• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.5
• /
• pp.53-64
• /
• 2019

The term 're-use' here signifies the re-use of end-of-life products without changing their form after they have been thoroughly inspected and cleaned. In the re-use network model, the distributor determines the product order quantity on the network through which new products are received from the suppliers or products are supplied to the customers through re-use of the recovered products. In this paper, we propose a reusable network model for reusable products that considers the total logistics cost from the forward logistics to the reverse logistics. We also propose a reusable network model that considers the processing and disposal costs for reuse in an optimal inventory management environment. The authors employe Genetic Algorithm (GA), which is one of the optimization techniques, to verify the validity of the proposed model. And in order to investigate the effect of the parameters on the solution, the priority-based GA (priGA) under three different parameters and the modified Hybrid GA (mhGA), in which parameters are adjusted for each generation, were applied to four examples with varying sizes in the simulation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1158-1165
• /
• 2021

This paper proposes a CNN accelerator which is optimized Pooling layer operation incorporated in Multiplication And Accumulation(MAC) to reduce the memory size. For optimizing memory and data path circuit, the quantized 8bit integer weights are used instead of 32bit floating-point weights for pre-training of MNIST data set. To reduce chip area, the proposed CNN model is reduced by a convolutional layer, a 4*4 Max Pooling, and two fully connected layers. And all the operations use specific MAC with approximation adders and multipliers. 94% of internal memory size reduction is achieved by simultaneously performing the convolution and the pooling operation in the proposed architecture. The proposed accelerator chip is designed by using TSMC65nmGP CMOS process. That has about half size of our previous paper, 0.8*0.9 = 0.72mm². The presented CNN accelerator chip achieves 94% accuracy and 77us inference time per an MNIST image.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.445-450
• /
• 2021

Bio-impedance measurement is a measurement device that can be used to obtain biometric information and diagnose skin diseases using convenience, low cost, and low cost devices. In this study, the bio-impedance was measured using a direct dry gold electrode and a simulation study through animal bio modeling to obtain biometric information in a biometric form. Impedance was measured by inserting electrodes into subcutaneous areas of animal tissue and applying frequencies of 100 uA, 1-100 kHz using a two-electrode method. As a result of the measurement, the resistance of the electrodes is measured high at 5 mm electrodes compared to 7.5 mm and 10 mm electrodes based on 5 mm electrodes. Based on the 5 mm electrode, an average difference of 1.49% was found for the 7.5 mm electrode in the total frequency range, and the impedance difference was confirmed to be 2.624% for the 10 mm electrode. In the future, the research results are expected to be valuable in designing and manufacturing electrodes for bio-inserted electrocardiogram sensors.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.72-73
• /
• 2016

In this paper, we studied a method for miniaturizing a broadband stacked patch antenna structure which is widely used for bandwidth improvement. Main patch is a rectangular microstrip patch antenna fed by a 50-ohm microstrip line, and a parasitic patch is laid above the main patch. The size of the main patch is designed to be resonated near the center frequency of the desired frequency band. Then parasitic patch longer than main patch is placed above the main patch. The distance between two patches might be adjusted so as to achieve impedance matching using a shunt open stub. The shunt matching stub is inserted underneath the parasitic patch and so it does not require additional space, which enables the proposed antenna structure to be advantageous in miniaturizing antenna. The effects of the various parameters on the antenna performance are examined, and we introduced the design procedure for the proposed antenna to operate in the frequency range of 2.3-2.7 GHz.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.19 no.2
• /
• pp.31-38
• /
• 2009

To provide the privacy of a keyword, a public key encryption with keyword search(PEKS) firstly was propsed by Boneh et al. The PEKS scheme enables that an email sender sends an encrypted email with receiver's public key to an email server and a server can obtain the relation between the given encrypted email and an encrypted query generated by a receiver. In this email system, we easily consider the situation that a user sends the one identical encrypted email to multi-receiver like as group e-mail. Hwang and Lee proposed a searchable public key encryption considering multi-receivers. To reduce the size of transmission data and the server's computation is important issue in multi-receiver setting. In this paper, we propose an efficient searchable public key encryption for multi-receiver (mPEKS) which is more efficient and reduces the server's pairing computation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.2
• /
• pp.187-192
• /
• 2021

