• Journal of Animal Science and Technology
• /
• 제63권6호
• /
• pp.1453-1463
• /
• 2021

Feeding is the most important behavior that represents the health and welfare of weanling pigs. The early detection of feed refusal is crucial for the control of disease in the initial stages and the detection of empty feeders for adding feed in a timely manner. This paper proposes a real-time technique for the detection and recognition of small pigs using a deep-leaning-based method. The proposed model focuses on detecting pigs on a feeder in a feeding position. Conventional methods detect pigs and then classify them into different behavior gestures. In contrast, in the proposed method, these two tasks are combined into a single process to detect only feeding behavior to increase the speed of detection. Considering the significant differences between pig behaviors at different sizes, adaptive adjustments are introduced into a you-only-look-once (YOLO) model, including an angle optimization strategy between the head and body for detecting a head in a feeder. According to experimental results, this method can detect the feeding behavior of pigs and screen non-feeding positions with 95.66%, 94.22%, and 96.56% average precision (AP) at an intersection over union (IoU) threshold of 0.5 for YOLOv3, YOLOv4, and an additional layer and with the proposed activation function, respectively. Drinking behavior was detected with 86.86%, 89.16%, and 86.41% AP at a 0.5 IoU threshold for YOLOv3, YOLOv4, and the proposed activation function, respectively. In terms of detection and classification, the results of our study demonstrate that the proposed method yields higher precision and recall compared to conventional methods.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제34권7호
• /
• pp.585-594
• /
• 2007

오류역전파 방법을 이용하는 신경망들은 패턴들의 학습시간이 매우 오래 걸리고 또한 추가학습과 반복학습의 한계를 가지며, 이런 단점을 보완할 수 있는 이진신경망(Binary Neural Network, BNN)이 Aleksander에 의해 제안되었다. 그러나 BNN도 반복학습에 있어서는 단점을 가지고 있으며, 일반화 패턴을 추출하기 어렵다. 본 논문에서는 BNN의 구조를 개선하여 반복학습과 추가학습이 가능할 뿐 아니라, 특징점들까지 추출할 수 있는 다중 판별자를 가지는 삼차원 뉴로 시스템을 제안한다. 제안된 모델은 기존의 BNN을 기반으로 하여 만들어진 이차원 특징을 가지는 Single Layer Network(SLN)에 귀환회로가 추가되어 특징점들을 누적할 수 있는 삼차원 신경망이다. 학습을 통해 누적된 정보는 판별자의 각 신경세포에 임계치를 조정함으로써 일반화 패턴을 추출할 수 있다. 그리고 생성된 일반화 패턴을 인식에 재사용함으로써 반복학습의 효율성을 높였다. 최종 판정 단계에서는 Maximum Response Detector(MRD)를 이용하였다. 본 논문에서 제안한 시스템을 평가하기 위하여 NIST에서 제공하는 숫자 자료를 이용하였으며, 99.3%의 인식률을 얻었다.

• 한국지능시스템학회논문지
• /
• 제13권4호
• /
• pp.474-479
• /
• 2003

In this paper, we proposed the novel method for the recognition of English calling cards by using the projection method and the enhanced RBF (Radial Basis Function) network. The recognition of calling cards consists of the extraction phase of character areas and the recognition phase of extracted characters. In the extraction phase, first of all, noises are removed from the images of calling cards, and the feature areas including character strings are separated from the calling card images by using the horizontal smearing method and the 8-directional contour tracking method. And using the image projection method, the feature areas are split into the areas of individual characters. We also proposed the enhanced RBF network that organizes the middle layer effectively by using the enhanced ART1 neural network adjusting the vigilance threshold dynamically according to the homogeneity between patterns. In the recognition phase, the proposed neural network is applied to recognize individual characters. Our experiment result showed that the proposed recognition algorithm has higher success rate of recognition and faster learning time than the existing neural network based recognition.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
• /
• pp.288-295
• /
• 1998

This paper proposes a new data classification method based on the tolerant rough set that extends the existing equivalent rough set. Similarity measure between two data is described by a distance function of all constituent attributes and they are defined to be tolerant when their similarity measure exceeds a similarity threshold value. The determination of optimal similarity theshold value is very important for the accurate classification. So, we determine it optimally by using the genetic algorithm (GA), where the goal of evolution is to balance two requirements such that (1) some tolerant objects are required to be included in the same class as many as possible. After finding the optimal similarity threshold value, a tolerant set of each object is obtained and the data set is grounded into the lower and upper approximation set depending on the coincidence of their classes. We propose a two-stage classification method that all data are classified by using the lower approxi ation at the first stage and then the non-classified data at the first stage are classified again by using the rough membership functions obtained from the upper approximation set. We apply the proposed classification method to the handwritten numeral character classification. problem and compare its classification performance and learning time with those of the feed forward neural network's back propagation algorithm.

