• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.229-230
• /
• 2022

본 논문에서는 CNN Object Detection과 더불어 3D 카메라 기반 디지털 좌표 인식 기술을 제안한다. 이 기술은 3D Depth Camera인 Intel 사의 Realsense D455를 이용해 대상을 감지하고 분류하며 대상의 위치를 파악한다. 또한 이 기술은 기존의 Depth Camera 내장 거리와는 다르게 좌표를 인식하여 좌표간의 거리까지 계산이 가능하다. 또한 Tensorflow SSD 구조와의 메모리 공유를 통해 시스템의 자원 낭비를 줄이며, 속도를 높이는 멀티쓰레드를 탑재했다. 본 기술을 통해 좌표간의 거리를 계산함으로써 스포츠, 심리, 놀이, 산업 등 다양한 환경에서 활용할 수 있다.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.162-162
• /
• 2017

구글에서 공개한 Tensorflow를 이용한 여러 학문 분야의 연구가 활발하다. 농업 시설환경을 대상으로 한 빅데이터의 축적이 증가함과 아울러 실효적인 정보 획득을 위한 각종 데이터 분석 및 마이닝 기법에 대한 연구 또한 활발한 상황이다. 한편, 타 분야의 성공적인 심층학습기법 응용사례에 비하여 농업 분야에서의 응용은 초기 성장 단계라 할 수 있다. 이는 농업 현장에서 취득한 정보의 난해성 및 완성도 높은 생육/환경 모델링 정보의 부재로 실효적인 전과정 처리 기술 도출에 소요되는 시간, 비용, 연구 환경이 상대적으로 부족하기 때문일 것이다. 특히, 센서 기반 데이터 취득 기술 증가에 따라 비약적으로 방대해진 수집 데이터를 시간 복잡도가 높은 심층 학습 모델링 연산에 기계적으로 단순 적용할 경우 시간 효율적인 측면에서 성공적인 결과 도출에 애로가 있을 것이다. 매우 높은 시간 복잡도를 해결하기 위하여 제시된 하드웨어 가속 기능의 경우 일부 개발환경에 국한이 되어 있다. 일례로, 구글의 Tensorflow는 오픈소스 기반 병렬 클러스터링 기술인 MPICH를 지원하는 알고리즘을 공개하지 않고 있다. 따라서, 본 연구에서는 심층학습 기법 연구에 있어서, 예상 가능한 다양한 자원을 활용하여 최대한 연산의 결과를 빨리 도출할 수 있는 하드웨어적인 접근 방법을 모색하였다. 호스트에서 수행하는 일방적인 학습 알고리즘과 달리 이기종간 심층 학습이 가능하기 위해선 우선, NFS(Network File System)를 이용하여 데이터 계층이 상호 연결이 되어야 한다. 이를 위해서 고속 네트워크를 기반으로 한 NFS의 이용이 필수적이다. 둘째로 제한된 자원의 한계를 극복하기 위한 메모 공유 라이브러리가 필요하다. 셋째로 이기종간 프로세서에 최적화된 병렬 처리용 컴파일러를 이용해야 한다. 가장 중요한 부분은 이기종간의 처리 능력에 따른 작업을 고르게 분배할 수 있는 작업 스케쥴링이 수행되어야 하며, 이는 처리하고자 하는 데이터의 형태에 따라 매우 가변적이므로 해당 데이터 도메인에 대한 엄밀한 사전 벤치마킹이 수행되어야 한다. 이러한 요구조건을 대부분 충족하는 Open-CL ver1.2(https://www.khronos.org/opencl/)를 이용하였다. 최신의 Open-CL 버전은 2.2이나 본 연구를 위하여 준비한 4가지 이기종 시스템에서 모두 공통적으로 지원하는 버전은 1.2이다. 실험적으로 선정된 4가지 이기종 시스템은 1) Windows 10 Pro, 2) Linux-Ubuntu 16.04.4 LTS-x86_64, 3) MAC OS X 10.11 4) Linux-Ubuntu 16.04.4 LTS-ARM Cortext-A15 이다. 비교 분석을 위하여 NVIDIA 사에서 제공하는 Pascal Titan X 2식을 SLI로 구성한 시스템을 준비하였다. 개별 시스템에서 별도로 컴파일 된 바이너리의 이름을 통일하고, 개별 시스템의 코어수를 동일하게 균등 배분하여 100 Hz의 데이터로 입력이 되는 온도 정보와 조도 정보를 입력으로 하고 이를 습도정보에 Linear Gradient Descent Optimizer를 이용하여 Epoch 10,000회의 학습을 수행하였다. 4종의 이기종에서 총 32개의 코어를 이용한 학습에서 17초 내외로 연산 수행을 마쳤으나, 비교 시스템에서는 11초 내외로 연산을 마치는 결과가 나왔다. 기보유 하드웨어의 적절한 활용이 가능한 심층학습 기법에 대한 연구를 지속할 것이다

