• The Journal of Information Systems
• /
• v.31 no.3
• /
• pp.197-220
• /
• 2022

Purpose The purpose of this study is to identifies the demand pattern categorization of repair parts of Automotive After-sales Service(A/S) and proposes a demand prediction model for Auto repair parts using Long Short-Term Memory (LSTM) of artificial neural networks (ANN). The optimal parts inventory quantity prediction model is implemented by applying daily, weekly, and monthly the parts demand data to the LSTM model for the Lumpy demand which is irregularly in a specific period among repair parts of the Automotive A/S service. Design/methodology/approach This study classified the four demand pattern categorization with 2 years demand time-series data of repair parts according to the Average demand interval(ADI) and coefficient of variation (CV²) of demand size. Of the 16,295 parts in the A/S service shop studied, 96.5% had a Lumpy demand pattern that large quantities occurred at a specific period. lumpy demand pattern's repair parts in the last three years is predicted by applying them to the LSTM for daily, weekly, and monthly time-series data. as the model prediction performance evaluation index, MAPE, RMSE, and RMSLE that can measure the error between the predicted value and the actual value were used. Findings As a result of this study, Daily time-series data were excellently predicted as indicators with the lowest MAPE, RMSE, and RMSLE values, followed by Weekly and Monthly time-series data. This is due to the decrease in training data for Weekly and Monthly. even if the demand period is extended to get the training data, the prediction performance is still low due to the discontinuation of current vehicle models and the use of alternative parts that they are contributed to no more demand. Therefore, sufficient training data is important, but the selection of the prediction demand period is also a critical factor.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.150-150
• /
• 2023

기작기반의 역학적 모델과 자료기반의 딥러닝 모델은 수질예측에 다양하게 적용되고 있으나, 각각의 모델은 고유한 구조와 가정으로 인해 장·단점을 가지고 있다. 특히, 딥러닝 모델은 우수한 예측 성능에도 불구하고 훈련자료가 부족한 경우 오차와 과적합에 따른 분산(variance) 문제를 야기하며, 기작기반 모델과 달리 물리법칙이 결여된 예측 결과를 생산할 수 있다. 본 연구의 목적은 주요 상수원인 댐 저수지를 대상으로 수심별 수온과 탁도를 예측하기 위해 기작기반과 자료기반 모델의 장점을 융합한 PGDL(Process-Guided Deep Learninig) 모델을 개발하고, 물리적 법칙 만족도와 예측 성능을 평가하는데 있다. PGDL 모델 개발에 사용된 기작기반 및 자료기반 모델은 각각 CE-QUAL-W2와 순환 신경망 딥러닝 모델인 LSTM(Long Short-Term Memory) 모델이다. 각 모델은 2020년 1월부터 12월까지 소양강댐 댐 앞의 K-water 자동측정망 지점에서 실측한 수온과 탁도 자료를 이용하여 각각 보정하고 훈련하였다. 수온 및 탁도 예측을 위한 PGDL 모델의 주요 알고리즘은 LSTM 모델의 목적함수(또는 손실함수)에 실측값과 예측값의 오차항 이외에 역학적 모델의 에너지 및 질량 수지 항을 제약 조건에 추가하여 예측결과가 물리적 보존법칙을 만족하지 않는 경우 penalty를 부가하여 매개변수를 최적화시켰다. 또한, 자료 부족에 따른 LSTM 모델의 예측성능 저하 문제를 극복하기 위해 보정되지 않은 역학적 모델의 모의 결과를 모델의 훈련자료로 사용하는 pre-training 기법을 활용하여 실측자료 비율에 따른 모델의 예측성능을 평가하였다. 연구결과, PGDL 모델은 저수지 수온과 탁도 예측에 있어서 경계조건을 통한 에너지와 질량 변화와 저수지 내 수온 및 탁도 증감에 따른 공간적 에너지와 질량 변화의 일치도에 있어서 LSTM보다 우수하였다. 또한 역학적 모델 결과를 LSTM 모델의 훈련자료의 일부로 사용한 PGDL 모델은 적은 양의 실측자료를 사용하여도 CE-QUAL-W2와 LSTM 보다 우수한 예측 성능을 보였다. 연구결과는 다차원의 역학적 수리수질 모델과 자료기반 딥러닝 모델의 장점을 결합한 새로운 모델링 기술의 적용 가능성을 보여주며, 자료기반 모델의 훈련자료 부족에 따른 예측 성능 저하 문제를 극복하기 위해 역학적 모델이 유용하게 활용될 수 있음을 시사한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.216-218
• /
• 2022