• 한국전자통신학회논문지
• /
• 제15권2호
• /
• pp.349-356
• /
• 2020

본 논문은 교통사고 방지를 위한 운전자의 눈 영상비를 이용한 상태 경고시스템의 설계에 대해 소개하고 있다. 제안하는 운전자 상태 경고 시스템은 눈 인식을 위한 카메라, 카메라를 통해 들어오는 정보를 처리하는 라즈베리파이, 그리고 그 정보를 통해 운전자에게 경고를 줄 때 필요한 부저와 진동기로 구성되어 있다. 운전자의 눈을 인식하기 위해서 기울기 방향성 히스토그램 기술과 딥러닝 기반의 얼굴 표지점 추정 기법을 사용하였다. 동작을 시작하면, 시스템은 눈 주변의 6개의 좌표를 통해 눈 영상비를 계산한다. 그리고 눈을 뜬 상태와 감은 상태의 눈 영상비를 각각 계산한 후 이 두 값으로부터 눈의 상태를 판단하는데 사용하는 문턱 값을 설정한다. 문턱 값이 운전자의 눈 크기에 적응하면서 설정되기 때문에 시스템은 최적의 문턱 값을 사용하여 운전자의 상태를 판단할 수 있다. 또한 낮은 조도에서도 눈을 인식할 수 있도록 회색조 변환 이미지와 LAB모델 이미지를 합성하여 사용하였다.

• 한국환경과학회지
• /
• 제30권12호
• /
• pp.1101-1111
• /
• 2021

In this study, among the W-S-R(Wiper-Signal-Rainfall) relationship methods used to produce sensor-based rain information in real time, we sought to produce actual rainfall information by applying machine learning techniques to account for the effects of wiper operation. To this end, we used the gradient descent and threshold map methods for pre-processing the cumulative value of the difference before and after wiper operation by utilizing four sensitive channels for optical sensors which collected rain sensor data produced by five rain conditions in indoor artificial rainfall experiments. These methods produced rainfall information by calculating the average value of the threshold according to the rainfall conditions and channels, creating a threshold map corresponding to the 4 (channel) × 5 (considering rainfall information) grid and applying Optima Rainfall Intensity among the big data processing techniques. To verify these proposed results, the application was evaluated by comparing rainfall observations.

• Journal of Audiology & Otology
• /
• 제25권2호
• /
• pp.65-71
• /
• 2021

Background and Objectives: In masking level difference (MLD), the masked detection threshold for a signal is determined as a function of the relative interaural differences between the signal and the masker. Study 1 analyzed the results of school-aged children with good school performance in the MLD test, and study 2 compared their results with those of a group of children with poor academic performance. Subjects and Methods: Study 1 was conducted with 47 school-aged children with good academic performance (GI) and study 2 was carried out with 32 school-aged children with poor academic performance (GII). The inclusion criteria adopted for both studies were hearing thresholds within normal limits in basic audiological evaluation. Study 1 also considered normal performance in the central auditory processing test battery and absence of auditory complaints and/or of attention, language or speech issues. The MLD test was administered with a pure pulsatile tone of 500 Hz, in a binaural mode and intensity of 50 dBSL, using a CD player and audiometer. Results: In study 1, no significant correlation was observed, considering the influence of the variables age and sex in relation to the results obtained in homophase (SoNo), antiphase (SπNo) and MLD threshold conditions. The final mean MLD threshold was 13.66 dB. In study 2, the variables did not influence the test performance either. There was a significant difference between test results in SπNo conditions of the two groups, while no differences were found both in SoNo conditions and the final result of MLD. Conclusions: In study 1, the cut-off criterion of school-aged children in the MLD test was 9.3 dB. The variables (sex and age) did not interfere with the MLD results. In study 2, school performance did not differ in the MLD results. GII group showed inferior results than GI group, only in SπNo condition.

