• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1271-1281
• /
• 2017

It is essential to collect and analyze target information around the vehicle for autonomous driving of the vehicle. Based on the analysis, environmental information such as location and direction should be analyzed in real time to control the vehicle. In particular, obstruction or cutting of objects in the image must be handled to provide accurate information about the vehicle environment and to facilitate safe operation. In this paper, we propose a method to simultaneously generate 2D and 3D bounding box proposals using LiDAR Edge generated by filtering LiDAR sensor information. We classify the classes of each proposal by connecting them with Region-based Fully-Covolutional Networks (R-FCN), which is an object classifier based on Deep Learning, which uses two-dimensional images as inputs. Each 3D box is rearranged by using the class label and the subcategory information of each class to finally complete the 3D bounding box corresponding to the object. Because 3D bounding boxes are created in 3D space, object information such as space coordinates and object size can be obtained at once, and 2D bounding boxes associated with 3D boxes do not have problems such as occlusion.

• 벤처창업연구
• /
• 제15권4호
• /
• pp.193-216
• /
• 2020

최근 글로벌 경제의 중장기적 불황과 성장률 하락에 기인하여, 대내외적으로 불투명한 환경하에서 생존하며 발전하기 위한 새로운 대안으로 새로운 서비스와 상품을 탄생시키고 생산방식의 변화와 업무 혁신 등으로 조직의 지속가능성을 높이는 기술혁신에 대한 관심이 날로 높아지고 있다. 이런 분위기 속에서 중소벤처기업의 성장은 국가 경제에 미치는 영향성이 지대하다는 것을 다수가 공감 중이며, 그런 중소벤처기업들이 기업 성과를 높이고 성과의 지속이 가능하도록 구성원들의 기술혁신 역량을 높이기 위한 여러 가지 노력이 지속되고 있다. 본 연구의 목적 역시 중소벤처 기업의 기술혁신 역량이 지식경영의 성과와 어떠한 상관관계를 가지고 있는가를 조사하고 기업의 전략적 활동을 조직화하여 가치 창출에 사용될 자원과 조직 능력을 외부 네트워크로부터 획득하게 하는 네트워크역량이 어떤 역할을 수행하는지에 대해 분석하여 확대 또는 강화해야 하는 영향요인을 정확히 파악하여 내·외부적인 역량을 강화하도록 하는 데 있다. 따라서 본 연구에서는 기술혁신역량이 중소벤처기업의 네트워크역량을 매개로 삼아, 기술혁신역량이 지식경영성과에 정(+)의 영향을 미칠 것이라는 가설을 검증하고자 한다. 기술혁신역량을 기반으로 한 경제활동이 코로나 등으로 불확실성이 높아진 환경에서 새로운 변화에 신속히 대응하며, 장기적 경기 침체 극복은 물론이고 거시적 경제 성장과 발전을 이끌어 조직의 지속적 성장과 생존뿐 아니라, 국가의 새로운 성장 동력이 될 수 있도록 해야 한다. 그리고 조직 내 가장 중요한 지식경영성과의 종속변수 설정을 통해서 본 연구를 진행하였다. 그 결과 기술혁신역량 중 연구개발역량과 학습역량은 재무적성과에 미치는 영향이 없는 것으로 나타났다. 그에 반해 기업혁신 활동은 재무적성과 및 비재무적성과에 모두 정(+)의 영향성을 가진 것으로 나타났다. 기술혁신역량을 활용하여 연구개발 활동을 하는 중소벤처기업 경영에서 무형적이며 비재무적인 요인 영향성이 확인되는 것은 선행연구 중 기업혁신 활동이 재무적성과에 영향성을 미친다는 다수의 연구와는 반대되는 결과이지만 일부 연구와는 유사한 결과이다. 이런 결과도출의 이유로는 조사기업들 다수의 업력이 7년 이상으로 스타트업 기업은 벗어났으나 매출은 100억 이하인 중소벤처기업들로서 매출 수익 일변도의 스타트업 시점과는 달리 연구개발역량과 학습역량이 재무적인 성과보다 무형적 비재무적성과에 긍정적 영향을 많이 끼치기 때문이라고 생각된다. 기업혁신 활동은 재무와 비재무적성과에 모두 긍정적(+)인 영향을 끼치는 것으로 나타났고, 연구개발역량과 학습역량은 네트워크역량을 매개변수로 재무적성과에 정(+)의 영향을 미치는 것으로 나타났다. 또한, 기업혁신 활동은 네트워크역량의 매개변수 영향성이 재무적성과와 비재무적성과 모두에 없는 것으로 나타났으며, 연구개발역량과 학습역량도 비재무적성과에는 영향성이 없었다. 네트워크역량의 매개변수 효과가 나타내는 것은 연구개발역량과 학습역량이 계량적 재무적성과를 도출할 때로 한정됨을 알 수 있다. 이런 결과들을 토대로 추후 연구개발사업의 성과측정에서는 비재무적성과 측정을 강화하도록 하는 정책 시행을 제시하는 바이다.

