• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.5
• /
• pp.50-60
• /
• 2010

For the last half a century, the personal computer and software industries have been prosperous due to the incessant evolution of computer systems. In the 21st century, the embedded system market has greatly increased as the market shifted to the mobile gadget field. While a lot of multimedia gadgets such as mobile phone, navigation system, PMP, etc. are pouring into the market, most industrial control systems still rely on 8-bit micro-controllers and simple application software techniques. Unfortunately, the technological barrier which requires additional investment and higher quality manpower to overcome, and the business risks which come from the uncertainty of the market growth and the competitiveness of the resulting products have prevented the companies in the industry from taking advantage of such fancy technologies. However, high performance, low-power and low-cost hardware and software platforms will enable their high-technology products to be developed and recognized by potential clients in the future. This paper presents such a platform for industrial embedded systems. The platform was designed based on Telechips TCC8300 multimedia processor which embedded a variety of parallel hardware for the implementation of multimedia functions. And open-source Embedded Linux, TinyX and GTK+ are used for implementation of GUI to minimize technology costs. In order to estimate the expected performance and power consumption, the performance improvement and the power consumption due to each of enabled hardware sub-systems including YUV2RGB frame converter are measured. An analytic model was devised to check the feasibility of a new application and trade off its performance and power consumption. The validity of the model has been confirmed by implementing a real target system. The cost can be further mitigated by using the hardware parts which are being used for mass production products mostly in the cell-phone market.

• Journal of Korean Home Economics Education Association
• /
• v.20 no.4
• /
• pp.157-171
• /
• 2008

The year of 2007 Reformed Curriculum encourages various activity materials in the textbook facilitate students oriented self-help learning. The purpose of this paper is to find out how much the activity materials in housing area of middle school Technology and Home Economics are practiced in the class and why they are used or not used. The data were collected from 253 middle school teachers who had ever taught the housing unit in any of 6 textbooks. The analyses indicated that the most frequent teaching methode was lecture based on the textbook and internet data focused on the figures and contents of the individual textbook. The average rate of practicing the activity materials was differ by textbooks and the characteristics of the materials such as type of materials, feature of non sentence materials, and type of activity. The main two reasons to practice the activity materials were it's adequacy to class goals and application to everyday life. Low interests of students and shortage of time were the two main reasons why not used the materials. Textbook writers should consider these reasons as well as the characteristics of activity materials practiced in the class by the teachers in order to meet the goals of the reformed as well as current curricula.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.175-197
• /
• 2021

Recently, with the development of deep learning technology, research on unstructured data analysis is being actively conducted, and it is showing remarkable results in various fields such as classification, summary, and generation. Among various text analysis fields, text classification is the most widely used technology in academia and industry. Text classification includes binary class classification with one label among two classes, multi-class classification with one label among several classes, and multi-label classification with multiple labels among several classes. In particular, multi-label classification requires a different training method from binary class classification and multi-class classification because of the characteristic of having multiple labels. In addition, since the number of labels to be predicted increases as the number of labels and classes increases, there is a limitation in that performance improvement is difficult due to an increase in prediction difficulty. To overcome these limitations, (i) compressing the initially given high-dimensional label space into a low-dimensional latent label space, (ii) after performing training to predict the compressed label, (iii) restoring the predicted label to the high-dimensional original label space, research on label embedding is being actively conducted. Typical label embedding techniques include Principal Label Space Transformation (PLST), Multi-Label Classification via Boolean Matrix Decomposition (MLC-BMaD), and Bayesian Multi-Label Compressed Sensing (BML-CS). However, since these techniques consider only the linear relationship between labels or compress the labels by random transformation, it is difficult to understand the non-linear relationship between labels, so there is a limitation in that it is not possible to create a latent label space sufficiently containing the information of the original label. Recently, there have been increasing attempts to improve performance by applying deep learning technology to label embedding. Label embedding using an autoencoder, a deep learning model that is effective for data compression and restoration, is representative. However, the traditional autoencoder-based label embedding has a limitation in that a large amount of information loss occurs when compressing a high-dimensional label space having a myriad of classes into a low-dimensional latent label space. This can be found in the gradient loss problem that occurs in the backpropagation process of learning. To solve this problem, skip connection was devised, and by adding the input of the layer to the output to prevent gradient loss during backpropagation, efficient learning is possible even when the layer is deep. Skip connection is mainly used for image feature extraction in convolutional neural networks, but studies using skip connection in autoencoder or label embedding process are still lacking. Therefore, in this study, we propose an autoencoder-based label embedding methodology in which skip connections are added to each of the encoder and decoder to form a low-dimensional latent label space that reflects the information of the high-dimensional label space well. In addition, the proposed methodology was applied to actual paper keywords to derive the high-dimensional keyword label space and the low-dimensional latent label space. Using this, we conducted an experiment to predict the compressed keyword vector existing in the latent label space from the paper abstract and to evaluate the multi-label classification by restoring the predicted keyword vector back to the original label space. As a result, the accuracy, precision, recall, and F1 score used as performance indicators showed far superior performance in multi-label classification based on the proposed methodology compared to traditional multi-label classification methods. This can be seen that the low-dimensional latent label space derived through the proposed methodology well reflected the information of the high-dimensional label space, which ultimately led to the improvement of the performance of the multi-label classification itself. In addition, the utility of the proposed methodology was identified by comparing the performance of the proposed methodology according to the domain characteristics and the number of dimensions of the latent label space.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.3
• /
• pp.247-262
• /
• 2022

