• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.522-524
• /
• 2019

In spite of a rapid development in the quality of built-in mobile cameras, their some physical restrictions hinder them to achieve the satisfactory results of digital single lens reflex (DSLR) cameras. In this work we propose an end-to-end deep learning method to translate ordinary images by mobile cameras into DSLR-quality photos. The method is based on the framework of generative adversarial networks (GANs) with several improvements. First, we combined the U-Net with DenseNet and connected dense block (DB) in terms of U-Net. The Dense U-Net acts as the generator in our GAN model. Then, we improved the perceptual loss by using the VGG features and pixel-wise content, which could provide stronger supervision for contrast enhancement and texture recovery.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.1
• /
• pp.64-76
• /
• 2017

Routing in mobile ad hoc networks (MANETs) is highly challenging because of the dynamic nature of network topology. AntHocNet is a bio-inspired routing protocol for MANETs that mimics the foraging behavior of ants. However, unlike many other MANET routing protocols, the paths constructed in AntHocNet are unidirectional, which requires a separate path setup if a route in the reverse direction is also required. Because most communication sessions are bidirectional, this unidirectional path setup approach is often inefficient. Moreover, AntHocNet suffers from looping problems because of its property of multiple paths and stochastic data routing. In this paper, we propose a modified path setup procedure that constructs bidirectional paths. We also propose solutions to some of the looping problems in AntHocNet. Simulation results show that performance is significantly enhanced in terms of overhead, end-to-end delay, and delivery ratio when loops are prevented. Performance is further improved, in terms of overhead, when bidirectional paths setup is employed.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.7
• /
• pp.631-636
• /
• 2007

An efficient obstacle avoidance algorithm is proposed in this paper to avoid dynamic obstacles using a collision vector while a tele-operated mobile robot is moving. For the verification of the algorithm, an operator watches through a monitor and controls the mobile robot with a force-reflection joystick. The force-reflection joystick transmits a virtual force to the operator through the Inter-net, which is generated by an adaptive impedance algorithm. To keep the mobile robot safe from collisions in an uncertain environment, the adaptive impedance algorithm generates the virtual force which changes the command of the operator by pushing the operator's hand to a direction to avoid the obstacle. In the conventional virtual force algorithm, the avoidance of moving obstacles was not solved since the operator cannot recognize the environment realistically by the limited communication bandwidth and the narrow view-angle of the camera. To achieve the dynamic obstacle avoidance, the adaptive virtual force algorithm is proposed based on the collision vector that is a normal vector from the obstacle to the mobile robot. To verify the effectiveness of the proposed algorithm, mobile robot navigation experiments with multiple moving obstacles have been performed, and the results are demonstrated.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.451-452
• /
• 2023

최근 CNN 이 다양한 산업에 확산되고 있으며, IoT 기기 및 엣지 컴퓨팅에 적합한 경량 모델에 대한 연구가 급증하고 있다. 본 논문에서는 CNN 모델의 파라미터 비트 연산을 위한 자동화 프레임워크를 제안하고, 파라미터 비트와 모델 정확도 사이의 관계를 실험 및 연구한다. 제안된 프레임워크는 하위 n- bit 를 0 으로 설정하여 정보 손실 발생시킴으로써 ImageNet 데이터셋으로 사전 학습된 CNN 모델의 파라미터와 정확도의 강인성을 비트 단위로 체계적으로 실험할 수 있다. 우리는 비트 연산을 수행한 파라미터로 InceptionV3, InceptionResnetV2, ResNet50, Xception, DenseNet121, MobileNetV1, MobileNetV2 모델의 정확도를 평가한다. 실험 결과는 성능이 낮은 모델일수록 파라미터와 정확도 간의 강인성이 높아 성능이 좋은 모델보다 정확도를 유지하는 비트 수가 적다는 것을 보여준다.

• Convergence Security Journal
• /
• v.20 no.3
• /
• pp.53-60
• /
• 2020

At the present stage of the fourth industrial revolution, machine learning and artificial intelligence technologies are rapidly developing, and there is a movement to apply machine learning technology in the security field. Malicious code, including new and transformed, generates an average of 390,000 a day worldwide. Statistics show that security companies ignore or miss 31 percent of alarms. As many malicious codes are generated, it is becoming difficult for humans to detect all malicious codes. As a result, research on the detection of malware and network intrusion events through machine learning is being actively conducted in academia and industry. In international conferences and journals, research on security data analysis using deep learning, a field of machine learning, is presented. have. However, these papers focus on detection accuracy and modify several parameters to improve detection accuracy but do not consider the ratio of dataset. Therefore, this paper aims to reduce the cost and resources of many machine learning research by finding the ratio of dataset that can derive the highest detection accuracy in CNN Mobile net-based malware detection model.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.11 s.353
• /
• pp.35-43
• /
• 2006

In this paper we have presented a network based high-speed handover protocol using NetLMM(Network based Localized Mobility Management) WG protocol in IETF(Internet Engineering Task Force). We use IEEE 802.21 MIHS(Media Independent Handover Services) for improving handover latency and we analysis proposed Fast NetLMM protocol performance using Fluid Flow Mobility Model. Evaluation results show that the Fast NetLMM protocol performance is better than other mobility management protocols.

