• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.5
• /
• pp.289-296
• /
• 2022

In this paper, we developed a deep learning-based recyclable object detection model. The model is developed based on YOLOv5 that is a one-stage detector. The deep learning model detects and classifies the recyclable object into 7 categories: paper, carton, can, glass, pet, plastic, and vinyl. We propose two methods for recyclable object detection models to solve problems during training. Bounding Box CutMix solved the no-objects training images problem of Mosaic, a data augmentation used in YOLOv5. Standardized Distance-based IoU replaced DIoU using a normalization factor that is not affected by the center point distance of the bounding boxes. The recyclable object detection model showed a final mAP performance of 0.91978 with Bounding Box CutMix and 0.91149 with Standardized Distance-based IoU.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.595-598
• /
• 2020

IoU (Intersection over Union) is the most commonly used index in target detection. The core requirement of target detection is what is in the image and where. Based on these two problems, classification training and positional regression training are needed. However, in the process of position regression, the most commonly used method is to obtain the IoU of the predicted bounding box and ground-truth bounding box. Calculating bounding box regression losses should take into account three important geometric measures, namely the overlap area, the distance, and the aspect ratio. Although GIoU (Generalized Intersection over Union) improves the calculation function of image overlap degree, it still can't represent the distance and aspect ratio of the graph well. As a result of technological progress, Bounding-Box is no longer represented by coordinates x,y,w and h of four positions. Therefore, the IoU can be further optimized with the center point and aspect ratio of Bounding-Box.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.1
• /
• pp.11-17
• /
• 2021

Due to the recent development of the Internet of Things (IoT) and the increase in services using drones, research on IoD is actively underway. Drones have limited computational power and storage size, and when communicating between drones, data is exchanged after proper authentication between entities. Drones must be secure from traceability because they contain sensitive information such as location and travel path. In this paper, we point out a fatal security vulnerability that can be caused by the use of pseudonyms and certificates in existing IoD research and propose a solution.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.143-156
• /
• 2023

To precisely and reliably analyze the contents of the satellite imagery, recognizing the clouds which are the obstacle to gathering the useful information is essential. In recent times, deep learning yielded satisfactory results in various tasks, so many studies using deep neural networks have been conducted to improve the performance of cloud detection. However, existing methods for cloud detection have the limitation on increasing the performance due to the adopting the network models for semantic image segmentation without modification. To tackle this problem, we introduced the multi-branch neural architecture search to find optimal network structure for cloud detection. Additionally, the proposed method adopts the soft intersection over union (IoU) as loss function to mitigate the disagreement between the loss function and the evaluation metric and uses the various data augmentation methods. The experiments are conducted using the cloud detection dataset acquired by Arirang-3/3A satellite imagery. The experimental results showed that the proposed network which are searched network architecture using cloud dataset is 4% higher than the existing network model which are searched network structure using urban street scenes with regard to the IoU. Also, the experimental results showed that the soft IoU exhibits the best performance on cloud detection among the various loss functions. When comparing the proposed method with the state-of-the-art (SOTA) models in the field of semantic segmentation, the proposed method showed better performance than the SOTA models with regard to the mean IoU and overall accuracy.

• Journal of the Institute of Convergence Signal Processing
• /
• v.18 no.1
• /
• pp.6-12
• /
• 2017

In this paper, we proposed IoT based Smart Health Service using Motion Recognition for Human UX/UI. Until now, sensor networks using M2M-based u-healthcare are using non-IP protocol instead of TCP / IP protocol. However, in order to increase the service utilization and facilitate the management of the IoT-based sensor network, many sensors are required to be connected to the Internet. Therefore, IoT-based smart health service is designed considering network mobility because it is necessary to communicate not only the data measured by sensors but also the Internet. In addition, IoT-based smart health service developed smart health service for motion detection as well as bio information unlike existing healthcare platform. WBAN communications used in u-healthcare typically consist of many networked devices and gateways. The method proposed in this paper can easily cope with dynamic changes even in a wireless environment by using a technology supporting mobility between WBAN sensor nodes, and systematic management is performed through detection of a user's motion.