In domestic tunnels, it is mandatory to install CCTVs in tunnels longer than 200 m which are also recommended by installation of a CCTV-based automatic accident detection system. In general, the CCTVs in the tunnel are installed at a low height as well as near by the moving vehicles due to the spatial limitation of tunnel structure, so a severe perspective effect takes place in the distance of installed CCTV and moving vehicles. Because of this effect, conventional CCTV-based accident detection systems in tunnel are known in general to be very hard to achieve the performance in detection of unexpected accidents such as stop or reversely moving vehicles, person on the road and fires, especially far from 100 m. Therefore, in this study, the region of interest is set up and a new concept of inverse perspective transformation technique is introduced. Since moving vehicles in the transformed image is enlarged proportionally to the distance from CCTV, it is possible to achieve consistency in object detection and identification of actual speed of moving vehicles in distance. To show this aspect, two datasets in the same conditions are composed with the original and the transformed images of CCTV in tunnel, respectively. A comparison of variation of appearance speed and size of moving vehicles in distance are made. Then, the performances of the object detection in distance are compared with respect to the both trained deep-learning models. As a result, the model case with the transformed images are able to achieve consistent performance in object and accident detections in distance even by 200 m.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.979-995
• /
• 2023

As wildfires are difficult to predict, real-time monitoring is crucial for a timely response. Geostationary satellite images are very useful for active fire detection because they can monitor a vast area with high temporal resolution (e.g., 2 min). Existing satellite-based active fire detection algorithms detect thermal outliers using threshold values based on the statistical analysis of brightness temperature. However, the difficulty in establishing suitable thresholds for such threshold-based methods hinders their ability to detect fires with low intensity and achieve generalized performance. In light of these challenges, machine learning has emerged as a potential-solution. Until now, relatively simple techniques such as random forest, Vanilla convolutional neural network (CNN), and U-net have been applied for active fire detection. Therefore, this study proposed an active fire detection algorithm using state-of-the-art (SOTA) deep learning techniques using data from the Advanced Himawari Imager and evaluated it over East Asia and Australia. The SOTA model was developed by applying EfficientNet and lion optimizer, and the results were compared with the model using the Vanilla CNN structure. EfficientNet outperformed CNN with F1-scores of 0.88 and 0.83 in East Asia and Australia, respectively. The performance was better after using weighted loss, equal sampling, and image augmentation techniques to fix data imbalance issues compared to before the techniques were used, resulting in F1-scores of 0.92 in East Asia and 0.84 in Australia. It is anticipated that timely responses facilitated by the SOTA deep learning-based approach for active fire detection will effectively mitigate the damage caused by wildfires.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.131-145
• /
• 2020