Natural disasters caused by abnormal climates are continuously increasing, and the types of natural disasters that cause the most damage are flood damage caused by heavy rains and typhoons. Therefore, in order to reduce flood damage, this paper proposes a system that can predict the water level, a major parameter of flood, in real time using LSTM and GRU. The input data used for flood prediction are upstream and downstream water levels, temperature, humidity, and precipitation, and real-time prediction is performed through the pre-trained LSTM-GRU model. The input data uses data from the past 20 hours to predict the water level for the next 3 hours. Through the system proposed in this paper, if the risk determination function can be added and an evacuation order can be issued to the people exposed to the flood, it is thought that a lot of damage caused by the flood can be reduced.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.3
• /
• pp.65-75
• /
• 2017

As a 360-degree image carries information of all directions, it often has too much information. Moreover, in order to investigate a 360-degree image on a 2D display, a user has to either click and drag the image with a mouse, or project it to a 2D panorama image, which inevitably introduces severe distortions. In consequence, investigating a 360-degree image and finding an object of interest in such a 360-degree image could be a tedious task. To resolve this issue, this paper proposes a method to find a region of interest and produces a 2D naturally looking image from a given 360-degree image that best matches a description given by a user in a natural language sentence. Our method also considers photo composition so that the resulting image is aesthetically pleasing. Our method first converts a 360-degree image to a 2D cubemap. As objects in a 360-degree image may appear distorted or split into multiple pieces in a typical cubemap, leading to failure of detection of such objects, we introduce a modified cubemap. Then our method applies a Long Short Term Memory (LSTM) network based object detection method to find a region of interest with a given natural language sentence. Finally, our method produces an image that contains the detected region, and also has aesthetically pleasing composition.

• Journal of IKEEE
• /
• v.22 no.3
• /
• pp.822-828
• /
• 2018

Recently, energy issues such as massive blackout due to increase in power consumption have been emerged, and it is necessary to improve the accuracy of prediction of power consumption as a solution for these problems. In this study, we investigate the difference between the actual power consumption and the predicted power consumption through the deep learning- based power consumption forecasting experiment, and the possibility of adjusting the power reserve ratio. In this paper, the prediction of the power consumption based on the deep learning can be used as a basis to reduce the power reserve ratio so as not to excessively produce extra power. The deep learning method used in this paper uses a learning model of long-short-term-memory (LSTM) structure that processes time series data. In the computer simulation, the generated power consumption data was learned, and the power consumption was predicted based on the learned model. We calculate the error between the actual and predicted power consumption amount, resulting in an error rate of 21.37%. Considering the recent power reserve ratio of 45.9%, it is possible to reduce the reserve ratio by 20% when applying the power consumption prediction algorithm proposed in this study.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.149-158
• /
• 2023

As data utilization is becoming more important recently, the importance of data centers is also increasing. However, the data center is a problem in terms of environment and economy because it is a massive power-consuming facility that runs 24 hours a day. Recently, studies using deep learning techniques to reduce power used in data centers or servers or predict traffic have been conducted from various perspectives. However, the amount of traffic data processed by the server is anomalous, which makes it difficult to manage the server. In addition, many studies on dynamic server management techniques are still required. Therefore, in this paper, we propose a dynamic server management technique based on Long-Term Short Memory (LSTM), which is robust to time series data prediction. The proposed model allows servers to be managed more reliably and efficiently in the field environment than before, and reduces power used by servers more effectively. For verification of the proposed model, we collect transmission and reception traffic data from six of Wikipedia's data centers, and then analyze and experiment with statistical-based analysis on the relationship of each traffic data. Experimental results show that the proposed model is helpful for reliably and efficiently running servers.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.28 no.4
• /
• pp.133-142
• /
• 2023

