• 한국멀티미디어학회논문지
• /
• 제20권5호
• /
• pp.769-781
• /
• 2017

Deep learning networks like Convolutional Neural Networks (CNNs) show successful performances in many computer vision applications such as image classification, object detection, and so on. For implementation of deep learning networks in embedded system with limited processing power and memory, deep learning network may need to be simplified. However, simplified deep learning network cannot learn every possible scene. One realistic strategy for embedded deep learning network is to construct a simplified deep learning network model optimized for the scene images of the installation place. Then, automatic training will be necessitated for commercialization. In this paper, as an intermediate step toward automatic training under fisheye camera environments, we study more precise human localization in fisheye images, and propose an accurate human localization method, Automatic Ground-Truth Labelling Method (AGTLM). AGTLM first localizes candidate human object bounding boxes by utilizing GoogLeNet-LSTM approach, and after reassurance process by GoogLeNet-based CNN network, finally refines them more correctly and precisely(tightly) by applying saliency object detection technique. The performance improvement of the proposed human localization method, AGTLM with respect to accuracy and tightness is shown through several experiments.

• 한국생활과학회지
• /
• 제21권5호
• /
• pp.929-945
• /
• 2012

This study examined structured social network types and their relationship to quality on life satisfaction of older adults. Respondents were 418 adults aged 60 or older living alone or as couples. The data was analyzed using K-means cluster analysis. Four networks types were identified: diverse, friend-neighbor focused, family focused, and restricted. Life satisfaction was highest for individuals in the diverse network group and lowest for individuals in the restricted network group. Stepwise multiple regression analysis indicated that life satisfaction of the elderly was affected by the diverse network, family focused network, the relationship quality with children, the relationship quality with neighbors, and the relationship quality with relatives. Results suggested that having diverse social network in close proximity is very important in old age and structural network types may have important practical implications for improving the quality of life among the elderly.

• 제어로봇시스템학회논문지
• /
• 제13권9호
• /
• pp.825-831
• /
• 2007

In this paper, an interface between a human and a computer is presented. The human and computer interface(HCI) serves as another area of human and machine interfaces. Methods for the HCI we used are voice recognition and image recognition for detecting human's emotional feelings. The idea is that the computer can recognize the present emotional state of the human operator, and amuses him/her in various ways such as turning on musics, searching webs, and talking. For the image recognition process, the human face is captured, and eye and mouth are selected from the facial image for recognition. To train images of the mouth, we use the Hopfield Net. The results show 88%$\sim$92% recognition of the emotion. For the vocal recognition, neural network shows 80%$\sim$98% recognition of voice.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.977-985
• /
• 2020

Aiming at the problem of complex feature extraction and low accuracy in human action recognition, this paper proposed a network structure combining batch normalization algorithm with GoogLeNet network model. Applying Batch Normalization idea in the field of image classification to action recognition field, it improved the algorithm by normalizing the network input training sample by mini-batch. For convolutional network, RGB image was the spatial input, and stacked optical flows was the temporal input. Then, it fused the spatio-temporal networks to get the final action recognition result. It trained and evaluated the architecture on the standard video actions benchmarks of UCF101 and HMDB51, which achieved the accuracy of 93.42% and 67.82%. The results show that the improved convolutional neural network has a significant improvement in improving the recognition rate and has obvious advantages in action recognition.

• Bioinformatics and Biosystems
• /
• 제2권2호
• /
• pp.71-74
• /
• 2007

Cell phenotypes are determined by groups of functionally related genes. Microarray profiling of gene expression provides us response of cellular state to its perturbation. Several methods for uncovering a cellular network show reliable network reconstruction. In this study, we present reconstruction of genetic regulatory network of inflammation bowel disease in human peripheral blood mononuclear cell. The microarray based on Affymetrix Gene Chip Human Genome U133 Array Set HG-U133A is processed and applied network reconstruction algorithm, ARACNe. As a result, we will show that inferred network composed of 450 nodes and 2017 edges is roughly scale-free network and hierarchical organization. The major hub, CCNL2 (cyclin A2), in inferred network is shown to be associated with inflammatory function as well as apoptotic function.

