• Journal of Advanced Marine Engineering and Technology
• /
• v.40 no.5
• /
• pp.437-446
• /
• 2016

Feature selection has become an essential technique to reduce the dimensionality of data sets. Many features are frequently irrelevant or redundant for the classification tasks. The purpose of feature selection is to select relevant features and remove irrelevant and redundant features. Applications of the feature selection range from text processing, face recognition, bioinformatics, speaker verification, and medical diagnosis to financial domains. In this study, we focus on filter methods based on information entropy : IG (Information Gain), FCBF (Fast Correlation Based Filter), and mRMR (minimum Redundancy Maximum Relevance). FCBF has the advantage of reducing computational burden by eliminating the redundant features that satisfy the condition of approximate Markov blanket. However, FCBF considers only the relevance between the feature and the class in order to select the best features, thus failing to take into consideration the interaction between features. In this paper, we propose an improved FCBF to overcome this shortcoming. We also perform a comparative study to evaluate the performance of the proposed method.

• ETRI Journal
• /
• v.42 no.5
• /
• pp.658-668
• /
• 2020

In edge computing, most procedures, including data collection, data processing, and service provision, are handled at edge nodes and not in the central cloud. This decreases the processing burden on the central cloud, enabling fast responses to end-device service requests in addition to reducing bandwidth consumption. However, edge nodes have restricted computing, storage, and energy resources to support computation-intensive tasks such as processing deep neural network (DNN) inference. In this study, we analyze the effect of models with single and multiple local exits on DNN inference in an edge-computing environment. Our test results show that a single-exit model performs better with respect to the number of local exited samples, inference accuracy, and inference latency than a multi-exit model at all exit points. These results signify that higher accuracy can be achieved with less computation when a single-exit model is adopted. In edge computing infrastructure, it is therefore more efficient to adopt a DNN model with only one or a few exit points to provide a fast and reliable inference service.

• Human Ecology Research
• /
• v.53 no.4
• /
• pp.463-473
• /
• 2015

The fashion industry has distinctive characteristics. It is important to understand the specific working environment and unique problems at fashion corporations in order enhance employee efficiency. However, studies on job stress for fashion employees remain limited. This study used qualitative research to examine major job stress factors for fashion company workers. In-depth interviews were conducted on 6 respondents who work in various departments at fashion manufacturing companies. We identified task-related factors and structural factors as the two major job stress factors. Task-related factors consisted of 4 elements (necessity of massive knowledge, overtime outside work, tight schedules, and organizational tasks); structural factors consisted of 3 elements (burden of sales outcome, formal relationships, and anxiety of salary retirement). The results indicated that respondents consistently tried to gain knowledge about the latest trends and field experiences that caused mental and physical exhaustion due to the necessity of working late. Designers and workers in the sales department were constantly evaluated by their sales results compared to other workers that caused high levels of stress. Respondents answered that building relationships was an important factor in the fashion industry and sometimes felt that building formal relationships was more important than the ability to do work.

• Journal of Environmental Health Sciences
• /
• v.47 no.5
• /
• pp.379-383
• /
• 2021

This paper discussed environmental health policies for the past and coming decade by reviewing the First Comprehensive Environmental Health Plan (2011~2020) and introducing the Second Comprehensive Environmental Health Plan (2021~2030). The major achievement of the First Comprehensive Environmental Health Plan was the establishment of receptor-oriented environmental health policies. However, the main limitations were insufficient policy support for relief and/or recovery from environmental pollution damage and low public awareness of environmental health policies. The Second Comprehensive Environmental Health Plan presents the following major policy tasks: establish an omnidirectional environment health investigation and monitoring system, provide customized environmental health services, improve the environmental health damage relief and recovery system, and promote regional environmental health policies. The Second Plan has a clear distinction from the First Plan in that it expands the field of environmental health from the prevention and management of environmental risk factors to proactive damage response and recovery, which will effectively contribute to alleviating the burden of environmental disease.

• Journal of agricultural medicine and community health
• /
• v.44 no.3
• /
• pp.138-143
• /
• 2019

Objectives: The purpose of this study was to assess the ergonomic risk factors in beekeeping, and to evaluate the effectiveness of assistive device hive lift. Methods: This study included 30 subjects of beekeeper in Pocheon, Korea. We assessed the ergonomic risk of main task in beekeeping with NLE, OWAS and evaluate the effectiveness of hive lift. We also surveyed prevalence of musculoskeletal symptoms among the subjects based on the Korea Working Condition Survey. Results: Moving to different floral origin, internal inspection of beehives, feeding syrup is the most burdensome to musculoskeletal system (NLE LI value=2~3. OWAS action category=4). The prevalence of musculoskeletal symptoms (lower and upper extremities) among the subjects was over 80 %. The introduction of assistive devices in the three hazardous tasks has dramatically reduced the risk by removing manual lifting hives (OWAS action category<1). Conclusions: Beekeeping is a heavy workload on the musculoskeletal system because it has a lot of manual lifting task. As a result of applying the hive lift, the burden could be reduced.