This study proposes a system for take-off in a forest or similar complex environment using an object detector. In the simulator, a raspberry pi is mounted on a quadcopter with a length of 550mm between motors on a diagonal line, and the experiment is conducted based on edge computing. As for the images to be used for learning, about 150 images of 640⁎480 size were obtained by selecting three points inside Kunsan University, and then converting them to black and white, and pre-processing the binarization by placing a boundary value of 127. After that, we trained the SSD_Inception model. In the simulation, as a result of the experiment of taking off the drone through the model trained with the verification image as an input, a trajectory similar to the takeoff was drawn using the label.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.7
• /
• pp.101-108
• /
• 2022

We propose an intrusion detection model that detects denial-of-service(DoS) and distributed reflection denial-of-service(DRDoS) attacks, based on the empirical data of each internet of things(IoT) device by training system and network metrics that can be commonly collected from various IoT devices. First, we collect 37 system and network metrics from each IoT device considering IoT attack scenarios; further, we train them using six types of machine learning models to identify the most effective machine learning models as well as important metrics in detecting and distinguishing IoT attacks. Our experimental results show that the Random Forest model has the best performance with accuracy of over 96%, followed by the K-Nearest Neighbor model and Decision Tree model. Of the 37 metrics, we identified five types of CPU, memory, and network metrics that best imply the characteristics of the attacks in all the experimental scenarios. Furthermore, we found out that packets with higher transmission speeds than larger size packets represent the characteristics of DoS and DRDoS attacks more clearly in IoT networks.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.5
• /
• pp.380-386
• /
• 2022

This paper proposes a method for structuring the preprocessing process of a training image when color is applied using Pix2Pix, one of the adversarial generative neural network techniques. This paper concentrate on the prediction result can be damaged according to the degree of light reflection of the training image. Therefore, image preprocesisng and parameters for model optimization were configured before model application. In order to increase the image resolution of training and prediction results, it is necessary to modify the of the model so this part is designed to be tuned with parameters. In addition, in this paper, the logic that processes only the part where the prediction result is damaged by light reflection is configured together, and the pre-processing logic that does not distort the prediction result is also configured.Therefore, in order to improve the usability, the accuracy was improved through experiments on the part that applies the light reflection tuning filter to the training image of the Pix2Pix model and the parameter configuration.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.201-212
• /
• 2021

This study attempted to compare the pattern with the absorption layer by analyzing the pattern of commercially available urinary incontinence panty products. Through this, it tried to obtain basic data necessary for the development of functional urinary incontinence panty for active seniors. Twelve commercially available products were decomposed to analyze size and patterns, and appearance and clothing pressure were evaluated through 3D simulation. As a result of comparing the size and pattern of urinary incontinence panty, it was analyzed that the size difference between parts was large even though the product was called the same. Products from the same brand also showed a big difference depending on design and absorption. As a result of the appearance evaluation for the 3D simulation, it was found that there were significant differences between products in all items such as the front, side, and back. Product No. 9 was analyzed to be the best except for the waist fit on the side. In the evaluation of clothing pressure, most of them were marked in red except for products 1, 2, and 8 due to the nature of the panty product. In the future, it is thought that actual wearing experiments and size standardization studies on urinary incontinence pants should be conducted.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.25 no.4
• /
• pp.151-162
• /
• 2022

Recently, the forests in Korea have accumulated damage due to continuous forest disasters, and the need for technologies to monitor forest managements is being issued. The size of the affected area is large terrain, technologies using drones, artificial intelligence, and big data are being studied. In this study, a standard dataset were conducted to develop an algorithm that automatically detects suspicious trees damaged by forest pests using deep learning and drones. Experiments using the YOLO model among object detection algorithm models, the YOLOv4-P7 model showed the highest recall rate of 69.69% and precision of 69.15%. It was confirmed that YOLOv4-P7 should be used as an automatic detection algorithm model for trees suspected of being damaged by forest pests, considering the detection target is an ortho-image with a large image size.