• 한국디지털정책학회:학술대회논문집
• /
• 한국디지털정책학회 2007년도 춘계학술대회
• /
• pp.51-58
• /
• 2007

Considering innovation a key to raising living standards, the Ministry of Science and Technology has put in place various measures meeting the needs of the newly promoted Deputy Prime Minister of Science and Technology. Such measures include business process reengineering as streamlining the work process to achieve the improvement in quality and efficiency: building the integrated performance management system to promote performance-or tented environment; and running the 1ifelong learning system for better competitiveness of government officials. Further to the innovation efforts at work, the number of steps of the R&D budget execution is streamlined from eight to five and its payment period is considerably reduced to 15 days from 60 days. In addition, the digitalized R&D budget management systems such as e-Contract System, One-click Processing Monitoring System, and Information Service System through Short Message Service (SMS) will contribute to improving R&D performance. And these systems are efficiently integrated into a portal interface named "Yeon-gu-ma-ru." The Ministry of Science and Technology, spearheading nationwide innovation, will continue efforts to make viable achievements of innovation.

• Asia pacific journal of information systems
• /
• 제20권4호
• /
• pp.101-123
• /
• 2010

Recently, firms are operating a number of teams to accomplish organizational performance. Especially, ad hoc teams like proposal preparation team are quite different from permanent teams like R&D team in the sense of how the team forms network structure and deals with organizational learning culture and knowledge management participation efforts. Moreover, depending on the team characteristics, individual creativity will differ from each other, which will lead to organizational performance eventually. Previous studies in the field of creativity are lacking in this issue. So main objectives of this study are organized as follows. First, the issue of how to improve individual creativity and organizational performance will be analyzed empirically. This issue will be performed depending on team characteristics such as ad hoc team and permanent team. Antecedents adopted for this research objective are cultural and knowledge factors such as organizational learning culture, and knowledge management participation. Second, the network structure such as degree centrality, and structural hole is used to analyze its influence on individual creativity and organizational performance. SI (System Integration) companies are facing severely tough requirements from clients to submit very creative proposals. Also, R&D teams are widely accepted as relatively creative teams because their responsibilities are focused on suggesting innovative techniques to make their companies remain competitive in the market. SI teams are usually ad hoc, while R&D teams are permanent on an average. By taking advantage of these characteristics of the two kinds of teams, we will prove the validity of the proposed research questions. To obtain the survey data, we accessed 7 SI teams (74 members), and 6 R&D teams (63 members), collecting 137 valid questionnaires. PLS technique was applied to analyze the survey data. Results are as follows. First, in case of SI teams, organizational learning culture affects individual creativity significantly. Meanwhile, knowledge management participation has a significant influence on Individual creativity for the permanent teams. Second, degree centrality Influences individual creativity significantly in case of SI teams. This is comparable with the fact that structural hole has a significant impact on individual creativity for the R&D teams. Practical implications can be summarized as follows: First, network structure of ad hoc team should be designed differently from one of permanent team. Ad hoc team is supposed to show a high creativity in a rather short period, implying that network density among team members should be improved, and those members with high degree centrality should be encouraged to show their Individual creativity and take a leading role by allowing them to get heavily engaged in knowledge sharing and diffusion. In contrast, permanent team should be designed to take advantage of structural hole instead of focusing on network density. Since structural hole can be utilized very effectively in the permanent team, strong arbitrators' merits in the permanent team will increase and therefore helps increase both network efficiency and effectiveness too. In this way, individual creativity in the permanent team is likely to lead to organizational creativity in a seamless way. Second, way of Increasing individual creativity should be sought from the perspective of organizational culture and knowledge management. Organization is supposed to provide a cultural atmosphere in which Innovative idea suggestions and active discussion among team members are encouraged. In this way, trust builds up among team members, facilitating the formation of organizational learning culture. Third, in the ad hoc team, organizational looming culture should be built such a way that individual creativity can grow up fast in a rather short period. Since time is tight, reasonable compensation policy, leader's Initiatives, and learning culture formation should be done In a short period so that mutual trust is built among members quickly, and necessary knowledge and information can be learnt rapidly. Fourth, in the permanent team, it should be kept in mind that the degree of participation in knowledge management determines level of Individual creativity. Therefore, the team ought to facilitate knowledge circulation process such as knowledge creation, storage, sharing, utilization, and learning among team members, which will lead to team performance. In this way, firms must control knowledge networks in permanent team and ad hoc team in a way mentioned above so that individual creativity as well as team performance can be maximized.

