• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.2
• /
• pp.168-175
• /
• 2023

In the era of the 4th Industrial Revolution, Logistic 4.0 using data-based technologies such as IoT, Bigdata, and AI is a keystone to logistics intelligence. In particular, the AI technology such as prognostics and health management for the maintenance of logistics facilities is being in the spotlight. In order to ensure the reliability of the facilities, Time-Based Maintenance (TBM) can be performed in every certain period of time, but this causes excessive maintenance costs and has limitations in preventing sudden failures and accidents. On the other hand, the predictive maintenance using AI fault diagnosis model can do not only overcome the limitation of TBM by automatically detecting abnormalities in logistics facilities, but also offer more advantages by predicting future failures and allowing proactive measures to ensure stable and reliable system management. In order to train and predict with AI machine learning model, data needs to be collected, processed, and analyzed. In this study, we have develop a system that utilizes an AI detection model that can detect abnormalities of logistics rotational equipment and diagnose their fault types. In the discussion, we will explain the entire experimental processes : experimental design, data collection procedure, signal processing methods, feature analysis methods, and the model development.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.685-691
• /
• 2020

In this study, an algorithm that recognizes numbers from 0 to 9 was developed using the data obtained after tracking hand movements using the echo signal of a millimeter-wave radar sensor at 77 GHz. The echo signals obtained from the radar sensor by detecting the motion of a hand gesture revealed a cluster of irregular dots due to the difference in scattering cross-sectional area. A valid center point was obtained from them by applying a K-Means algorithm using 3D coordinate values. In addition, the obtained center points were connected to produce a numeric image. The recognition rate was compared by inputting the obtained image and an image similar to human handwriting by applying the smoothing technique to a CNN (Convolutional Neural Network) model trained with MNIST (Modified National Institute of Standards and Technology database). The experiment was conducted in two ways. First, in the recognition experiments using images with and without smoothing, average recognition rates of 77.0% and 81.0% were obtained, respectively. In the experiment of the CNN model with augmentation of learning data, a recognition rate of 97.5% and 99.0% on average was obtained in the recognition experiment using the image with and without smoothing technique, respectively. This study can be applied to various non-contact recognition technologies using radar sensors.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.2
• /
• pp.39-49
• /
• 2002

This paper proposes the MAWUPC (Motion Adaptive Weighted Unmatched Pixel Count) algorithm to track multiple objects of similar color The MAWUPC algorithm has the new method that combines color and motion effectively. We apply the MAWUPC algorithm to face and hand tracking against complex background in an image sequence captured by using single camera. The MAWUPC algorithm is an improvement of previously proposed AWUPC (Adaptive weighted Unmatched Pixel Count) algorithm based on the concept of the Moving Color that combines effectively color and motion information. The proposed algorithm incorporates a color transform for enhancing a specific color, the UPC(Unmatched Pixel Count) operation for detecting motion, and the discrete Kalman filter for reflecting motion. The proposed algorithm has advantages in reducing the bad effect of occlusion among target objects and, at the same time, in rejecting static background objects that have a similar color to tracking objects's color. This paper shows the efficiency of the proposed MAWUPC algorithm by face and hands tracking experiments for several image sequences that have complex backgrounds, face-hand occlusion, and hands crossing.

• Clinics in Shoulder and Elbow
• /
• v.11 no.2
• /
• pp.90-95
• /
• 2008

Purpose: We wanted to assess the accuracy of ultrasound for detecting abnormality of the long head of the biceps tendon in patients with rotator cuff disorders. Materials and Methods: Between January 2006 and March 2007, we reviewed the arthroscopic findings of biceps tendons in 67 patients with rotator cuff disorder and who underwent ultrasonography pre-operatively. The patients' average age was 58 years and there were 41 males and 26 females. The statuses of the biceps tendons were described as 'normal', 'dislocation', 'subluxation', 'partial or complete tears', and 'tendinopathy'. We investigated the correspondence between the arthroscopic and ultrasonographic findings. Results: On ultrasonography, the biceps tendons were 'normal' in 37 patients and 'abnormal' in 30 patients. On arthroscopy, 5 biceps tendons turned out to have partial tears, which were 'normal' on ultrasonography. On the other hand, 8 biceps tendons were 'normal' which were 'abnormal' on ultrasonography. Three dislocations and 4 complete tears of biceps tendons were identified on arthroscopy, and all of them were detected by ultrasonography. Of the 20 cases of 'tendinopathy' seen on ultrasonography, 15 patients had partial tears and the remaining 5 patients were normal on arthroscopy. Conclusion: Ultrasonography is accurate for detecting some biceps pathologies, such as dislocation or complete tear, but it is not accurate for the detection of partial tear.

• Science of Emotion and Sensibility
• /
• v.14 no.4
• /
• pp.627-636
• /
• 2011

The purpose of this study is to develop the multi-modal interaction system. This system provides realistic and an immersive experience through multi-modal interaction. The system recognizes user behavior, intention, and attention, which overcomes the limitations of uni-modal interaction. The multi-modal interaction system is based upon gesture interaction methods, intuitive gesture interaction and attention evaluation technology. The gesture interaction methods were based on the sensors that were selected to analyze the accuracy of the 3-D gesture recognition technology using meta-analysis. The elements of intuitive gesture interaction were reflected through the results of experiments. The attention evaluation technology was developed by the physiological signal analysis. This system is divided into 3 modules; a motion cognitive system, an eye gaze detecting system, and a bio-reaction sensing system. The first module is the motion cognitive system which uses the accelerator sensor and flexible sensors to recognize hand and finger movements of the user. The second module is an eye gaze detecting system that detects pupil movements and reactions. The final module consists of a bio-reaction sensing system or attention evaluating system which tracks cardiovascular and skin temperature reactions. This study will be used for the development of realistic digital entertainment technology.

