• Smart Structures and Systems
• /
• v.31 no.5
• /
• pp.485-500
• /
• 2023

Machine learning-based structural health monitoring (ML-based SHM) methods are researched extensively in the recent decade due to the availability of advanced information and sensing technology. ML methods are well-known for their pattern recognition capability for complex problems. However, the main obstacle of ML-based SHM is that it often requires pre-collected historical data for model training. In most actual scenarios, damage presence can be detected using the unsupervised learning method through anomaly detection, but to further identify the damage types would require prior knowledge or historical events as references. This creates the cold-start problem, especially for new and unobserved structures. Modal-based methods identify damages based on the changes in the structural global properties but often require dense measurements for accurate results. Therefore, a two-stage hybrid modal-machine learning damage detection scheme is proposed. The first stage detects damage presence using Principal Component Analysis-Frequency Response Function (PCA-FRF) in an unsupervised manner, whereas the second stage further identifies the damage. To solve the cold-start problem, mode shape assessment using the first mode is initiated when no trained model is available yet in the second stage. The damage identified by the modal-based method would be stored for future training. This work highlights the performance of the scheme in alleviating the cold-start issue as it transitions through different phases, starting from zero damage sample available. Results showed that single and multiple damages can be identified at an acceptable accuracy level even when training samples are limited.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.137-147
• /
• 2023

LiDAR is used in autonomous driving and various industrial fields to measure the size and distance of an object. In addition, the sensor also provides intensity images based on the amount of reflected light. This has a positive effect on sensor data processing by providing information on the shape of the object. LiDAR guarantees higher performance as the resolution increases but at an increased cost. These conditions also apply to LiDAR intensity images. Expensive equipment is essential to acquire high-resolution LiDAR intensity images. This study developed artificial intelligence to improve low-resolution LiDAR intensity images into high-resolution ones. Therefore, this study performed parameter analysis for the optimal super-resolution neural network model. The super-resolution algorithm was trained and verified using 2,500 LiDAR intensity images. As a result, the resolution of the intensity images were improved. These results can be applied to the autonomous driving field and help improve driving environment recognition and obstacle detection performance

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1379-1386
• /
• 2023

In this paper, research was conducted to prevent various safety accidents that may occur from infant carriages carrying children and to make the use of infant carriages easier. In order to prevent the baby car from running without protection, a brake function is installed on the baby car wheels using a pressure sensor and a servo motor. Then, a pressure sensor and LCD are used to determine whether the seat belt is fastened to prevent the child from falling out of the baby car. In addition, it was designed to use LCD and LED to turn on a warning light when the temperature and humidity exceed a certain level, so that infants can be in a comfortable environment when using the baby car.

• The Journal of Industrial Distribution & Business
• /
• v.9 no.5
• /
• pp.83-91
• /
• 2018

Purpose - The purpose of this study is to explore the introduction and activation of smart training for the effective training of vocational ability development of companies in the 4th industrial revolution era, we analyze the present status of smart training introduction and related difficulties and propose concrete activation plan. Research design, data, and methodology - Through the online survey, we tried to confirm the recognition of corporate about smart training. Questionnaires include what are the benefits, expectations, and difficulties of smart training, etc. The survey was conducted from August 21, 2017 to September 4, 2017. A total of 69 companies participated in the questionnaire. The questionnaire results were analyzed through frequency analysis and contents analysis. Based on the results of the questionnaire, we found out the cause of inhibition of smart training activation and suggested activation strategies. Results - The main reason for the provision of smart training is the expectation of the training performance and the recognition that it is possible to provide training in a flexible manner. The effectiveness of smart training operation was evaluated as a high level of contribution to the development of creative training course and the capacity of training institute. As a result of checking factors that hinders the activation of smart training, the most important reason is that the time and cost burden of the training institutes is excessive. The lack of expertise in the design of smart training courses and the burden of employers and trainees. Conclusions - In order to activate smart training, it is necessary to find solutions to the obstacles at the internal or external level of training institutions. The internal barriers to the training organization are lack of internal competence for preparation and course management. In this regard, we need to consider providing consulting, best practices or guidance in the process of designing and operating smart training. On the other hand, as an external obstacle factor, it is necessary to provide incentives to participate in smart training. In addition, further research is needed on strategies that can lead to participation in smart training from the viewpoint of employers and learners.