• KIPS Transactions on Computer and Communication Systems
• /
• v.3 no.10
• /
• pp.371-376
• /
• 2014

Consistently collecting a variety of vital signs is crucial in u-Healthcare. In order to do so, IoT is being considered as a top solution nowadays as an efficient network environment between the sensor and the server. This paper proposes a transmission method and compression algorithm which are appropriate for IoT environment. Results were compared to widely used compression methods, and were compared to other prior researches. The results showed that the compression ratio of our proposed algorithm was 11.7.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.07a
• /
• pp.109-110
• /
• 2015

ICT 기술의 발달에 따라, 현대인들이 컴퓨터 앞에서 작업하는 시간은 증가했으며 장시간 의자에 앉아 한 자세 및 부적절한 자세와 생활 습관으로 인한 척추 측만증 및 허리 디스크 발병률은 점점 증가하고 있다. 척추는 몸을 지탱하는 기둥으로써 사람의 몸의 중추적인 역할을 하는데 척추가 여러 원인으로 꼬이고 굽어져 'S'형으로 흰 상태를 척추 측만증이라고 한다. 유비쿼터스 컴퓨팅 기술의 발달로 언제 어디서나 자신의 건강상태를 모니터링 할 수 있는 U-Health 시스템이 주목받고 있기 때문에 따라서 본 논문에서 일상 생활에서도 자신의 자세를 측정 및 교정이 가능하며 센서로부터 측정한 값은 사람의 체형마다 다르다는 단점을 보완하고 환자-의사가 통신 할 수 있는 IoT를 결합한 아두이노 기반의 척추 측만증 예방을 위한 자세 교정기 및 U-Health 시스템을 개발하였다.

• Journal of KIISE
• /
• v.45 no.1
• /
• pp.94-98
• /
• 2018

We propose Wide Inception ResNet (WIR Net) an optimized neural network architecture as a real-time semantic segmentation method for autonomous driving. The neural network architecture consists of an encoder that extracts features by applying a residual connection and inception module, and a decoder that increases the resolution by using transposed convolution and a low layer feature map. We also improved the performance by applying an ELU activation function and optimized the neural network by reducing the number of layers and increasing the number of filters. The performance evaluations used an NVIDIA Geforce GTX 1080 and TX1 boards to assess the class and category IoU for cityscapes data in the driving environment. The experimental results show that the accuracy of class IoU 53.4, category IoU 81.8 and the execution speed of $640{\times}360$, $720{\times}480$ resolution image processing 17.8fps and 13.0fps on TX1 board.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1109-1124
• /
• 2022

This study proposes a marine debris monitoring methods using satellite and drone multispectral images. A multi-layer perceptron (MLP) model was applied to detect marine debris using Sentinel-2 satellite image. And for the detection of marine debris using drone multispectral images, performance evaluation and comparison of U-Net, DeepLabv3+ (ResNet50) and DeepLabv3+ (Inceptionv3) among deep learning models were performed (mIoU 0.68). As a result of marine debris detection using satellite image, the F1-Score was 0.97. Marine debris detection using drone multispectral images was performed on vegetative debris and plastics. As a result of detection, when DeepLabv3+ (Inceptionv3) was used, the most model accuracy, mean intersection over union (mIoU), was 0.68. Vegetative debris showed an F1-Score of 0.93 and IoU of 0.86, while plastics showed low performance with an F1-Score of 0.5 and IoU of 0.33. However, the F1-Score of the spectral index applied to generate plastic mask images was 0.81, which was higher than the plastics detection performance of DeepLabv3+ (Inceptionv3), and it was confirmed that plastics monitoring using the spectral index was possible. The marine debris monitoring technique proposed in this study can be used to establish a plan for marine debris collection and treatment as well as to provide quantitative data on marine debris generation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.973-976
• /
• 2015

Inernet of Things(IoT) is interaction with each other, collecting, sharing, and analysing the data. IoT has been noted in combining the fields of medical service in particular. However, the security issue is caused, while IoT is receiving attention. U-Health and medical devices, which deal mainly the personal health information, is required to a high level of privacy and security of health information. This study analyzes cases of leakage of personal medical information, security of IoT, privacy flow, and the response strategies.