• 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.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.372-375
• /
• 2003

The incidence of blindness resulting from diabetic retinopathy has significantly increased despite the intervention of insulin to control diabetes mellitus. Early signs are microaneurysms, exudates, intraretinal hemorrhages, cotton wool patches, microvascular abnormalities, and venous beading. Advanced stages include neovascularization, fibrous formations, preretinal and vitreous microhemorrhages, and retinal detachment. Microaneurysm count is important because it is an indicator of retinopathy progression. The purpose of this paper is to apply data mining to detect diabetic retinopathy patterns in routine fundus fluorescein angiography. Early symptoms are of principal interest and therefore the emphasis is on detecting microaneurysms rather than vessel tortuosity. The analysis does not involve image-recognition algorithms. Instead, mathematical filtering isolates microaneurysms, microhemorrhages, and exudates as objects of disconnected sets. A neural network is trained on their distribution to return fractal dimension. Hausdorff and box counting dimensions grade progression of the disease. The field is acquired on fluorescein angiography with resolution superior to color ophthalmoscopy, or on patterns produced by physical or mathematical simulations that model viscous fingering of water with additives percolated through porous media. A mathematical filter and neural network perform the screening process thereby eliminating the time consuming operation of determining fractal set dimension in every case.

• Journal of The Korean Association For Science Education
• /
• v.21 no.1
• /
• pp.76-88
• /
• 2001

This study explored people's accuracy and methods of estimating some base physical quantities, i.e. length, mass, time and temperature. A total of 40 members, ranging from freshmen to professors, of a physics education department of a local university were asked to make two different kinds of estimations, intuitive and operational, on two sets of objects. For intuitive estimation, they were asked to make estimations on four given objects (length - wood chopsticks, mass - rubber eraser, time electric fan, temperature - water in a cup) as soon as they faced with the objects, usually within a few seconds of seeing. For operational estimation, they were allowed to make estimations on a different set of objects (length - plastic rod, mass - lock, time - simple pendulum, temperature - water in a cup) with enough time and they could apply various available methods (e.g. using pencil to estimate the object's length, counting their own pulse rate to estimate time) for the estimation. The findings of this study can be summarized as follows: (1) for length, mass and temperature the intuitive estimations were better performed while for the time estimation the result was the reverse; (2) there was no positive relationship between the amount of physics experience and the accuracy of the estimation; (3) in general, people's accuracy of the length estimation was best performed while their mass estimation was worst performed; (4) people used their own various methods for estimation, esp. using nearby objects around them and applying mental units which have convenient values (e.g. 30cm, 50cm, 1kg, 1 Keun, 1 second).

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.6
• /
• pp.191-201
• /
• 2019

A fast and accurate integrated traffic object detection framework was proposed and developed, harnessing a computer-vision based deep-learning approach performing automatic object detections, a multi object tracking technology, and video pre-processing tools. The proposed method is capable of detecting traffic object such as autos, buses, trucks and vans from video recordings taken under a various kinds of external conditions such as stability of video, weather conditions, video angles, and counting the objects by tracking them on a real-time basis. By creating plausible experimental scenarios dealing with various conditions that likely affect video quality, it is discovered that the proposed method achieves outstanding performances except for the cases of rain and snow, thereby resulting in 98% ~ 100% of accuracy.

• The Mathematical Education
• /
• v.40 no.2
• /
• pp.195-215
• /
• 2001

The purpose of this paper is to present a specific set of home teaching methods in hopes to prevent slow learner of the elementary mathematics. This paper deals with the number and operations, one of five topics in the elementary mathematics A survey of two hundred elementary school teachers was made to see the teacher's opinions of the role of home studying and to concretize the contents of the research topics. There were asked which is the most essential contents for the concrete loaming and which is the most difficult monad that might cause slow leaner. And those were found to be; counting, and arithmetic operations(addition and subtraction) of one or two-digit numbers and multiplication and their concepts representations and operations(addition and subtraction) of fractions. The home teaching methods are based on the situated learning about problem solving in real life situations and on the active teaming which induces children's participation in the process of teaching and learning. Those activities in teaching each contents are designed to deal with real objects and situations. Most teaching methods are presented in the order of school curriculum. To teach the concepts of numbers and the place value, useful activities using manipulative materials (Base ten blocks, Unifix, etc.) or real objects are also proposed. Natural number's operations such as addition, subtraction and multiplication are subdivided into small steps depending upon current curriculum, then for understanding of operational meaning and generalization, games and activities related to the calculation of changes are suggested. For fractions, this paper suggest 10 learning steps, say equivalent partition, fractional pattern, fractional size, relationship between the mixed fractions and the improper fraction, identifying fractions on the number line, 1 as a unit, discrete view point of fractions, comparison of fractional sizes, addition and subtraction, quantitative concepts. This research basically centers on the informal activities of kids under the real-life situation because such experiences are believed to be useful to prevent slow learner. All activities and learnings in this paper assume children's active participation and we believe that such active and informal learning would be more effective for learning transfer and generalization.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2002.09a
• /
• pp.379-381
• /
• 2002

A single CdZnTe detector is tested for suitability in a prototype CT/ SPECT system designed to acquire both emission and transmission data. The detector has the size of 1${\times}$l-cm$^2$ with 4${\times}$4 1.5${\times}$l.5mm$^2$ pixellated anodes. Since the detector is smaller than imaged object, we translated it in an arc centered at the x-ray tube to image larger objects. Pulse counting electronics with very short shaping time (50 ns) are used to satisfy high photon rates in x-ray imaging, and response linearity up to 3${\times}$10$\^$5/ counts per second per detector element is achieved. The energy resolution of 122-keV gamma-ray is measured to be 14%. We have characterized the system performance by scanning a radiographic resolution phantom .and the Hoffman brain phantom. The spatial resolution of CT and SPECT are about 1 mm and 7 mm, respectively.

