• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.2
• /
• pp.177-185
• /
• 2001

This study shows the process design and forming analysis of permalloy shielding can that support the automobile multi-display parts to indicate the accurate information of car. This study is particularly important, since the strain and thickness of permalloy shielding can is known to affect the magnetic properties such as coercivity and permeability quite thickness of permalloy shielding can is known to affect the magnetic properties such as coercivity and permeability quite sensitively. The objective functions are strain and thickness deviation. The punch radius, die radius and blank holding force are considered as design parameters. Orthogonal array (OA) table and characteristics are applied to neural network (NN) as train data. After training, the optimal and robust condition of design parameters is selected. This study shows the correlation between the design methodology of NN and the statistical design of experiments (DOE) approach.

• Journal of the Semiconductor & Display Technology
• /
• v.16 no.3
• /
• pp.65-70
• /
• 2017

This paper presents the implementation for the master changing algorithm between nodes in a general electric vehicle. The packet processing method based on the unique network method of an electric vehicle is that the method of processing a communication packet has the priority from the node of a vehicle installed at both ends. An important factor in deciding master or slave in a train is that the request data, the status data, and transmits or control codes of sub-devices are controlled from the node which master becomes. If the request data or the status data is transmitted from the non- master side, it is very important that only one of the devices of both stages be master since the data of the request data may collide with each other. This paper proposes an algorithm to select master or slave depending on which vehicle is started first, which node is master or slave, and whether the vehicle key is operation. Finally experimental results show the stable performance and effectiveness of the proposed algorithm.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.4
• /
• pp.83-92
• /
• 2020

A recent study to determine the fall is focused on analyzing fall motions using a recurrent neural network (RNN), and uses a deep learning approach to get good results for detecting human poses in 2D from a mono color image. In this paper, we investigated the improved detection method to estimate the position of the head and shoulder key points and the acceleration of position change using the skeletal key points information extracted using PoseNet from the image obtained from the 2D RGB low-cost camera, and to increase the accuracy of the fall judgment. In particular, we propose a fall detection method based on the characteristics of post-fall posture in the fall motion analysis method and on the velocity of human body skeleton key points change as well as the ratio change of body bounding box's width and height. The public data set was used to extract human skeletal features and to train deep learning, GRU, and as a result of an experiment to find a feature extraction method that can achieve high classification accuracy, the proposed method showed a 99.8% success rate in detecting falls more effectively than the conventional primitive skeletal data use method.

• Annals of Clinical Neurophysiology
• /
• v.1 no.2
• /
• pp.147-153
• /
• 1999

Hippocampal slice models can be a powerful tool to study the mechanism of partial epilepsy. Despite the loss of connection with the rest of the brain, in vitro hippocampal slice preparations allow detailed physiological and pharmacological studies, which would be impossible, in vivo. There are several methods to induce electrographic seizures on hippocampal slice models. Those are electrical pulse train stimulation, 0 $Mg^{2+}$ artificial cerebrational fluid and high concentration of extracelluar $K^+$ on bath. Among them, the electrically triggered seizure may mimic the physiological communication between neuronal populations without any deterioration of normal physiologic and chemical status of the hippocampal slice models. Presumably, such communication from hyperexcitable areas to other neuronal populations is involved in the development of epilepsy. Electrographic seizures in hippocampal slice models occur in the network of neurons that are involved in epileptic seizures in the hippocampus in vivo. Because these models have many advantages and are very valuable to research of epileptogenesis on partial epilepsy, I would like to introduce the electrophysiological methods to induce electrographic seizure or epilepsy on hippocampal slice models briefly in this paper.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.2 no.1
• /
• pp.23-35
• /
• 2008

Mobile IP (MIP) is the solution supporting the mobility of Mobile Nodes (MNs), however, it is known to lack the support for NEtwork MObility (NEMO). NEMO manages situations when an entire network, composed of one or more subnets, dynamically changes its point of attachment to the Internet. NEMO Basic Support (NBS) protocol ensures session continuity for all the nodes in a mobile network, however, there exists a serious pinball routing problem. To overcome this weakness, there are many Route Optimization (RO) solutions such as Bi-directional Tunneling (BT) mechanism, Aggregation and Surrogate (A&S) mechanism, Recursive Approach, etc. The A&S RO mechanism is known to outperform the other RO mechanisms, except for the Binding Update (BU) cost. Although Improved Prefix Delegation (IPD) reduces the cost problem of Prefix Delegation (PD), a well-known A&S protocol, the BU cost problem still presents, especially when a large number of Mobile Routers (MRs) and MNs exist in the environment such as train, bus, ship, or aircraft. In this paper, a solution to reduce the cost of delivering the BU messages is proposed using a multicast mechanism instead of unicasting such as the traditional BU of the RO. The performance of the proposed multicast-based BU scheme is examined with an analytical model which shows that the BU cost enhancement is up to 32.9% over IPDbased, hence, it is feasible to predict that the proposed scheme could benefit in other NEMO RO protocols.

