• Journal of the Earthquake Engineering Society of Korea
• /
• v.28 no.2
• /
• pp.113-119
• /
• 2024

Existing reinforced concrete buildings with seismically deficient column details affect the overall behavior depending on the failure type of column. This study aims to develop and validate a machine learning-based prediction model for the column failure modes (shear, flexure-shear, and flexure failure modes). For this purpose, artificial neural network (ANN), K-nearest neighbor (KNN), decision tree (DT), and random forest (RF) models were used, considering previously collected experimental data. Using four machine learning methodologies, we developed a classification learning model that can predict the column failure modes in terms of the input variables using concrete compressive strength, steel yield strength, axial load ratio, height-to-dept aspect ratio, longitudinal reinforcement ratio, and transverse reinforcement ratio. The performance of each machine learning model was compared and verified by calculating accuracy, precision, recall, F1-Score, and ROC. Based on the performance measurements of the classification model, the RF model represents the highest average value of the classification model performance measurements among the considered learning methods, and it can conservatively predict the shear failure mode. Thus, the RF model can rapidly predict the column failure modes with simple column details.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.2
• /
• pp.483-503
• /
• 2014

In this paper, human action recognition using pyramid histograms of oriented gradients and collaborative multi-task learning is proposed. First, we accumulate global activities and construct motion history image (MHI) for both RGB and depth channels respectively to encode the dynamics of one action in different modalities, and then different action descriptors are extracted from depth and RGB MHI to represent global textual and structural characteristics of these actions. Specially, average value in hierarchical block, GIST and pyramid histograms of oriented gradients descriptors are employed to represent human motion. To demonstrate the superiority of the proposed method, we evaluate them by KNN, SVM with linear and RBF kernels, SRC and CRC models on DHA dataset, the well-known dataset for human action recognition. Large scale experimental results show our descriptors are robust, stable and efficient, and outperform the state-of-the-art methods. In addition, we investigate the performance of our descriptors further by combining these descriptors on DHA dataset, and observe that the performances of combined descriptors are much better than just using only sole descriptor. With multimodal features, we also propose a collaborative multi-task learning method for model learning and inference based on transfer learning theory. The main contributions lie in four aspects: 1) the proposed encoding the scheme can filter the stationary part of human body and reduce noise interference; 2) different kind of features and models are assessed, and the neighbor gradients information and pyramid layers are very helpful for representing these actions; 3) The proposed model can fuse the features from different modalities regardless of the sensor types, the ranges of the value, and the dimensions of different features; 4) The latent common knowledge among different modalities can be discovered by transfer learning to boost the performance.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.83-92
• /
• 2004

Gene expression profile is numerical data of gene expression level from organism measured on the microarray. Generally, each specific tissue indicates different expression levels in related genes, so that we can classify cancer with gene expression profile. Because not all the genes are related to classification, it is needed to select related genes that is called feature selection. This paper proposes a new gene selection method using forward selection method in regression analysis. This method reduces redundant information in the selected genes to have more efficient classification. We used k-nearest neighbor as a classifier and tested with colon cancer dataset. The results are compared with Pearson's coefficient and Spearman's coefficient methods and the proposed method showed better performance. It showed 90.3% accuracy in classification. The method also successfully applied to lymphoma cancer dataset.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.27 no.6
• /
• pp.367-371
• /
• 2014

We investigated dielectric relaxation properties of $0.95(Na_{0.5}K_{0.5})NbO_3-0.05BaTiO_3$ ceramics by addition (0~0.3 wt%) of $(Ba,Ca)SiO_3$ glass frit. All composition of $0.95(Na_{0.5}K_{0.5})NbO_3-0.05BaTiO_3$ added $(Ba,Ca)SiO_3$ glass frit showed the same crystallographic properties, coexistence of orthorhombic and tetragonal phase. By increasing addition of $(Ba,Ca)SiO_3$ glass frit, the Curie temperatures of $0.95(Na_{0.5}K_{0.5})NbO_3-0.05BaTiO_3$ ceramics were decreased, whereas maximum dielectric constants of $0.95(Na_{0.5}K_{0.5})NbO_3-0.05BaTiO_3$ ceramics were dramatically increased. Especially the deviations of Curie temperature $0.95(Na_{0.5}K_{0.5})NbO_3-0.05BaTiO_3$ ceramics were increased by increasing amount of $(Ba,Ca)SiO_3$ glass frit, and it indicated that $0.95(Na_{0.5}K_{0.5})NbO_3-0.05BaTiO_3$ ceramics added $(Ba,Ca)SiO_3$ glass frit have relaxor characteristics.

• Journal of Internet Computing and Services
• /
• v.10 no.4
• /
• pp.1-11
• /
• 2009

Recently there has arisen concern in both the database community and the graphics society about data retrieval from large motion databases because the high dimensionality of motion data implies high costs. In this circumstance, finding an effective distance measure and an efficient query processing method for such data is a challenging problem. This paper presents an elaborate motion query processing system, SMoFinder (Similar Motion Finder), which incorporates a novel kinematic distance measure and an efficient indexing strategy via adaptive frame segmentation. To this end, we regard human motions as multi-linkage kinematics and propose the weighted Minkowski distance metric. For efficient indexing, we devise a new adaptive segmentation method that chooses representative frames among similar frames and stores chosen frames instead of all frames. For efficient search, we propose a new search method that processes k-nearest neighbors queries over only representative frames. Our experimental results show that the size of motion databases is reduced greatly (${\times}1/25$) but the search capability of SMoFinder is equal to or superior to that of other systems.

• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.120-126
• /
• 2020

We present a user recognition method using human body impulse response signals. The body compositions vary from person to person depending on the portion of water, muscle, and fat. In the body communication study, the body has been interpreted circuit models using capacitance and resistances, and its characteristics are determined by the body compositions. Therefore, the individual body channel is unique and can be used for user recognition. In this paper, we applied pseudo impulse signals to the left hand and recorded received signals from the right hand. The empirical mode decomposition (EMD) method removed noise from the received signals and 10 peak values are extracted. We set the differences between peak amplitudes as a key feature to identify individuals. We collected data from 6 subjects and achieved accuracy of 97.71% for the user recognition application.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2006.06a
• /
• pp.282-283
• /
• 2006

본 연구에서는 분말입자의 미립화에 따른 $(K,Na)NbO_3$(KNN) 세라믹스의 소결밀도와 압전특성을 평가하였다. 먼저 입자를 미립화 시키기 위해 planetary milling machine을 이용하였으며, 소결밀도 및 압전 특성을 측정하였다. Ball milling을 24~72시간동안 한 결과 particle size는 730~490nm 정도였다. Milling 시간이 증가할수록 입자크기는 감소하였고, 소결밀도는 particle size가 작을수록 증가하였고, $4.50g/cm^3$으로 가장 높은 밀도를 나타냈다. 또한 소결 밀도가 증가함에 따라 기계적 품질 계수(Qm) 역시 증가한 반면, particle size가 작아짐에 따라 전기기계 결합계수(Kp)는 감소하는 경황을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.581-584
• /
• 2019

Food consumption is growing worldwide every year owing to a growing population. Hence, the increasing population needs the production of sufficient and good quality food products. Strawberry is one of the world's most famous fruit. To obtain the highest strawberry output, we worked with three strawberry varieties supplied with three kinds of nutrient water in a greenhouse and with the outcome of the strawberry production, the highest yielding strawberry variety is detected. This Study uses the nutrient water consumed every day by the highest yielding strawberry variety. The atmospheric temperature, humidity and CO2 levels within the greenhouse are identified and used for the prediction, since the water consumption by any plant depends primarily on weather conditions. Machine learning techniques show successful outcomes in a multitude of issues including time series and regression issues. In this study, daily nutrient water consumption of strawberry plants is predicted using machine learning algorithms is proposed. Four Machine learning algorithms are used such as Linear Regression (LR), K nearest neighbour (KNN), Support Vector Machine with Radial Kernel (SVM) and Gradient Boosting Machine (GBM). Gradient Boosting System produces the best results.

• Journal of Korean Medical Science
• /
• v.33 no.48
• /
• pp.309.1-309.13
• /
• 2018

Background: The aim of this study was to observe long-term outcomes of very low birth weight infants (VLBWIs) born between 2013 and 2014 in Korea, especially focusing on neurodevelopmental outcomes. Methods: The data were collected from Korean Neonatal Network (KNN) registry from 43 and 54 participating units in 2013 and 2014, respectively. A standardized electronic case report form containing 30 items related to long-term follow up was used after data validation. Results: Of 2,660 VLBWI, the mean gestational age and birth weight were $29^{1/7}{\pm}2^{6/7}$ weeks and $1,093{\pm}268g$ in 2013 and $29^{2/7}{\pm}2^{6/7}$ weeks and $1,125{\pm}261g$ in 2014, respectively. The post-discharge mortality rate was 1.2%-1.5%. Weight < 50th percentile was 46.5% in 2013 and 66.1% in 2014. The overall prevalence of cerebral palsy among the follow up infants was 6.2% in 2013 and 6.6% in 2014. The Bayley Scales of Infant Developmental Outcomes version II showed 14%-25% of infants had developmental delay and 3%-8% of infants in Bayley version III. For the Korean developmental screening test for infants and children, the area "Further evaluation needed" was 5%-12%. Blindness in both eyes was reported to be 0.2%-0.3%. For hearing impairment, 0.8%-1.9% showed bilateral hearing loss. Almost 50% were readmitted to hospital with respiratory illness as a leading cause. Conclusion: The overall prevalence of long-term outcomes was not largely different among the VLBWI born between 2013 and 2014. This study is the first large national data study of long-term outcomes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3708-3728
• /
• 2021

Indian herbal plants are used in agriculture and in the food, cosmetics, and pharmaceutical industries. Laboratory-based tests are routinely used to identify and classify similar herb species by analyzing their internal cell structures. In this paper, we have applied computer vision techniques to do the same. The original leaf image was preprocessed using the Chan-Vese active contour segmentation algorithm to efface the background from the image by setting the contraction bias as (v) -1 and smoothing factor (µ) as 0.5, and bringing the initial contour close to the image boundary. Thereafter the segmented grayscale image was fed to a leaky capacitance fired neuron model (LCFN), which differentiates between similar herbs by combining different groups of pixels in the leaf image. The LFCN's decay constant (f), decay constant (g) and threshold (h) parameters were empirically assigned as 0.7, 0.6 and h=18 to generate the 1D feature vector. The LCFN time sequence identified the internal leaf structure at different iterations. Our proposed framework was tested against newly collected herbal species of natural images, geometrically variant images in terms of size, orientation and position. The 1D sequence and shape features of aloe, betel, Indian borage, bittergourd, grape, insulin herb, guava, mango, nilavembu, nithiyakalyani, sweet basil and pomegranate were fed into the 5-fold Bayesian regularization neural network (BRNN), K-nearest neighbors (KNN), support vector machine (SVM), and ensemble classifier to obtain the highest classification accuracy of 91.19%.