• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.980-997
• /
• 2024

To improve the brightness of images and reveal hidden information in dark areas is the main objective of low-light image enhancement (LLIE). LLIE methods based on deep learning show good performance. However, there are some limitations to these methods, such as the complex network model requires highly configurable environments, and deficient enhancement of edge details leads to blurring of the target content. Single-scale feature extraction results in the insufficient recovery of the hidden content of the enhanced images. This paper proposed an edge detection-based multi-scale feature enhancement network for LLIE (EDMFEN). To reduce the loss of edge details in the enhanced images, an edge extraction module consisting of a Sobel operator is introduced to obtain edge information by computing gradients of images. In addition, a multi-scale feature enhancement module (MSFEM) consisting of multi-scale feature extraction block (MSFEB) and a spatial attention mechanism is proposed to thoroughly recover the hidden content of the enhanced images and obtain richer features. Since the fused features may contain some useless information, the MSFEB is introduced so as to obtain the image features with different perceptual fields. To use the multi-scale features more effectively, a spatial attention mechanism module is used to retain the key features and improve the model performance after fusing multi-scale features. Experimental results on two datasets and five baseline datasets show that EDMFEN has good performance when compared with the stateof-the-art LLIE methods.

• Journal of the Korea Convergence Society
• /
• v.11 no.9
• /
• pp.21-29
• /
• 2020

The Topic Modeling research, the methodology for deduction keyword within literature, has become active with the explosion of data from digital society transition. The research objective is to investigate research trends in D.N.A.(Data, Network, Artificial Intelligence) field using DTM(Dynamic Topic Model). DTM model was applied to the 1,519 of research projects with SW·A.I technology classifications among ICT(Information and Communication Technology) field projects between 6 years(2015~2020). As a result, technology keyword for D.N.A. field; Big data, Cloud, Artificial Intelligence, extended keyword; Unstructured, Edge Computing, Learning, Recognition was appeared every year, and accordingly that the above technology is being researched inclusively from other projects can be inferred. Finally, it is expected that the result from this paper become useful for future policy·R&D planning and corporation's technology·marketing strategy.

• KNOM Review
• /
• v.23 no.1
• /
• pp.34-42
• /
• 2020

Network Function Virtualization (NFV) environment can deal with dynamic changes in traffic status with appropriate deployment and scaling of Virtualized Network Function (VNF). However, determining and applying the optimal VNF deployment is a complicated and difficult task. In particular, it is necessary to predict the situation at a future point because it takes for the process to be applied and the deployment decision to the actual NFV environment. In this paper, we randomly generate service requests in Multiaccess Edge Computing (MEC) topology, then obtain training data for machine learning model from an Integer Linear Programming (ILP) solution. We use the simulation data to train the machine learning model which predicts the optimal VNF deployment in a predefined future point. The prediction model shows the accuracy over 90% compared to the ILP solution in a 5-minute future time point.

• Annual Conference of KIPS
• /
• 2020.05a
• /
• pp.109-110
• /
• 2020

최근 엣지 컴퓨팅을 활용한 자율주행차 서비스 개발 연구가 진행 중이다. 특히, 최근 개발 중인 차량 엣지 컴퓨팅 기술은 도로 상황 및 교통 정보를 실시간으로 수집하여 빠른 처리를 통해 안정된 차량 및 교통 서비스를 제공할 수 있는 기술로 평가받고 있다. 따라서 본 논문에서는 자율주행차 서비스를 위해 차량 엣지 컴퓨팅 간, 엣지-클라우드간 협업 모델을 제안하고 차량 안전 메시지와 같은 긴급 메시지의 빠른 전달을 위한 초지연 메지시 전달 기법을 제안한다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.1
• /
• pp.1-11
• /
• 2021

This paper presents a procedure to extract lane line models using a set of proposed methods. Firstly, an image warping method based on homography is proposed to transform a target image into an image which is efficient to find lane pixels within a certain region in the image. Secondly, a method to use the combination of the results of edge detection and HSL (Hue, Saturation, and Lightness) transform is proposed to detect lane candidate pixels with reliability. Thirdly, erroneous candidate lane pixels are eliminated using a selection area method. Fourthly, a method to fit lane pixels to quadratic polynomials is proposed. In order to test the validity of the proposed procedure, a set of black-box images captured under varying illumination and noise conditions were used. The experimental results show that the proposed procedure could overcome the problems of color-only and edge-only based methods and extract lane pixels and model the lane line geometry effectively within less than 0.6 seconds per frame under a low-cost computing environment.

