• Journal of Animal Science and Technology
• /
• v.65 no.6
• /
• pp.1254-1269
• /
• 2023

This study aims to predict the change in corn share according to the grazing of 20 gestational sows in a mature corn field by taking images with a camera-equipped unmanned air vehicle (UAV). Deep learning based on convolutional neural networks (CNNs) has been verified for its performance in various areas. It has also demonstrated high recognition accuracy and detection time in agricultural applications such as pest and disease diagnosis and prediction. A large amount of data is required to train CNNs effectively. Still, since UAVs capture only a limited number of images, we propose a data augmentation method that can effectively increase data. And most occupancy prediction predicts occupancy by designing a CNN-based object detector for an image and counting the number of recognized objects or calculating the number of pixels occupied by an object. These methods require complex occupancy rate calculations; the accuracy depends on whether the object features of interest are visible in the image. However, in this study, CNN is not approached as a corn object detection and classification problem but as a function approximation and regression problem so that the occupancy rate of corn objects in an image can be represented as the CNN output. The proposed method effectively estimates occupancy for a limited number of cornfield photos, shows excellent prediction accuracy, and confirms the potential and scalability of deep learning.

• KDI Journal of Economic Policy
• /
• v.31 no.2
• /
• pp.15-45
• /
• 2009

This paper estimates the term structure of interest rates with the setup of 3-factor no arbitrage model and investigates the trend of term premia and the effectiveness of changes in policy interest rates. The term premia are found to be high in a three-year medium term objective, which can be interpreted as reflecting the recognition of investors who expect a higher uncertainty in real activities for the coming three years than for a longer term. Then, in order to look into the effect of policy interest rates after the recent change of benchmark interest rate, this paper analyzes the effects of the changes in short-term interest rates of the financial market on the yield curve of the bond market at time of change. Empirical results show that the discrepancy between call rate, short-term rate in money market, and instantaneous short rate, short-term rate in the bond market, is found to be significantly widened, comparing to the periods before the change in benchmark interest rate. It is not easy to conclude clearly for now whether such a widening gap is caused by the lack of experiences with managing new benchmark interest rate or is just an exceptional case due to the recent turmoil in the global financial market. However, monetary policy needs to be operated in a manner that could reduce the gap to enhance its effectiveness.

• Journal of Environmental Policy
• /
• v.12 no.4
• /
• pp.71-92
• /
• 2013

Unlike general public investment projects, when it comes to environmental public investment projects, there is a gap between those who pay the costs, and those who receive the benefits. This is because of the long term nature of environmental investments, which entails that the majority of the costs are paid by the current generation, while the benefits are reaped by future generations. Because of this, when the social discount rate is set at a standard, singular rate, an issue of relative underestimation of the benefits reaped by future generations may occur during the analytic process. This paper begins with the recognition of this problem, and attempts to estimate a suitable social discount rate that can be applied to environmental investment projects. Taking into account recent economic situations, the social discount rate is currently being estimated at between 2.9 ~ 4.9%. Also, this paper used preliminary feasibility studies that took place so far, to analyze the standard pattern of benefit generation. This revealed that alterations in social discount rates can bring significant changes in economic feasibility test results. Simulation results showed that roughly 6% of B/C ratios could be increased by 1%p. resulting in a decrease in social discount rates. Also if we use hyperbolic discount rates, instead of using the current singular rate, there would be a meaningful increase in the benefits for the future generation.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.33 no.6
• /
• pp.660-668
• /
• 2007

We investigated 248 patients who were diagnosed as malignant tumor in the department of Oral and maxillofacial Surgery of Kyungpook National University from 1999 to 2006, and following results were obtained. 1. Among 248 patients who have malignant tumor, 164 were men and 84 were women, which made the ratio of male to female 1.95:1. 2. The average age of oral cancer patients was 58.3. 3. As of the primary origin site, lower alveolus and gingiva were the greatest with 70 cases(28.2%), followed by tongue(l6.9%), upper alveolus and gingiva(14.9%), palate(13.7%), mouth floor(9.7%), buccal mucosa(4.8%), retromolar trigone(4.4%), Mx. & Mn. bone(3.2%) and lip(2.8%). 4. As of histologic distribution, squamous cell carcinoma was the greatest with 170 cases(68.6%), followed by sarcoma with 17 cases(6.9%), adenoid cystic carcinoma with 17 cases(6.9%), malignant lymphoma with 15 cases(6.0%), mucoepidermoid carcinoma with 13 cases(5.2%), metastatic carcinoma with 6 cases(2.4%) and malignant melanoma with 4 cases(1.6%). 5. Period between recognition of the symptom and the first visit to hospital was less than 3 months for 58.9% of the patients, and more than 3 months for 41% of the patients. 6. Investigation of whether the patients drink or smoke revealed that the number of non-smoking and non-drinking patients was 63 among 170 patients(37.0%) that were able to investigate. The number of patients who smoke only was 29(17.1%) and both drinking and smoking patients were 78(45.9%). 7. In clinical stage order, Stage IV(61.7%) was found th be the largest, followed by stage I(17.2%), stage II(13%) and stage III(7.8%). 8. The 5-year survival rate of the entire oral cancer patients appeared to be 57.7%. The survival rate was higher in younger group and women had higher survival rate but there was no statistical significance to this. In the aspect of stage, the survival rate was Stage I, Stage II, Stage IV and Stage III in decreasing order. The order according to T classification was the same. In N classification, patients with N0 had the highest survival rate and the survival rate decreased in the order of N1 and N2. Survival rate was especially low in patients with N2.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.10
• /
• pp.63-70
• /
• 2018