In line with the trend of industrial innovation, IoT technology utilized in a variety of fields is emerging as a key element in creation of new business models and the provision of user-friendly services through the combination of big data. The accumulated data from devices with the Internet-of-Things (IoT) is being used in many ways to build a convenience-based smart system as it can provide customized intelligent systems through user environment and pattern analysis. Recently, it has been applied to innovation in the public domain and has been using it for smart city and smart transportation, such as solving traffic and crime problems using CCTV. In particular, it is necessary to comprehensively consider the easiness of securing real-time service data and the stability of security when planning underground services or establishing movement amount control information system to enhance citizens' or commuters' convenience in circumstances with the congestion of public transportation such as subways, urban railways, etc. However, previous studies that utilize image data have limitations in reducing the performance of object detection under private issue and abnormal conditions. The IoT device-based sensor data used in this study is free from private issue because it does not require identification for individuals, and can be effectively utilized to build intelligent public services for unspecified people. Especially, sensor data stored by the IoT device need not be identified to an individual, and can be effectively utilized for constructing intelligent public services for many and unspecified people as data free form private issue. We utilize the IoT-based infrared sensor devices for an intelligent pedestrian tracking system in metro service which many people use on a daily basis and temperature data measured by sensors are therein transmitted in real time. The experimental environment for collecting data detected in real time from sensors was established for the equally-spaced midpoints of 4×4 upper parts in the ceiling of subway entrances where the actual movement amount of passengers is high, and it measured the temperature change for objects entering and leaving the detection spots. The measured data have gone through a preprocessing in which the reference values for 16 different areas are set and the difference values between the temperatures in 16 distinct areas and their reference values per unit of time are calculated. This corresponds to the methodology that maximizes movement within the detection area. In addition, the size of the data was increased by 10 times in order to more sensitively reflect the difference in temperature by area. For example, if the temperature data collected from the sensor at a given time were 28.5℃, the data analysis was conducted by changing the value to 285. As above, the data collected from sensors have the characteristics of time series data and image data with 4×4 resolution. Reflecting the characteristics of the measured, preprocessed data, we finally propose a hybrid algorithm that combines CNN in superior performance for image classification and LSTM, especially suitable for analyzing time series data, as referred to CNN-LSTM (Convolutional Neural Network-Long Short Term Memory). In the study, the CNN-LSTM algorithm is used to predict the number of passing persons in one of 4×4 detection areas. We verified the validation of the proposed model by taking performance comparison with other artificial intelligence algorithms such as Multi-Layer Perceptron (MLP), Long Short Term Memory (LSTM) and RNN-LSTM (Recurrent Neural Network-Long Short Term Memory). As a result of the experiment, proposed CNN-LSTM hybrid model compared to MLP, LSTM and RNN-LSTM has the best predictive performance. By utilizing the proposed devices and models, it is expected various metro services will be provided with no illegal issue about the personal information such as real-time monitoring of public transport facilities and emergency situation response services on the basis of congestion. However, the data have been collected by selecting one side of the entrances as the subject of analysis, and the data collected for a short period of time have been applied to the prediction. There exists the limitation that the verification of application in other environments needs to be carried out. In the future, it is expected that more reliability will be provided for the proposed model if experimental data is sufficiently collected in various environments or if learning data is further configured by measuring data in other sensors.