• Health Policy and Management
• /
• v.32 no.3
• /
• pp.247-257
• /
• 2022

The presidential election and the inauguration of the new government are a period of the policy window opening. The newly launched government is expected to improve the quality of life of the people. The Yoon Suk-yeol Government is also launched with new expectations with a transitional period in health care. The sustainability of health care in Korea is threatened. The environment of health care and the main policy issues of health care are difficult to secure the necessary finance for health care in spite of the increasing health care burden. Accordingly, the Yoon Suk-yeol Government's health care policy aims to provide intensive support to those in need of health and welfare and to improve the health of the people through investment in health. And for integrating fragmented health care and welfare services and creating people-centered community-based health care, a health care innovation center will be established for the evaluation platform of new delivery and payment systems, a health care development plan will be established for the blueprint of health care, and reorganizing the central & local government should be reviewed. Although we are facing unfavorable situations such as the distribution of the National Assembly, inflation, and the possibility of economic recession, we expect that announced health care policies will be implemented, recognizing that health care innovation is the only way to improve health care sustainability.

• Fashion & Textile Research Journal
• /
• v.24 no.5
• /
• pp.655-665
• /
• 2022

This study evaluated the validity of a newly developed mobility protocol examining the comfort functions and requirements of personal protective equipment (PPE) for COVID-19 healthcare workers. Eight males (age: 24.7 ± 3.0 y, height: 173.4 ± 2.3 cm, and body weight 69.9 ± 3.7 kg) participated in the following three PPE conditions: (1) Plastic gown ensemble, (2) Level D ensemble, and (3) Powered air purifying respirator (PAPR) ensemble. The mobility protocol consisted of 10 different tasks in addition to donning and doffing. The 10 tasks were repeated twice at an air temperature of 25oC with 74% RH. The results showed significant differences among the three PPE conditions in mean skin temperature, local skin temperatures (the forehead, thigh, calf, and foot), clothing microclimate (the chest and back), thermal sensation, thermal comfort, and humidity sensation, while there were no significant differences in heart rate or total sweat rate. At rest, the subjects felt less warm and more comfortable in the PAPR than in the Level D condition (P<0.05). However, subjective perceptions in the PAPR and Level D conditions became similar as the tasks progressed and mean skin and leg temperature became greater for the PAPR than the Level D condition (P<0.05). An interview was conducted just after completing the mobility test protocol, and suggestions for improving each PPE item were obtained. To sum up, the mobility test protocol was valid for evaluating the comfort functions of PPE for healthcare workers and obtaining requirements for improving the mobility of each PPE item.

• Korean Journal of Cognitive Science
• /
• v.19 no.4
• /
• pp.419-441
• /
• 2008

As the Web and digital libraries have become a commodity, they are used for a variety of purposes and tasks that may require a great deal of cognitive efforts. However, most search engines in the Web and digital libraries support users with only searching and browsing capabilities, leaving all the cognitive burdens of manipulating information objects to the users. We propose a two-level model for human-Web interactions, consisting of knowledge and information spaces, and a tool that provides knowledge space and inter-space operations in addition to searching and browsing at the information level. Knowledge space is an explication of user's conceptual view of the information objects being explored through interactions with the Web or a digital library. Topics are created and related with associations at the knowledge level and connected to information objects in information space. The tool implemented using the Topic Maps framework has been tested for efficacy as an aid to reducing cognitive burden under exploratory search task.

• Korean Journal of Social Welfare
• /
• v.53
• /
• pp.231-255
• /
• 2003

The purpose of this study was to determine the effectiveness of social work intervention for the family caregivers of the older persons with stroke. Twelve caregivers were assigned to either a treatment group or a control group. The treatment group intervention consisted of 8 weekly, 2-hour sessions which included education, peer and professional support, individual counselling. Wilcoxon test of the pretest and posttest scores of the two groups showed that those in the treatment program experienced significant decrease in caregiving burden and loneliness compared with caregivers who received no intervention. They also experienced increase in self-esteem, self-efficacy in dealing with caregiving tasks, satisfaction with a relationship with the care-receiver, emotional support. Most of these intervention effects were maintained in the 3-month follow-up measurement except loneliness and the caregiver-carereceiver relationship. Caregivers in the treatment group showed overall satisfaction with the program and willingness to continue to attend in the interventions. Based on these findings, implications for social work practice including self-help groups, psychotherapy for the caregivers, expanding social work intervention for the family caregivers of the older persons were discussed.

• Journal of the Korea Society for Simulation
• /
• v.18 no.4
• /
• pp.9-20
• /
• 2009

Navigation system providing route-guidance and traffic information is one of the most widely used driver-support system these days. Most of the navigation system is based on the 2D map paradigm so the information is ed and encoded from the real world. As a result it imposes a cognitive burden to the driver to interpret and translate the ed information to real world information. As a new concept of navigation system, augmented-reality navigation system (AR navigation) is suggested recently. It provides navigational guidance by imposing graphical information on real image captured by camera mounted on a vehicle in real-time. The ultimate goal of navigation system is to assist the driving task with least driving workload whether it is based on the abstracted graphic paradigm or realistic image paradigm. In this paper, we describe the comparative studies on how map navigation and AR navigation affect for driving tasks by experimental research. From the result of this research we obtained a basic knowledge about the two paradigms of navigation systems. On the basis of this knowledge, we are going to find the optimal design of navigation system supporting driving task most effectively, by analyzing characteristics of driving tasks and navigational information from the human-vehicle interface point of view.