• 한국자원식물학회:학술대회논문집
• /
• 한국자원식물학회 2019년도 춘계학술대회
• /
• pp.107-107
• /
• 2019

Millets are provided considerable amounts of nutrients and gluten-free cereal products and their rich non-nutritional compounds having proven health benefits, especially phenolic compounds. The aim of present investigation was to determine phenolic composition and antioxidant and SOD activity of three different millet of genetic resources namely, foxtail, proso and finger millet. Phenolic compounds were extracted from dehulled grain of genetic resources using methanol and examined for their total phenolic content (TPC), antioxidant activities and superoxide dismutase (SOD)-like activity. The TPC range of hog millet, finger millet and finger millet range from 3.3 to 25.1, 11.1 to 29.0 and 3.8 to 94.3 gallic acid equivalent (GAE)mg/g, respectively. Most of TCP content in dehulled millet grains was distributed from 10 to 20 gallic acid equivalent (GAE)/g, but two accessions of finger millet (IT235690 and 235689) were showed over than 90. The antioxidant activities were measured by 1,1-diphenyl-2-picrylhydrazyl (DPPH) free radical scavenging activity. Finger millet and hog millet showed 26.4% and 26.7% in the mean of DPPH scavenging activity percentage, but foxtail millet was 13%. The finger millet showed the higher value than hog and foxtail millet in superoxide dismutase (SOD)-like activity. Particularly, two accessions of finger millet (IT235690 and 235689) showed the highest phenolic content and antioxidant activities among the used millet genetic resources and will be primary resources for finger millet breeding to develop the appropriate breeding strategies.

• 농촌계획
• /
• 제25권2호
• /
• pp.15-21
• /
• 2019

The agricultural environment is changing and becoming more advanced due to the influence of the 4th Industrial Revolution. From the basic plan of Rural Informatics to the current level of 2nd generation smart farms aimed at improving productivity using Big data, cloud network and more IoT technology. We are continuing to provide support and research and development. However, many problems remain to be solved in order to supply and settle smart farms in Korea. The purpose of this study is to provide a method of collecting and sharing data on farming environment and to help improve the income and productivity of farmers based on collected data. In the case of hog farm, the multiple sensors for environmental data like temperature, humidity and gases and the network environment for connecting the internet were established. The environment sensor was made using the ESP8266 Node MCU board as micro-controller, DHT22 sensor for temperature and humidity, and MQ series sensors for various gases in the hog pens. The network sensor was applied experimentally for one month and the environmental data of the hog farm was stored on a web database. This study is expected to raise the importance of collecting and managing the agricultural and environmental data, for the next generation farmers to understand the smart farm more easily and to try it by themselves.

• Asian-Australasian Journal of Animal Sciences
• /
• 제7권4호
• /
• pp.523-526
• /
• 1994

This study was carried out to examine the salting and desalting of small casings from hog and to determine the shelf-life during cold storage. The concentration of salt in the casings equilibrated with that of the added salt after 1 day for 10%, after 2 days for 20% after 7 days for 40% salting level. During desalting at 15 and $30^{\circ}C$, residual salt concentrations in the casings decreased to less than 1% after 1 hour for 10% salt, after 12 hours for 20% salt and after 24 hours for 40% salt. The total colony count of the freshly prepared casing was about log10 4.2. The initial microflora of the prepared casings was dominated by lactic acid bacteria. The higher the salting level, the greater the microbial growth was suppressed during 6 months of storage at refrigerator temperature ($4^{\circ}C$). A salt content of 20% is satisfactory if the casings are being stored for less than 1 month before being used.

• 한국멀티미디어학회논문지
• /
• 제19권6호
• /
• pp.1003-1013
• /
• 2016

This paper proposes a framework of superpixel-based vehicle detection method using plane normal vector in disparity space. We utilize two common factors for detecting vehicles: Hypothesis Generation (HG) and Hypothesis Verification (HV). At the stage of HG, we set the regions of interest (ROI) by estimating the lane, and track them to reduce computational cost of the overall processes. The image is then divided into compact superpixels, each of which is viewed as a plane composed of the normal vector in disparity space. After that, the representative normal vector is computed at a superpixel-level, which alleviates the well-known problems of conventional color-based and depth-based approaches. Based on the assumption that the central-bottom of the input image is always on the navigable region, the road and obstacle candidates are simultaneously extracted by the plane normal vectors obtained from K-means algorithm. At the stage of HV, the separated obstacle candidates are verified by employing HOG and SVM as for a feature and classifying function, respectively. To achieve this, we trained SVM classifier by HOG features of KITTI training dataset. The experimental results demonstrate that the proposed vehicle detection system outperforms the conventional HOG-based methods qualitatively and quantitatively.

• Journal of Multimedia Information System
• /
• 제3권4호
• /
• pp.119-128
• /
• 2016

This study aims to suggest a new algorithm for detecting two-wheelers on road that have various shapes according to the viewing angle for vision based intelligent vehicles. This article describes a new approach to two-wheelers detection algorithm riding on people based on modified Histogram of Oriented Gradients (HOG) using correlation coefficient (CC). The CC between two local area variables, in which one is the person riding a bike and other is its background, can represent correlation relation. First, we extract edge vectors using HOG which includes gradient information and differential magnitude as cell based. And then, the value, which is calculated by the CC between the area of each cell and one of two-wheelers, can be extracted as the weighting factor in process for normalizing the modified HOG cell. This paper applied the Adaboost algorithm to make a strong classification from weak classification. In this experiment, we can get the result that the detection rate of the proposed method is higher than that of the traditional method.