• The Journal of the Korea Contents Association
• /
• v.20 no.10
• /
• pp.688-701
• /
• 2020

In this study, a total of 68 domestic and international papers were selected from 1993 to August 2020 in order to examine the research trends related to artificial intelligence for the visually impaired. The papers were compared and analyzed by the number of papers published by year, research method, research topic, keyword analysis status, research type, and implementation method. As a result of the study, the number of papers during the study period seemed to increase steadily. But in the case of domestic research, It can be seen that it has become active since 2016. As for research methods, development research accounted for 89.7% of both domestic and foreign research. Keywords was in Visually Impaired, Deep Learning, and Assistive Device order in domestic research. And it was in Visually Impaired, Deep learning, Artificial intelligence order in foreign research. There was a difference in the frequency of words. Research type were Design, development and implementation both in domestic and foreign. Implementation method were in System 13.2%, Solution 7.4%, App. 4.4% order in domestic research, and it was in System 32.4%, App. 13.2%, Device 7.4% order in foreign research. As for the applied technology of the implementation method, were in YOLO 2.7%, TTS 2.1%, Tensorflow 2.1% order in domestic research, and it was used in CNN 8.0%, TTS 5.3%, MS-COCO 4.3% order in foreign research. The purpose of this study was to compare and analyze the trends of artificial intelligence-related research targeting the visually impaired, to immediately know the current status of domestic and foreign research, and to present the direction of artificial intelligence research for the visually impaired in the future.

• Journal of the Korea Convergence Society
• /
• v.9 no.9
• /
• pp.431-440
• /
• 2018

In this study, authors predicted probability of resignation of newly employed nurses using TensorFlow, an open source software library for numerical computation and machine learning developed by Google, and suggested strategic human resources management plan. Data of 1,018 nurses who resigned between 2010 and 2017 in single university hospital were collected. After the order of data were randomly shuffled, 80% of total data were used for machine leaning and the remaining data were used for testing purpose. We utilized multiple neural network with one input layer, one output layer and 3 hidden layers. The machine-learning algorithm correctly predicted for 88.7% of resignation of nursing staff with in one year of employment and 79.8% of that within 3 years of employment. Most of resigned nurses were in their late 20s and 30s. Leading causes of resignation were marriage, childbirth, childcare and personal affairs. However, the most common cause of resignation of nursing staff with in one year of employment were maladaptation to the work and problems in interpersonal relationship.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.3
• /
• pp.527-533
• /
• 2018

Recently, the device-to-device (D2D) communication has been conceived as the key technology for the next-generation mobile communication systems. The neighbor discovery in which the nearby users are found, is essential for the proper operation of the D2D communication. In this paper, we propose new neighbor discovery scheme based on deep learning technology which has gained a lot of attention recently. In the proposed scheme, the neighboring users can be found using the uplink pilot transmission of users only, unlike conventional neighbor discovery schemes in which direct pilot communication among users is required, such that the signaling overhead can be greatly reduced in our proposed scheme. Moreover, the neighbors with different proximity can also be classified accordingly which enables more accurate neighbor discovery compared to the conventional schemes. The performance of our proposed scheme is verified through the tensorflow-based computer simulations.

• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.59-70
• /
• 2018

In order to provide stable district heat supplying service to the certain limited residential area, it is the most important to forecast the short-term future demand more accurately and produce and supply heat in efficient way. However, it is very difficult to develop a universal heat demand forecasting model that can be applied to general situations because the factors affecting the heat consumption are very diverse and the consumption patterns are changed according to individual consumers and regional characteristics. In particular, considering all of the various variables that can affect heat demand does not help improve performance in terms of accuracy and versatility. Therefore, this study aims to develop a demand forecasting model using deep learning based on only limited information that can be acquired in real time. A demand forecasting model was developed by learning the artificial neural network of the Tensorflow using past data consisting only of the outdoor temperature of the area and date as input variables. The performance of the proposed model was evaluated by comparing the accuracy of demand predicted with the previous regression model. The proposed heat demand forecasting model in this research showed that it is possible to enhance the accuracy using only limited variables which can be secured in real time. For the demand forecasting in a certain region, the proposed model can be customized by adding some features which can reflect the regional characteristics.

