• Tunnel and Underground Space
• /
• v.34 no.3
• /
• pp.218-230
• /
• 2024

Recently, many studies have been conducted for safety management in construction sites by incorporating computer vision. Anchor box parameters are used in state-of-the-art deep learning-based object detection and segmentation, and the optimized parameters are critical in the training process to ensure consistent accuracy. Those parameters are generally tuned by fixing the shape and size by the user's heuristic method, and a single parameter controls the training rate in the model. However, the anchor box parameters are sensitive depending on the type of object and the size of the object, and as the number of training data increases. There is a limit to reflecting all the characteristics of the training data with a single parameter. Therefore, this paper suggests a method of applying multiple parameters optimized through data split to solve the above-mentioned problem. Criteria for efficiently segmenting integrated training data according to object size, number of objects, and shape of objects were established, and the effectiveness of the proposed data split method was verified through a comparative study of conventional scheme and proposed methods.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.29 no.4
• /
• pp.159-166
• /
• 2017

The growing global interest in energy saving is particularly evident in the building sector. The transmitted solar irradiance is an important input in the prediction of the building-energy load, but it is a value that is difficult to measure. In this paper, a calculation method, for which the total horizontal irradiance that can be easily measured is employed, for the measurement of the transmitted solar irradiance through windows is proposed. The method includes a direct and diffuse split model and a variable-transmittance model. The results of the proposed calculation model are compared with the TRNSYS-simulation results at each stage for the purpose of validation. The final results show that the CVRMSE over the year between the proposed model and the reference is less than 30 %, whereby the ASHRAE guideline was achieved.

• Journal of Korean Port Research
• /
• v.14 no.3
• /
• pp.269-278
• /
• 2000

Today the pedestrian-related problems a key subject requiring the attention of the traffic engineers for improving the transportation system. Particularly in urban and CBD locations, the pedestrian presents an element of sharp conflict with vehicular traffic. Therefore pedestrian movements must be studied for the purpose of providing guideline for the design and operation of walking transportation systems. This paper is to address the characteristics of walking transportation in a big city. Especially the focuses are emphasized on the ratio occupied by pedestrian traffic among the whole unlinked trips in a city and walking time. The data for analysis are collected in Seoul metropolitan city through sampling 1,006 citizens. Compared with other similar research works this paper utilized diversified tools to acquire more useful results. Finally, policy directions for pedestrian environment improvement were suggested.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2000.11a
• /
• pp.53.2-60
• /
• 2000

One of the elements requiring the attention of the traffic engineer is the pedestrian. Particularly in urban and CBD locations ,the pedestrian presents an element of sharp conflict with vehicular traffic. Therefore pedestrian movements must be studied for the purpose of providing guideline for the design and operation of transportation systems. This paper addressed the characteristics of walking transportation in a big city. Especially the focuses are emphasized on the ratio occupied by pedestrian traffic among the whole unlinked trips in a city and walking time. The data for analysis are gathered in Seoul metropolitan city sampling 1,006 citizens. Compared with other similar research works this paper utilized diversified tools to acquire more useful results.

• Journal of Korean Academy of Nursing
• /
• v.46 no.1
• /
• pp.29-38
• /
• 2016

Purpose: The Perinatal Post-Traumatic Stress Disorder Questionnaire (PPQ) was designed to measure post-traumatic symptoms related to childbirth and symptoms during postnatal period. The purpose of this study was to develop a translated Korean version of the PPQ and to evaluate reliability and validity of the Korean PPQ. Methods: Participants were 196 mothers at one to 18 months after giving childbirth and data were collected through e-mails. The PPQ was translated into Korean using translation guideline from World Health Organization. For this study Cronbach's alpha and split-half reliability were used to evaluate the reliability of the PPQ. Exploratory Factor Analysis (EFA), Confirmatory Factor Analysis (CFA), and known-group validity were conducted to examine construct validity. Correlations of the PPQ with Impact of Event Scale (IES), Beck Depression Inventory II (BDI-II), and Beck Anxiety Inventory (BAI) were used to test a criterion validity of the PPQ. Results: Cronbach's alpha and Spearman-Brown split-half correlation coefficient were 0.91 and 0.77, respectively. EFA identified a 3-factor solution including arousal, avoidance, and intrusion factors and CFA revealed the strongest support for the 3-factor model. The correlations of the PPQ with IES, BDI-II, and BAI were .99, .60, and .72, respectively, pointing to criterion validity of a high level. Conclusion: The Korean version PPQ is a useful tool for screening and assessing mothers' experiencing emotional distress related to child birth and during the postnatal period. The PPQ also reflects Post Traumatic Stress Disorder's diagnostic standards well.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.830-860
• /
• 2022

[Introduction] Nowadays, many companies are shifting their businesses online due to the growing trend among customers to buy and shop online, as people prefer online purchasing products. [Problem] Users share a vast amount of information about products, making it difficult and challenging for the end-users to make certain decisions. [Motivation] Therefore, we need a mechanism to automatically analyze end-user opinions, thoughts, or feelings in the social media platform about the products that might be useful for the customers to make or change their decisions about buying or purchasing specific products. [Proposed Solution] For this purpose, we proposed an automated SentiDecpective approach, which classifies end-user reviews into negative, positive, and neutral sentiments and identifies deceptive crowd-users rating information in the social media platform to help the user in decision-making. [Methodology] For this purpose, we first collected 11781 end-users comments from the Amazon store and Flipkart web application covering distant products, such as watches, mobile, shoes, clothes, and perfumes. Next, we develop a coding guideline used as a base for the comments annotation process. We then applied the content analysis approach and existing VADER library to annotate the end-user comments in the data set with the identified codes, which results in a labelled data set used as an input to the machine learning classifiers. Finally, we applied the sentiment analysis approach to identify the end-users opinions and overcome the deceptive rating information in the social media platforms by first preprocessing the input data to remove the irrelevant (stop words, special characters, etc.) data from the dataset, employing two standard resampling approaches to balance the data set, i-e, oversampling, and under-sampling, extract different features (TF-IDF and BOW) from the textual data in the data set and then train & test the machine learning algorithms by applying a standard cross-validation approach (KFold and Shuffle Split). [Results/Outcomes] Furthermore, to support our research study, we developed an automated tool that automatically analyzes each customer feedback and displays the collective sentiments of customers about a specific product with the help of a graph, which helps customers to make certain decisions. In a nutshell, our proposed sentiments approach produces good results when identifying the customer sentiments from the online user feedbacks, i-e, obtained an average 94.01% precision, 93.69% recall, and 93.81% F-measure value for classifying positive sentiments.