• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.411-425
• /
• 2021

In this paper, a vehicle recognition algorithm based on deep convolutional neural network and compression dictionary is proposed. Firstly, the network structure of fine vehicle recognition based on convolutional neural network is introduced. Then, a vehicle recognition system based on multi-scale pyramid convolutional neural network is constructed. The contribution of different networks to the recognition results is adjusted by the adaptive fusion method that adjusts the network according to the recognition accuracy of a single network. The proportion of output in the network output of the entire multiscale network. Then, the compressed dictionary learning and the data dimension reduction are carried out using the effective block structure method combined with very sparse random projection matrix, which solves the computational complexity caused by high-dimensional features and shortens the dictionary learning time. Finally, the sparse representation classification method is used to realize vehicle type recognition. The experimental results show that the detection effect of the proposed algorithm is stable in sunny, cloudy and rainy weather, and it has strong adaptability to typical application scenarios such as occlusion and blurring, with an average recognition rate of more than 95%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.358-361
• /
• 2021

In order to improve the accuracy of small target detection more effectively, this paper proposes an improved single shot detector (SSD) target detection and recognition method based on cspdarknet53, which introduces lightweight ECA attention mechanism and Feature Pyramid Network (FPN). First, the original SSD backbone network is replaced with cspdarknet53 to enhance the learning ability of the network. Then, a lightweight ECA attention mechanism is added to the basic convolution block to optimize the network. Finally, FPN is used to gradually fuse the multi-scale feature maps used for detection in the SSD from the deep to the shallow layers of the network to improve the positioning accuracy and classification accuracy of the network. Experiments show that the proposed target detection algorithm has better detection accuracy, and it improves the detection accuracy especially for small targets.

• Korean Journal of Heritage: History & Science
• /
• v.45 no.3
• /
• pp.174-193
• /
• 2012

This study focused on distribution ratio of stone properties based on material characteristic analysis, provenance presumption and transportation route interpretation of the Sungnyemun stone block foundation. The stone block foundation is composed of pinkish granite (56.0%), reddish granite (4.5%) and leucocratic granite (26.2%) of original stones and pinkish granite of new stones(13.3%). The rock-forming minerals for granites are consisted mainly of quartz, alkali-feldspar, plagioclase and biotite, and are similar geochemical evolution trend of major, rare earth, compatible and incompatible elements. Therefore, it is clear that the rocks are genetically same origin. As a result of magnetic susceptibility measurement, the pinkish and reddish granite of original stones and pinkish granite of new stones showed normal distribution around about 4.00(${\times}10^{-3}SI\;unit$). But the leucocratic granite of original stones were confirmed ilmenite series under about 1.00(${\times}10^{-3}SI\;unit$). As a result of provenance interpretation and transportation route analysis based on the petrological results, the provenance of pinkish granite and reddish granite of original stones are presumed the north slope in Namsan mountain and Naksan mountain. Also, the leucocratic granite of original stones and the pinkish granite of new stones are strongly possible furnished from the south and north slope in Namsan mountain and Naksan mountain, respectively.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.36 no.2
• /
• pp.13-24
• /
• 2020

This study derives the characteristics of the private external space planning in multi-family housing through the analysis of the good case built after 2000 in Europe. First, the cases were categorized into block or block perimeter, linear and point type to examine the relationship between the type of building in urban context and the location of private external space. By block or block perimeter and linear type, private external spaces are planned in the inner courtyards or open space between buildings used as common space for residents, inducing communications between neighbors. And the direction of private external space depends on the arrangement of the building mass in urban context. In the classification as point type, there are many cases, where private external spaces are arranged in all directions, connected almost all interior spaces. Second, based on the above results, the planned characteristics of the private external space are derived by dividing it into three categories: intermediated space between inside and outside, intermediate space between private and public /individual and collective space and the identity of the intermediate space. (1) In most cases, direction, size of enclosed area and location of private extern space is designed to fit the surrounding context, so residents can perceive as much of the assets of the surrounding environment as possible, and it can be used as an extended area of living space. In another cases, it is divided into various sub-areas to experience the spatial transition from inside to outside or vice versa. 2) The private external space, which is placed in a courtyard or in a collective open space, is partially enclosed and blocked, allowing interaction with the neighbors without pressure. Along the street, they are designed to allow residents to experience the vitality of the city and to be formative element of the facade, which could confidently reveal the lifestyle and taste of residents. 3) By some of point types, which facade is three-demensional layer as a habitable external space, the private external space is very flexible for use. This intermediate space is composed of diverse spaces for various needs, or it has generous size with positional conditions connected with all interior spaces to be used multi-functional.

• Journal of Sericultural and Entomological Science
• /
• v.31 no.2
• /
• pp.102-112
• /
• 1989

Principal component analysis and cluster analysis were performed on the nine quantitative characters of the one hundred and forty eight silkworm genetic stocks. The six major quantitative characters such as cocoon yield, cocoon weight, cocoon shell weight, cocoon shell percentage, larval period of the 5th instar silkworm, and total larval period showed significantly positive correlation between them. The first three principal components extracted form the initial nine variables by principal component analysis accounted for about eighty percent of original information. The first and second principal components were characterized as factors related to silk productivity, and cocoon productivity, respectively. On the basis of multivariate analysis using city block distance determined from the first three principal components to measure the phenotypic diversity, the one hundred and forty eight silkworm genetic stocks could be clustered into seven varietal groups, and the phenotypic diversity between the varietal groups was partly related to their geographical origins. Among 7 varietal group, group II and IV revealed higher silk and cocoon productivity.