• International Journal of Computer Science & Network Security
• /
• 제21권12호
• /
• pp.110-116
• /
• 2021

The article focuses on the need to deepen the issue of human resource management in logistics processes. It is noted that changes in market conditions and turbulence in the institutional environment require managers to form a highly effective human resources policy capable to ensure the innovative development of the enterprise. Functional strategies for human resource management in logistical processes are proposed, namely: adaptive, innovative, selective and exclusive. Innovative technologies that should be used in the adaptive human resources policy process are identified.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.299-309
• /
• 2022

Human factor represents a very challenging issue to organizations. Human factor is responsible for many cybersecurity incidents by noncompliance with the organization security policies. In this paper we conduct a comprehensive review of the literature to identify strategies to address human factor. Security awareness, training and education program is the main strategy to address human factor. Scholars have consistently argued that importance of security awareness to prevent incidents from human behavior.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2007년도 한국컴퓨터종합학술대회논문집 Vol.34 No.1 (D)
• /
• pp.204-207
• /
• 2007

최근 대두되고 있는 무선 센서네트워크는 실생활의 많은 부분에 있어 그 응용 분야를 넓혀 가고 있다. 본 연구는 WSN의 응용 중 Human Health Care에 주안을 두어 WSN을 이용한 원격 진료 시스템에 대해 설계 및 구현을 하였다. 원격 진료 시스템을 위해 각 센서 노드들은 인체의 Body 정보를 수집할 수 있는 센서들을 가지고 신체의 각 부위에 부착된다. 또한 각 센서 노드들은 고유의 Human Body Code를 가지고 있으며 이 고유의 Code에 의해 인체의 어느 부위에서 측정된 Data인지를 Sink 노드로 전송하게 된다. Sink 노드는 수집된 정보를 원격에 위치한 의료진들에게 전송하며 원격의 의료진들은 Sink 노드에서 전송된 정보를 바탕으로 진료 정보를 환자 및 User에게 Feedback하게 된다. Human Body Code는 인체를 세분화하고 각 세분화한 신체 부위에 계층적으로 고유의 Code를 부여한다. 본 연구에서는 실제 Human Body Code를 직접 제작한 센서 Node에 주입하여 Human Body Network을 구성하여 인체에서 센싱되는 Data를 원격에 위치한 PC에서 진료 가능한 원격 진료 시스템을 구현하였다.

• 인터넷정보학회논문지
• /
• 제21권5호
• /
• pp.21-29
• /
• 2020

Accurate estimation of human pose relies on backbone method in which its role is to extract feature map. Up to dated, the method of backbone feature extraction is conducted by the plain convolutional neural networks named by CNN and the residual neural networks named by Resnet, both of which have various architectures and performances. The CNN family network such as VGG which is well-known as a multiple stacked hidden layers architecture of deep learning methods, is base and simple while Resnet which is a bottleneck layers architecture yields fewer parameters and outperform. They have achieved inspired results as a backbone network in human pose estimation. However, they were used then followed by different pose estimation networks named by pose parsing module. Therefore, in this paper, we present a comparison between the plain CNN family network (VGG) and bottleneck network (Resnet) as a backbone method in the same pose parsing module. We investigate their performances such as number of parameters, loss score, precision and recall. We experiment them in the bottom-up method of human pose estimation system by adapted the pose parsing module of openpose. Our experimental results show that the backbone method using VGG network outperforms the Resent network with fewer parameter, lower loss score and higher accuracy of precision and recall.

• 한국전자파학회논문지
• /
• 제25권1호
• /
• pp.62-69
• /
• 2014

본 논문에서는 WBAN(Wireless Body Area Network) On-body 시스템에서 표면 지향 안테나를 사용하여 인체 내부 기관에 의한 영향을 분석하였다. 인체 내부 기관의 영향을 확인하기 위하여 인체 상반신 모델과 실제 인체에 안테나를 부착하여 수신 신호의 세기를 측정하였다. 실험은 인체에 대한 고유 영향을 보기 위하여 무반향실에서 움직임 없이 수행하였고, VNA(Vector Network Analyzer)를 이용하여 수신 신호 세기를 측정하였다. 측정된 데이터를 이용하여 인체 모델과 상반신 모델의 수신 신호 세기를 비교하였고, 인체 내부 기관이 안테나 수신 신호 세기에 미치는 효과를 분석하였다.