• Journal of Biosystems Engineering
• /
• v.29 no.4
• /
• pp.341-346
• /
• 2004

Recent livestock people concern not only increase of production, but also superior quality of animal-breeding environment. So far, the optimization of the breeding and air environment has been focused on the production increase. In the very near future, the optimization will be emphasized on the environment for the animal welfare and health. Especially, cattle farming demands the precision livestock farming and special attention has to be given to the management of feeding, animal health and fertility. The management of individual animal is the first step for precision livestock farming and animal welfare, and recognizing each individual is important for that. Though electronic identification of a cattle such as RFID(Radio Frequency Identification) has many advantages, RFID implementations practically involve several problems such as the reading speed and distance. In that sense, computer vision might be more effective than RFID for the identification of an individual animal. The researches on the identification of cattle via image processing were mostly performed with the cows having black-white patterns of the Holstein. But, the native Korean and Japanese cattle do not have any definite pattern on the body. The purpose of this research is to identify the Japanese black cattle that does not have a body pattern using computer vision technology and neural network algorithm. Twelve heads of Japanese black cattle have been tested to verify the proposed scheme. The values of input parameters were specified and then computed using the face images of cattle. The images of cattle faces were trained using associate neural network algorithm, and the algorithm was verified by the face images that were transformed using brightness, distortion, and noise factors. As a result, there was difference due to transform ratio of the brightness, distortion, and noise. And, the proposed algorithm could identify 100% in the range from -3 to +3 degrees of the brightness, from -2 to +4 degrees of the distortion, and from 0% to 60% of the noise transformed images. It is concluded that our system can not be applied in real time recognition of the moving cows, but can be used for the cattle being at a standstill.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.1
• /
• pp.148-154
• /
• 2020

This study examines room assignments to improve accessibility in a university dormitory depending on the student grade, taking into account frequency of using a certain common space. An integer programming model is presented to minimize the total moving distance from the common space to the students' rooms for accessibility. The model also constrains the maximum capacity of a room, and disallows different grade students to be assigned to the same room. This model is similar to a facility location problem used widely in the supply chain management field. Applying our optimization model to a small group at the dormitory of Unversity A as the case study, our results indicate that lower grade students are assigned rooms closer to the common space due to their higher frequency of using that space to guarantee high accessibility. Moreover, if higher grade students are prioritized to select their rooms, we suggest an objective function that imposes a penalty in cases when lower grade students select rooms with priority. Based on the results obtained, we propose assigning rooms to students in a dormitory by considering their complex requirements and convenience to use the common space.

• Korean Journal of Applied Biomechanics
• /
• v.13 no.1
• /
• pp.73-94
• /
• 2003

The purpose of this investigation was to analyze A kinematic analysis of the Kuzushi-arm motion when performing Morote-Seoinage in judo who was 5 females university representative judokas of light weight category in judo, and filmed on video cameras(60field/s). The data of this study digitizied by KWON3D 2.1 program computed the average and standard deviation calculated individual 5 trials with Programing Lab view 6i. From the data analysis & discussion, the following conclusions were drawn : 1) distance variable of attacking hand arm in kuzushi motion Left right(X direction) displacement variable was all of A, B, C pattern with moving left to right and leaning. Strip of displacement variable was ordo. to C(55.6cm), A(53.3cm), B(43.9cm) pattern, C pattern largely leaned to left Front Rear(Y direction) displacement variable was different A($131.3cm{\pm}3.1cm$), B($128.7{\pm}4.0cm$) and C(111.0cm) on ready position, 3 pattern leaned to rear direction. Strip of displacement was order to B(43.4cm), A(41.1cm) and C pattern(28.3cm). Up down(Z direction) displacement variable was all of A, B, C pattern leaned to up in the Kuzushi-phase and leaned to down in the Kake-phase. Strip of displacement was order to A(83.9cm), B(80.4cm), C pattern(71.9cm). 2) Shoulder joint angle variable Flexion and extension Ready position' angle was A($138.3{\pm}4.9^{\circ}$), B($142.9{\pm}3.7^{\circ}$) and C($164.5^{\circ}$) pattern, strip of flexion extension was order to C($80.9^{\circ}$), A($79.9^{\circ}$) and B($39.0^{\circ}$) pattern, greatly C pattern had largely angle change. Adduction and abduction : B and C pattern's angle change were adduction and abduction in the Kuzushi-phase after adduction in the Kake phase, A pattern's angle change was abduction in the Kuzushi-phase after adduction in the Kake phase. internal and external rotation : 3 pattern were internal rotation in the Tsukuri phase and external rotation in the Kake phase. After B and C pattern were external rotation and A pattern was internal rotation. 3) Elbow joint angle variable Flexion and extension 3 pattern's ready position angle were A($142.0{\pm}4.4^{\circ}$), B($123.5{\pm}5.5^{\circ}$) and C($105.5^{\circ}$) and flexion. Strip of flexion extension were order to A($57.9^{\circ}$), C($34.6^{\circ}$) and B($25.2^{\circ}$) pattern.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.10
• /
• pp.1-8
• /
• 2016

