• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.408-415
• /
• 2022

In this paper, we propose a 3D point cloud reconstruction technique from 2D images using efficient feature map extraction network. The originality of the method proposed in this paper is as follows. First, we use a new feature map extraction network that is about 27% efficient than existing techniques in terms of memory. The proposed network does not reduce the size to the middle of the deep learning network, so important information required for 3D point cloud reconstruction is not lost. We solved the memory increase problem caused by the non-reduced image size by reducing the number of channels and by efficiently configuring the deep learning network to be shallow. Second, by preserving the high-resolution features of the 2D image, the accuracy can be further improved than that of the conventional technique. The feature map extracted from the non-reduced image contains more detailed information than the existing method, which can further improve the reconstruction accuracy of the 3D point cloud. Third, we use a divergence loss that does not require shooting information. The fact that not only the 2D image but also the shooting angle is required for learning, the dataset must contain detailed information and it is a disadvantage that makes it difficult to construct the dataset. In this paper, the accuracy of the reconstruction of the 3D point cloud can be increased by increasing the diversity of information through randomness without additional shooting information. In order to objectively evaluate the performance of the proposed method, using the ShapeNet dataset and using the same method as in the comparative papers, the CD value of the method proposed in this paper is 5.87, the EMD value is 5.81, and the FLOPs value is 2.9G. It was calculated. On the other hand, the lower the CD and EMD values, the better the accuracy of the reconstructed 3D point cloud approaches the original. In addition, the lower the number of FLOPs, the less memory is required for the deep learning network. Therefore, the CD, EMD, and FLOPs performance evaluation results of the proposed method showed about 27% improvement in memory and 6.3% in terms of accuracy compared to the methods in other papers, demonstrating objective performance.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1739-1756
• /
• 2021

Atmospheric nitrogen dioxide (NO₂) is mainly caused by anthropogenic emissions. It contributes to the formation of secondary pollutants and ozone through chemical reactions, and adversely affects human health. Although ground stations to monitor NO₂ concentrations in real time are operated in Korea, they have a limitation that it is difficult to analyze the spatial distribution of NO₂ concentrations, especially over the areas with no stations. Therefore, this study conducted a comparative experiment of spatial interpolation of NO₂ concentrations based on two linear-regression methods(i.e., multi linear regression (MLR), and regression kriging (RK)), and two machine learning approaches (i.e., random forest (RF), and support vector regression (SVR)) for the year of 2020. Four approaches were compared using leave-one-out-cross validation (LOOCV). The daily LOOCV results showed that MLR, RK, and SVR produced the average daily index of agreement (IOA) of 0.57, which was higher than that of RF (0.50). The average daily normalized root mean square error of RK was 0.9483%, which was slightly lower than those of the other models. MLR, RK and SVR showed similar seasonal distribution patterns, and the dynamic range of the resultant NO₂ concentrations from these three models was similar while that from RF was relatively small. The multivariate linear regression approaches are expected to be a promising method for spatial interpolation of ground-level NO₂ concentrations and other parameters in urban areas.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.1
• /
• pp.141-149
• /
• 2020

The proportion of commercial vehicles currently used by the private sector among the vehicles operated by the military is very high at 58% and plans to increase further in the future. As the proportion of commercial vehicles in the military has increased, it is also an important issue to determine whether to disuse of commercial vehicles. At present, the decision of disuse of commercial vehicles is subjectively judged by vehicle technical inspector using design life and vehicle usage information. However, the difference according to the military operation environment is not reflected and objective judgment criteria are not presented. The purpose of this study is to develop a model to determine the disuse status of commercial vehicles in consideration of military operating environment. The data used in the study were 1,746 commercial vehicles of three types: cars, vans and trucks. Using the information of the operating area, climate characteristic, vehicle condition the decision model of disuse status was constructed using the classification machine learning technique. The proposed decision model of disuse status has an average accuracy of about 97% and can be used in the field. Based on the results of the study, the policy suggestions were proposed in the short and long term to improve the performance of decision model of disuse status of commercial vehicles in the future and to establish a new data construction method within the logistics information system.

• Communications of Mathematical Education
• /
• v.19 no.1 s.21
• /
• pp.69-100
• /
• 2005

