• International Journal of Advanced Culture Technology
• /
• v.11 no.1
• /
• pp.270-275
• /
• 2023

The government has defined domestic violence as one of the four major social evils and tried to prepare laws and systems to prevent it. Nevertheless, domestic violence has emerged as a serious social issue, and compare to the number of domestic violence cases that are constantly increasing, the report rate of domestic violence is significantly lower. This suggests the need to improve citizens' perception of domestic violence as the issue to solve it together in society, not as a private matter at home. Most of existing contents for preventing domestic violence and improving awareness are simple viewing forms of video contents, which have little effect on recognition. We aim to confirm the possibility of improving social awareness about domestic violence by producing Virtual Reality (VR) contents that have great features of user's immersion and empathy. In this VR content, the user can interact with various objects in the virtual reality of domestic violence and directly or indirectly experience the victim's position. Users who view the violent environment from the victim's point of view can have a subjective empathy for the problem, which is expected to induce more active awareness about domestic violence.

• Journal of the Korean Society for Precision Engineering
• /
• v.11 no.1
• /
• pp.138-149
• /
• 1994

This paper introduces a new monitoring technique which utilizes an adaptive signal processing for feature generation, coupled with a multilayered merual network for pattern recognition. The cutting force signal in face milling operation was modeled by a low order discrete autoregressive model, shere parameters were estimated recursively at each sampling instant using a parameter adaptation algorithm based on an RLS(recursive least square) method with discounted measurements. The influences of the adaptation algorithm parameters as well as some considerations for modeling on the estimation results are discussed. The sensitivity of the extimated model parameters to the tool state(new and worn tool)is presented, and the application of a multilayered neural network to tool state monitoring using the previously generated features is also demonstrated with a high success rate. The methodology turned out to be quite suitable for in-process tool wear monitoring in the sense that the model parameters are effective as tool state features in milling operation and that the classifier successfully maps the sensors data to correct output decision.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.460-462
• /
• 2021

Food basically must have nutrition and safety. Recently, a number of symptoms of food poisoning occurred in a kindergarten in Ansan, where food safety was suspected. Therefore, the safety of food is more demanding. In this paper, we propose a method to inprove the detector to secure food safety. The proposed method is to learn through the network of convolution neural network (CNN) and Faster region-CNN (Faster R-CNN) and test the images of normal and foreign products. As a result of testing through a deep learning model, the method that used Faster R-CNN in parallel with the existing foreign body detector algorithm showed better detection rate than other methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.75-77
• /
• 2021

In order to find objects in an image through deep learning technology, an image dataset for learning is required. In order to increase the recognition rate of objects, a large amount of image learning data is required. It is difficult for individuals to build large amounts of datasets because it is expensive. This paper introduces a method for more easily constructing an image dataset including several sides of an object by photographing a rotating image. A method of constructing a dataset by placing an object on a rotating plate, photographing it, and dividing and synthesizing the captured images according to the needs is proposed.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.625-627
• /
• 2022

In the construction and development of modern industrial production technology, the traditional technology management mode is faced with many problems such as low qualification rates and high application costs. In the research, an improved workpiece defect detection method based on deep learning is proposed, which can control the application cost and improve the detection efficiency of irregular defects. Based on the research of the current situation of deep learning applications, this paper uses the improved Faster R-CNN network structure model as the core detection algorithm to automatically locate and classify the defect areas of the workpiece. Firstly, the robustness of the model was improved by appropriately changing the depth and the number of channels of the backbone network, and the hyperparameters of the improved model were adjusted. Then the deformable convolution is added to improve the detection ability of irregular defects. The final experimental results show that this method's average detection accuracy (mAP) is 4.5% higher than that of other methods. The model with anchor size and aspect ratio (65,129,257,519) and (0.2,0.5,1,1) has the highest defect recognition rate, and the detection accuracy reaches 93.88%.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.602-603
• /
• 2015

Despite all efforts to reduce construction disaster, construction site accident rate has steadily increased in Korea since 2008. As a different approach from traditional research, there is a growing issue about design for safety concept to prevent construction disaster. The notion is that construction worker's safety need to be considered at design phase, not only at construction phase. Globally, the notion has been noted that to improve the safety of the worker and used in practice. However, in Korea, most of safety management guidelines are limited to construction phase. From recent statistics, only 1.4 percent of designer feel responsible for safety accident at construction site. In this circumstance, this research find out safety guidelines through literatures reviews and practical experience of safety management in other country which apply design for safety concept. Selected guidelines are verified by survey which is evaluated with risk, function, cost, time and aesthetic view categories. Through the survey, define guidelines which could be effectively applied in Korea. By using proposed safety guidelines for design phase, preventing construction accident and improving designer's recognition of safety issue at design phase are expected.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.05a
• /
• pp.381-382
• /
• 2023