Automation of inventory management in a steel plate factory was a difficult problem unresolved for a long time. And now, it is also necessary to work diligently in the steel industry on efficient inventory management of thick plates. So far, the environmental characteristics of stacked thick plates means it is not easy to apply advanced technology for their automatic identification. In this paper, we propose a thick-plate robotic scanning system based on radio-frequency identification (RFID) that can provide quick and accurate inventory management by acquiring plate information after the scanning automatically recognizes the RFID tags under difficult load conditions. This system is equipped with a crane to move the plates in a pulled-up operation. It is equipped with a plate-only linear dipole antenna only for scanning the position of the plate tag. Only the linear dipole antenna, while moving the x-axis and y-axis information, automatically identifies the tag information attached to the plate. The tag information acquired by the system is used for stockpiling and is managed by steel plate inventory control software. The effectiveness of the proposed system is verified through field performance evaluation. As a result, the recognition rate of the plate tags is 99.9% at a maximum distance of 320 cm. The developed thick-plate antenna showed excellent performance compared to an existing commercial antenna.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2060-2077
• /
• 2019

Recently, mobile healthcare services have attracted significant attention because of the emerging development and supply of diverse wearable devices. Smartwatches and health bands are the most common type of mobile-based wearable devices and their market size is increasing considerably. However, simple value comparisons based on accumulated data have revealed certain problems, such as the standardized nature of health management and the lack of personalized health management service models. The convergence of information technology (IT) and biotechnology (BT) has shifted the medical paradigm from continuous health management and disease prevention to the development of a system that can be used to provide ground-based medical services regardless of the user's location. Moreover, the IT-BT convergence has necessitated the development of lifestyle improvement models and services that utilize big data analysis and machine learning to provide mobile healthcare-based personal health management and disease prevention information. Users' health data, which are specific as they change over time, are collected by different means according to the users' lifestyle and surrounding circumstances. In this paper, we propose a prediction model of user physical activity that uses data characteristics-based long short-term memory (DC-LSTM) recurrent neural networks (RNNs). To provide personalized services, the characteristics and surrounding circumstances of data collectable from mobile host devices were considered in the selection of variables for the model. The data characteristics considered were ease of collection, which represents whether or not variables are collectable, and frequency of occurrence, which represents whether or not changes made to input values constitute significant variables in terms of activity. The variables selected for providing personalized services were activity, weather, temperature, mean daily temperature, humidity, UV, fine dust, asthma and lung disease probability index, skin disease probability index, cadence, travel distance, mean heart rate, and sleep hours. The selected variables were classified according to the data characteristics. To predict activity, an LSTM RNN was built that uses the classified variables as input data and learns the dynamic characteristics of time series data. LSTM RNNs resolve the vanishing gradient problem that occurs in existing RNNs. They are classified into three different types according to data characteristics and constructed through connections among the LSTMs. The constructed neural network learns training data and predicts user activity. To evaluate the proposed model, the root mean square error (RMSE) was used in the performance evaluation of the user physical activity prediction method for which an autoregressive integrated moving average (ARIMA) model, a convolutional neural network (CNN), and an RNN were used. The results show that the proposed DC-LSTM RNN method yields an excellent mean RMSE value of 0.616. The proposed method is used for predicting significant activity considering the surrounding circumstances and user status utilizing the existing standardized activity prediction services. It can also be used to predict user physical activity and provide personalized healthcare based on the data collectable from mobile host devices.

• Journal of IKEEE
• /
• v.25 no.2
• /
• pp.243-251
• /
• 2021

In this paper, we propose a measurement technique of indoor location based on markerless applicable to AR. The proposed technique has the following originality. The first is to extract feature points and use them to generate local patches to enable faster computation by learning and using only local patches that are more useful than the surroundings without learning the entire image. Second, learning is performed through deep learning using the convolution neural network structure to improve accuracy by reducing the error rate. Third, unlike the existing feature point matching technique, it enables indoor location measurement including left and right movement. Fourth, since the indoor location is newly measured every frame, errors occurring in the front side during movement are prevented from accumulating. Therefore, it has the advantage that the error between the final arrival point and the predicted indoor location does not increase even if the moving distance increases. As a result of the experiment conducted to evaluate the time required and accuracy of the measurement technique of indoor location based on markerless applicable to AR proposed in this paper, the difference between the actual indoor location and the measured indoor location is an average of 12.8cm and a maximum of 21.2cm. As measured, the indoor location measurement accuracy was better than that of the existing IEEE paper. In addition, it was determined that it was possible to measure the user's indoor location in real time by displaying the measured result at 20 frames per second.

