• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.17-22
• /
• 2022

In this paper, we design a lightweight embedded device that can support intelligent edge computing, and show that the device quickly detects an object in an image input from a camera device in real time. The proposed system can be applied to environments without pre-installed infrastructure, such as an intelligent video control system for industrial sites or military areas, or video security systems mounted on autonomous vehicles such as drones. The On-Device AI(Artificial intelligence) technology is increasingly required for the widespread application of intelligent vision recognition systems. Computing offloading from an image data acquisition device to a nearby edge device enables fast service with less network and system resources than AI services performed in the cloud. In addition, it is expected to be safely applied to various industries as it can reduce the attack surface vulnerable to various hacking attacks and minimize the disclosure of sensitive data.

• Smart Media Journal
• /
• v.11 no.11
• /
• pp.25-31
• /
• 2022

Deep learning-based image processing is essential for autonomous vehicles. To process road images in real-time in a System-on-Chip (SoC) environment, we need to execute deep learning models on a NPU (Neural Procesing Units) specialized for deep learning operations. In this study, we imported seven open-source image processing deep learning models, that were developed on GPU servers, to Texas Instrument Deep Learning (TIDL) NPU environment. We confirmed that the models imported in this study operate normally in the SoC virtual environment through performance evaluation and visualization. This paper introduces the problems that occurred during the migration process due to the limitations of NPU environment and how to solve them, and thereby, presents a reference case worth referring to for developers and researchers who want to port deep learning models to SoC environments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.250-252
• /
• 2022

Recently, with the development of IoT technology and AI, unmanned and automated systems are progressing in various fields, and various application technologies are being studied in systems using algorithms such as object detection, recognition, and tracking. In the case of a system operating based on an image, noise removal is performed as a pre-processing process, and precise noise removal is sometimes required depending on the environment of the system. In this paper, we propose a modified central weight filter algorithm using pixel division of local regions to minimize the blurring that tends to occur in the filtering process and to emphasize the details of the resulting image. In the proposed algorithm, when a pixel of a local area is divided into two areas, the center of the dominant area among the divided areas is set as a criterion for the weight filter algorithm. The resulting image is calculated by convolving the transformed center weight with the pixel value inside the filtering mask.

• Journal of Korea Spatial Information System Society
• /
• v.10 no.4
• /
• pp.47-58
• /
• 2008

With the recent development of the ubiquitous computing technology, there are increasing interest and research in technologies such as sensors and RFID related to information recognition and location positioning in various ubiquitous fields. Especially, a standard specification was required for compatibility and interoperability in various RTLS(Real-Time Locating Systems) according to the development of RTLS to provide location and status information of moving objects using the RFID Tag. For these reasons, the ISO/IEC published the RTLS standard specification for compatibility and interoperability in RTLS. Therefore, in this paper, we designed and im plemented RTLS based on the spatial DSMS(Data Stream Management Stream) for efficiently managing and searching the incoming data stream of moving objects. The spatial DSMS is an extended system of STREAM(STanford stREam datA Manager) developed by Standford University to make various spatial operations possible. RTLS based on the spatial DSMS uses the SOAP(Simple Object Access Protocol) message between client and server for interoperability and translates client's SOAP message into CQL(Continuous Query Language) of the spatial DSMS. Finally, we proved the efficiency of RTLS based on the spatial DSMS by applying it for the staff location management service.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.43 no.3
• /
• pp.360-366
• /
• 2014

Kimchi is a Korean traditional fermented food with various health functionalities. However, the protective effects of kimchi against Alzheimer's disease (AD) have not been studied yet. In this study, the protective activities of kimchi extract against oxidative stress and AD were investigated in an amyloid beta ($A{\beta}$)-induced AD model using ICR mice. Kimchi extract exerted strong scavenging activities against 1,1-diphenyl-2-picrylhydrazyl and hydroxyl radical. In addition, T-maze, object cognition, and water maze tests were carried out using the AD model. The $A{\beta}_{25-35}$-injected groups showed impairment of cognition and memory. However, the abilities of novel object recognition and new route awareness were improved by administration of kimchi extract (100 and 200 mg/kg/day) for 2 weeks. Furthermore, the results on water maze test indicated that kimchi extract exerted protective activity against cognitive impairment induced by $A{\beta}_{25-35}$. The present study suggested that kimchi protected against $A{\beta}$-induced impairment of memory and cognition as well as attenuated oxidative stress.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.114-123
• /
• 2024

This paper proposes AR stone tower content, an experiential content based on wearable augmented reality (AR). Although wearable augmented reality is gaining attention, the acceptance of the technology is still focused on specialized applications such as industrial sites. On the other hand, the proposed AR stone tower content is based on the material of 'stone tower' so that general users can relate to it and easily participate in it, and it is organized to utilize space in a moving environment and find and stack stones based on natural hand gestures. The proposed AR stone tower content was implemented in the HoloLens 2 environment and evaluated by general users through a pilot exhibition in a small art museum. The evaluation results showed that the overall satisfaction with the content averaged 3.85, and the content appropriateness for the stone tower material was very high at 4.15. In particular, users were highly satisfied with content comprehension and sound, but somewhat less satisfied with object recognition, body adaptation, and object control. The above user evaluations confirm the resonance and positive response to the material, but also highlight the difficulties of the average user in experiencing and interacting with the wearable AR environment.

