• ETRI Journal
• /
• v.42 no.1
• /
• pp.78-89
• /
• 2020

Human activity recognition (HAR) has become effective as a computer vision tool for video surveillance systems. In this paper, a novel biometric system that can detect human activities in 3D space is proposed. In order to implement HAR, joint angles obtained using an RGB-depth sensor are used as features. Because HAR is operated in the time domain, angle information is stored using the sliding kernel method. Haar-wavelet transform (HWT) is applied to preserve the information of the features before reducing the data dimension. Dimension reduction using an averaging algorithm is also applied to decrease the computational cost, which provides faster performance while maintaining high accuracy. Before the classification, a proposed thresholding method with inverse HWT is conducted to extract the final feature set. Finally, the K-nearest neighbor (k-NN) algorithm is used to recognize the activity with respect to the given data. The method compares favorably with the results using other machine learning algorithms.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.333-337
• /
• 2017

본 논문에서는 개체명 인식과 언어 모델의 다중 학습을 이용한 한국어 개체명 인식 방법을 제안한다. 다중 학습은 1 개의 모델에서 2 개 이상의 작업을 동시에 분석하여 성능 향상을 기대할 수 있는 방법이지만, 이를 적용하기 위해서 말뭉치에 각 작업에 해당하는 태그가 부착되어야 하는 문제가 있다. 본 논문에서는 추가적인 태그 부착 없이 정보를 획득할 수 있는 언어 모델을 개체명 인식 작업과 결합하여 성능 향상을 이루고자 한다. 또한 단순한 형태소 입력의 한계를 극복하기 위해 입력 표상을 자소 및 형태소 품사의 임베딩으로 확장하였다. 기계 학습 방법은 순차적 레이블링에서 높은 성능을 제공하는 Bi-directional LSTM CRF 모델을 사용하였고, 실험 결과 언어 모델이 개체명 인식의 오류를 효과적으로 개선함을 확인하였다.

• Journal of the Korean Society of Industry Convergence
• /
• v.21 no.1
• /
• pp.17-27
• /
• 2018

We propose a new approach to control a biped robot motion based on iterative learning of voice command for the implementation of smart factory. The real-time processing of speech signal is very important for high-speed and precise automatic voice recognition technology. Recently, voice recognition is being used for intelligent robot control, artificial life, wireless communication and IoT application. In order to extract valuable information from the speech signal, make decisions on the process, and obtain results, the data needs to be manipulated and analyzed. Basic method used for extracting the features of the voice signal is to find the Mel frequency cepstral coefficients. Mel-frequency cepstral coefficients are the coefficients that collectively represent the short-term power spectrum of a sound, based on a linear cosine transform of a log power spectrum on a nonlinear mel scale of frequency. The reliability of voice command to control of the biped robot's motion is illustrated by computer simulation and experiment for biped walking robot with 24 joint.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.8
• /
• pp.9-16
• /
• 2018

In this paper, a kidnapping detection scheme in which human pose estimation is used to classify accurately between kidnapping cases and normal ones is proposed. To estimate human poses from input video, human's 10 joint information is extracted by OpenPose library. In addition to the features which are used in the previous study to represent the size change rates and the regularities of human activities, the human pose estimation features which are computed from the location of detected human's joints are used as the features to distinguish kidnapping situations from the normal accompanying ones. A frame-based kidnapping detection scheme is generated according to the selection of J48 decision tree model from the comparison of several representative classification models. When a video has more frames of kidnapping situation than the threshold ratio after two people meet in the video, the proposed scheme detects and notifies the occurrence of kidnapping event. To check the feasibility of the proposed scheme, the detection accuracy of our newly proposed scheme is compared with that of the previous scheme. According to the experiment results, the proposed scheme could detect kidnapping situations more 4.73% correctly than the previous scheme.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.1
• /
• pp.215-226
• /
• 2016

Modeling, control and implementation of a real redundant robot with five Degrees Freedom (DOF) of the SCARA (Selective Compliant Assembly Robot Arm) manipulator type is presented. Through geometric methods and structural and functional considerations, the inverse kinematics for redundant robot can be obtained. By means of a modification of the classical sliding mode control law through a hyperbolic function, we get a new algorithm which enables reducing the chattering effect of the real actuators, which together with the learning and adaptive controllers, is applied to the model and to the real robot. A simulation environment including the actuator dynamics is elaborated. A 5 DOF robot, a communication interface and a signal conditioning circuit are designed and implemented for feedback. Three control laws are executed in: a simulation structure (together with the dynamic model of the SCARA type redundant manipulator and the actuator dynamics) and a real redundant manipulator of the SCARA type carried out using MatLab/Simulink programming tools. The results, obtained through simulation and implementation, were represented by comparative curves and RMS indices of the joint errors, and they showed that the redundant manipulator, both in the simulation and the implementation, followed the test trajectory with less pronounced maximum errors using the adaptive controller than the other controllers, with more homogeneous motions of the manipulator.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2003.11a
• /
• pp.1251-1258
• /
• 2003