Biomedical signal measurement technology using images has been developed, and researches on respiration signal measurement technology for maintaining life have been continuously carried out. The existing technology measured respiratory signals through a thermal imaging camera that measures heat emitted from a person's body. In addition, research was conducted to measure respiration rate by analyzing human chest movement in real time. However, the image processing using the infrared thermal image may be difficult to detect the respiratory organ due to the external environmental factors (temperature change, noise, etc.), and thus the accuracy of the measurement of the respiration rate is low.In this study, the images were acquired using visible light and infrared thermal camera to enhance the area of the respiratory tract. Then, based on the two images, features of the respiratory tract region are extracted through processes such as face recognition and image matching. The pattern of the respiratory signal is classified through the k-nearest neighbor classifier, which is one of the statistical classification methods. The respiration rate was calculated according to the characteristics of the classified patterns and the possibility of breathing rate measurement was verified by analyzing the measured respiration rate with the actual respiration rate.

• ETRI Journal
• /
• v.36 no.5
• /
• pp.714-720
• /
• 2014

In this paper, we propose the use of data-driven probabilistic utterance-level decision logic to improve Weighted Finite State Transducer (WFST)-based endpoint detection. In general, endpoint detection is dealt with using two cascaded decision processes. The first process is frame-level speech/non-speech classification based on statistical hypothesis testing, and the second process is a heuristic-knowledge-based utterance-level speech boundary decision. To handle these two processes within a unified framework, we propose a WFST-based approach. However, a WFST-based approach has the same limitations as conventional approaches in that the utterance-level decision is based on heuristic knowledge and the decision parameters are tuned sequentially. Therefore, to obtain decision knowledge from a speech corpus and optimize the parameters at the same time, we propose the use of data-driven probabilistic utterance-level decision logic. The proposed method reduces the average detection failure rate by about 14% for various noisy-speech corpora collected for an endpoint detection evaluation.

• Journal of Power Electronics
• /
• v.6 no.4
• /
• pp.307-314
• /
• 2006

This paper presents a wavelet and neural network based technology for the monitoring and classification of various types of power quality (PQ) disturbances. Simultaneous and automatic detection and classification of PQ transients, is recommended, however these processes have not been thoroughly investigated so far. In this paper, the hardware and software of a power quality data acquisition system (PQDAS) is described. In this system, an auto-classifying system combines the properties of the wavelet transform with the advantages of a neural network. Additionally, to improve recognition rate, extraction technology is considered.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2004.05a
• /
• pp.113-117
• /
• 2004

We need the contingency cost in order to deal with the uncertainty to be accompanied inevitably at the construction and an every kind risk not to forecast in advance. And also the contingency colt needed for the change order and we need it for reduction of the delay and reduce the trouble between owner and constructor. This study, through checking and analyzing the risk factor, in the step of domestic construction, suggests optimal management reserve to specific business about the contract type and the scale. The main results of this research are summarized as follow. First, I investigated the recognition about the contingency cost, grasped the risk to be happened at the construction step and found out the frequency occurrence, through making up question to engineer are carrying out their job in the domestic construction. Second, I computed optimal contingency cost rate by the statistics investigation, and proposed an improvement plan and problem when compute a contingency cost.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.26 no.2
• /
• pp.51-60
• /
• 2012

An improved method for detecting fault distance in overhead transmission lines is described in this paper. Based on single-ended measurement, propagation theory of traveling waves together with the wavelet transform technique is used. In estimating fault location, a simple, but fundamental method using the time difference between the two consecutive peaks of transient signals is considered; however, a new method to enhance measurement sensitivity and its accuracy is sought. The algorithm is developed based on the lattice diagram for traveling waves. Representing both the ground mode and alpha mode of traveling waves, in a lattice diagram, several relationships to enhance recognition rate or estimation accuracy for fault location can be found. For various cases with fault types, fault locations, and fault inception angles, fault resistances are examined using the proposed algorithm on a typical transmission line configuration. As a result, it is shown that the proposed system can be used effectively to detect fault distance.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.426-439
• /
• 1996

In this paper, we propose a simple algorithm to calculate the numbers of the passing cars by using an image processing sensor for the digital black and white images with 256 tone level. Shadow is one of the most troublesome factor in image processing. By differencing the tone level, we cannot discriminate between the body of the car and its shadow. In our proposed algorithm, the area of the shadow is excluded by recognizing the position of each traffic lane. For real-time operation and simple calculation, two lines of the tone level are extracted and the existences of cars are recognized. In the experimental application on a high-way, the recognition rate of the real-time operation is more than 94%.