• Science of Emotion and Sensibility
• /
• v.21 no.1
• /
• pp.59-70
• /
• 2018

With the breakthrough of speech recognition technology, conversational agents have become pervasive through smartphones and smart speakers. The recognition accuracy of speech recognition technology has developed to the level of human beings, but it still shows limitations on understanding the underlying meaning or intention of words, or understanding long conversation. Accordingly, the users experience various errors when interacting with the conversational agents, which may negatively affect the user experience. In addition, in the case of smart speakers with a voice as the main interface, the lack of feedback on system and transparency was reported as the main issue when the users using. Therefore, there is a strong need for research on how users can better understand the capability of the conversational agents and mitigate negative emotions in error situations. In this study, we applied social strategies, "forewarning" and "apology", to conversational agent and investigated how these strategies affect users' perceptions of the agent in breakdown situations. For the study, we created a series of demo videos of a user interacting with a conversational agent. After watching the demo videos, the participants were asked to evaluate how they liked and trusted the agent through an online survey. A total of 104 respondents were analyzed and found to be contrary to our expectation based on the literature study. The result showed that forewarning gave a negative impression to the user, especially the reliability of the agent. Also, apology in a breakdown situation did not affect the users' perceptions. In the following in-depth interviews, participants explained that they perceived the smart speaker as a machine rather than a human-like object, and for this reason, the social strategies did not work. These results show that the social strategies should be applied according to the perceptions that user has toward agents.

• Korean Journal of Construction Engineering and Management
• /
• v.23 no.4
• /
• pp.3-14
• /
• 2022

Autonomous equipment requires a large amount of data from various environments. However, it takes a lot of time and cost for an experiment in a real construction sites, which are difficulties in data collection and processing. Therefore, this study aims to develop a virtual environment for autonomous tower cranes technology development and validation. The authors defined automation functions and operation conditions of tower cranes with three performance criteria: operational design domain, object and event detection and response, and minimum functional conditions. Afterward, this study developed a virtual environment for learning and validation for autonomous functions such as recognition, decision making, and control using the Unity game engine. Validation was conducted by construction industry experts with a fidelity which is the representative matrix for virtual environment assessment. Through the virtual environment platform developed in this study, it will be possible to reduce the cost and time for data collection and technology development. Also, it is also expected to contribute to autonomous driving for not only tower cranes but also other construction equipment.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.4
• /
• pp.115-123
• /
• 2024

In this paper, we propose a vibration notification system that combines navigation information and wearable bands to ensure safe driving for the transportation vulnerable. This system transmits navigation driving information to a linked application, converts it into a vibration signal, and provides notifications through a wearable band. Existing navigation systems focus on providing route guidance and location information, so the driver's concentration is dispersed, and safety and convenience are deteriorated, especially for those with mobility impairments, due to standard vision and delayed recognition of stimuli, resulting in an increasingly high traffic accident rate. To solve this problem, navigation driving information is converted into vibration signals through a linked application, and vibration notifications for events, left turns, right turns, and speeding are provided through a wearable band to ensure driver safety and convenience. In the future, we will use cameras and vehicle sensors to increase awareness of safety inside and outside the vehicle by adding a function that provides notifications with vibration and LED when the vehicle approaches or recognizes an object, and we will continue to conduct research to build a safer driving environment. plan.

• Journal of KIISE
• /
• v.43 no.3
• /
• pp.370-379
• /
• 2016

Recently personal media were produced in a variety of ways as a lot of smart devices have been spread and services using these data have been desired. Therefore, research has been actively conducted for the media analysis and recognition technology and we can recognize the meaningful object from the media. The system using the media ontology has the disadvantage that can't classify the media appearing in the video because of the use of a video title, tags, and script information. In this paper, we propose a system to automatically classify video using the objects shown in the media data. To do this, we use a description logic-based reasoning and a rule-based inference for event processing which may vary in order. Description logic-based reasoning system proposed in this paper represents the relation of the objects in the media as activity ontology. We describe how to another rule-based reasoning system defines an event according to the order of the inference activity and order based reasoning system automatically classify the appropriate event to the category. To evaluate the efficiency of the proposed approach, we conducted an experiment using the media data classified as a valid category by the analysis of the Youtube video.