• Journal of Biomedical Engineering Research
• /
• v.44 no.2
• /
• pp.147-156
• /
• 2023

Efforts to employ smart home sensors to monitor the indoor activities of elderly single residents have been made to assess the feasibility of a safe and healthy lifestyle. However, the bathroom remains an area of blind spot. In this study, we have developed and evaluated a new edge computer device that can automatically detect water usage activities in the bathroom and record the activity log on a cloud server. Three kinds of sound as flushing, showering, and washing using wash basin generated during water usage were recorded and cut into 1-second scenes. These sound clips were then converted into a 2-dimensional image using MEL-spectrogram. Sound data augmentation techniques were adopted to obtain better learning effect from smaller number of data sets. These techniques, some of which are applied in time domain and others in frequency domain, increased the number of training data set by 30 times. A deep learning model, called CRNN, combining Convolutional Neural Network and Recurrent Neural Network was employed. The edge device was implemented using Raspberry Pi 4 and was equipped with a condenser microphone and amplifier to run the pre-trained model in real-time. The detected activities were recorded as text-based activity logs on a Firebase server. Performance was evaluated in two bathrooms for the three water usage activities, resulting in an accuracy of 96.1% and 88.2%, and F1 Score of 96.1% and 87.8%, respectively. Most of the classification errors were observed in the water sound from washing. In conclusion, this system demonstrates the potential for use in recording the activities as a lifelog of elderly single residents to a cloud server over the long-term.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1075-1084
• /
• 2022

Internet of Things(IoT) has become a key available technology for efficiently implementing device to device(D2D) services in various domains such as smart home, healthcare, smart city, agriculture, energy, logistics, and transportation. A lightweight publish/subscribe(Pub/Sub) messaging protocol not only establishes data dissemination pattern but also supports connectivity between IoT devices and their applications. Also, a Pub/Sub broker is deployed to facilitate data exchange among IoT devices. A scalable edge-based publish/subscribe (Pub/Sub) broker overlay networks support latency-sensitive IoT applications. In this paper, we design a hypercube grid quorum(HGQ) for distributed Pub/Sub systems based IoT applications. In designing HGQ, the network of hypercube structures suitable for the publish/subscribe model is built in the edge layer, and the proposed HGQ is designed by embedding a mesh overlay network in the hypercube. As their applications, we propose an HGQ-based mechansim for dissemination of the data of sensors or the message/event of IoT devices in IoT environments. The performance of HGQ is evaluated by analytical models. As the results, the latency and load balancing of applications based on the distributed Pub/Sub system using HGQ are improved.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.2
• /
• pp.67-72
• /
• 2022

Recently, various intelligent application services using artificial intelligence are being actively developed. In particular, research on artificial intelligence-based real-time prediction services is being actively conducted in the manufacturing industry, and the demand for artificial intelligence services that can detect and predict fire and odors is very high. However, most of the existing detection and prediction systems do not predict the occurrence of fires and odors, but rather provide detection services after occurrence. This is because AI-based prediction service technology is not applied in existing systems. In addition, fire prediction, odor detection and odor level prediction services are services with ultra-low delay characteristics. Therefore, in order to provide ultra-low-latency prediction service, edge computing technology is combined with artificial intelligence models, so that faster inference results can be applied to the field faster than the cloud is being developed. Therefore, in this paper, we propose an LSTM algorithm-based learning model that can be used for fire prediction and odor detection/prediction, which are most required in the manufacturing industry. In addition, the proposed learning model is designed to be implemented in edge devices, and it is proposed to receive real-time sensor data from the IoT terminal and apply this data to the inference model to predict fire and odor conditions in real time. The proposed model evaluated the prediction accuracy of the learning model through three performance indicators, and the evaluation result showed an average performance of over 90%.

• Journal of Animal Environmental Science
• /
• v.18 no.2
• /
• pp.85-90
• /
• 2012

In Korea, livestock has grown into the most value-added business in the agricultural and forest industry. But due to the recent outbreak of deadly infectious diseases such as foot-and-mount disease and avian influenza (AI), the demand for IT-enabled cutting-edge management system is getting stronger. As for humans, pilot projects and researches concerning U-healthcare have been carried out since early 2000. So this study explored the current progress of U-healthcare introduction, and suggested the strategies to develop technologies of collecting, processing, and utilizing information; to apply elements for a service model development and prioritization; to provide policy and institutional support. Therefore it is expected to vitalize the livestock U-healthcare in the future through continuous study based on these results.

• Electronics and Telecommunications Trends
• /
• v.39 no.4
• /
• pp.82-92
• /
• 2024

This paper introduces the technological development trends in on-device SLMs (Small Language Models). Large Language Models (LLMs) based on the transformer model have gained global attention with the emergence of ChatGPT, providing detailed and sophisticated responses across various knowledge domains, thereby increasing their impact across society. While major global tech companies are continuously announcing new LLMs or enhancing their capabilities, the development of SLMs, which are lightweight versions of LLMs, is intensely progressing. SLMs have the advantage of being able to run as on-device AI on smartphones or edge devices with limited memory and computing resources, enabling their application in various fields from a commercialization perspective. This paper examines the technical features for developing SLMs, lightweight technologies, semiconductor technology development trends for on-device AI, and potential applications across various industries.