• Journal of Surface Science and Engineering
• /
• v.41 no.2
• /
• pp.76-82
• /
• 2008

We investigated sterilization characteristics of UV lights by counting the number of bacteria units with varying sterilization time and distance from the light source. We focused on an idea that UV light of 184.9 nm could generate ozone and developed a new sterilizer. The UV-ozone duplex system sterilized bacteria faster than UV-only sterilizers. To reduce shadowing effects by target objects, we used UV transparent quartz plate as a support and put a reflecting plate. Distribution of UV irradiation intensity and ozone supply were analyzed by a 3D model and measured by a semiconductor UV sensor. But even with an Al reflector, multi-layered pens could not be treated properly from UV irradiation only. Ozone generating lamp could treat more uniformly multi-layered pens with a stirring fan by supplying ozone to shadowed surfaces.

• Journal of Korea Multimedia Society
• /
• v.7 no.2
• /
• pp.173-186
• /
• 2004

This paper proposed the content-based retrieval system as a method for performing image retrieval through the effective feature extraction of the object of significant meaning based on the characteristics of man's visual system. To allow the object region of interest to be primarily detected, the region, being comparatively large size, greatly different from the background color and located in the middle of the image, was judged as the major object with a meaning. To get the original features of the image, the cumulative sum of tile declination difference vector the segment of the object contour had and the signature of the bipartite object were extracted and used in the form of being applied to the rotation of the object and the change of the size after partition of the total length of the object contour of the image into the normalized segment. Starting with this form feature, it was possible to make a retrieval robust to any change in translation, rotation and scaling by combining information on the texture sample, color and eccentricity and measuring the degree of similarity. It responded less sensitively to the phenomenon of distortion of the object feature due to the partial change or damage of the region. Also, the method of imposing a different weight of similarity on the image feature based on the relationship of complexity between measured objects using the fractal dimension by the Boxing-Counting Dimension minimized the wrong retrieval and showed more efficient retrieval rate.

• Education of Primary School Mathematics
• /
• v.22 no.3
• /
• pp.149-166
• /
• 2019

The purpose of this study is to analyze the statistical literacy in elementary school students when they beginning inference. Picto-graphs provide statistical information and often data-related arguments they certainly qualify as objects for interpretation, for critical evaluation, and for discussion or communication of the conclusions presented. For research, the inference from pictograph task was designed and statistical literacy standards for evaluating the student's level was presented based on prior studies. Evaluating student's statistical literacy is meaningful in that it can check their current level. To know the student's current level can help them achieve a higher level of performance. The outcomes of this research indicate that pictograph can provide a basis for rich tasks displaying not only student's counting skills but also their appreciation of variation and uncertainty in prediction. Raising statistical thinking by students is an important goal in statistical education, and the experience of informal statistical reasoning can help with formal statistical reasoning that will be learned later. Therefore, the task about the inference from a pictograph, discussions on statistical learning of elementary school children are expected to present meaningful implications for statistical education.

• Korean Journal of Childcare and Education
• /
• v.10 no.5
• /
• pp.229-248
• /
• 2014

The purpose of this study is to draw guidelines on how to select traditional games that would efficiently help and develop multiple intelligences in children. Guidelines standard of section inquiries were prepared through a Delphi survey targeting twenty experts in early childhood education and traditional games. As a result, linguistic intelligence questions regarding writing, listening, speaking and vocabulary acquisition were selected. logical-mathematical intelligence questions regarding strategy, counting, patterns, hypothesis, verification, and comparing, contrasting, calculating ability were selected. Spatial intelligence questions regarding drawing, coloring, representation activities, operating and creating were selected, physical performance intelligence questions regarding global muscles, eye-hand coordination, flexibility, accommodation force, balance, agility and muscular strength were selected. Musical intelligence included questions about singing, and playing musical instruments. Interpersonal intelligence included perspective-taking, role-sharing, cooperation and discussion. For intrapersonal intelligence questions regarding personal significance-ties, planning-decision making, emotional expression and problem solving were selected. Finally, in relation to naturalist intelligence, questions regarding living organisms, inanimate objects and seasons were selected. In addition, traditional games were analyzed based on the finalized guidelines, and the results showed that each of the traditional games would not only work with one intelligence at a time but with other different intelligence as well. In the light of that, the study confirmed the validity of the guidelines on how to select traditional games that would develop multiple intelligences in children.