이 연구는 내신성적이 우수함에도 불구하고 수능성적이 저조한 학생들이 문제 해결과정에서 나타내는 특성과 수학불안 요인을 분석하는데 있다. 연구의 대상은 인천시 5고등학교 자연계열 2학년 학생 중 내신성적이 상위 10%안에 드나 수능성적(모의수능성적)은 그렇지 못한 학생 5명이고, 이들의 수학적 성향, 수학 성취도, 개인별 특성 등에 대한 사전 면담자료, 문제풀이과정에 대한 사후 심층면담자료, 현장노트, 수학불안검사를 바탕으로 그들의 특성과 수학불안 요인을 분석한 결과는 다음과 같다. (1) 내신성적은 좋으나 수능성적이 저조한 학생들의 수학 문제 해결 과정에서 나타나는 특성은 수학전 영역에서의 개념부족, 공식암기 부족 등으로 인하여 문제풀이계획을 세우지 못하거나 설사 문제를 푼다고 해도 계산 실수, 착각, 부주의 등으로 인해 정확한 답을 구하지 못하는 것으로 나타났다. (2) 내신성적은 좋으나 수능성적이 저조한 학생들은 어느 정도의 수학 불안은 가지고 있었다. 불안의 요인은 개념부족, 응용력 부족 등 개인적 인지능력에 의한 저조한 수학 성취수준과 수학 공부시간 부족, 풀이시간 부족 등의 환경적 요인에 때문인 것으로 밝혀졌다. 특히 수학개념이 부족한 학생일수록 수학불안 현상이 심하게 나타났다. 따라서 이들 학생들의 수학 문제풀이 과정 중에 나타나는 계산 실수, 부주의, 착각은 그들의 수학 자신감에 많은 악영향을 미치게 되므로, 교사가 이를 그냥 방관할 것이 아니라 적극적으로 확인하고 지도해줄 필요가 있다. 또 교실 수업에서도 수능시험에서 다루고 있는 수학 내적, 외적 문제해결문제, 추론문제, 응용문제, 통합문제에 대한 문제풀이 경험을 하게하여 수학불안을 해소해줄 필요가 있다.)값을 보였으나, 10,000Hz의 높은 측정주파수에서는 더 큰 $E_a$값을 나타냄으로서 반응온도변화에 민감함을 보여주었다.원으로부터 부유물을 증가로 사료되었으며, 이에 대한 대책마련이 시급한 것으로 사료되었다. 수질이 휴양용수로서 사용하는 데에 적합하도록 충분한 차집시설과 환경 기초시설의 설치 운영이 필요할 것으로 판단된다.TEX>$K_s$값이 높고 $V_m/K_s$비율은 낮아 수게에서 질소가 저농도 일 때에는 다른 미세조류와 비교하면 경쟁력이 떨어지고 질소에 대한 기질 친화력은 약한 것으로 나타났다. 낙동강 하류지역에서 M. aeruginosa가 대발생하는 시기에 수중 영양염의 농도 변동은 M. aeruginosa의 영양생리 kinetics 특성과 잘 부합하는 것으로 나타났다.부분을 보완하기 위한 연구가 이루어져야 할 것으로 보인다. 연마방법 간에 상호 연관성이 없었다. FE-SEM관찰에서 레진전색제를 적용한 후의 표면은 모든 군에서 대체적으로 평활한 표면을 나타내었다. 4. 동일한 복합레진과 연마방법으로 처리된 군에서 레진전색제 적용 전과 후의 표면조도 값은 M1B군이 M1군보다, S1B군이 S1군보다 통계학적으로 높게 나타났으며, M4B군과 M5B군은 각각 M4군과 M5군 보다. 그리고 S5B군은 S5군 보다 통계학적으로 낮게 나타났다 (p<0.05). 본 연구를 종합하여 보면, 복합레진의 종류에 따라 표면조도의 순서는 다르게 나타났고, polyester strip 하에서 복합레진이 중합된 경우 가장 낮은 표면조도 값과 평활한 표면을 제공하였으며 전반적으로 anishing bur는 가장 높은 Ra값과 거친 표면을 제공하였다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.3
• /
• pp.96-103
• /
• 2018

An analysis using a statistical method is generally used to determine the effective temperature based on the temperature design load of a bridge. In this study, the effective temperature was calculated by building an artificial neural network (ANN) capable of improving the statistical method. A Steel box girder bridge specimen was made with a width of 2.0 m, height of 2.0 m, and length of 3.0 m and 0.2 m the upper slab. Twenty one temperature gauges were attached to measure the temperature between 2014 and 2016 for three years. An ANN was learned using the data measured from 2014~2015 and the results were compared with the Euro codes. The error rate between the Euro code and statistical analysis values was analyzed to be 4.1 % for the total measurement point. The ANN was verified and the effective bridge temperatures were calculated using the temperature data measured in 2016. The results revealed an approximate 3.97 % difference from the statistical analysis values. This degree of error is considered to be acceptable in terms of engineering for the analysis of an ANN. An ANN can easily predict the effective temperature of a bridge by knowing the input values of the region's highest temperature, bridge type, and upper asphalt thickness when designing the bridge's temperature loads.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.11
• /
• pp.554-560
• /
• 2020