• Journal of Digital Contents Society
• /
• v.14 no.1
• /
• pp.89-95
• /
• 2013

Many peer-to-peer (p2p) systems have been studied in distributed, ubiquitous computing environments. Distributed hash table (DHT)-based p2p systems can improve load-balancing even though locality utilization and user mobility are not guaranteed. We propose a mobile locality-based hierarchical p2p overlay network (MLH-Net) to address locality problems without any other services. MLH-Net utilizes mobility features in a mobile environment. MLH-Net is constructed as two layers, an upper layer formed with super-nodes and a lower layer formed with normal-nodes. The simulation results demonstrate that MLH-Net can decrease discovery routing hops by 13% compared with JXTA and 69% compared with Chord. It can decrease the discovery routing distance by 17% compared with JXTA and 83% compared with Chord depending on the environment.

• Nutrition Research and Practice
• /
• v.13 no.6
• /
• pp.521-528
• /
• 2019

BACKGROUND/OBJECTIVES: The aim of this study was to develop Korean food image detection and recognition model for use in mobile devices for accurate estimation of dietary intake. MATERIALS/METHODS: We collected food images by taking pictures or by searching web images and built an image dataset for use in training a complex recognition model for Korean food. Augmentation techniques were performed in order to increase the dataset size. The dataset for training contained more than 92,000 images categorized into 23 groups of Korean food. All images were down-sampled to a fixed resolution of $150{\times}150$ and then randomly divided into training and testing groups at a ratio of 3:1, resulting in 69,000 training images and 23,000 test images. We used a Deep Convolutional Neural Network (DCNN) for the complex recognition model and compared the results with those of other networks: AlexNet, GoogLeNet, Very Deep Convolutional Neural Network, VGG and ResNet, for large-scale image recognition. RESULTS: Our complex food recognition model, K-foodNet, had higher test accuracy (91.3%) and faster recognition time (0.4 ms) than those of the other networks. CONCLUSION: The results showed that K-foodNet achieved better performance in detecting and recognizing Korean food compared to other state-of-the-art models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.1981-1995
• /
• 2021

When a person tries to conceal emotions, real emotions will manifest themselves in the form of micro-expressions. Research on facial micro-expression recognition is still extremely challenging in the field of pattern recognition. This is because it is difficult to implement the best feature extraction method to cope with micro-expressions with small changes and short duration. Most methods are based on hand-crafted features to extract subtle facial movements. In this study, we introduce a method that incorporates optical flow and deep learning. First, we take out the onset frame and the apex frame from each video sequence. Then, the motion features between these two frames are extracted using the optical flow method. Finally, the features are inputted into an improved MobileNetV2 model, where SVM is applied to classify expressions. In order to evaluate the effectiveness of the method, we conduct experiments on the public spontaneous micro-expression database CASME II. Under the condition of applying the leave-one-subject-out cross-validation method, the recognition accuracy rate reaches 53.01%, and the F-score reaches 0.5231. The results show that the proposed method can significantly improve the micro-expression recognition performance.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.141-151
• /
• 2022

In recent years, the industry and research communities have focused on developing autonomous crack inspection approaches, which mainly include image acquisition and crack detection. In these approaches, mobile devices such as cameras, drones or smartphones are utilized as sensing platforms to acquire structural images, and the deep learning (DL)-based methods are being developed as important crack detection approaches. However, the process of image acquisition and collection is time-consuming, which delays the inspection. Also, the present mobile devices such as smartphones can be not only a sensing platform but also a computing platform that can be embedded with deep neural networks (DNNs) to conduct on-site crack detection. Due to the limited computing resources of mobile devices, the size of the DNNs should be reduced to improve the computational efficiency. In this study, an architecture called pruned crack recognition network (PCR-Net) was developed for the detection of structural cracks. A dataset containing 11000 images was established based on the raw images from bridge inspections. A pruning method was introduced to reduce the size of the base architecture for the optimization of the model size. Comparative studies were conducted with image processing techniques (IPTs) and other DNNs for the evaluation of the performance of the proposed PCR-Net. Furthermore, a modularly designed framework that integrated the PCR-Net was developed to realize a DL-based crack detection application for smartphones. Finally, on-site crack detection experiments were carried out to validate the performance of the developed system of smartphone-based detection of structural cracks.