

• Journal of Preventive Medicine and Public Health
• /
• v.56 no.1
• /
• pp.41-49
• /
• 2023

Objectives: Rwanda reported a stunting rate of 33% in 2020, decreasing from 38% in 2015; however, stunting remains an issue. Globally, child deaths from malnutrition stand at 45%. The best options for the early detection and treatment of stunting should be made a community policy priority, and health services remain an issue. Hence, this research aimed to develop a model for predicting stunting in Rwandan children. Methods: The Rwanda Demographic and Health Survey 2019-2020 was used as secondary data. Stratified 10-fold cross-validation was used, and different machine learning classifiers were trained to predict stunting status. The prediction models were compared using different metrics, and the best model was chosen. Results: The best model was developed with the gradient boosting classifier algorithm, with a training accuracy of 80.49% based on the performance indicators of several models. Based on a confusion matrix, the test accuracy, sensitivity, specificity, and F1 were calculated, yielding the model's ability to classify stunting cases correctly at 79.33%, identify stunted children accurately at 72.51%, and categorize non-stunted children correctly at 94.49%, with an area under the curve of 0.89. The model found that the mother's height, television, the child's age, province, mother's education, birth weight, and childbirth size were the most important predictors of stunting status. Conclusions: Therefore, machine-learning techniques may be used in Rwanda to construct an accurate model that can detect the early stages of stunting and offer the best predictive attributes to help prevent and control stunting in under five Rwandan children.

• Korean Journal of Radiology
• /
• v.20 no.8
• /
• pp.1275-1284
• /
• 2019

Objective: To develop algorithms using convolutional neural networks (CNNs) for automatic segmentation of acute ischemic lesions on diffusion-weighted imaging (DWI) and compare them with conventional algorithms, including a thresholding-based segmentation. Materials and Methods: Between September 2005 and August 2015, 429 patients presenting with acute cerebral ischemia (training:validation:test set = 246:89:94) were retrospectively enrolled in this study, which was performed under Institutional Review Board approval. Ground truth segmentations for acute ischemic lesions on DWI were manually drawn under the consensus of two expert radiologists. CNN algorithms were developed using two-dimensional U-Net with squeeze-and-excitation blocks (U-Net) and a DenseNet with squeeze-and-excitation blocks (DenseNet) with squeeze-and-excitation operations for automatic segmentation of acute ischemic lesions on DWI. The CNN algorithms were compared with conventional algorithms based on DWI and the apparent diffusion coefficient (ADC) signal intensity. The performances of the algorithms were assessed using the Dice index with 5-fold cross-validation. The Dice indices were analyzed according to infarct volumes (< 10 mL, ≥ 10 mL), number of infarcts (≤ 5, 6-10, ≥ 11), and b-value of 1000 (b1000) signal intensities (< 50, 50-100, > 100), time intervals to DWI, and DWI protocols. Results: The CNN algorithms were significantly superior to conventional algorithms (p < 0.001). Dice indices for the CNN algorithms were 0.85 for U-Net and DenseNet and 0.86 for an ensemble of U-Net and DenseNet, while the indices were 0.58 for ADC-b1000 and b1000-ADC and 0.52 for the commercial ADC algorithm. The Dice indices for small and large lesions, respectively, were 0.81 and 0.88 with U-Net, 0.80 and 0.88 with DenseNet, and 0.82 and 0.89 with the ensemble of U-Net and DenseNet. The CNN algorithms showed significant differences in Dice indices according to infarct volumes (p < 0.001). Conclusion: The CNN algorithm for automatic segmentation of acute ischemic lesions on DWI achieved Dice indices greater than or equal to 0.85 and showed superior performance to conventional algorithms.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_4
• /
• pp.1179-1194
• /
• 2020

This study investigates the feasibility of three algorithms, K-Nearest Neighbors (K-NN), Random Forest (RF) and Neural Network (NN), for estimating the air temperature of an unobserved area where the weather station is not installed. The satellite image were obtained from Landsat-8 and MODIS Aqua/Terra acquired in 2019, and the meteorological ground weather data were from AWS/ASOS data of Korea Meteorological Administration and Korea Forest Service. In addition, in order to improve the estimation accuracy, a digital surface model, solar radiation, aspect and slope were used. The accuracy assessment of machine learning methods was performed by calculating the statistics of R² (determination coefficient) and Root Mean Square Error (RMSE) through 10-fold cross-validation and the estimated values were compared for each target area. As a result, the neural network algorithm showed the most stable result among the three algorithms with R² = 0.805 and RMSE = 0.508. The neural network algorithm was applied to each data set on Landsat imagery scene. It was possible to generate an mean air temperature map from June to September 2019 and confirmed that detailed air temperature information could be estimated. The result is expected to be utilized for national disaster safety management such as heat wave response policies and heat island mitigation research.

• Korean Journal of Cognitive Science
• /
• v.28 no.4
• /
• pp.299-314
• /
• 2017

Predicting compound-protein interactions in-silico is significant for the drug discovery. In this paper, we propose an scalable machine learning model to predict compound-protein interaction. The key idea of this scalable machine learning model is the architecture of pairwise neural network model and feature embedding method from the raw data, especially for protein. This method automatically extracts the features without additional knowledge of compound and protein. Also, the pairwise architecture elevate the expressiveness and compact dimension of feature by preventing biased learning from occurring due to the dimension and type of features. Through the 5-fold cross validation results on large scale database show that pairwise neural network improves the performance of predicting compound-protein interaction compared to previous prediction models.