• 한국지구과학회:학술대회논문집
• /
• 2010.04a
• /
• pp.88-89
• /
• 2010

최근 인간의 활동범위와 영역이 확대되고 산업이 발전하면서 인간의 삶과 지속가능한 발전 등 도시 기후에 관한 관심도 높아지고 있다. 산업혁명 이후 도시화와 산업화로 인해 인구가 증가하고 도시지역으로 집중됨으로써 도시 열섬화 현상에 대한 도시환경문제가 부각되고 있다. 이는 최근까지도 도시개발에 있어서 기능과 효율성이 우선시 되어 도시기후에 대한 배려가 이루어지지 못하고 있으며, 오히려 과도한 냉난방을 가동하는 등 쾌적한 실내 환경 조성을 위한 노력만을 행해왔다. 도시화에 따른 도시의 열환경 구조의 변화는 토지이용의 변화에 따른 피복상태와 밀접한 관련이 있다는 연구들이 수행된 바 있다. 이렇듯 도시화가 진행됨에 따라서 도심 지표면을 덮고 있는 포장재도 변하고 있다. 대표적인 토지피복재로는 콘크리트와 아스팔트 등의 인공포장재, 수계, 삼림 등으로 크게 나누어 볼 수 있다. 최근 도심의 발달로 인해 도심의 표면은 점차 인공포장재인 아스팔트와 콘크리트로 덮여지고 있다. 인공포장재는 맑은 여름철 낮에 받아들인 열을 야간에도 머금고 있어 도시열섬현상의 주요원인이 된다. 도시화가 진행됨에 따라 토지이용형태가 변화하고 있으며 이러한 토지피복의 변화는 그 지역의 기온과 풍향, 풍속뿐만 아니라 지표온도도 변화시키므로 도시 열환경 구조에 적지 않은 영향을 미치고 있다. 과거에는 자연 환경과 도시공간에 대한 인식이 다른 분야로 나누어져서 다루었지만 현재 위성영상 기술의 발달로 많은 공간 정보를 파악할 수 있게 된 바 도시기후변화에 더욱 직접적이고 근본적인 접근이 쉬워졌다. 원격탐사기법의 활용은 위성자료를 이용하여 동시간대 평면적인 열구조를 정량적으로 파악하는데에 중요한 자료를 제공하여 도시지역을 덮고 있는 인공자재의 존재가 도시열섬의 형성과 밀접하게 연관이 있다는 사실을 짐작할 수 있다. 따라서 도시기후변화의 문제점을 더욱 적극적으로 해결하기 위해서는 토지이용에 따른 지표면 온도 상승의 현황을 파악하고 이를 저감 시킬 수 있는 대책들이 수립되어야 한다. 본 연구는 보다 세분화된 도시 열환경을 정량적으로 분석 평가하기 위해서 토지피복별 분류를 3가지로 대구시 중구 경북대학교 부속 고등학교(이하 사대부고 지점)를 도심지역으로, 경상남도 창녕군 창녕읍 우포늪(이하 우포지점)을 수계지점으로, 경상북도 안동시 길안면 만음리(이하 안동지점) 지점과 대구시 칠곡군 동명면 득명리 팔공산 한티재 도립공원(이하 팔공지점)을 산림으로 분류하여 연구하였다. 대구 계명대학교 기후환경연구실에서 보유하고 있는 AWS(Automatic Weather Station) 자료로 기상요소를 분석하였으며, MODIS Terra 위성영상을 이용하여 지표온도를 추출하고 분석하였다. 또 기상요소와 지표온도를 이용해 회귀식을 도출하여 추정기온을 산출하였다. 그 결과 첫째, 계절에 따른 기온의 시간변화는 여름의 평균기온이 $25.13^{\circ}C$와 $24.12^{\circ}C$로 사대지점과 우포지점의 평균기온이 가장 높게 나타났으며, 이는 도심에서 발생되는 인공열의 영향으로, 우포지점은 수계의 특징이 반영된 결과라 할 수 있다. 둘째, 계절에 따른 풍속의 시간변화는 여름의 경우 우포지점의 풍속이 1.63m/s로 가장 높은 반면 안동지점의 풍속이 0.27m/s로 가장 낮은 것으로 나타났다. 겨울의 경우 팔공지점의 풍속이 1.82m/s로 가장 높게 나타났다. 토지피복에 따른 지표면의 변화가 도시기후에 미치는 영향을 정량적으로 평가하고, 또 지표면 온도와 기온과의 차이를 알아보기 위하여 MODIS 위성 영상을 이용하여 세 지점을 대상으로 토지피복에 따른 열환경을 평가 분석하여 다음과 같은 결론을 얻을 수 있었다. 첫째, MODIS 위성영상을 이용하여 산출한 지표면 온도는 여름철 주간에 안동지점의 경우 주변지역에 비해 지표면 온도가 약 $26^{\circ}C$로 낮게 나타났으며 우포지점의 경우 수계가 가지는 열 완충능력으로 약 $27^{\circ}C$의 낮은 지표면 온도를 나타내었다. 사대지점의 경우 약 $34^{\circ}C$이상의 높은 지표면 온도를 나타내었다. 둘째, MODIS 위성영상을 이용하여 산출한 지표면 온도와 관측된 기온과의 회귀식을 도출하여 상관분석 한 결과, 모든 지점의 값에서 상관성 및 신뢰도가 높은 것으로 나타났다. 셋째, 상관분석의 결과를 통하여 추정한 기온은 지표면 온도와의 차이가 있지만 유사한 패턴의 결과로 추출되었다. 이러한 결과로 볼 때 도시의 인공자재를 이용한 건축과 개발이 도시열섬현상을 유발하는데 중요한 역할을 하는 것을 정량적으로 평가할 수 있었다. 따라서 본 논문의 연구결과를 바탕으로 도시계획에 있어서 인공구조물에 의한 기온과 풍속이 받는 영향을 고려하여 도심의 인공구조물의 배치나 자재에 대한 개발이 이루어져야 할 것이며 열교환의 방해 및 바람순환이 확보되는 구조로 개선되어야 할 것이다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.37 no.1
• /
• pp.203-215
• /
• 2017

