• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.530-535
• /
• 2002

Pneumatic control system has been applied to build many industrial automation systems. But most of them are sequence control type because of their low costs, safety, reliability, etc. Pneumatic servo system is rarely applied to real industrial fields because accurate position control is very difficult due to its nonlinearity and compressibility of air. In pneumatic servo control system, a pneumatic servo valve can be applied, But it is very expensive and has no advantage of low cost compared with a common pneumatic system. This paper is concerned with the accurate position control of a rodless pneumatic cylinder using on/off solenoid valve. A novel Intelligent Modified Pulse Width Modulation(MPWM) is newly proposed. The control performance of this pneumatic cylinder depends on the external loads. To overcome this problem, switching of control parameter using artificial neural network is newly proposed, which estimates external loads on rodless pneumatic cylinder using this training neural network. As an underlying controller, a state feedback controller using position, velocity and acceleration is applied in the switching control the system. The effectiveness of the proposed control algorithms are demonstrated through experiments nth various loads.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.4
• /
• pp.505-510
• /
• 2005

The RPO(randomized policy optimizer) algorithm, which utilizes probabilistic policy for the action selection, is a recently developed tool in the area of reinforcement learning, and has been shown to be very successful in several application problems. In this paper, we propose a modified RPO algorithm, whose critic network is adapted via RLS(Recursive Least Square) algorithm. In order to illustrate the applicability of the modified RPO method, we applied the modified algorithm to Kimura's robot and observed very good performance. We also developed a MATLAB-based animation program, by which the effectiveness of the training algorithms on the acceleration or the robot movement were observed.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.23 no.6
• /
• pp.615-622
• /
• 2015

Recently Digital-TachoGraph(DTG) was mounted mandatorily in commercial vehicles(Taxi, Bus, etc.). DTG records accurate and detailed information of the running state of vehicles related to traffic accident, such as Time, Distance, Velocity, RPM, Brake ON/OFF, GPS, Azimuth, Acceleration. Thus those standardized data can play an important role in traffic accident investigation and reconstruction. To develope the accurate and objective method using the DTG data for the reconstruction of traffic accident, we had conducted several tests such as driving test, high speed circuit test, braking test, slalom test at Korea Automobile Testing & Research Institute(KATRI), and collision test at Korea Automobile insurance repair Research and Training center(KART) with the vehicle equipped with several DTG. Development of the program which enables the reading and analysis of the DTG data was followed. In the experiments, we have found velocity error, RPM error, brake signal error and azimuth error in several products, and also non-continuous event data. The cause of these errors was deduced to be related to the correction factor, the durability of electronic parts and the algorithm.

• Journal of Korean Academy of Nursing
• /
• v.49 no.5
• /
• pp.562-574
• /
• 2019

Purpose: The purpose of this study was to identify the response patterns of nursing unit managers regarding workplace bullying. Methods: Q methodology was used to identify the response patterns. Thirty-six Q samples were selected from the Q population of 210 that included literature reviews and in-depth interviews with clinical nurses and nursing managers. Participants were 30 nursing unit managers who had experience managing workplace bullying and they classified the Q samples into a normal distribution frame measured on a nine-point scale. The data were analyzed using the PC-QUANL program. Results: Five types of response patterns were identified: (1) sympathetic-understanding acceleration, (2) harmonious-team approach, (3) preventive-organizational management, (4) passive observation, and (5) leading-active intervention. The preventive-organizational management type was most frequently used by the nursing unit managers. Conclusion: The results of this study indicated that nursing unit managers attempted to prevent and solve workplace bullying in various ways. Therefore, it is necessary to develop and conduct leadership training and intervention programs that appropriately address the response patterns of nursing unit managers, such as those identified in this study.

• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.53-69
• /
• 2011

Vision and voice-based technologies are commonly utilized for human-robot interaction. But it is widely recognized that the performance of vision and voice-based interaction systems is deteriorated by a large margin in the real-world situations due to environmental and user variances. Human users need to be very cooperative to get reasonable performance, which significantly limits the usability of the vision and voice-based human-robot interaction technologies. As a result, touch screens are still the major medium of human-robot interaction for the real-world applications. To empower the usability of robots for various services, alternative interaction technologies should be developed to complement the problems of vision and voice-based technologies. In this paper, we propose the use of accelerometer-based gesture interface as one of the alternative technologies, because accelerometers are effective in detecting the movements of human body, while their performance is not limited by environmental contexts such as lighting conditions or camera's field-of-view. Moreover, accelerometers are widely available nowadays in many mobile devices. We tackle the problem of classifying acceleration signal patterns of 26 English alphabets, which is one of the essential repertoires for the realization of education services based on robots. Recognizing 26 English handwriting patterns based on accelerometers is a very difficult task to take over because of its large scale of pattern classes and the complexity of each pattern. The most difficult problem that has been undertaken which is similar to our problem was recognizing acceleration signal patterns of 10 handwritten digits. Most previous studies dealt with pattern sets of 8~10 simple and easily distinguishable gestures that are useful for controlling home appliances, computer applications, robots etc. Good features are essential for the success of pattern recognition. To promote the discriminative power upon complex English alphabet patterns, we extracted 'motion trajectories' out of input acceleration signal and used them as the main feature. Investigative experiments showed that classifiers based on trajectory performed 3%~5% better than those with raw features e.g. acceleration signal itself or statistical figures. To minimize the distortion of trajectories, we applied a simple but effective set of smoothing filters and band-pass filters. It is well known that acceleration patterns for the same gesture is very different among different performers. To tackle the problem, online incremental learning is applied for our system to make it adaptive to the users' distinctive motion properties. Our system is based on instance-based learning (IBL) where each training sample is memorized as a reference pattern. Brute-force incremental learning in IBL continuously accumulates reference patterns, which is a problem because it not only slows down the classification but also downgrades the recall performance. Regarding the latter phenomenon, we observed a tendency that as the number of reference patterns grows, some reference patterns contribute more to the false positive classification. Thus, we devised an algorithm for optimizing the reference pattern set based on the positive and negative contribution of each reference pattern. The algorithm is performed periodically to remove reference patterns that have a very low positive contribution or a high negative contribution. Experiments were performed on 6500 gesture patterns collected from 50 adults of 30~50 years old. Each alphabet was performed 5 times per participant using $Nintendo{(R)}$ $Wii^{TM}$ remote. Acceleration signal was sampled in 100hz on 3 axes. Mean recall rate for all the alphabets was 95.48%. Some alphabets recorded very low recall rate and exhibited very high pairwise confusion rate. Major confusion pairs are D(88%) and P(74%), I(81%) and U(75%), N(88%) and W(100%). Though W was recalled perfectly, it contributed much to the false positive classification of N. By comparison with major previous results from VTT (96% for 8 control gestures), CMU (97% for 10 control gestures) and Samsung Electronics(97% for 10 digits and a control gesture), we could find that the performance of our system is superior regarding the number of pattern classes and the complexity of patterns. Using our gesture interaction system, we conducted 2 case studies of robot-based edutainment services. The services were implemented on various robot platforms and mobile devices including $iPhone^{TM}$. The participating children exhibited improved concentration and active reaction on the service with our gesture interface. To prove the effectiveness of our gesture interface, a test was taken by the children after experiencing an English teaching service. The test result showed that those who played with the gesture interface-based robot content marked 10% better score than those with conventional teaching. We conclude that the accelerometer-based gesture interface is a promising technology for flourishing real-world robot-based services and content by complementing the limits of today's conventional interfaces e.g. touch screen, vision and voice.

• Korean Journal of Veterinary Research
• /
• v.39 no.6
• /
• pp.1081-1090
• /
• 1999

To establish the protocol of a standardized exercise test for evaluating exercise intolerance and degree of fitness in Thoroughbred racehorses, we examined serum lactate concentrations related to exercise intensities using the high speed treadmill. Twelve clinically healthy Thoroughbred racehorses with or without previous training or racing history were assigned to two gorups, fit and unfit group, respectively. The protocol used for the standardized exercise test was consisted of two stages : stage of warm-up and that of acceleration. During the warm-up, the horses exercised 5 min at 1.8m/s and 3 min 3.4m/s without inclination. At the acceleration stage, exercise test was performed at 10% slope and the speed was increased from the initial 5m/s to the maximal speed which each tested horse could keep up with. The speed was increased with incremental steps of 1 m/s every minute. During the last 15 sec of each step, blood samples were collected for serum lactate determination. $V_{max}$(maximal treadmill speed which tested horses could keep up with) of the fit group ($10.93{\pm}0.33m/s$, mean${\pm}$SE, n = 6) was higher than that of the unfit group ($9.52{\pm}0.23m/s$, mean${\pm}$SE, n = 6). Serum lactate concentrations increased exponentially according to exercise intensities. $V_{La4}$(speed producing a serum lactate concentration of 4mmol/l) of the fit group, $6.45{\pm}0.26m/s$, was higher than that of the unfit group, $5.45{\pm}0.23m/s$. $La_{peak}$(peak plasma lactate concentration during the exercise test) was lower in the fit group ($20.34{\pm}1.62mmol/l$ at 1 min after maximal intensity exercise) than in the unfit group ($24.78{\pm}1.09mmol/l$ at 2 min after maximal exercise step). $t_{50%}$(time required for the recovery of lactate concentration to be one-half of $La_{peak}$ after maximal exercise) of the unfit group and the fit group were 40.0 and 18.0 min, respectively. Therefore, the protocol of the incremental standardized exercise test utilized in this study seems to be reliable for the assessment of fitness and exercise intolerance for the Thoroughbred racehorses.

