• Journal of the Ergonomics Society of Korea
• /
• v.30 no.5
• /
• pp.571-579
• /
• 2011

Objective: The purpose of this research is to provide exercise programs for the prevention of work related chronic back pain. Background: In order to prevent musculoskeletal disease, including proper medical care health promotion programs are needed. Method: This is a research of musculoskeletal disease looking at 618 workers working at a car engine manufacturing factory from April to July of 2008. Through questionnaire specific areas of musculoskeletal diseases experienced by the workers were identified and preventative exercise program for chronic low back pain was recommended. Result: Research showed that of the musculoskeletal disease experienced by the workers, 197 presented with low back pain, 171 presented with shoulder pain, 64 presented with neck pain and 44 presented with knee pain. The symptoms of low back pain included stiffness(143), twinge and burning sensation(24) and absence of sensation(19). Using this result 4 types of exercise programs were recommended for prevention of chronic low back pain. Conclusion: Preventative exercise programs recommended for the workers in this research is easily accessible for the workers. Use of the suggested exercise programs will inevitably decrease work related low back pain. Also 2 other recommendations were made: 1) Internal structural change may be necessary using ergonomics. 2) More exercise programs to be used to increase adaptation and tolerance of joints and muscles that are constantly used for repetitive work. Application: This study can be used to provide for the prevention of work-related Chronic Low Back pain.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.24 no.2
• /
• pp.232-237
• /
• 2018

According to the MAIIF report, from 1998 to 2009, 101 incidents involving entering enclosed spaces aboard ships resulted in 93 deaths and 96 casualties. IMO has therefore amended the Recommendations for entering Enclosed Spaces Entry and SOLAS 1974 Convention Chapter 3 Regulation 19, which mandates enclosed spaces entry and rescue drill on a regular basis. The training of entering such enclosed spaces should be practical, recognizing all possible risks of entering enclosed spaces aboard ships, while also considering the safety of trainees during the training. Recently, educational contents utilizing virtual reality (VR) have been applied in various fields to improve education and training effects, and these methods have proven to have advantages in actual and repetitive learning without being limited to physical space. In this study, the effectiveness, characteristics and differentiation of training of entering enclosed spaces aboard ships using VR were compared with traditional class room lectures through quantitative evaluation and questionnaires of training participants. Through the evaluation and questionnaire, it was found that participants using VR understood and learned the required training elements better than the control group, all of whom were trained through the normal class room lecture. Moreover, participants reported to display preference for training with the help of VR. As a result of the study, it was confirmed that the learning effects of VR onboard training can be used as an effective training method, especially by using video and other types of simulators.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.1
• /
• pp.14-26
• /
• 2019

For bus drivers' safe driving, a policy that analyzes the causes of the drivers' traffic accidents and then assists their safe driving is required. Therefore, the Ministry of Land, Infrastructure and Transport set up its plan to gradually expand the equipping of commercial vehicles with FCWS (Forward Collision Warning System) and LDWS(Lane Departure Warning System), from the driver-supporting ADAS(Advanced Driver Assistance Systems). However, there is not much basic research on the analysis of bus drivers' traffic accidents in Korea. As such, the time is appropriate to research what is the most necessary ADAS for bus drivers going forward to prevent bus accidents. The purpose of this research is to analyze how serious the accidents were in the different bus routes and whether the accidents were repetitive, and to give recommendations on how to support ADAS for buses, as an improvement. A model of ordered logit was used to analyze how serious the accidents were and as a result, vehicle to pedestrian accidents which directly affected individuals were statistically significant in all of the models, and violations of regulations, such as speeding, traffic signal violation and violation of safeguards for passengers, were indicated in common in several models. Therefore, the pedestrian-sensor system and automatic emergency control device for pedestrian should be installed to reduce bus accidents directly affecting persons in the future, and education for drivers and ADAS are to be offered to reduce the violations of regulations.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.249-263
• /
• 2023

Collaborative Filtering, a representative recommendation system methodology, consists of two approaches: neighbor methods and latent factor models. Among these, the latent factor model using matrix factorization decomposes the user-item interaction matrix into two lower-dimensional rectangular matrices, predicting the item's rating through the product of these matrices. Due to the factor vectors inferred from rating patterns capturing user and item characteristics, this method is superior in scalability, accuracy, and flexibility compared to neighbor-based methods. However, it has a fundamental drawback: the need to reflect the diversity of preferences of different individuals for items with no ratings. This limitation leads to repetitive and inaccurate recommendations. The Adaptive Deep Latent Factor Model (ADLFM) was developed to address this issue. This model adaptively learns the preferences for each item by using the item description, which provides a detailed summary and explanation of the item. ADLFM takes in item description as input, calculates latent vectors of the user and item, and presents a method that can reflect personal diversity using an attention score. However, due to the requirement of a dataset that includes item descriptions, the domain that can apply ADLFM is limited, resulting in generalization limitations. This study proposes a Generalized Adaptive Deep Latent Factor Recommendation Model, G-ADLFRM, to improve the limitations of ADLFM. Firstly, we use item ID, commonly used in recommendation systems, as input instead of the item description. Additionally, we apply improved deep learning model structures such as Self-Attention, Multi-head Attention, and Multi-Conv1D. We conducted experiments on various datasets with input and model structure changes. The results showed that when only the input was changed, MAE increased slightly compared to ADLFM due to accompanying information loss, resulting in decreased recommendation performance. However, the average learning speed per epoch significantly improved as the amount of information to be processed decreased. When both the input and the model structure were changed, the best-performing Multi-Conv1d structure showed similar performance to ADLFM, sufficiently counteracting the information loss caused by the input change. We conclude that G-ADLFRM is a new, lightweight, and generalizable model that maintains the performance of the existing ADLFM while enabling fast learning and inference.