In this paper, we built a data-driven artificial intelligence model using RNN-LSTM (Recurrent Neural Networks-Long Short-Term Memory) to predict the Lorenz system, and examined the possibility of whether this model can replace chaotic dynamic models. We confirmed that the data-driven model reflects the chaotic nature of the Lorenz system, where a small error in the initial conditions produces fundamentally different results, and the system moves around two stable poles, repeating the transition process, the characteristic of "deterministic non-periodic flow", and simulates the bifurcation phenomenon. We also demonstrated the advantage of adjusting integration time intervals to reduce computational resources in data-driven models. Thus, we anticipate expanding the applicability of data-driven artificial intelligence models through future research on refining data-driven models and data assimilation techniques for data-driven models.

• Smart Media Journal
• /
• v.12 no.10
• /
• pp.63-70
• /
• 2023

Recently, energy consumption for heating costs, which is 35% of smart farm energy costs, has increased, requiring energy consumption efficiency, and the importance of new and renewable energy is increasing due to concerns about the realization of electricity bills. Renewable energy belongs to hydropower, wind, and solar power, of which solar energy is a power generation technology that converts it into electrical energy, and this technology has less impact on the environment and is simple to maintain. In this study, based on the greenhouse heat storage tank and heat pump data, the factors that affect the heat storage tank are selected and a heat storage tank supply temperature prediction model is developed. It is predicted using Long Short-Term Memory (LSTM), which is effective for time series data analysis and prediction, and XGBoost model, which is superior to other ensemble learning techniques. By predicting the temperature of the heat pump heat storage tank, energy consumption may be optimized and system operation may be optimized. In addition, we intend to link it to the smart farm energy integrated operation system, such as reducing heating and cooling costs and improving the energy independence of farmers due to the use of solar power. By managing the supply of waste heat energy through the platform and deriving the maximum heating load and energy values required for crop growth by season and time, an optimal energy management plan is derived based on this.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.4
• /
• pp.1400-1418
• /
• 2020

In the development of commercial promotion, chatbot is known as one of significant skill by application of natural language processing (NLP). Conventional design methods are using bag-of-words model (BOW) alone based on Google database and other online corpus. For one thing, in the bag-of-words model, the vectors are Irrelevant to one another. Even though this method is friendly to discrete features, it is not conducive to the machine to understand continuous statements due to the loss of the connection between words in the encoded word vector. For other thing, existing methods are used to test in state-of-the-art online corpus but it is hard to apply in real applications such as telemarketing data. In this paper, we propose an improved chatbot design way using hybrid bag-of-words model and skip-gram model based on the real telemarketing data. Specifically, we first collect the real data in the telemarketing field and perform data cleaning and data classification on the constructed corpus. Second, the word representation is adopted hybrid bag-of-words model and skip-gram model. The skip-gram model maps synonyms in the vicinity of vector space. The correlation between words is expressed, so the amount of information contained in the word vector is increased, making up for the shortcomings caused by using bag-of-words model alone. Third, we use the term frequency-inverse document frequency (TF-IDF) weighting method to improve the weight of key words, then output the final word expression. At last, the answer is produced using hybrid retrieval model and generate model. The retrieval model can accurately answer questions in the field. The generate model can supplement the question of answering the open domain, in which the answer to the final reply is completed by long-short term memory (LSTM) training and prediction. Experimental results show which the hybrid word vector expression model can improve the accuracy of the response and the whole system can communicate with humans.

• Journal of IKEEE
• /
• v.24 no.2
• /
• pp.632-637
• /
• 2020

The non-intrusive load monitoring (NILM) is an important way to cost-effective real-time monitoring the energy consumption and time of use for each appliance in a home or business using aggregated energy from a single recording meter. In this paper, we collect from the smart farm's power consumption data acquisition system to the server via an LTE modem, converted the total power consumption, and the power of individual electric devices into HDF5 format and performed NILM analysis. We perform NILM analysis using open source denoising autoencoder (DAE), long short-term memory (LSTM), gated recurrent unit (GRU), and sequence-to-point (seq2point) learning methods.