• Economic and Environmental Geology
• /
• v.55 no.3
• /
• pp.309-316
• /
• 2022

In order to minimize the human and time consumption required for rock classification, research on rock classification using artificial intelligence (AI) has recently developed. In this study, basic volcanic rocks were subdivided by using polarizing microscope thin section images. A convolutional neural network (CNN) model based on Tensorflow and Keras libraries was self-producted for rock classification. A total of 720 images of olivine basalt, basaltic andesite, olivine tholeiite, trachytic olivine basalt reference specimens were mounted with open nicol, cross nicol, and adding gypsum plates, and trained at the training : test = 7 : 3 ratio. As a result of machine learning, the classification accuracy was over 80-90%. When we confirmed the classification accuracy of each AI model, it is expected that the rock classification method of this model will not be much different from the rock classification process of a geologist. Furthermore, if not only this model but also models that subdivide more diverse rock types are produced and integrated, the AI model that satisfies both the speed of data classification and the accessibility of non-experts can be developed, thereby providing a new framework for basic petrology research.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.10
• /
• pp.323-332
• /
• 2022

As various services using AI technology are being developed, much attention is being paid to AI service production. Recently, AI technology is acknowledged as one of ICT services, a lot of research is being conducted for general-purpose AI service production. In this paper, I describe the research results in terms of systems for AI service production, focusing on the distribution and production of machine learning models, which are the final steps of general machine learning development procedures. Three different Ubuntu systems were built, and experiments were conducted on the system, using data from 2017 validation COCO dataset in combination of different AI models (RFCN, SSD-Mobilenet) and different communication methods (gRPC, REST) to request and perform AI services through Tensorflow serving. Through various experiments, it was found that the type of AI model has a greater influence on AI service inference time than AI machine communication method, and in the case of object detection AI service, the number and complexity of objects in the image are more affected than the file size of the image to be detected. In addition, it was confirmed that if the AI service is performed remotely rather than locally, even if it is a machine with good performance, it takes more time to infer the AI service than if it is performed locally. Through the results of this study, it is expected that system design suitable for service goals, AI model development, and efficient AI service production will be possible.

• Journal of Korean Society of Disaster and Security
• /
• v.14 no.4
• /
• pp.17-27
• /
• 2021

Streamflow prediction is a very vital disaster mitigation approach for effective flood management and water resources planning. Lately, torrential rainfall caused by climate change has been reported to have increased globally, thereby causing enormous infrastructural loss, properties and lives. This study evaluates the contribution of rainfall to streamflow prediction in normal and peak rainfall scenarios, typical of the recent flood at Piney Resort in Vernon, Hickman County, Tennessee, United States. Daily streamflow, water level, and rainfall data for 20 years (2000-2019) from two USGS gage stations (03602500 upstream and 03599500 downstream) of the Piney River watershed were obtained, preprocesssed and fitted with Long short term memory (LSTM) model. Tensorflow and Keras machine learning frameworks were used with Python to predict streamflow values with a sequence size of 14 days, to determine whether the model could have predicted the flooding event in August 21, 2021. Model skill analysis showed that LSTM model with full data (water level, streamflow and rainfall) performed better than the Naive Model except some rainfall models, indicating that only rainfall is insufficient for streamflow prediction. The final LSTM model recorded optimal NSE and RMSE values of 0.68 and 13.84 m³/s and predicted peak flow with the lowest prediction error of 11.6%, indicating that the final model could have predicted the flood on August 24, 2021 given a peak rainfall scenario. Adequate knowledge of rainfall patterns will guide hydrologists and disaster prevention managers in designing efficient early warning systems and policies aimed at mitigating flood risks.

• Korean Journal of Artificial Intelligence
• /
• v.5 no.1
• /
• pp.29-37
• /
• 2017

The range of problems that can be handled by the activation of big data and the development of hardware has been rapidly expanded and machine learning such as deep learning has become a very versatile technology. In this paper, mnist data set is used as experimental data, and the Cross Entropy function is used as a loss model for evaluating the efficiency of machine learning, and the value of the loss function in the steepest descent method is We applied the Gradient Descent Optimize algorithm to minimize and updated weight and bias via backpropagation. In this way we analyze optimal reliability value corresponding to the number of exercises and optimal reliability value without overfitting. And comparing the overfitting time according to the number of data changes based on the number of training times, when the training frequency was 1110 times, we obtained the result of 92%, which is the optimal reliability value without overfitting.