• 생물환경조절학회지
• /
• 제29권4호
• /
• pp.381-387
• /
• 2020

작물의 생체중을 추정하기 위해 다양한 연구가 시도되었지만, 이미지를 활용하여 생체중을 추정한 예는 없었다. 최근 합성곱 신경망을 사용한 이미지 처리 연구가 늘고 있으며, 합성곱 신경망은 미가공 데이터를 그대로 사용할 수 있다. 본 연구에서는 합성곱 신경망을 이용하여 미가공 데이터 상태인 특정 시점의 파프리카 이미지를 입력으로 작물의 생체중을 추정하도록 학습하였다. 실험은 파프리카(Capsicum annuum L.)를 재배하는 온실에서 수행하였다. 합성곱 신경망의 출력값인 생체중은 파괴조사를 통해 수집한 데이터를 기반으로 회귀 분석하였다. 학습된 합성곱 신경망의 결정 계수(R²)의 최고값은 0.95로 나타났다. 생체중 추정값은 실제 측정값과 매우 유사한 경향성을 보여주었다.

• 컴퓨터교육학회논문지
• /
• 제22권3호
• /
• pp.123-133
• /
• 2019

본 연구는 스마트교육의 한 요소인 스마트 기기를 활용하여 축적된 데이터를 기초로 유아의 개별 맞춤학습을 위한 스마트교육환경을 구축하는데 목적을 두고 있다. 이를 위해 유치원 만5세 학급에서 자유선택활동 운영을 위한 개선 방안을 제안하고, 유아 스스로 놀이 계획을 세우고 평가하는 자유선택활동 운영시스템을 구현하였다. 본 연구 참여한 유아들은 놀이계획, 놀이수행 및 수행평가등 전체 활동시간을 스스로가 적극적이며 즐겁게 참여하였다. 그 결과 유아는 스마트기기를 통한 자신의 흥미영역에 대한 활동선택에 기존교육환경보다 적극적으로 참여하는 것을 확인할 수 있었다. 본 연구에서 제안된 자유선택활동 운영시스템을 이용한 교사는 분석된 자료를 활용하여 스마트기기를 이용한 개별유아의 흥미분야와 학습수준 및 교실의 각 영역별 이용형태를 혼자서 쉽게 파악할 수 있었다.