• Journal of Satellite, Information and Communications
• /
• v.8 no.4
• /
• pp.135-141
• /
• 2013

Subway in Korea, most of a metropolitan public transport use only worth ten million people a day floating population of wireless communication can be considered HOT SOPT. These three operators' 2G/3G/4G / Wi-Fi / T-DMB frequency and the number of services to co-exist, and the subway train passengers and subway party for operation and management of the communication network is also the co-subway passenger safety and for this service for the effects of mutual interference of whether the verification was necessary. This research and testing different frequency / communication interference between services and testing to determine whether, through the subway authorities and mobile operators in each frequency-specific interaction check and there is no interference to the safety and quality of subway passengers communication services that can be verified as the data was found. The verification methods in the metro area, not just from one region to determine whether the interference with a common verification methods can be applied.

• Journal of The Korean Astronomical Society
• /
• v.56 no.2
• /
• pp.213-224
• /
• 2023

Type II solar radio bursts show frequency drifts from high to low over time. They have been known as a signature of coronal shock associated with Coronal Mass Ejections (CMEs) and/or flares, which cause an abrupt change in the space environment near the Earth (space weather). Therefore, early detection of type II bursts is important for forecasting of space weather. In this study, we develop a deep-learning (DL) model for the automatic detection of type II bursts. For this purpose, we adopted a 1-D Convolution Neutral Network (CNN) as it is well-suited for processing spatiotemporal information within the applied data set. We utilized a total of 286 radio burst spectrum images obtained by Hiraiso Radio Spectrograph (HiRAS) from 1991 and 2012, along with 231 spectrum images without the bursts from 2009 to 2015, to recognizes type II bursts. The burst types were labeled manually according to their spectra features in an answer table. Subsequently, we applied the 1-D CNN technique to the spectrum images using two filter windows with different size along time axis. To develop the DL model, we randomly selected 412 spectrum images (80%) for training and validation. The train history shows that both train and validation losses drop rapidly, while train and validation accuracies increased within approximately 100 epoches. For evaluation of the model's performance, we used 105 test images (20%) and employed a contingence table. It is found that false alarm ratio (FAR) and critical success index (CSI) were 0.14 and 0.83, respectively. Furthermore, we confirmed above result by adopting five-fold cross-validation method, in which we re-sampled five groups randomly. The estimated mean FAR and CSI of the five groups were 0.05 and 0.87, respectively. For experimental purposes, we applied our proposed model to 85 HiRAS type II radio bursts listed in the NGDC catalogue from 2009 to 2016 and 184 quiet (no bursts) spectrum images before and after the type II bursts. As a result, our model successfully detected 79 events (93%) of type II events. This results demonstrates, for the first time, that the 1-D CNN algorithm is useful for detecting type II bursts.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.12
• /
• pp.778-784
• /
• 2017

In this paper, we propose wired and wireless distributed control systems designed to improve the freight logistics efficiency and verify wired distributed control systems. The verification condition required that 50 cargo vehicles be connected and operated to travel 21 km from Busan Sinhang station to Jinlye Station at an average speed of about 100km/h. The verification results show that the traction output and braking output of the control and controlled cars are dispersed by the wired distributed control system. The application is expected to more than double the efficiency of the logistics compared to the existing freight transportation system. However, in the case of the wired distributed control system, cable installation and maintenance are difficult, and it is impossible to change the combination of freight vehicles. Through the verification of the wired distributed control system, the applicability of distributed control systems to freight vehicles in Korea was confirmed and the system was further developed to produce a wireless distributed control system. In order to apply the wireless distributed control system, a propagation environment analysis for the ISM band was performed in the testbed and, as a result, it was confirmed that Wifi technology using the ISM band could be utilized. In order to use the WDP (Wireless Distributed Power) devices newly installed in the target vehicles, the transmission / reception control signals associated with the propulsion / braking / total control devices are defined. In the case of wireless distributed control systems, the convenience of their application and operation is guaranteed, but reliability and emergency safety measures should because of the dependence of the control of the vehicle on radio signals.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.227-233
• /
• 2019

Recently, along with the recent development of deep learning technique, neural networks are achieving success in computer vision filed. Convolutional neural network have shown outstanding performance in not only for a simple image classification task, but also for tasks with high difficulty such as object segmentation and detection. However many such deep learning models are based on supervised-learning, which requires more annotation labels than image-level label. Especially image semantic segmentation model requires pixel-level annotations for training, which is very. To solve these problems, this paper proposes a weakly-supervised semantic segmentation method which requires only image level label to train network. Existing weakly-supervised learning methods have limitations in detecting only specific area of object. In this paper, on the other hand, we use multi-classifier deep learning architecture so that our model recognizes more different parts of objects. The proposed method is evaluated using VOC 2012 validation dataset.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.111-118
• /
• 2022

In computer vision research, the two-dimensional human pose is a very extensive research direction, especially in pose tracking and behavior recognition, which has very important research significance. The acquisition of human pose targets, which is essentially the study of how to accurately identify human targets from pictures, is of great research significance and has been a hot research topic of great interest in recent years. Human pose recognition is used in artificial intelligence on the one hand and in daily life on the other. The excellent effect of pose recognition is mainly determined by the success rate and the accuracy of the recognition process, so it reflects the importance of human pose recognition in terms of recognition rate. In this human body gesture recognition, the human body is divided into 17 key points for labeling. Not only that but also the key points are segmented to ensure the accuracy of the labeling information. In the recognition design, use the comprehensive data set MS COCO for deep learning to design a neural network model to train a large number of samples, from simple step-by-step to efficient training, so that a good accuracy rate can be obtained.