• 생물환경조절학회지
• /
• 제23권2호
• /
• pp.123-130
• /
• 2014

참외 재배환경은 토양 위의 수평바닥에서 재배된 것을 수확하여야 하며, 참외가 잎으로 덮여져 있어 인식이 어렵고, 덩굴성 줄기로 인해 참외를 그립하기에도 매우 불리하다. 이러한 재배환경에 적합하도록 엔드이펙트, 머니퓰레이터, 인식장치 등의 참외 수확 로봇을 개발하였고 이를 시험하였다. 엔드이펙터는 수확물을 잡기 위한 그립퍼와 줄기를 절단하는 커터로 구분되며, 그립퍼는 4개의 핑거가 동시에 구동하고, 커터는 2개로 전후진 동작이 되도록 설계하여 파지력과 절단력을 제어할 수 있도록 하였다. 머니퓰레이터는 중심축을 기준으로 회전을 하는 L-R형 모델에 직교 좌표형과 셔틀형 머니퓰레이터를 조합한 4축 매니플레이트 구조로 설계하였다. 인식장치는 1차 인식장치인 GVC와 2차 인식장치인 LVC를 이용하여 참외를 식별하고 그 중에서 당도나 숙도를 예측하여 선별하였다. 이 장치를 이용하여 로봇의 성능시험을 한 결과 수확시간은 평균 18.2sec/ea, 픽업율은 평균 91.4%, 손상율은 평균 8.2%, 선별율은 평균 72.6%로 나타났다.

• 대한치과교정학회지
• /
• 제51권2호
• /
• pp.77-85
• /
• 2021

Objective: To evaluate the accuracy of a multi-stage convolutional neural network (CNN) model-based automated identification system for posteroanterior (PA) cephalometric landmarks. Methods: The multi-stage CNN model was implemented with a personal computer. A total of 430 PA-cephalograms synthesized from cone-beam computed tomography scans (CBCT-PA) were selected as samples. Twenty-three landmarks used for Tweemac analysis were manually identified on all CBCT-PA images by a single examiner. Intra-examiner reproducibility was confirmed by repeating the identification on 85 randomly selected images, which were subsequently set as test data, with a two-week interval before training. For initial learning stage of the multi-stage CNN model, the data from 345 of 430 CBCT-PA images were used, after which the multi-stage CNN model was tested with previous 85 images. The first manual identification on these 85 images was set as a truth ground. The mean radial error (MRE) and successful detection rate (SDR) were calculated to evaluate the errors in manual identification and artificial intelligence (AI) prediction. Results: The AI showed an average MRE of 2.23 ± 2.02 mm with an SDR of 60.88% for errors of 2 mm or lower. However, in a comparison of the repetitive task, the AI predicted landmarks at the same position, while the MRE for the repeated manual identification was 1.31 ± 0.94 mm. Conclusions: Automated identification for CBCT-synthesized PA cephalometric landmarks did not sufficiently achieve the clinically favorable error range of less than 2 mm. However, AI landmark identification on PA cephalograms showed better consistency than manual identification.

• 한국지진공학회논문집
• /
• 제5권4호
• /
• pp.97-105
• /
• 2001

고무제품에 근간을 둔 면진장치는 상당한 저온효과와 약간의 변형도 속도효과를 보여준다. 면진장치의 비탄성거동에 영향을 미치는 이들의 속성은 면진장치의 거동을 정확히 모델링하기 위해 반드시 고려되어져야 하기 때문에, 고무와 납 모두에 영향을 미치는 저온효과와 변형도 속도효과를 고려할 수 있는 해석모델을 제시하였다. 얼린 면진장치를 일정 수직하중에서 수평방향 반복하중을 가한 실험결과들로부터 시스템 식별(SI : system identification)을 적용하여 해석모델에 필요한 고무와 납의 매개변수들을 구하였다. 제안된 해석모델은 면진장치의 거동을 유사하게 표현할 수 있음을 보여준다.