• 대한청각학회지
• /
• 제25권2호
• /
• pp.65-71
• /
• 2021

Background and Objectives: In masking level difference (MLD), the masked detection threshold for a signal is determined as a function of the relative interaural differences between the signal and the masker. Study 1 analyzed the results of school-aged children with good school performance in the MLD test, and study 2 compared their results with those of a group of children with poor academic performance. Subjects and Methods: Study 1 was conducted with 47 school-aged children with good academic performance (GI) and study 2 was carried out with 32 school-aged children with poor academic performance (GII). The inclusion criteria adopted for both studies were hearing thresholds within normal limits in basic audiological evaluation. Study 1 also considered normal performance in the central auditory processing test battery and absence of auditory complaints and/or of attention, language or speech issues. The MLD test was administered with a pure pulsatile tone of 500 Hz, in a binaural mode and intensity of 50 dBSL, using a CD player and audiometer. Results: In study 1, no significant correlation was observed, considering the influence of the variables age and sex in relation to the results obtained in homophase (SoNo), antiphase (SπNo) and MLD threshold conditions. The final mean MLD threshold was 13.66 dB. In study 2, the variables did not influence the test performance either. There was a significant difference between test results in SπNo conditions of the two groups, while no differences were found both in SoNo conditions and the final result of MLD. Conclusions: In study 1, the cut-off criterion of school-aged children in the MLD test was 9.3 dB. The variables (sex and age) did not interfere with the MLD results. In study 2, school performance did not differ in the MLD results. GII group showed inferior results than GI group, only in SπNo condition.

• 한국방재안전학회논문집
• /
• 제14권2호
• /
• pp.1-11
• /
• 2021

최근 우리나라에서는 기후변화로 인하여 기상재해의 위험성이 증가하고 있고 특히 강우로 인한 피해가 계속해서 강조되고 있다. 현재의 기상예보가 정량적 강우를 제시해주지만 피해 정도를 예상하는 데에는 여러 가지 어려움이 존재한다. 그래서 피해에 따른 영향을 파악하기 위해서는 유역별 한계강우량이 필요하다. 강우로 인한 피해는 지역별로 상이하게 일어나고 있고 각 유역의 특성인자가 고려된 분석은 한계가 존재한다. 또한 강우가 올 때마다 수문모델을 통한 강유-유출분석에는 시간이 많이 소모되고 단순 강우 데이터만 사용하여 분석되는 경우가 많다. 본 연구는 GIS데이터를 이용하였고 2개의 수문모델을 커플링하여 침수를 유발하는 한계유출량으로부터 한계강우량을 산정하였다. 산정결과는 실제사례와 비교하여 결과를 검증하였고 대체로 위험지역에 대해 피해가 난 것으로 분석되었다. 향후 본 연구를 통해 사전에 침수위험지역에 대해 대비를 할 수 있을 것이고 머신러닝 분석방법을 추가한다면 정확도가 높아질 것으로 예상된다.

• 산업융합연구
• /
• 제18권1호
• /
• pp.79-85
• /
• 2020

최근 원격조종과 자율조종이 가능한 무인항공기(RPAS:Remotely Piloted Aircraft System)가 택배 드론, 소방드론, 구급 드론, 농업용 드론, 예술 드론, 드론 택시 등 각 산업 분야와 공공기관에서의 관심과 활용이 높아지고 있다. 자율조종이 가능한 무인드론의 안정성 문제는 앞으로 드론 산업의 발달과 함께 진화하면서 해결해야 할 가장 큰 과제이기도 하다. 드론은 자율비행제어 시스템이 지정한 경로로 비행하고 목적지에 정확하게 자동 착륙을 수행할 수 있어야 한다. 본 연구는 드론의 센서와 GPS의 위치 정보의 오류를 보완하는 방법으로서 착륙지점 영상을 통해 드론의 도착 여부를 확인하고 정확한 위치에서의 착륙을 제어하는 기법을 제안한다. 서버에서 도착지 영상을 구글맵 API로부터 수신받아 딥러닝으로 학습하고, 드론에 NAVIO2와 라즈베리파이, 카메라를 장착하여 착륙지점의 이미지를 촬영한 다음 이미지를 서버에 전송한다. Deep Learning으로 학습된 결과와 비교하여 임계치에 맞게 드론의 위치를 조정한 후 착륙지점에 자동으로 착륙할 수 있다.