• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.4
• /
• pp.243-248
• /
• 2004

Automatic fingerprint identification is a process of direction extraction, binarization, thinning, minutiae extraction of fingerprint identification. In this process, binarization after direction extraction affects a process of thinning and minutiae extraction. The fasle binarization is increased the false minutiae extraction rate. In this paper, we proposed more exact minutiae extraction algorithm with more enhanced binarization method, compared with traditional binarization process. We could have more enhanced results by using the direction and the half distance between ridges as the threshold of binarization process. In an experiment, Fingerprint images from NIST DBI are tested and the result shows that the proposed binarization algorithm increases minutiae extraction.

• Korean Journal of Veterinary Service
• /
• v.15 no.1
• /
• pp.81-88
• /
• 1992

This study was conducted to determine the microorganisms inhabitating in sow genital organs and their anti-microbial drug susceptibility During the period between February, 1991 and November 1991, 128 sow genital organs were sampled at six abattoirs. Gross pathological examination and bacterial isolation and identification were performed from the genital organ. In addition, antimicrobial drug susceptibility for the major organisms isolated were examined. 1. Among the bateria isolated from normal genital organs, E. coli(30.7%) Stahylococcus spp.(29.4%), Corynebarterium pyogenes(C. pyogenes) (14.7%), Streptococcus spp.(13.3%) were most freqently isolated, whereas the genera of Klebsiella, Actinobacillus, and Serratia were detected less freqently. 2. Among the bacteria isolated from abnormal genital organs, C. pyogenes,(37.7%), Stahylococcus spp.(30.2%), Proteus spp. (26.4%) , Pasteurella spp. (18.9%) , Steptococcus spp. (9.4%) were most freqently isolated whereas the genera of Pseudomonas, Serratia and Klebsiella were detected less freqently. 3. From sow genital organs showing lesion of endometritis and purulent endometritis C. pyogenes were most freqently isolated, the isolation rate being 67.7％ and followed by Stahylococcus spp., E. coli, Proteus spp., Steptococcus spp. and Pasteurella spp. in the order. 4. Antimicrobial drug susceptibility of the major organisms showed that all the isolates were susceptible to cephalothin, ampicillin, chloramphenicol and sulfamethoxazole / trimethoprim, but resistant to penicillin and streptomycin.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.105-108
• /
• 2011

RFID(Radio Frequency Identification)를 이용한 창고관리시스템은 작업환경을 개선시키고 작업처리 속도와 정확성을 증가시킨다. RFID 기술은 기존의 바코드를 대체하여 물품관리를 네트워크화하고 지능화함으로써 창고의 물품관리에 혁신을 선도하고 있다. 그러나 RFID는 포장의 물질적 특성, 태그부착 위치, 노이즈 발생원이 있는 주위작업 환경 등에 따라 인식률에 상당한 차이를 낼 수 있고, 이러한 문제 때문에 실제 비즈니스 영역에서의 적용이 다소 제한받고 있다. 그러므로 RFID를 이용한 창고관리시스템이 모든 업무에 가동되어 업무 효율성을 높이기 위해서는 업무 흐름 도중에 발생할 수 있는 다양한 예외상황을 찾아내고 이를 빠르게 해결할 수 있는 방안이 필요하다. 본 논문에서는 RFID를 이용하는 냉동창고에서 업무 자동화가 끊어짐없이(seamless) 이어질 수 있도록 다양한 유형의 RFID 오류원인을 식별해내고 이를 해결할 수 있는 방안에 대해 제시한다. 이를 위해 RFID가 동작하는 작업환경을 업무 별로 분류하고, 각 작업환경에서 진행되는 업무흐름을 분석하여 각 오류를 유형별로 체계화 시킨다. 분류된 오류들에 대해 이를 감지하고 해결할 수 있는 방안을 찾음으로써 냉동창고 내의 전체적인 업무흐름을 원활히 하여 업무처리 소요시간을 줄일 수 있게 한다.

• Quantitative Bio-Science
• /
• v.37 no.2
• /
• pp.125-132
• /
• 2018

In this study, noble strains of lactic acid bacteria were isolated and identified by genetic analysis of 16s rRNA. Also, pH-dependent growth curve, cholesterol assimilation ability and sugar production efficiency were measured. Lactic acid bacteria were identified to inhabit in the milks from various animals. Results of sequence analysis showed that there were differences in 16S rRNA sequence among strains and part of gene deletion was also recognized. Growth rates were varied, too, depending on the pH of the medium. Lactobacillus rhamnosus LOCK908 isolated from cow milk showed the highest growth rate and high cholesterol assimilation ability. Results of sugar fermentation tests were relatively consistent with the sequencing results. So, we propose newly isolated Lactobacillus rhamnosus LOCK908 as useful candidate for a starter of fermented beverage and probiotics. Results of this study will contribute to the isolation and identification of noble Lactic acid bacteria and to the public health.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.712-714
• /
• 2016

The PS algorithm divides the tags within the identification range of reader into smaller groups by increasing the transmission power incrementally and identifies them. In 13.56MHz RFID system of Auto-ID center, STAC protocol is defined as an anti-collision algorithm for multiple tag reading. In this paper, we propose a STAC/PS algorithm that the PS algorithm is applied in the STAC protocol. The simulation results show that the STAC/PS algorithm can achieve faster tag identification speed compared with STAC protocol due to the low collision rate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.1
• /
• pp.131-146
• /
• 2021