• 한국도로학회논문집
• /
• 제16권6호
• /
• pp.181-189
• /
• 2014

PURPOSES : Ambiguous decision on whether rural or urban area for road design can increase the construction cost and restrict the land use of surrounding area. However, administrative classification on rural and urban area is not directly related to road design because of this classification is not based on the engineering viewpoint, so method which can explain the road design context is required. METHODS : Method which enables to identify the area for road design is suggested based on the deceleration expected to be experienced by drivers who use the road section concerned. Deceleration rate corresponding to the area such as rural or urban suggested in Road Design Guideline is used as the criteria to identify the area by comparing this value with the estimated deceleration rate at the road section concerned. Speed profile method is utilized to derive the deceleration rate, and speed estimation way for reflecting both road geometry and intersection is suggested using stopping sight distance concept. RESULTS : The procedure of the method application is suggested, and the design example utilizing the method is provided. CONCLUSIONS : The method is expected to be used to identify the area for road design with engineering viewpoint, and design consistency among the roads with similar driving environment can be made.

• 한국작물학회지
• /
• 제44권2호
• /
• pp.166-170
• /
• 1999

The identification of quantitative trait loci (QTL) has the potential to enhance the efficiency of im- proving food processing traits of soybean. In this study, 92 restriction fragment length polymorphism (RFLP) loci and two morphological markers (W$_1$ and T) were used to identify QTL associated with food processing traits of soybean for sprout in 83 F$_2$-derived lines from a cross of ＇Pureun＇ x ＇Jinpum 2＇. The genetic map consisted of 76 loci which covered about 760 cM and converged into 20 linkage groups. Eighteen markers remained unlinked. Phenotypic data were collected for hypocotyl length, abnormal seedling rate, and sprout yield seven days after seed germination at 2$0^{\circ}C$. Based on the single-factor analysis of variance, eight independent markers were associated with hypocotyl length. Four of seven markers associated with abnormal seedling rate were identified as independent. Seven loci were associated with sprout yield. For three different traits, much of genetic variation was explained by the identified QTL in this population. Several RFLP markers in linkage group (LG) Bl were detected as being associated with three traits, providing a genetic explanation for the biological correlation of sprout yield with hypocotyl length (r=OA07＊＊＊) and with abnormal seedling rate (r=-406＊＊＊).

• 한국컴퓨터정보학회논문지
• /
• 제20권12호
• /
• pp.1-8
• /
• 2015

Wear leveling techniques have been studied to prolong the lifetime of NAND flash memory. Most of studies have used Program/Erase(P/E) cycles as wear index for wear leveling. Unfortunately, P/E cycles could not predict the real lifetime of NAND flash blocks. Therefore, these algorithms have the limited performance from prolonging the lifetime when applied to the SSD. In order to apply the real lifetime, wear leveling algorithms, which use raw Bit Error Rate(rBER) as wear index, have been studied in recent years. In this paper, we propose CrEWL(Cold data identification using raw Bit error rate in Wear Leveling), which uses rBER as wear index to apply to the real lifetime. The proposed wear leveling reduces an overhead of garbage collections by using HBSQ(Hot Block Sequence Queue) which identifies hot data. In order to reduce overhead of wear leveling, CrEWL does not perform wear leveling until rBER of the some blocks reaches a threshold value. We evaluate CrEWL in comparison with the previous studies under the traces having the different Hot/Cold rate, and the experimental results show that our wear leveling technique can reduce the overhead up to 41% and prolong the lifetime up to 72% compared with previous wear leveling techniques.