Frequent accidents occur when workers at construction sites leave the safety zone, and particularly in the past 5 years, 9 fatal accidents occurred at the Korea Railroad Corporation due to train accidents on other tracks during track work. With the Severe Accident Punishment Act taking effect in January 2022, it is a priority to secure a safe work environment for workers at industrial (construction) sites. Therefore, there is a need to manage workers' departure from the safety zone (construction zone) and to facilitate communication within the construction zone. In this study, a mobile edge computing CCTV system is proposed that uses geofencing to determine whether workers are working in the danger zone, which can judge and respond in real-time to the ever-changing field environment. The proposed system is mobile and flexible, rather than server-based fixed CCTV. However, since it is designed mainly based on images, it has limitations in recognition rate depending on the environment such as distance, viewing angle, and illumination. As a way to compensate for this, it is required to develop more reliable equipment by combining technologies such as LiDAR and Radar.

• Journal of Korean Academy of Nursing
• /
• v.53 no.6
• /
• pp.622-634
• /
• 2023

Purpose: This study aimed to identify the mediating effects of career motivation and job-esteem and the effect of the nursing work environment on intention to stay among hospital nurses. Methods: Data were collected from 289 nurses working at an advanced general hospital. The research model design was based on the PROCESS macro proposed by Hayes and analyzed using SPSS 24.0 program. Results: The results showed a positive correlation between intention to stay and nursing work environment (r = .19, p = .001), career motivation (r = .34, p < .001), and job-esteem (r = .37, p < .001). Nursing work environment (B = 0.34 [.09~.59]) and job-esteem (B = 0.27 [.04~.49]) had a direct effect on intention to stay. There was a two-mediator sereal mediation effect of career motivation and job-esteem. The nursing work environment showed a significant effect on the intention to stay among hospital nurses through career motivation and job-esteem. Conclusion: In order to increase the retention rate of hospital nurses, it is suggested that government and medical institutions provide multifaceted support that can increase nurses' motivation for career development and recognition of the nursing profession through improvement of the nursing work environment.

• Clinical Endoscopy
• /
• v.56 no.4
• /
• pp.433-445
• /
• 2023

Endoscopic retrograde cholangiopancreatography (ERCP) plays a crucial role in the management of pancreaticobiliary disorders. Although the ERCP technique has been refined over the past five decades, it remains one of the endoscopic procedures with the highest rate of complications. Risk factors for ERCP-related complications are broadly classified into patient-, procedure-, and operator-related risk factors. Although non-modifiable, patient-related risk factors allow for the closer monitoring and instatement of preventive measures. Post-ERCP pancreatitis is the most common complication of ERCP. Risk reduction strategies include intravenous hydration, rectal nonsteroidal anti-inflammatory drugs, and pancreatic stent placement in selected patients. Perforation is associated with significant morbidity and mortality, and prompt recognition and treatment of ERCP-related perforations are key to ensuring good clinical outcomes. Endoscopy plays an expanding role in the treatment of perforations. Specific management strategies depend on the location of the perforation and the patient's clinical status. The risk of post-ERCP bleeding can be attenuated by preprocedural optimization and adoption of intra-procedural techniques. Endoscopic measures are the mainstay of management for post-ERCP bleeding. Escalation to angioembolization or surgery may be required for refractory bleeding. Post-ERCP cholangitis can be reduced with antibiotic prophylaxis in high risk patients. Bile culture-directed therapy plays an important role in antimicrobial treatment.

• Electronics and Telecommunications Trends
• /
• v.38 no.3
• /
• pp.57-65
• /
• 2023

Emergency numbers, such as 112 and 119, are used in many countries to connect people in need with emergency services such as police, fire, and medical assistance. We describe development directions of intelligent response technology for emergency calls. The development of this technology refers to enhancing the efficiency and effectiveness of response systems by using advanced methods such as artificial intelligence, machine learning, and big data analytics. We focus on a system that assists the receptionist of an emergency call. In the future, the recognition rate and decision-making accuracy of intelligent response technologies should be improved considering characteristics of public safety and emergency domain data. Although the current technology remains at the level of assisting a receptionist, a fully autonomous response technology is expected to emerge in the future.