This paper is a study on the pedal placement and driving position of forklift according to the various body dimensions. Comfortable driving position were measured angles of joint(ankle, knee, hip) by Goniometer. From SIP(seat index point) to basis of pedals were measured about X and Y axises. In addition, Z axises were gauged between floor and pedals. In this paper, The 27 male subjects with no experience in driving forklift were measured in the test in order to exclusion of learning effect. Therefore the subjects have a preference for pedal location to the body dimensions, if as long as their body dimensions was very long, they would required each pedal's location of Y axis to increase. However, driving position is no influence. The pedal location of X and Z axises weren't related with various body dimensions and subjects have symmetrical location to the pedals of inching and break and hight of brake pedal is lower than the others. They hope that brake pedal is lower than others.

• Knowledge Management Research
• /
• v.17 no.2
• /
• pp.75-101
• /
• 2016

Since 2009, China has become biggest automobile supplier and consumer all over the world. Chinese government and automobile firms have been executed strategic and aggressive industry policy and business strategy for nurturing automobile industry as a core manufacturing industry. However, can we assure that all of these policy and strategy have positive effect on Chinese automobile industry? For fulfilling this gab, our research examined the government policy and firm's strategy in different development stage of Chinese automobile industry. According to research result, at initial stage(1983-1996), Chinese automobile industry has grown by technological learning and reverse engineering from Soviet Union, Japan and Germany. In rapid growing stage(1996-2009), Chinese automobile firms have succeed to develop and produce own brand product with 100% own technology. And this kind of quantum jump in technology development was conducted by joint venture policy and M&A strategy. However, at the fourth stage(2010-), Chinese government and firms have over invested and focused on Electric Vehicle manufacturing without developing core technology or SW. Overall, the old-fashioned policy and strategy module in manufacturing industry of China could have negative effect on its industry development.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.1
• /
• pp.153-158
• /
• 2020

The study aims to identify the factors affecting employee loyalty in the case of small and medium enterprises (SMEs) in Tra Vinh province, Viet Nam and to find out critical factors affecting the loyalty of employees in SMEs. This is implemented with the method of collecting primary data of 320 employees working at SMEs in 5 districts including: Cau Ngang, Tra Cu, Chau Thanh, Cang Long, Tieu Can) and Tra Vinh City, Viet Nam. Using the multivariate regression method, the researchers have found 6 factors affecting employee loyalty: colleagues, leaders, job characteristics, remuneration policies, organizational culture, and working environment. Particularly, learning opportunities may not be not statistically significant for employees' loyalty towards small and medium-sized enterprises in Tra Vinh province. From the above research results, the authors have proposed implicational piolicies such as: focusing on colleague relationships, improving leadership of business owners, attaching importance to appropriate work arrangement, having appropriate remuneration policies for laborers, building effective organizational culture and working environment to improve employee loyalty at SMEs. From the above policy implications, helping business owners realize the aspirations of workers in small and medium-sized enterprises more closely in the future, in order to sustainably develop the business system in Vietnam.

• Journal of the Korean Institute of Navigation
• /
• v.23 no.2
• /
• pp.1-9
• /
• 1999

A trailer truck is a major equipment for transporting containers, and its driving is difficult due to two degrees of freedom which exist in the joint part between truck and trailer. Especially Backing a trailer truck to a parking home is a difficult exercise for all but the most skilled truck drivers. Normal driving instincts lead to erroneous movements. When watching a truck driver backing toward a parking home, one often observes the driver backing, going forward, backing again, going forward, etc., and finally backing to the desired position along the parking home. This paper discusses the design of the controller to control the steering of a trailer truck while only backing up to a parking home from an initial position. In this paper, we propose a backing up control system for a container trailer truck using fuzzy theory where the primitive fuzzy control rules are macroscopically designed using an expert's knowledge, and the control rules are regulated by LIBL(Linguistic Instruction Based Learning) to enable to back up successfully the trailer tuck to a parking home from arbitrary initial position. The validity of the proposed parking control system is shown by applying it to some initial positions on the simulator for container trailer truck.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.6
• /
• pp.238-245
• /
• 2013

Gesture recognition has been widely one of the research areas for natural user interface. This paper presents a novel gesture recognition method using tree classification and multiclass SVM(Support Vector Machine). In the learning step, 3D trajectory of human gesture obtained by a Kinect sensor is classified into the tree nodes according to their distributions. The gestures are resampled and we obtain the histogram of the chain code from the normalized data. Then multiclass SVM is applied to the classified gestures in the node. The input gesture classified using the constructed tree is recognized with multiclass SVM.