• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.361-364
• /
• 2022

본 논문에서는 스마트 기기를 사용할 시 자세가 거북목 자세인지 아닌지 판별하는 시스템을 제안한다. 거북목 증후군이란 목이 구부정하게 앞으로 나오는 자세를 오래 취해 목이 일자목으로 바뀌고 뒷목, 어깨, 허리 등에 통증이 생기는 증상을 말하며, 수술이나 약물치료보다 평소의 자세 습관을 고치는 방법이 효과적이다. 기존의 연구들은 노트북에 내장되어있는 웹캠을 이용한 CNN기반의 학습모델은 영상의 명도와 학습 데이터 등에 많은 영향을 받고 학습 데이터를 모을 때 초상권 문제로 수집이 어렵다. 본 논문에서는 이러한 문제를 예방하고자 Openpose 오픈 소스를 이용한 뼈대를 기반으로 측면에서의 앉은 자세를 한습 모델로 실시간 검증하여, 거북목 자세인지 아닌지를 효율적이고 정확하게 판별한다.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.286-299
• /
• 2022

Human activity recognition in real time is a challenging task. Recently, a plethora of studies has been proposed using deep learning architectures. The implementation of these architectures requires the high computing power of the machine and a massive database. However, handcrafted features-based machine learning models need less computing power and very accurate where features are effectively extracted. In this study, we propose a handcrafted model based on three-dimensional sequential skeleton data. The human body skeleton movement over a frame is computed through joint positions in a frame. The joints of these skeletal frames are projected into two-dimensional space, forming a "movement polygon." These polygons are further transformed into a one-dimensional space by computing amplitudes at different angles from the centroid of polygons. The feature vector is formed by the sampling of these amplitudes at different angles. The performance of the algorithm is evaluated using a support vector machine on four public datasets: MSR Action3D, Berkeley MHAD, TST Fall Detection, and NTU-RGB+D, and the highest accuracies achieved on these datasets are 94.13%, 93.34%, 95.7%, and 86.8%, respectively. These accuracies are compared with similar state-of-the-art and show superior performance.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.43-50
• /
• 2021

In this paper, we design and implement KITNESS, a windows application that feeds back the accuracy of fitness motions based on Kinect sensors. The feature of this application is to use Kinect's camera and joint recognition sensor to give feedback to the user to exercise in the correct fitness position. At this time, the distance between the user and the Kinect is measured using Kinect's IR Emitter and IR Depth Sensor, and the joint, which is the user's joint position, and the Skeleton data of each joint are measured. Using this data, a certain distance is calculated for each joint position and posture of the user, and the accuracy of the posture is determined. And it is implemented so that users can check their posture through Kinect's RGB camera. That is, if the user's posture is correct, the skeleton information is displayed as a green line, and if it is not correct, the inaccurate part is displayed as a red line to inform intuitively. Through this application, the user receives feedback on the accuracy of the exercise position, so he can exercise himself in the correct position. This application classifies the exercise area into three areas: neck, waist, and leg, and increases the recognition rate of Kinect by excluding positions that Kinect does not recognize due to overlapping joints in the position of each exercise area. And at the end of the application, the last exercise is shown as an image for 5 seconds to inspire a sense of accomplishment and to continuously exercise.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.15 no.3
• /
• pp.157-166
• /
• 2013

Features of the Occult Culture is preferred that powers, demons, magic, magical, unreal etc. Currently Occultism is getting a lot of attention to the public in the society, culture, arts and the play. Fashion in the period that includes all circumstances is a field. Thus, the current Occultism and modern fashion will also be related. Objective of the study is to figure out the form and meaning of Occultism in Contemporary Fashion. An example of the best of contemporary trends is the mass media, For this reason, Occultism symptoms range of case studies mess media(television programs and film). Research on contemporary fashion range was used 2000-2013 fashion collection extracted from the data. Represented in the mess media features of occultism is 'Witchcraft and Sorcery' and 'Death and Horror'. They are story of wizard exorcism and unnatural horror. In the 21st century, modern people are enjoying occultism, and occultism is the one of the entertainment. Expressed in contemporary fashion features of occultism is 'Super-human organism', that is out of the human body, ignoring body shape and type of transformed organism. Second distinction is 'Ghost', they are something like the dark and dismal, shape of ghosts and look pale. Third distinction is 'Neo-Macabre', it is the shape of the skeleton. Skeleton symbolizing the end of life, skeleton to express Occultism has emerged as the most representative motifs in the 21st century fashion. Occultism expressed in fashion is a gothic fantasy, because the fashion can be expressed. In addition, people in modern society wants to be against the norms and taboos. The trend Occult-culture is a symbol of the public's desires and needs.

• Applied Chemistry for Engineering
• /
• v.29 no.3
• /
• pp.303-306
• /
• 2018

Methyl 4-formylbenzoate (MFB), a by-product of the DMT production process, which has been disposed, was used as a starting material for the synthesis of six new fluorescent whitening agent's candidates with 4,4'-di((E)-styryl)-1,1'-biphenyl skeleton attached with an aromatic ester, the same as that of the commercial product family. All candidates were synthesized by the reaction of MFB, and its derivatives with tetraethyl biphenyl-4,4'-diylbis(methylene)diphosphonate using Wittig-Horner reaction. UV spectra for all candidates were recorded and the data were used for calculating the molar absorptivity in order to confirm the usability as a fluorescent whitening agent. All of them showed overall molar extinction coefficients (log ${\varepsilon}$ 4.59~5.00) similar to those of conventional commercial products (log ${\varepsilon}$ 4.85). In particular, compounds 16 and 17 having a dimethoxyphenyl group exhibited a molar extinction coefficient superior to those of conventional commercial products, and thus a field testing for commercialization will be conducted.