• Smart Structures and Systems
• /
• v.29 no.4
• /
• pp.625-640
• /
• 2022

Maglev rail joints are vital components serving as connections between the adjacent F-type rail sections in maglev guideway. Damage to maglev rail joints such as bolt looseness may result in rough suspension gap fluctuation, failure of suspension control, and even sudden clash between the electromagnets and F-type rail. The condition monitoring of maglev rail joints is therefore highly desirable to maintain safe operation of maglev. In this connection, an online damage detection approach based on three-dimensional (3D) convolutional neural network (CNN) and time-frequency characterization is developed for simultaneous detection of multiple damage of maglev rail joints in this paper. The training and testing data used for condition evaluation of maglev rail joints consist of two months of acceleration recordings, which were acquired in-situ from different rail joints by an integrated online monitoring system during a maglev train running on a test line. Short-time Fourier transform (STFT) method is applied to transform the raw monitoring data into time-frequency spectrograms (TFS). Three CNN architectures, i.e., small-sized CNN (S-CNN), middle-sized CNN (M-CNN), and large-sized CNN (L-CNN), are configured for trial calculation and the M-CNN model with excellent prediction accuracy and high computational efficiency is finally optioned for multiple damage detection of maglev rail joints. Results show that the rail joints in three different conditions (bolt-looseness-caused rail step, misalignment-caused lateral dislocation, and normal condition) are successfully identified by the proposed approach, even when using data collected from rail joints from which no data were used in the CNN training. The capability of the proposed method is further examined by using the data collected after the loosed bolts have been replaced. In addition, by comparison with the results of CNN using frequency spectrum and traditional neural network using TFS, the proposed TFS-CNN framework is proven more accurate and robust for multiple damage detection of maglev rail joints.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.179-188
• /
• 2024

Recently, unmanned terminals (kiosks) have greatly increased their scope of use by allowing orders or payments to be made efficiently while replacing existing manpower. With the acceleration of digital transformation, the rate of kiosk installations has soared, making it an important task to help all age groups easily use kiosks. In this study, based on the function of the game engine and Hand Tracking technology, we developed content that can conduct kiosk education in a virtual world. The goal of this content is to help users unfamiliar with kiosks confidently cope with real-world situations by experiencing visual and auditory stress caused by waiting guests in virtual reality. To this end, two VR contents were developed. One is a simple kiosk experience content, and the other is specialized content that causes visual and auditory stress. The experiment was divided into two groups: one group experienced general VR content, while the other group experienced specialized VR content. After the experience, both groups proceeded to place orders in an actual store. Survey results showed that 85% of the experimental group and 95% of the control group were satisfied with the training. This confirms that the specialized experience described in this paper is effective for kiosk education.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.18 no.3
• /
• pp.239-247
• /
• 2008

Low back disorders (LBDs) have been the most common musculoskeletal problem in Korean workplaces. It affects many workers, and is associated with high costs to many companies as well as the individual, which can negatively influence even the quality of life of workers. The _evaluation of low back disorder risk associated with manual materials handling tasks can be performed using variety of ergonomic assessment tools such as National Institute for Occupational Safety and Health (NIOSH) Revised Lifting Equation (NLE), the Washington Administrative Code 296-62-0517 (WAC), the Snook Tables etc. But most of these tools provide limited information for choosing the most appropriate assessment method for a particular job and in finding out advantage and disadvantage of the methods, and few have been assessed for their predictive ability. The focus of this study was to _evaluate spinal loads in real time with lifting and pulling heavy cow leathers in variety of postures. Data for estimating mean trunk motions were collected as employees did their work at the job site, using the Lumbar Motion Monitor. Eight employees (2 males, 6 females) were selected in this study, in which the load weight and the vertical start and destination heights of the activity remained constant throughout the task. Variance components (three dimensional spaces) of mean trunk kinematic measures were estimated in a hierarchical design. They were used to compute velocity and acceleration of multiple employees performing the same task and to repetitive movements within a task. Therefore, a results of this study could be used as a quantitative, objective measure to design the workplace so that the risk of occupationally related low back disorder should be minimized.

• Journal of Korea Game Society
• /
• v.2 no.1
• /
• pp.16-22
• /
• 2002

After that Internet was introduced to Korea, Web page has developed from text centered to graphic-centered at its fist stage. At the present, it is improving to a design for users. Furthermore, with the acceleration of Information super-highway construction and generalization of basic technology for multi-media, the educational environment has transformed to demander-focused and internet basis service which transcends time and space. Consequently, the educational structure is converting from instructors unilateral lead to student-centered. Additionally, the common usage and digitalization of information have an effect on progress of education quality and cost saving. Although there are plenty of educational web pages on internet, we can notice that many of them are inconvenient for users to put into practice. The reason is that many experts overlook the fundamental which is the basic skill for design and understanding of Web must be accompanied with Web design. Therefore, this thesis will find out the points users should consider for use of Web page and realize the educational web page, reflected for VRML training.