• 대한수의학회지
• /
• 제6권1호
• /
• pp.1-9
• /
• 1966

돈(豚)콜레라는 세계각처(世界各處)에서 널리 유행(流行)되는 돼지의 중요(重要)한 질병(疾病)이다. 그러나 이 질병(疾病)을 혈청학적(血淸學的)으로 진단(診斷)할 수 있는 간단(簡單)하고 고도(高度)로 특이(特異)한 방법(方法)은 아직 없다. 이 연구(硏究)에서는 보체결합반응(補體結合反應)을 이용(利用)한 보다 우수한 혈청적진단법(血淸的診斷法)을 실험(實驗)하여 좋은 성적(成績)을 얻었다. 검출항원(檢出抗原)은 감염돈(感染豚)의 췌장유제(膵臟乳劑)이 양성예(陽性例)에서의 역가(力價)는 1/16 이상이였다. 항혈청(抗血淸)은 조직배양원(組織培養源) 바이러스 재료(材料)를 가토(家兎)에 접종(接種)하여 만들었고 이의 역가(力價)는 1/32 이상이었다. 보체(補體)는 1.1~1.2 충분단위(充分單位)를 사용하였고 감작적혈구(感作赤血球)는 2 단위(單位) 2%로 하였다. 이 방법(方法)으로써 감염돈(感染豚)의 95% 이상이 특이적(特異的)으로 검출(檢出)될 수 있었고, 비감염돈(非感染豚)은 97% 이상이 음성(陰性)으로 검출(檢出)될 수 있었다. 따라서 이 방법(方法)은 돈(豚)콜레라를 진단(診斷)하는데 이용(利用)될 수 있는 보다 낳은 혈청학적(血淸學的) 방법(方法)으로 믿어진다.

• 제어로봇시스템학회논문지
• /
• 제16권8호
• /
• pp.761-765
• /
• 2010

This paper presents the design of optimal fuzzy classifier for human detection by using genetic algorithms, one of the best-known meta-heuristic search methods. For this purpose, encoding scheme to search the optimal sequential intersection points between adjacent fuzzy membership functions is originally presented for the fuzzy classifier design for HOG (Histograms of Oriented Gradient) descriptors. The intersection points are sequentially encoded in the proposed encoding scheme to reduce the redundancy of search space occurred in the combinational problem. Furthermore, the fitness function is modified with the true-positive and true-negative of the confusion matrix instead of the total success rate. Experimental results show that the two proposed approaches give superior performance in HOG datasets.

• 한국컴퓨터정보학회논문지
• /
• 제22권12호
• /
• pp.79-85
• /
• 2017

In this paper, we propose a CNN-based swimmer detection algorithm. Every year, water safety accidents have been occurred frequently, and accordingly, intelligent video surveillance systems are being developed to prevent accidents. Intelligent video surveillance system is a real-time system that detects objects which users want to do. It classifies or detects objects in real-time using algorithms such as GMM (Gaussian Mixture Model), HOG (Histogram of Oriented Gradients), and SVM (Support Vector Machine). However, HOG has a problem that it cannot accurately detect the swimmer in a complex and dynamic environment such as a beach. In other words, there are many false positives that detect swimmers as waves and false negatives that detect waves as swimmers. To solve this problem, in this paper, we propose a swimmer detection algorithm using CNN (Convolutional Neural Network), specialized for small object sizes, in order to detect dynamic objects and swimmers more accurately and efficiently in complex environment. The proposed CNN sets the size of the input image and the size of the filter used in the convolution operation according to the size of objects. In addition, the aspect ratio of the input is adjusted according to the ratio of detected objects. As a result, experimental results show that the proposed CNN-based swimmer detection method performs better than conventional techniques.

• Journal of Multimedia Information System
• /
• 제2권4호
• /
• pp.303-310
• /
• 2015

Vulnerable road users such as bike, motorcycle, small automobiles, and etc. are easily attacked or threatened with bigger vehicles than them. So this paper suggests a new approach two-wheelers detection system riding on people based on modified histogram of oriented gradients (HOGs) which is weighted by curvature and local correlation coefficient. This correlation coefficient between two variables, in which one is the person riding a bike and other is its background, can represent correlation relation. First, we extract edge vectors using the curvature of Gaussian and Histogram of Oriented Gradients (HOG) which includes gradient information and differential magnitude as cell based. And then, the value, which is calculated by the correlation coefficient between the area of each cell and one of bike, can be used as the weighting factor in process for normalizing the HOG cell. This paper applied the Adaboost algorithm to make a strong classification from weak classification. The experimental results validate the effectiveness of our proposed algorithm show higher than that of the traditional method and under challenging, such as various two-wheeler postures, complex background, and even conclusion.

• Journal of Information Processing Systems
• /
• 제10권3호
• /
• pp.443-458
• /
• 2014

An extreme learning machine (ELM) is a recently proposed learning algorithm for a single-layer feed forward neural network. In this paper we studied the ensemble of ELM by using a bagging algorithm for facial expression recognition (FER). Facial expression analysis is widely used in the behavior interpretation of emotions, for cognitive science, and social interactions. This paper presents a method for FER based on the histogram of orientation gradient (HOG) features using an ELM ensemble. First, the HOG features were extracted from the face image by dividing it into a number of small cells. A bagging algorithm was then used to construct many different bags of training data and each of them was trained by using separate ELMs. To recognize the expression of the input face image, HOG features were fed to each trained ELM and the results were combined by using a majority voting scheme. The ELM ensemble using bagging improves the generalized capability of the network significantly. The two available datasets (JAFFE and CK+) of facial expressions were used to evaluate the performance of the proposed classification system. Even the performance of individual ELM was smaller and the ELM ensemble using a bagging algorithm improved the recognition performance significantly.