• The Korean Journal of Applied Statistics
• /
• v.37 no.5
• /
• pp.643-661
• /
• 2024

This study investigates the effectiveness of 3D skeleton data for human action recognition by comparing the classification performance of machine learning and deep learning models. We use the subset of the NTU RGB+D dataset, containing only frontal-view recordings of 40 individuals performing 60 different actions. Our study uses linear discriminant analysis (LDA), support vector machine (SVM), and random forest (RF) as machine learning models, while the deep learning models are hierarchical bidirectional RNN (HBRNN) and semantics-guided neural network (SGN). To evaluate model performance, cross-subject cross-validation is conducted. Our analysis demonstrates that action type significantly impacts model performance. Cluster analysis by action category shows no significant difference in classification performance between machine learning and deep learning models for easily recognizable actions. However, for actions requiring precise differentiation based on frontal-view joint coordinates such as 'clapping' or 'rubbing hands', deep learning models show a higher performance in capturing subtle joint movements compared to machine learning models.

• Journal of Digital Contents Society
• /
• v.15 no.4
• /
• pp.473-480
• /
• 2014

As the use of computer has been popularized these days, an active research is in progress to make much more convenient and natural interface compared to the existing user interfaces such as keyboard or mouse. For this reason, there is an increasing interest toward Microsoft's motion sensing module called Kinect, which can perform hand motions and speech recognition system in order to realize communication between people. Kinect uses its built-in sensor to recognize the main joint movements and depth of the body. It can also provide a simple speech recognition through the built-in microphone. In this paper, the goal is to use Kinect's depth value data, skeleton tracking and labeling algorithm to recognize information about the extraction and movement of hand, and replace the role of existing peripherals using a virtual mouse, a virtual keyboard, and a speech recognition.

• Steel and Composite Structures
• /
• v.22 no.6
• /
• pp.1217-1238
• /
• 2016

Mega composite structure systems have been widely used in high rise buildings in China. Compared to other structures, this type of composite structure systems has a larger cross-section with less weight. Concrete filled steel tubular (CFST) laced column to box-beam connections are gaining popularity, in particular for the mega composite structure system in high rise buildings. To enable a better understanding of the destruction characteristics and aseismic performance of these connections, three different connection types of specimens including single-limb bracing, cross bracing and diaphragms for core area of connections were tested under low cyclic and reciprocating loading. Hysteresis curves and skeleton curves were obtained from cyclic loading tests under axial loading. Based on these tested curves, a new trilinear hysteretic restoring force model considering rigidity degradation is proposed for CFST laced column to box-beam connections in a mega composite structure system, including a trilinear skeleton model based on calculation, law of stiffness degradation and hysteresis rules. The trilinear hysteretic restoring force model is compared with the experimental results. The experimental data shows that the new hysteretic restoring force model tallies with the test curves well and can be referenced for elastic-plastic seismic analysis of CFST laced column to composite box-beam connection in a mega composite structure system.

• Structural Engineering and Mechanics
• /
• v.88 no.5
• /
• pp.501-519
• /
• 2023

This paper introduces a new hybrid structural connection joint that combines shear walls with section steel beams, fundamentally resolving the construction complexity issue of requiring pre-embedded connectors in the connection between shear walls and steel beams. Initially, a quasi-static loading scheme with load-deformation dual control was employed to conduct low-cycle repeated loading experiments on five new connection joints. Data was acquired using displacement and strain gauges to compare the energy dissipation coefficients of each specimen. The destruction process of the new connection joints was meticulously observed and recorded, delineating it into three stages. Hysteresis curves and skeleton curves of the joint specimens were plotted based on experimental results, summarizing the energy dissipation performance of the joints. It's noteworthy that the addition of shear walls led to an approximate 17% increase in the energy dissipation coefficient. The energy dissipation coefficients of dog-bone-shaped connection joints with shear walls and cover plates reached 2.043 and 2.059, respectively, exhibiting the most comprehensive hysteresis curves. Additionally, the impact of laminated steel plates covering composite concrete floors on the stiffness of semi-rigid joint ends under excessive stretching should not be disregarded. A comparison with finite element analysis results yielded an error of merely 2.2%, offering substantial evidence for the wide-ranging application prospects of this innovative joint in seismic performance.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.10
• /
• pp.129-135
• /
• 2024

In this paper, we design and implement a worker musculoskeletal assessment platform. The three core components of this platform are the Mobile App, the Modeling Server, and the Web Platform. The Mobile App is an Android application developed in Kotlin, targeting Android platform 12 (S) and Android API Level 31 devices. The app utilizes the camera to capture various worker motion data and transmits it to the Modeling Server. The Modeling Server is implemented using Node.js. This server converts the worker's motion data-such as points, skeleton, and x, y, z coordinate data, measured by the mobile app-into multidimensional arrays. It then applies machine learning frameworks like TensorFlow and Keras to predict the worker's posture. The worker posture learning model is built using Teachable Machine. The Web Platform is developed using React and visualizes the worker's movements as 3D animations along a timeline. The machine learning-based worker musculoskeletal assessment platform developed in this paper aims to contribute to minimizing musculoskeletal disorders in workers at industrial sites.