• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.242-248
• /
• 2019

Fire flame and smoke detection algorithm studies are challenging task in computer vision due to the variety of shapes, rapid spread and colors. The performance of a typical sensor based fire detection system is largely limited by environmental factors (indoor and fire locations). To solve this problem, a deep learning method is applied. Because it extracts the feature of the object using several methods, so that if a similar shape exists in the frame, it can be detected as false postive. This study proposes a new algorithm to reduce false positives by using frame similarity before using deep learning to decrease the false detection rate. Experimental results show that the fire detection performance is maintained and the false positives are reduced by applying the proposed method. It is confirmed that the proposed method has excellent false detection performance.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.29-35
• /
• 2019

As the fourth industrial revolution is emerging, many companies are increasingly interested in smart factories and the importance of sensors is being emphasized. In the case that sensors for collecting sensing data fail, the plant could not be optimized and further it could not be operated properly, which may incur a financial loss. For this purpose, it is necessary to diagnose the status of sensors to prevent sensor' fault. In the paper, we propose a scheme to diagnose digital-sensor' fault by analyzing the rising time and falling time of digital sensors through the LSTM(Long Short Term Memory) of Deep Learning RNN algorithm. Experimental results of the proposed scheme are compared with those of rule-based fault diagnosis algorithm in terms of AUC(Area Under the Curve) of accuracy and ROC(Receiver Operating Characteristic) curve. Experimental results show that the proposed system has better and more stable performance than the rule-based fault diagnosis algorithm.

• Journal of Convergence for Information Technology
• /
• v.11 no.1
• /
• pp.28-33
• /
• 2021

Since the stock price is a measure of the future value of the company, when analyzing the stock price, the company's growth potential, such as sales and profits, is considered and invested in stocks. In order to set the criteria for selecting stocks, institutional investors look at current industry trends and macroeconomic indicators, first select relevant fields that can grow, then select related companies, analyze them, set a target price, then buy, and sell when the target price is reached. Stock trading is carried out in the same way. However, general individual investors do not have any knowledge of investment, and invest in items recommended by experts or acquaintances without analysis of financial statements or growth potential of the company, which is lower in terms of return than institutional investors and foreign investors. Therefore, in this study, we propose a research method to select undervalued stocks by analyzing ROE, an indicator that considers the growth potential of a company, such as sales and profits, and predict the stock price flow of the selected stock through deep learning algorithms. This study is conducted to help with investment.

• Journal of the Korea Convergence Society
• /
• v.12 no.3
• /
• pp.17-25
• /
• 2021

When a person wears clothing, it is important to configure an outfit appropriate to the intended occasion. Therefore, T.P.O(Time, Place, Occasion) of the outfit is considered in various fashion recommendation systems based on artificial intelligence. However, there are few studies that directly infer the T.P.O from outfit images, as the nature of the problem causes multi-label and class imbalance problems, which makes model training challenging. Therefore, in this study, we propose a model that can infer the T.P.O of outfit images by employing a label-distribution-aware margin(LDAM) loss function. Datasets for the model training and evaluation were collected from fashion shopping malls. As a result of measuring performance, it was confirmed that the proposed model showed balanced performance in all T.P.O classes compared to baselines.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.3
• /
• pp.59-73
• /
• 2021

There are many lives lost due traffic accidents, and which have not decreased despite advances in technology. In order to prevent traffic accidents, it is necessary to accurately forecast how they will change in the future. Until now, traffic accident-frequency forecasting has not been a major research field, but has been analyzed microscopically by traditional methods, mainly based on statistics over a previous period of time. Despite the recent introduction of AI to the traffic accident field, the focus is mainly on forecasting traffic flow. This study converts into time series data the records from 1,339,587 traffic accidents that occurred in Korea from 2014 to 2019, and uses the AI algorithm to forecast the frequency of traffic accidents based on driver's age and time of day. In addition, the forecast values and the actual values were compared and verified based on changes in the traffic environment due to COVID-19. In the future, these research results are expected to lead to improvements in policies that prevent traffic accidents.

• Journal of Digital Convergence
• /
• v.19 no.7
• /
• pp.199-208
• /
• 2021

Automatic Post Editing(APE) is the study that automatically correcting errors included in the machine translated sentences. The goal of APE task is to generate error correcting models that improve translation quality, regardless of the translation system. For training these models, source sentence, machine translation, and post edit, which is manually edited by human translator, are utilized. Especially in the recent APE research, multilingual pretrained language models are being adopted, prior to the training by APE data. This study deals with multilingual pretrained language models adopted to the latest APE researches, and the specific application method for each APE study. Furthermore, based on the current research trend, we propose future research directions utilizing translation model or mBART model.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.1067-1078
• /
• 2020

With the development of internet technology, a lot of content is produced, and the demand for it is increasing. Accordingly, the number of contents in circulation is increasing, while the number of distributing illegal copies that infringe on copyright is also increasing. The Korea Copyright Protection Agency operates a illegal content obstruction program based on substring matching, and it is difficult to accurately search because a large number of noises are inserted to bypass this. Recently, researches using natural language processing and AI deep learning technologies to remove noise and various blockchain technologies for copyright protection are being studied, but there are limitations. In this paper, noise is removed from data collected online, and keyword-based illegal copies are searched. In addition, the same heavy uploader is estimated through profiling analysis for heavy uploaders. In the future, it is expected that copyright damage will be minimized if the illegal copy search technology and blocking and response technology are combined based on the results of profiling analysis for heavy uploaders.

• Journal of the Korea Convergence Society
• /
• v.12 no.2
• /
• pp.21-28
• /
• 2021

In this study, we propose a deep learning-based NILM technique using actual measured power data for 5 kinds of home appliances and verify its effectiveness. For about 3 weeks, the active power of the central power measuring device and five kinds of home appliances (refrigerator, induction, TV, washing machine, air cleaner) was individually measured. The preprocessing method of the measured data was introduced, and characteristics of each household appliance were analyzed through spectogram analysis. The characteristics of each household appliance are organized into a learning data set. All the power data measured by the central power measuring device and 5 kinds of home appliances were time-series mapping, and training was performed using a LSTM neural network, which is excellent for time series data prediction. An algorithm that can disaggregate five types of energies using only the power data of the main central power measuring device is proposed.

• Journal of the Korea Convergence Society
• /
• v.12 no.8
• /
• pp.317-325
• /
• 2021

By analyzing the recognition analysis and motivation method of the determinants, this study investigates the future development direction of health exercise biodata analysis face-to-face practice education content. The participants were 40 millennial and zoomers (MZ) generation college graduates. Factors related to the decision to participate in face-to-face practice classes in the field of health exercise biodata and bio-digital content convergence technology in the era of COVID-19 were measured. Of the participants, 67.5% voluntarily decided to participate in small group classes while observing social distancing rules. This study presented the most effective and learning motive methods to participate in face-to-face training. Health exercise biodata needs improvement in terms of integrating with adjacent disciplines such as big data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.24-29
• /
• 2022

Semantic role labeling task used in various natural language processing fields, such as information extraction and question answering systems, is the task of identifying the arugments for a given sentence and predicate. Predicate used as semantic role labeling input are extracted using lexical analysis results such as POS-tagging, but the problem is that predicate can't extract all linguistic patterns because predicate in korean language has various patterns, depending on the meaning of sentence. In this paper, we propose a korean predicate recognition method using neural network model with pre-trained embedding models and lexical features. The experiments compare the performance on the hyper parameters of models and with or without the use of embedding models and lexical features. As a result, we confirm that the performance of the proposed neural network model was 92.63%.