Multimodal biometric-based recognition has been an active topic because of its higher convenience in recent years. Due to high user convenience of finger, finger-based personal identification has been widely used in practice. Hence, taking Finger-Print (FP), Finger-Vein (FV) and Finger-Knuckle-Print (FKP) as the ingredients of characteristic, their feature representation were helpful for improving the universality and reliability in identification. To usefully fuse the multimodal finger-features together, a new robust representation algorithm was proposed based on hierarchical model. Firstly, to obtain more robust features, the feature maps were obtained by Gabor magnitude feature coding and then described by Local Binary Pattern (LBP). Secondly, the LGBP-based feature maps were processed hierarchically in bottom-up mode by variable rectangle and circle granules, respectively. Finally, the intension of each granule was represented by Local-invariant Gray Features (LGFs) and called Hierarchical Local-Gabor-based Gray Invariant Features (HLGGIFs). Experiment results revealed that the proposed algorithm is capable of improving rotation variation of finger-pose, and achieving lower Equal Error Rate (EER) in our homemade database.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.1818-1832
• /
• 2022

Violence in the Internet era poses a new challenge to the current counter-riot work, and according to research and analysis, most of the violent incidents occurring are related to the dissemination of violence images. The use of the popular deep learning neural network to automatically analyze the massive amount of images on the Internet has become one of the important tools in the current counter-violence work. This paper focuses on the use of transfer learning techniques and the introduction of an attention mechanism to the residual network (ResNet) model for the classification and identification of violence images. Firstly, the feature elements of the violence images are identified and a targeted dataset is constructed; secondly, due to the small number of positive samples of violence images, pre-training and attention mechanisms are introduced to suggest improvements to the traditional residual network; finally, the improved model is trained and tested on the constructed dedicated dataset. The research results show that the improved network model can quickly and accurately identify violence images with an average accuracy rate of 92.20%, thus effectively reducing the cost of manual identification and providing decision support for combating rebel organization activities.

• Structural Monitoring and Maintenance
• /
• v.9 no.3
• /
• pp.289-303
• /
• 2022

In this study, the impact of assigned pixel labels on the accuracy of crack image identification of steel structures is examined by using an atrous separable convolution neural network (ASCNN). Firstly, images containing fatigue cracks collected from steel structures are classified into four datasets by assigning different pixel labels based on image features. Secondly, the DeepLab v3+ algorithm is used to determine optimal parameters of the ASCNN model by maximizing the average mean-intersection-over-union (mIoU) metric of the datasets. Thirdly, the ASCNN model is trained for various image sizes and hyper-parameters, such as the learning rule, learning rate, and epoch. The optimal parameters of the ASCNN model are determined based on the average mIoU metric. Finally, the trained ASCNN model is evaluated by using 10% untrained images. The result shows that the ASCNN model can segment cracks and other objects in the captured images with an average mIoU of 0.716.

• Nuclear Engineering and Technology
• /
• v.53 no.2
• /
• pp.532-548
• /
• 2021

Nuclear power plants contain several monitoring systems that can identify the in-vessel phenomena of a severe accident (SA). Though a lot of analysis and research is carried out on SA, right from the development of the nuclear industry, not all the possible circumstances are taken into consideration. Therefore, to improve the efficacy of the safety of nuclear power plants, additional analytical studies are needed that can directly monitor severe accident phenomena. This paper presents an interacting multiple model (IMM) based fault detection and diagnosis (FDD) approach for the identification of in-vessel phenomena to provide the accident propagation information using reactor vessel (RV) out-wall temperature distribution during severe accidents in a nuclear power plant. The estimation of wall temperature is treated as a state estimation problem where the time-varying wall temperature is estimated using IMM employing three multiple models for temperature evolution. From the estimated RV out-wall temperature and rate of temperature, the in-vessel phenomena are identified such as core meltdown, corium relocation, reactor vessel damage, reflooding, etc. We tested the proposed method with five different types of SA scenarios and the results show that the proposed method has estimated the outer wall temperature with good accuracy.

• Fisheries and Aquatic Sciences
• /
• v.25 no.12
• /
• pp.637-647
• /
• 2022

A spotted scat, Scatophagus argus, has a high nutritional value and is among Asia's most widely consumed fish species. Thua Thien Hue's consumption market considers this species to be of high economic value and requires protection and conservation of the population. However, the studies on the identification and genetic diversity of S. argus distributed in Vietnam are still lacking. Therefore, mitochondrial cytochrome c oxidase subunit I (COI) gene was utilized to distinguish different populations and investigate the genetic diversity of two populations of S. argus from Tam Giang lagoon, Thua Thien Hue province (n = 31) and Ca Mau province (n = 14). The sequencing results indicated 13 distinct haplotypes among 45 sequences. Five single nucleotide polymorphisms were observed to distinguish Hue spotted scat population. The S. argus population in Ca Mau province was higher haplotype diversity (Hd) and nucleotide diversity (π) than those of Thua Thien Hue province, which demonstrates that there are minor differences between haplotypes. There were genetic distances ranging from 0%-4% within the populations and 6.67% between the two populations. In addition to the sequencing, the comparison of morphology, biology, culture, and the growth rate was sufficient to distinguish the spotted scat S. argus in Thua Thien Hue from Ca Mau.