• Journal of Korea Port Economic Association
• /
• v.38 no.3
• /
• pp.69-86
• /
• 2022

This study analyses the necessity of the large-size shipyard and explores competitiveness factors of it. Furthermore, the competitiveness is evaluated and the economic feasibility of building and operation of shipyard is examined. As a result of AHP analysis of the determining factors of the competitiveness of the repairing shipyard, the importance of the factors was found in the order of arrival and departure safety, repair technology, dock and wharf facilities, repair cost, repair period (on time delivery), and repair parts supply. Moving distance, repair service quality, repair parts supply, arrival and departure safety, repair technology, dock and quay wall facilities, and repair period (on time delivery) were identified as key factors in the AHP analysis for competitiveness of the Busan Port repair shipyard to be built in the future. As a result of the analysing economic feasibility, the net present value of the Busan Port repair shipyard construction and operation investment project was KRW 435.6 billion, and the internal rate of return was 9.8%, higher than the social discount rate (4.5%), and the cost-benefit ratio (B/C) was high at 1.167. As a result of the study, the necessity and economic feasibility of the Busan Port repair shipyard are sufficiently ensured, and the competitiveness assessment was highly positive.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.1
• /
• pp.25-31
• /
• 2023

In order to estimate the radial speed of an underwater object so-called target with active sonar, Continuous Wave (CW) pulse is generally used, but if a target is slow and at near distance, it is not easy to estimate the radial velocity of the target due to acoustic reverberation in the ocean. In 2017, Wang et al. utilized broadband signal of two Hyperbolic Frequency Modulation (HFM) pulses, which is known as a doppler-invariant pulse, with equal frequency band and in opposite sweep directions to overcome this problem and successfully estimate the radial speed of slow-moving nearby target. They demonstrated the estimation of the radial velocity with computer simulation using the parameters of two HFM starting time differences and receiving times. However, for it uses two HFM pulses with equal frequency, cross-correlation between the two pulses negatively affect the detection performance. To mitigate this cross-correlation effect, we suggest using two different band HFM with the opposite sweep directions. In this paper, a method of radial velocity estimation is derived and simulated using two HFM pulses with the pulse length of 1 second and bandwidth of 400 Hz. Applying the suggested method, the radial velocity was estimated with approximately 6 % of relative error in the simulation.

• Journal of the Korean earth science society
• /
• v.44 no.2
• /
• pp.148-160
• /
• 2023

The Pliny Letter, the first historical record of volcanic eruptions and disasters on Earth, was studied to better understand the Vesuvius' eruption patterns in 79 AD. The two-day eruption, which began at 1 a.m. on August 24th 79 AD, produced large amounts of volcanic ash and pumice, which were carried by the wind and fell on nearby cities. Furthermore, during the eruption, fast-moving pyroclastic flows flowed down the volcano's sides, and several phenomena such as earthquakes and tsunamis occurred. Cities near Mount Vesuvius were buried and destroyed by volcanic ash and pyroclastic flows. Previous studies were collected, analyzed, and investigated and the scope of damage was chosen from Pompeii, Herculaneum, Stabiae, and Oplontis. The sedimentary stratigraphy and thickness vary according to location and distance from Vesuvius in each region. Within the depositional layers, the remains of residents who died during the eruption were also discovered, and 1,150 remains have been discovered in Pompeii, 306 in Herculaneum, 111 in Stabiae, and 54 in Oplontis, but the exact number of people who killed is unknown. The eruption that exhibited the pattern seen in AD 79 was named the Plinian eruption after Pliny and classified as a new type of eruption as a result of Pliny's detailed description of the eruption.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.3D
• /
• pp.453-459
• /
• 2006

This paper presents an experimental evaluation of wandering effect on asphalt concrete pavement responses. A laser-based wandering system has been developed and its performance is verified under various field conditions. The portable wandering system composed of two laser sensors with Position Sensitive Devices can allow one to measure the distance between laser sensors and tire edges of moving vehicle. Therefore, lateral position of each wheel on the pavement can be determined in a real time manner. Pavement responses due to different loading paths are investigated using a roll over test which is carried out on one of asphalt surfaced pavements in the Korea Highway Corporation test road. The pavement section (A5) consists of 5 cm thick surface course; 7 cm intermediate course; and 18 mm base course, and is heavily instrumented with strain gauges, vertical soil pressure cells and thermo-couples. From the center of wheel paths, seven equally-spaced lateral loading paths are carefully selected over an 140 cm wandering zone. Test results show that lateral horizontal strains in both surface and intermediate courses are mostly compressive right under the loading path and tensile strains start to develop as the loading offset becomes 40 cm from the wheel path. The development of the vertical stresses in the top layers of subbase and anti-frost is found to be minimal once the loading offset becomes 50 cm.