Recently, interest in Pedestrian Navigation Service (PNS) is being increased due to the diffusion of smart phone and the improvement of location determination technology and it is efficient to use landmarks in route guidance for pedestrians due to the characteristics of pedestrians' movement and success rate of path finding. Accordingly, researches on extracting landmarks have been progressed. However, preceding researches have a limit that they only considered the difference between buildings and did not consider visual attention of maps in display of PNS. This study improves this problem by defining building attributes as local variable and global variable. Local variables reflect the saliency of buildings by representing the difference between buildings and global variables reflects the visual attention by representing the inherent characteristics of buildings. Also, this study considers the connectivity of network and solves the overlapping problem of landmark candidate groups by network voronoi diagram. To extract landmarks, we defined building attribute data based on preceding researches. Next, we selected a choice point for pedestrians in pedestrian network data, and determined landmark candidate groups at each choice point. Building attribute data were calculated in the extracted landmark candidate groups and finally landmarks were extracted by principal component analysis. We applied the proposed method to a part of Gwanak-gu, Seoul and this study evaluated the extracted landmarks by making a comparison with labels and landmarks used by portal sites such as the NAVER and the DAUM. In conclusion, 132 landmarks (60.3%) among 219 landmarks of the NAVER and the DAUM were extracted by the proposed method and we confirmed that 228 landmarks which there are not labels or landmarks in the NAVER and the DAUM were helpful to determine a change of direction in path finding of local level.

• Journal of the Korean Society of Radiology
• /
• v.14 no.6
• /
• pp.773-780
• /
• 2020

With the development of the 4th industrial, research is being conducted to prevent diseases and reduce damage in various fields of science and technology such as medicine, health, and bio. As a result, artificial intelligence technology has been introduced and researched for image analysis of radiological examinations. In this paper, we will directly apply a deep learning model for classification and detection of pneumonia using chest X-ray images, and evaluate whether the deep learning model of the Inception series is a useful model for detecting pneumonia. As the experimental material, a chest X-ray image data set provided and shared free of charge by Kaggle was used, and out of the total 3,470 chest X-ray image data, it was classified into 1,870 training data sets, 1,100 validation data sets, and 500 test data sets. I did. As a result of the experiment, the result of metric evaluation of the Inception V3 deep learning model was 94.80% for accuracy, 97.24% for precision, 94.00% for recall, and 95.59 for F1 score. In addition, the accuracy of the final epoch for Inception V3 deep learning modeling was 94.91% for learning modeling and 89.68% for verification modeling for pneumonia detection and classification of chest X-ray images. For the evaluation of the loss function value, the learning modeling was 1.127% and the validation modeling was 4.603%. As a result, it was evaluated that the Inception V3 deep learning model is a very excellent deep learning model in extracting and classifying features of chest image data, and its learning state is also very good. As a result of matrix accuracy evaluation for test modeling, the accuracy of 96% for normal chest X-ray image data and 97% for pneumonia chest X-ray image data was proven. The deep learning model of the Inception series is considered to be a useful deep learning model for classification of chest diseases, and it is expected that it can also play an auxiliary role of human resources, so it is considered that it will be a solution to the problem of insufficient medical personnel. In the future, this study is expected to be presented as basic data for similar studies in the case of similar studies on the diagnosis of pneumonia using deep learning.

• Journal of Korea Water Resources Association
• /
• v.55 no.11
• /
• pp.923-929
• /
• 2022

The Chuncheon Mullori area is an underprivileged area of water welfare where local water supply is not supplied, and it is supplying water to the villages with small water supply facilities using lateral flow and groundwater as water sources. This is an area with poor water supply conditions, such as relying on water trucks due to water shortages during the recent severe drought. Therefore, in order to solve the problem of water shortage during drought and to prepare for the increasing water demand, a sand dam was installed along the valley, and this facility has been operating since May 2022. In this study, repeated simulations were performed according to the hydraulic conductivity of the filler material and the storage coefficient value for the inflow condition for about two years from mid-March 2020 to mid-March 2022. For each case, the amount of discharge through the perforated drain pipe was calculated. Overall, as the hydraulic conductivity increased, the amount of discharge and its ratio increased. However, when the hydraulic conductivity of the second floor was relatively low, the amount of discharge increased and then decreased as the hydraulic conductivity of the third floor increased. This is considered to be due to the fact that the water level was kept low due to the rapid drainage compared to the net inflow into the third floor because the water permeability of the third floor and the drainage coefficient of the drain pipe were large. As a result of simulating the flow of the open channel in the upper part of the sand dam as a hypothetical groundwater layer with very high hydraulic conductivity, the decrease in discharge rate was slower than the increase in the hydraulic conductivity of the hypothetical layer, but it was clearly shown that the discharge volume decreased relatively as the hydraulic conductivity of the virtual layer increased.