• The Korean Journal of Archival Studies
• /
• no.68
• /
• pp.107-150
• /
• 2021

Representation of an entity starts with recognition of its existence, and recording is mutually circular in that it acts as a means to enable the recognition of the existence. No record is left on an unrecognized entity, record is distorted if any, and the distorted reproduction represents the entity, reinforcing its invisibility. Spivak describes those who cannot speak on their own and cannot be represented as subaltern. This paper examines public record, the media and research records of female restaurant workers, identifies the subaltern characteristics and limitations of their records, and suggests the points to be considered and specific roles required for recording the subalterns. If it is possible to increase the possibility of representation by completely recording a person as an entity that contains the times and society, the accountability of the record to provide an account will extend beyond institutions to the times and society, and individuals and community will be established as political subjects.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.9
• /
• pp.525-531
• /
• 2019

Efforts to utilize human gestures to effectively implement a more natural and interactive interface between humans and computers have been ongoing in recent years. In this paper, we propose a new algorithm that accepts consecutive three-dimensional (3D) depth images, defines a hand model, and robustly extracts the human hand region based on six palm joints and 15 finger joints. Then, the 3D depth images are adaptively binarized to exclude non-interest areas, such as the background, and accurately extracts only the hand of the person, which is the area of interest. Experimental results show that the presented algorithm detects only the human hand region 2.4% more accurately than the existing method. The hand region extraction algorithm proposed in this paper is expected to be useful in various practical applications related to computer vision and image processing, such as gesture recognition, virtual reality implementation, 3D motion games, and sign recognition.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.4
• /
• pp.93-102
• /
• 2019

As interest in wellness grows, There is a lot of research about monitoring individual health using wearable devices. Accordingly, a variety of methods have been studied to distinguish exercise from daily activities using wearable devices. Most of these existing studies are machine learning methods. However, there are problems with over-fitting on individual person's learning, data discontinuously recognition by independent segmenting and fake activity. This paper suggests a detection method for exercise activity based on the physiological response principle of heart rate up and down during exercise. This proposed method calculates activity intensity and heart rate from triaxial and photoplethysmography sensor to determine a heart rate recovery, then detects exercise by estimating activity intensity or detecting a heart rate rising state. Experimental results show that our proposed algorithm has 98.64% of averaged accuracy, 98.05% of averaged precision and 98.62% of averaged recall.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.45-53
• /
• 2020

The purpose of this paper is to reduce the ratio of the patient accidents that may occur in nursing hospitals. In other words, it determines whether the person approaching the dangerous area is a elderly (patient uniform) group or a practitioner(Casual Clothing) group, based on the clothing displayed by CCTV. We collected the basic learning data from web crawling techniques and nursing hospitals. Then model training data was created with Image Generator and Labeling program. Due to the limited performance of CCTV, it is difficult to create a good model with both high accuracy and speed. Therefore, we implemented the ResNet model with relatively excellent accuracy and the YOLO3 model with relatively excellent speed. Then we wanted to allow nursing hospitals to choose a model that they wanted. As a result of the study, we implemented a model that can distinguish patient and casual clothes with appropriate accuracy. Therefore, it is believed that it will contribute to the reduction of safety accidents in nursing hospitals by preventing the elderly from accessing the danger zone.

• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.1-9
• /
• 2022

Recently, the functions of smart speakers have diversified, and the penetration rate of smart speakers is increasing. As it becomes more widespread, various techniques have been proposed to cause anomalous behavior against smart speakers. Dolphin Attack, which causes anomalous behavior against the Voice Controllable System (VCS) during various attacks, is a representative method. With this method, a third party controls VCS using ultrasonic band (f>20kHz) without the user's recognition. However, since the method uses the ultrasonic band, it is necessary to install an ultrasonic speaker or an ultrasonic dedicated device which is capable of outputting an ultrasonic signal. In this paper, a smart speaker is controlled by generating an audio signal modulated at a frequency (18 to 20) which is difficult for a person to hear although it is in the human audible frequency band without installing an additional device, that is, an ultrasonic device. As a result with the method proposed in this paper, while humans could not recognize voice commands even in the audible band, it was possible to control the smart speaker with a probability of 82 to 96%.

• Smart Media Journal
• /
• v.12 no.9
• /
• pp.81-88
• /
• 2023

Recently, communication through online is increasing due to the spread of non-face-to-face services due to COVID-19. In non-face-to-face situations, the other person's opinions and emotions are recognized through modalities such as text, speech, and images. Currently, research on multimodal emotion recognition that combines various modalities is actively underway. Among them, emotion recognition using speech data is attracting attention as a means of understanding emotions through sound and language information, but most of the time, emotions are recognized using a single speech feature value. However, because a variety of emotions exist in a complex manner in a conversation, a method for recognizing multiple emotions is needed. Therefore, in this paper, we propose a multi-emotion regression model that extracts feature vectors after preprocessing speech data to recognize complex, inherent emotions and takes into account the passage of time.