• 전기학회논문지
• /
• 제57권10호
• /
• pp.1861-1868
• /
• 2008

In this paper, Passive Telemerty RF Sensor System using Unscented Kalman Filter algorithm(UKF) is proposed. General Passive Telemerty RF Sensor System means that it should be "wireless", "implantable" and "batterless". Conventional Passive Telemerty RF Sensor System adopts Integrated Circuit type, but there are defects like complexity of structure and limit of large power consumption in some cases. In order to overcome these kinds of faults, Passive Telemetry RF Sensor System based on inductive coupling principle is proposed in this paper. Because passive components R, L, C have stray parameters in the range of high frequency such as about 200[KHz] used in this paper, Passive Telemetry RF Sensor System considering stray parameters has to be derived for accurate model identification. Proposed Passive Telemetry RF Sensor System is simple because it consists of R, L and C and measures the change of environment like pressure and humidity in the type of capacitive value. This system adopted UKF algorithm for estimation of this capacitive parameter included in nonlinear system like Passive Telemetry RF Sensor System. For the purpose of obtaining learning data pairs for UKF Algorithm, Phase Difference Detector and Amplitude Detector are proposed respectively which make it possible to get amplitude and phase between input and output voltage. Finally, it is verified that capacitive parameter of proposed Passive Telemetry RF Sensor System using UKF algorithm can be estimated in noisy environment efficiently.

• 한국대기환경학회지
• /
• 제10권4호
• /
• pp.224-232
• /
• 1994

A new neural network model has been developed to predict short-term air pollution concentration. In addition, a multiple regression model widely used in statistical analysis was tested. These models were applied for prediction of daily maximum ozone concentration in Seoul during the summer season of 1991. The time periods between May and September 1989 and 1990 were utilized to train set of learning patterns in neural network model, and to estimate multiple regression model. To evaluate the results of the different models, several Performance indices were used. The results indicated that the multiple regression model tended to underpredict the daily maximum ozone concentration with small r$^{2}$(0.38). Also, large errors were found in this model; 21.1 ppb for RMSE, 0.324 for NMSE, and -0.164 for MRE. On the other hand, the results obtained from the neural network model were very promising. Thus, we can know that this model has a prominent efficiency in the adaptive control for the non-linear multi- variable systems such as photochemical oxidants. Also, when the recent new information was added in the neural network model, prediction accuracy was increased. From the new model, the values of RMSE, NMSE and r$^{2}$ were 13.2ppb, 0.089, 0.003 and 0.55 respectively.

• 한국컴퓨터정보학회논문지
• /
• 제22권4호
• /
• pp.9-16
• /
• 2017

Machine learning has found widespread implementations and applications in many different domains in our life. Logistic regression is a type of classification in machine leaning, and is used widely in many fields, including medicine, economics, marketing and social sciences. In this paper, we present the MapReduce implementation of three existing algorithms, this is, Gradient Descent algorithm, Cost Minimization algorithm and Newton-Raphson algorithm, for logistic regression on RHadoop that integrates R and Hadoop environment applicable to large scale data. We compare the performance of these algorithms for estimation of logistic regression coefficients with real and simulated data sets. We also compare the performance of our RHadoop and RHIPE platforms. The performance experiments showed that our Newton-Raphson algorithm when compared to Gradient Descent and Cost Minimization algorithms appeared to be better to all data tested, also showed that our RHadoop was better than RHIPE in real data, and was opposite in simulated data.

• 한국환경과학회지
• /
• 제32권8호
• /
• pp.595-611
• /
• 2023

The purpose of this study is to improve the daily prediction results of PM2.5 from the air quality diagnosis and evaluation system operated by the Busan Institute of Health and Environment in real time. The air quality diagnosis and evaluation system is based on the photochemical numerical model, CMAQ (Community multiscale air quality modeling system), and includes a 3-day forecast at the end of the model's calculation. The photochemical numerical model basically has limitations because of the uncertainty of input data and simplification of physical and chemical processes. To overcome these limitations, this study applied DNN (Deep Neural Network), a deep learning technique, to the results of the numerical model. As a result of applying DNN, the r of the model was significantly improved. The r value for GFS (Global forecast system) and UM (Unified model) increased from 0.77 to 0.87 and 0.70 to 0.83, respectively. The RMSE (Root mean square error), which indicates the model's error rate, was also significantly improved (GFS: 5.01 to 6.52 ug/m³ , UM: 5.76 to 7.44 ug/m³ ). The prediction results for each concentration grade performed in the field also improved significantly (GFS: 74.4 to 80.1%, UM: 70.0 to 77.9%). In particular, it was confirmed that the improvement effect at the high concentration grade was excellent.