In the manufacturing process of flat panel displays, a high-precision planar motion stage is used to position a specimen. Stages of this type typically use frictionless linear motors and air bearings, and laser interferometers. Real-time dynamic correction of the yaw motion error is very important because the inevitable yaw motion error of the stage means a change in the specimen orientation. Gantry control is generally used to compensate for yaw motion errors. Flexure units that allow rotational motion are applied to the stage to apply this method to a stage using an air-bearing guide. This paper proposes a method to improve the constant speed motion performance of a H-type XY stage equipped with air bearing and flexure units. When applying the gantry control to the stage, including the flexure units, the cause of the mutual ripple generated from the linear motors is analyzed, and adaptive learning control is proposed to compensate for the mutual ripple. A simulation was performed to verify the proposed method. The speed ripple was reduced to approximately the 22 % level. The ripple reduction was verified by simulating the stage state where yaw motion error occurs.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.7
• /
• pp.539-547
• /
• 2017

This study examined the perception of disasters and post-traumatic stress disorder in occupational therapy majors to provide the basic data necessary for future occupational therapy. A questionnaire survey was conducted on 545 students in occupational therapy departments of three year and four year universities. The frequency of the questionnaire was calculated by frequency analysis using the SPSS 19.0 win program. A chi-squared test was conducted to verify the analyzed questionnaire data. The reliability of the questionnaire in this study showed a Cronbach' alpha value of 0.891. According to the survey results, approximately 20% of learners who majored in occupational therapy were unaware of the symptoms, developmental mechanism, and diagnostic criteria of post-traumatic stress disorder(PTSD). Knowledge of the underlying causes of psychological symptoms, such as post-traumatic stress disorder as well as physical damage through industrial accidents, was found to be 2.92 on the Likert 5-point scale. To be effective in rehabilitation treatment, the degree of the approach to education from the viewpoint of occupational therapy is important enough to be recognized as 3.90 on the Likert 5-point scale. The Pearson correlation coefficient for the need for education on disasters was higher than the correlation with the awareness of disasters.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.11
• /
• pp.705-710
• /
• 2017

This paper proposes an estimation method of populations of Grapholita molestas using object segmentation and an SVM classifier in the moth images. Object segmentation and moth classification were performed on images of Grapholita molestas moth acquired on a pheromone trap equipped in an orchard. Object segmentation consisted of pre-processing, thresholding, morphological filtering, and object labeling process. The classification of Grapholita molestas in the moth images consisted of the training and classification of an SVM classifier and estimation of the moth populations. The object segmentation simplifies the moth classification process by segmenting the individual objects before passing an input image to the SVM classifier. The image blocks were extracted around the center point and principle axis of the segmented objects, and fed into the SVM classifier. In the experiments, the proposed method performed an estimation of the moth populations for 10 moth images and achieved an average estimation precision rate of 97%. Therefore, it showed an effective monitoring method of populations of Grapholita molestas in the orchard. In addition, the mean processing time of the proposed method and sliding window technique were 2.4 seconds and 5.7 seconds, respectively. Therefore, the proposed method has a 2.4 times faster processing time than the latter technique.

• The Journal of the Korea Contents Association
• /
• v.20 no.7
• /
• pp.674-682
• /
• 2020

Recently, the problem of air pollution has become a global concern due to industrialization and overcrowding. Air pollution can cause various adverse effects on human health, among which respiratory diseases such as asthma, which have been of interest in this study, can be directly affected. Previous studies have used clinical data to identify how air pollutant affect diseases such as asthma based on relatively small samples. This is high likely to result in inconsistent results for each collection samples, and has significant limitations in that research is difficult for anyone other than the medical profession. In this study, the main focus was on predicting the actual asthmatic occurrence, based on data on the atmospheric environment data released by the government and the frequency of asthma outbreaks. First of all, this study verified the significant effects of each air pollutant with a time lag on the outbreak of asthma through the time-lag Pearson Correlation Coefficient. Second, train data built on the basis of verification results are utilized in Deep Learning algorithms, and models optimized for predicting the asthmatic occurrence are designed. The average error rate of the model was about 11.86%, indicating superior performance compared to other machine learning-based algorithms. The proposed model can be used for efficiency in the national insurance system and health budget management, and can also provide efficiency in the deployment and supply of medical personnel in hospitals. And it can also contribute to the promotion of national health through early warning of the risk of outbreak by atmospheric environment for chronic asthma patients.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.278-284
• /
• 2003

Speech act is the speaker's intentions indicated through utterances. It is important for understanding natural language dialogues and generating responses. This paper proposes the method of two stage that increases the performance of the korean speech act decision. The first stage is to select features from the part of speech results in sentence and from the context that uses previous speech acts. We use x$^2$ statistics(CHI) for selecting features that have showed high performance in text categorization. The second stage is to determine speech act with selected features and Neural Network. The proposed method shows the possibility of automatic speech act decision using only POS results, makes good performance by using the higher informative features and speed up by decreasing the number of features. We tested the system using our proposed method in Korean dialogue corpus transcribed from recording in real fields, and this corpus consists of 10,285 utterances and 17 speech acts. We trained it with 8,349 utterances and have test it with 1,936 utterances, obtained the correct speech act for 1,709 utterances(88.3%). This result is about 8% higher accuracy than without selecting features.