• Smart Media Journal
• /
• v.13 no.5
• /
• pp.19-25
• /
• 2024

The biggest type of behavior that prevents people with developmental disabilities from entering society is aggressive behavior. Aggressive behavior can pose a threat not only to the personal safety of the person with a developmental disability, but also to the physical safety of others. In this study, we propose a wearable system using a low-power processor. The proposed system uses an IMU (Inertial Measurement Unit) to analyze user behavior, and when attack behavior is not detected for a certain period of time through an LED array attached to the developed system, an interesting LED is displayed. By expressing patterns, we provide behavioral intervention through compensation to people with developmental disabilities. In order to implement a system that must be worn for a long time in a power-limited environment, we present a method to optimize performance and energy consumption across all stages, from data preprocessing to AI model application.

• The Journal of the Korea Contents Association
• /
• v.18 no.2
• /
• pp.178-187
• /
• 2018

This study aimed to develop a model of the program for automation measuring the preference of the portraits based on the relationship between the image quality factors and the preferences in the portraits for manufacturers aiming at high utilization of the users. in order to proceed with the evaluation, the image quality measurement was divided into objective and subjective items, and the evaluation was done through image processing and statistical methods. the image quality measurement items can be divided into objective evaluation items and subjective evaluation items. RSC Contrast, Dynamic Range and Noise were selected for the objective evaluation items, and the numerical values were statistically analyzed and evaluated through the program. Exposure, Color Tone, composition of person, position of person, and out of focus were selected for subjective evaluation items and evaluated by image processing method. By applying objective and subjective assessment items, the results were very accurate, with the results obtained by the developed program and the results of the actual visual inspection. but since the currently developed program can be evalua ted only after facial recognition of the person, future research will need to develop a program that can evaluate all kinds of portraits.

• Asia Marketing Journal
• /
• v.15 no.2
• /
• pp.49-73
• /
• 2013

In this study, the author develops and tests a model that incorporates the mediating effects of two frontline employee psychological variables (emotional exhaustion and intrinsic motivation) based on job demand and resource model. As a form of environmental resource, person-organization fit was proposed as a leading factor of frontline employee boundary spanning behavior through emotional exhaustion and intrinsic motivation. All measures were adapted from or developed based on prior research. Data for the study were collected from a cross-sectional sample of retail bank employees in South Korea. Questionnaires were distributed to 500 frontline employees across several banks. Of these, 322 usable questionnaires were returned. To analyze the data, a structural equation model procedure using LISREL 8.5 was employed. Results show that an employee's perceived fit with his/her organization enhances intrinsic motivation and reduces emotional exhaustion. These mechanisms, in turn, increase the employee's boundary spanning behavior. These results support the notion that person-organization fit should be one of the factors affecting motivation, affect and attachment, and extends such an understanding to a purely service-based environment among customer contact employees. Results also confirms that P-O fit can be viewed as environmental resources, and the JD-R model provides a theoretical base in further studying the antecedent role of P-O fit on frontline employees's boundary spanning behavior through intrinsic motivation and emotional exhaustion. These results suggest that organizations have to do their best to manage P-O fit, be it through employee screening or training and workshops to try and align organization and employee values and objectives. If managers of organizations are positively evaluated by the employees, it will be easier for them to, give things of value to employees, such as sense of direction, values, and recognition, and receive other things in return such as esteem and responsiveness. Consequently, organizational leaders are not only able to manage employee experiences, but also their fit with the organization. Even if a manager cannot control employee P-O fit, this research suggests, that a focus on reducing emotional exhaustion rather than increasing intrinsic motivation seems optimal. This research also supports the idea that motivation has a direct association with a frontline employee's boundary spanning behavior. Even in situations where emotional exhaustion cannot be reduced, organizations may still influence frontline behaviors through motivation.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.29-35
• /
• 2023

CCTV is used for various purposes such as crime prevention, public safety reinforcement, and traffic management. However, as the range and resolution of the camera improve, there is a risk of exposing personal information in the video. Therefore, there is a need for new technologies that can identify individuals while protecting personal information in images. In this paper, we propose histogram-based singular value decomposition for object identification and tracking. The proposed method distinguishes different objects present in the image using color information of the object. For object recognition, YOLO and DeepSORT are used to detect and extract people present in the image. Color values are extracted with a black-and-white histogram using location information of the detected person. Singular value decomposition is used to extract and use only meaningful information among the extracted color values. When using singular value decomposition, the accuracy of object color extraction is increased by using the average of the upper singular value in the result. Color information extracted using singular value decomposition is compared with colors present in other images, and the same person present in different images is detected. Euclidean distance is used for color information comparison, and Top-N is used for accuracy evaluation. As a result of the evaluation, when detecting the same person using a black-and-white histogram and singular value decomposition, it recorded a maximum of 100% to a minimum of 74%.