• Journal of Advanced Navigation Technology
• /
• v.26 no.4
• /
• pp.211-218
• /
• 2022

Continuous wave (CW) radar has the advantage of reliability and accuracy compared to other sensors such as camera and lidar. In addition, binarized neural network (BNN) has a characteristic that dramatically reduces memory usage and complexity compared to other deep learning networks. Therefore, this paper proposes binarized neural network based human identification and motion classification system using CW radar. After receiving a signal from CW radar, a spectrogram is generated through a short-time Fourier transform (STFT). Based on this spectrogram, we propose an algorithm that detects whether a person approaches a radar. Also, we designed an optimized BNN model that can support the accuracy of 90.0% for human identification and 98.3% for motion classification. In order to accelerate BNN operation, we designed BNN hardware accelerator on field programmable gate array (FPGA). The accelerator was implemented with 1,030 logics, 836 registers, and 334.904 Kbit block memory, and it was confirmed that the real-time operation was possible with a total calculation time of 6 ms from inference to transferring result.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.8 no.3
• /
• pp.129-143
• /
• 2006

This study is to review the printed cotton textile industry of Europe in 17th-l8th century, and specially investigate the development of the Toile do Jouy, printed French fabrics around the 18th century. Generally, the Toile de Jouy has two different meanings. The first meaning is the popular printed cotton textiles producted by wood block printing, copper plate printing and roller printing techniques at Jouy on Joas factory in France, around 18th century. The second meaning is the monochromatic upholstery fabrics printed by copper plate. Actually, this monochromatic printed textiles were the most popular printed cotton fabrics with large scale scenic designs with people, trees, birds, buildings, mythical heroes, protagonists of novel and country scenes of shepherds, sheep and other animals manufactured by Jouy on Joas factory. Main issue of this paper is to propose features of pattern, color and classify types of patterns expressed on the Toile de Jouy fabrics according to printing techniques such as wood block printing, copper plate printing and copper roller printing. And this study is also to analyze on origins of the variety of names called the printed cotton textiles in those days. The results of this study can help to understand the knowledge of printed cotton textiles in Europe and be effectively applied to develop printed fabric design in the textile industry.

• Journal of the Korean Geotechnical Society
• /
• v.18 no.2
• /
• pp.23-37
• /
• 2002

Failure of the cut slope is triggered by combination of internal and extemal failure factors. Internal failure factors are related to geological and geometrical conditions of slope itself, and natural and/or artificial loadings on slope can be the external failure factors. Influences of these failure factors show different intensity according to the ground condition and are controlled by behavior characters of the slope. In this study, the soil depth ratio(SR), block size ratio(BR) and rock strength are used as the criteria to divide ground condition based on behavior characteristics. Ground condition of the slope is divided into discontinuous jointed rock mass and continuos soil-like mass, highly fractured rock mass and massive rock mass by the criteria(SR and BR). The SFi-system is a rating system to determine the slope failure index(SFi) by analyzing internal and external factors based on classification of the ground condition. The results of the SFi-system application to the real cut slopes show close relationship between the SFi value and potential or dimension of the failure. Therefore, the SFi-system can be used as a useful tool to predict and analyze the characteristic of the slope failure.

• Journal of The Korean Dental Society of Anesthesiology
• /
• v.9 no.1
• /
• pp.24-29
• /
• 2009

When performing the inferior alveolar nerve block anesthesia, surgeon often faced a difficulty of the surgical operation due to the incomplete anesthesia. One of the reason is the variety of mandibular canal anatomy. Up to now, there are some reports of index cases about bifid mandibular canal among mandibular canal anatomic variation, and some classification is applied according to anatomical location and configuration. When surgical operation is performed involving mandible such as dantal implant treatment, extraction of an impacted third molar, sagittal split ramus osteotomy, etc, the position of mandibular canal should be considered. Bifid mandibular canal clinically causes troublesome cases of anesthesia when inferior alvelor nerve block, especially is performed extraction of an impacted third molar. Therefore, It is important for clinicians to recognize the presence of bifid canals on radiographys. Nowadays, the position of mandibular canal can be measured precisely by using Dental CT. It is not found by panorama image but is found by Dental CT sometimes. Among the patients, which take panorama and Dental CT simultaneously, for tooth extraction of lower impacted third molar in our department, we report the case that did not identifying in panorama but identifying it in Dental CT.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.3
• /
• pp.74-80
• /
• 2007

Advances in electronic and computer technologies have paved the way for the proliferation of WSN(wireless sensor networks). Accordingly, necessity of anti-collusion and authentication technology is increasing on the sensor network system. Some of the algorithm developed for the anti-collision sensor network can be easily adopted to wireless sensor network platforms and in the same time they can meet the requirements for sensor networks like: simple parallel distributed computation, distributed storage, data robustness and auto-classification of sensor readings. To achieve security in wireless sensor networks, it is important to be able to establish safely channel among sensor nodes. In this paper, we proposed the USN(Ubiquitous Sensor Network) channel establishment algorithm for sensor's authentication and anti-collision. Two different data aggregation architectures will be presented, with algorithms which use wavelet filter to establish channels among sensor nodes and BIBD (Balanced Incomplete Block Design) which use anti-collision methods of the sensors. As a result, the proposed algorithm based on BIBD and wavelet filter was made for 98% collision detection rate on the ideal environment.