• Korean Journal of Remote Sensing
• /
• v.34 no.2_2
• /
• pp.431-437
• /
• 2018

We analyzed the feasibility of detecting wave gliders moving on the sea surface using SAR images. For the experiment, a model was constructed and placed on the sea using a towing ship before and after the satellite observation time. In the acquisition of KOMPSAT-5 image, high resolution SAR data of spotlight mode was collected considering the small size of wave glider. As a result of the backscattering intensity analysis around the towing ship along with wave glider, several scattering points away from the ship were observed, which are not strong but clearly distinguished from the surrounding clutter values. Considering the distance from the center of the ship, it seems to be a signal by the wave glider. On the other hand, it is confirmed that the wave glider can be detected even at the very low false alarm rate ($10^{-6}$) of the target detection using CFAR. Although the scatter signal by the wave glider could be distinguished from the surrounding ocean clutter in the high resolution SAR image, further research is needed to determine if actual wave gliders are detected in various marine environments.

• The Korean Journal of Nuclear Medicine
• /
• v.38 no.4
• /
• pp.288-293
• /
• 2004

Purpose: increased uptake of wrist and hand joints in three phase bone scintigraphy (TPBS) have been used in the detection of reflex sympathetic dystrophy syndrome (RSDS). TPBS frequently shows increased shoulder uptake in the hemiplegic RSDS patients. We investigated the significance of the shoulder uptake in the detection of these patients. Materials and Methods: Twenty three patients who had hemiplegia due to brain stroke and diagnosed as RSD were enrolled in this study (M:F=16:7, R:L=11:12). The mean age was $63{\pm}10$ yrs. Ter normal volunteer (mean age: $60{\pm}5$, M:F=1:9) data was used as control group. TPBS was performed $59{\pm}32$ days after stoke (acute stage). We obtained the count ratios of bilateral hands by drawing a region of interest (ROI) in three phase images and compared to the count ratios of shoulders in the delayed image. Hand ROI included an ipsilateral wrist. Sensitivity of detecting the affected limb was defined using the right/left count ratio of normal control. Results: Sensitivities using count ratios of hand blood flow, blood pool and delayed image were 45%, 76% and 78%, respectively. Sensitivity of shoulder count ratio was 74%. Log of right/left counts of hand delayed image and that of shoulder delayed image were correlated well with statistical significance (Spearman's R=0.824, p<0.001). Conclusion: Shoulder uptake showed good correlation with hand uptake in the delayed image of TPBS. Shoulder uptake maybe helpful in the diagnosis of reflex sympathetic dystrophy syndrome in patients with hemiplegia.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.11
• /
• pp.151-159
• /
• 2016

This paper proposes a ceramic heating element-based tankless instant electric water heater for hand/face washing that does not require a lot of hot water. The heating module, which heats the input water and outputs hot water, operates the ceramic heating element detecting input water using a flow sensor. Inside of the heating module is designed to form one flow path in order to get almost $15^{\circ}C$ increased heated water compared to the input water temperature within 2 second after 1.5 liter per minute water supply. The design validity is verified using a heat flow analysis of the water flow and temperature variations inside of the heating module also. Based on the design data, the heating module is constructed including a single rod-type ceramic heating element. After that, a prototype system having temperature setting function by three steps were constructed. The prototype system is connected to a 1.5 liter per minute water supply line, and the water output temperature and time measurement experiments confirmed that the proposed system output the heated water increased by $18.3^{\circ}C$ in case of third step setting within 2 second after water supply. And standby power is under 1 W and peak power does not exceed the permissible range for the general house usage. Several performance results verify that the proposed tankless instant electric water heater is applicable for the washstand of the house, highway rest area and factory so on as winter-time hand/face washing.

• Korean Journal of Cognitive Science
• /
• v.23 no.2
• /
• pp.185-204
• /
• 2012

A three factor experiment was conducted to explore the effects of giving prompts and asking for self explanation and the modulating effect of the need for cognition (NC) on the two interventions. The effects of giving prompts and asking for self explanation were different depending on the task and the level of need for cognition. Participants of low NC conditions showed the prompt effect and the self explanation effect in the memory tests. On the other hand, participants in the high NC conditions performed better in the comprehension test when they were given prompts and were asked to self explain. However, high NC participants performed worse when they were asked to self explain without providing the prompts. The results were interpreted to suggest the importance of detecting the right parts in getting the self explanation effect.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.3
• /
• pp.61-69
• /
• 2010

This paper presents an efficient object selection algorithm by analyzing and detecting of human activity. Generally, when people point any something, they will put a face on the target direction. Therefore, the direction of the face and fingers and was ordered to be connected to a straight line. At first, in order to detect the moving objects from the input frames, we extract the interesting objects in real time using background subtraction. And the judgment of movement is determined by Principal Component Analysis and a designated time period. When user is motionless, we estimate the user's indication by estimation in relation to vector from the head to the hand. Through experiments using the multiple views, we confirm that the proposed algorithm can estimate the movement and indication of user more efficiently.