• The Journal of the Korea Contents Association
• /
• v.21 no.2
• /
• pp.406-420
• /
• 2021

This study used Glaser's grounded theory method for the recognition of college students' majors in counseling psychology. Among the 3rd and 4th grade students majoring in counseling psychology, 19 students participated in the study, focusing on them for 5 months and collecting data through individual interviews. As a result of analyzing the data, 103 concepts, 26 subcategories, 9 upper categories, and 1 core category were derived. As a result of the study, first, the participants wanted to relieve the burden of people's hearts and had the hope of becoming a healer. Second, among the participants, in terms of their personality and aptitude for their major field, they perceived it as joy and satisfaction, such as 'It fits well with the major,' 'I made a good choice,' and 'It became a turning point in life.' However, they also recognized the incompatibility of the major, such as disharmony of aptitude, burden of the role of counselor, and rejection of major. Third, although participants showed usefulness in their major learning, their perception of the career path in their major was acting as anxiety and conflict, but their concerns and conflicts resulted in financial difficulties, poor job conditions, and emotional exhaustion caused by long-term study. The burden of job, fear of counseling job, limit of undergraduate graduation, uncertainty of career, etc. acted as an obstacle in choosing a major career. Fourth, as a result of analyzing the interview data of the participants, a core category called' understanding and growth and the will of the counselor to realize the dream' was derived. In conclusion, the participant's perception of their major is the change and growth of themselves, the formation of a healthy relationship with others, and satisfaction with the suitability of their major and their aptitudes. It turned out to have a lasting will to do.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.9
• /
• pp.363-370
• /
• 2022

Grasping a target object among clutter objects without collision requires machine intelligence. Machine intelligence includes environment recognition, target & obstacle recognition, collision-free path planning, and object grasping intelligence of robot hands. In this work, we implement such system in simulation and hardware to grasp a target object without collision. We use a RGB-D image sensor to recognize the environment and objects. Various path-finding algorithms been implemented and tested to find collision-free paths. Finally for an anthropomorphic robot hand, object grasping intelligence is learned through deep reinforcement learning. In our simulation environment, grasping a target out of five clutter objects, showed an average success rate of 78.8%and a collision rate of 34% without path planning. Whereas our system combined with path planning showed an average success rate of 94% and an average collision rate of 20%. In our hardware environment grasping a target out of three clutter objects showed an average success rate of 30% and a collision rate of 97% without path planning whereas our system combined with path planning showed an average success rate of 90% and an average collision rate of 23%. Our results show that grasping a target object in clutter is feasible with vision intelligence, path planning, and deep RL.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.166-172
• /
• 2022

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.2
• /
• pp.119-125
• /
• 2023

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• Journal of KIISE
• /
• v.44 no.9
• /
• pp.932-945
• /
• 2017

In this paper, a new hardware and software architecture for a stereo vision processing system including rectification, disparity estimation, and visualization was developed. The developed method, named LArge scale stereo matching method using Support Point Interpolation (LASPI), shows excellence in real-time processing for obtaining dense disparity maps from high quality image regions that contain high density support points. In the real-time processing of high definition (HD) images, LASPI does not degrade the quality level of disparity maps compared to existing stereo-matching methods such as Efficient LArge-scale Stereo matching (ELAS). LASPI has been designed to meet a high frame-rate, accurate distance resolution performance, and a low resource usage even in a limited resource environment. These characteristics enable LASPI to be deployed to safety-critical applications such as an obstacle recognition system and distance detection system for autonomous vehicles. A Field Programmable Gate Array (FPGA) for the LASPI algorithm has been implemented in order to support parallel processing and 4-stage pipelining. From various experiments, it was verified that the developed FPGA system (Xilinx Virtex-7 FPGA, 148.5MHz Clock) is capable of processing 30 HD ($1280{\times}720pixels$) frames per second in real-time while it generates disparity maps that are applicable to real vehicles.

• Korean journal of food and cookery science
• /
• v.30 no.2
• /
• pp.219-227
• /
• 2014

The objective of this study was to research the health status of the elderly population and their perception and compliance to cook medicated juk. The results from this research will be used as basic data for medicated juk development. In addition, the purpose of this study was to find a way to popularize the juk and improve their usage as medicated juk in communal feeding and convalescent hospital for elderly. The study surveyed 300 elderly residents of age over 65, in Daejeon. The following data were collected: general characteristic, health status, perception of medicated juk, and preferred kind of juk for cooking. Moreover, the study researched the constraints in cooking the juk. Data were analyzed by SPSS Windows V. 18.0 and t-test verified the differences among the questions, according to frequency analysis of each item and characteristics of the aged. You might want to specify this characteristic. Within the surveyed elderly population, 80.6% had various existing diseases with circulatory diseases being the most prevalent with 68.9%. This emphasizes on the significance of proper diet, but this recognition is not put into practice. The survey also showed that as the individuals age, they tend to care less about the necessity of proper diet. Despite of this lack of perception, 84.5% of the elderly population responded positively to the question, "Would you like to have medicated juk for curing diseases, if such juk is available?" In addition, the elderly population was in favor of developing the juk that helps to prevent and cure diseases, and many were willing to cook them. The reasons behind their will to cook are arranged in the following order: higher efficacy in curing disease than regular juk, excellence in nutrition, and unavailability of the medicated juk in the stores that requires them to cook. The sources constraining the elderly population in cooking are arranged in the following order: not knowing how to cook the juk, lack of physical strength, financial burden, and lack of information order. Please clarify this part. Suggested change: not knowing what medicated juk is. Furthermore, the main obstacle in cooking the juk is lack of cooking technique, followed by inaccessibility to the ingredients and the financial burden to purchase the ingredients.