• 대한의생명과학회지
• /
• 제27권2호
• /
• pp.105-110
• /
• 2021

Short Tandem Repeats (STR) analysis which characterized by genetic polymorphism has been widely used in the forensic genetic fields. Unfortunately, mutation occurred in various STR loci could make it difficult to interpret STR data. Thus, the mutation rate of STR loci plays an important role for the data interpretation in human identification and paternity test. To verify the mutation of the STR loci in the Korean population, 545 trio sets (father, mother, and child) were analyzed with two commercial STR kits that include the 23 autosomal STR loci (D1S1656, TPOX, D2S441, D2S1338, D3S1358, FGA, D5S818, CSF1PO, D7S820, D8S1179, D10S1248, TH01, D12S391, VWA D13S317, D16S539, D18S51, D19S433, D21S11, D22S1045, SE33, Penta E and Penta D). As a result, 36 mutations were observed in 14 STR loci. The types of mutation were also classified by the increase or decrease of the alleles. The overall mutation rate was 1.4×10^-3, and the paternal mutation rate was four times higher than that of the maternal. This study will provide more detailed criterion for human identification by the mutation rate of STR loci in the Korean population.

• 동의생리병리학회지
• /
• 제25권6호
• /
• pp.1113-1118
• /
• 2011

In this paper, when a physician make a diagnosis of the pattern identification (PI) in Korean stroke patients, the development methods of the PI classification function is considered by diagnostic questionnaire of the PI for stroke patients. Clinical data collected from 1,502 stroke patients who was identically diagnosed for the PI subtypes diagnosed by two physicians with more than 3 years experiences in 13 oriental medical hospitals. In order to develop the classification function into PI using Korean Stroke Syndrome Differentiation Standard was consist of the 44 items (Fire heat(19), Qi deficiency(11), Yin deficiency(7), Dampness-phlegm(7)). Using the 44 items, we took diagnostic and prediction accuracy rate through of discriminant model. The overall diagnostic and prediction accuracy rate of the PI subtypes for discriminant model was 74.37%, 70.88% respectively.

• 한국자동차공학회논문집
• /
• 제8권6호
• /
• pp.142-155
• /
• 2000

A MIMO model reference control scheme incorporating the variable structure theory for a vehicle four wheel steering system(4WS) is proposed and evaluated for a class of continuous-time nonlinear dynamics with known or unknown uncertainties. The scheme employs an neural network to identify the plant systems, where the neural network estimates the nonlinear dynamics of the plant. By the Lyapunov direct method, the algorithm is proven to be globally stable, with tracking errors converging to the neighborhood of zero. The merits of this scheme is that the global system stability is guaranteed and it is not necessary to know the exact structure of the system. With the resulting identification model which contains the neural networks, it does not need higher degrees of freedom vehicle model than 3 degree of freedom model. Th proposed scheme is applied to the active four wheel system and shows the validity is used to investigate vehicle handing performances. In simulation of the J-turn maneuver, the reduction of yaw rate overshoot of a typical mid-size car improved by 30% compared to a two wheel steering system(2WS) case, resulting that the proposed scheme gives faster yaw rate response and smaller side angle than the 2WS case.

• 대한의용생체공학회:의공학회지
• /
• 제31권5호
• /
• pp.365-374
• /
• 2010

This paper is about the personal identification algorithm using an ECG that has been studied by a few researchers recently. Previously published algorithm can be classified as two methods. One is the method that analyzes ECG features and the other is the morphological analysis of ECG. The main characteristic of proposed algorithm uses together two methods. The algorithm consists of training and testing procedures. In training procedure, the features of all recognition objects' ECG were extracted and the PCA was performed for morphological analysis of ECG. In testing procedure, 6 candidate ECG's were chosen by morphological analysis and then the analysis of features among candidate ECG's was performed for final recognition. We choose 18 ECG files from MIT-BIH Normal Sinus Rhythm Database for estimating algorithm performance. The algorithm extracts 100 heartbeats from each ECG file, and use 40 heartbeats for training and 60 heartbeats for testing. The proposed algorithm shows clearly superior performance in all ECG data, amounting to 90.96% heartbeat recognition rate and 100% ECG recognition rate.