• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.599-614
• /
• 2021

This paper proposes a digital signage system based on an intelligent recommendation model. The proposed system consists of a server and an edge. The server manages the data, learns the advertisement recommendation model, and uses the trained advertisement recommendation model to determine the advertisements to be promoted in real time. The advertisement recommendation model provides predictions for various products and probabilities. The purchase index between the product and weather data was extracted and reflected using correlation analysis to improve the accuracy of predicting the probability of purchasing a product. First, the user information and product information are input to a deep neural network as a vector through an embedding process. With this information, the product candidate group generation model reduces the product candidates that can be purchased by a certain user. The advertisement recommendation model uses a wide and deep recommendation model to derive the recommendation list by predicting the probability of purchase for the selected products. Finally, the most suitable advertisements are selected using the predicted probability of purchase for all the users within the advertisement range. The proposed system does not communicate with the server. Therefore, it determines the advertisements using a model trained at the edge. It can also be applied to digital signage that requires immediate response from several users.

• Journal of the Korean Society of Safety
• /
• v.36 no.1
• /
• pp.56-63
• /
• 2021

The narrative texts of industrial accident reports help to identify accident risk factors. They relate the accident triggers to the sequence of events and the outcomes of an accident. Particularly, a set of related keywords in the context of the narrative can represent how the accident proceeded. Previous studies on text analytics for structuring accident reports have been limited to extracting individual keywords without context. We proposed a context-based analysis using a Natural Language Processing (NLP) algorithm to remedy this shortcoming. This study aims to apply Word2Vec of the NLP algorithm to extract adjacent keywords, known as word embedding, conducted by the neural network algorithm based on supervised learning. During processing, Word2Vec is conducted by adjacent keywords in narrative texts as inputs to achieve its supervised learning; keyword weights emerge as the vectors representing the degree of neighboring among keywords. Similar keyword weights mean that the keywords are closely arranged within sentences in the narrative text. Consequently, a set of keywords that have similar weights presents similar accidents. We extracted ten accident processes containing related keywords and used them to understand the risk factors determining how an accident proceeds. This information helps identify how a checklist for an accident report should be structured.

• Journal of Korea Multimedia Society
• /
• v.24 no.6
• /
• pp.805-814
• /
• 2021

Push-ups are one of the body exercises that can be easily measured anytime, anywhere. As one of the most widely used techniques as a test tool for evaluating physical strength, they are broadly used in various fields, especially in fields that require physical ability to estimate, such as military, police, and firefighters. However, social distancing is currently being implemented, and the issue of fairness has been steadily raised due to subtle differences between measurement. Accordingly, in this paper, the correct posture for each individual was photographed and learned by a high-performance computer, and the result was derived by comparing it with the case of performing the incorrect posture of the individual. If method is introduced into the physical fitness evaluation through the proposed method, the individual takes the correct posture and learns the photographed photo, and measures the posture with several images taken during a given time. Through this, it is possible to measure more objectively because it measures with the merit that can be measured even in the present situation and with one's correct posture.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1690-1707
• /
• 2021

Precipitation prediction during flood season has been a key task of climate prediction for a long time. This type of prediction is linked with the national economy and people's livelihood, and is also one of the difficult problems in climatology. At present, there are some precipitation forecast models for the flood season, but there are also some deviations from these models, which makes it difficult to forecast accurately. In this paper, based on the measured precipitation data from the flood season from 1993 to 2019 and the precipitation return data of CWRF, ANN cycle modeling and a weighted integration method is used to correct the CWRF used in today's operational systems. The MAE and TCC of the precipitation forecast in the flood season are used to check the prediction performance of the proposed algorithm model. The results demonstrate a good correction effect for the proposed algorithm. In particular, the MAE error of the new algorithm is reduced by about 50%, while the time correlation TCC is improved by about 40%. Therefore, both the generalization of the correction results and the prediction performance are improved.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.79-87
• /
• 2021

In recent years research on automatic font generation with machine learning mainly focus on using transformation-based methods, in comparison, generative model-based methods of font generation have received less attention. Transformation-based methods learn a mapping of the transformations from an existing input to a target. This makes them ambiguous because in some cases a single input reference may correspond to multiple possible outputs. In this work, we focus on font generation using the generative model-based methods which learn the buildup of the characters from noise-to-image. We propose a novel way to train a conditional generative deep neural model so that we can achieve font style control on the generated font images. Our research demonstrates how to generate new font images conditioned on both character class labels and character style labels when using the generative model-based methods. We achieve this by introducing a modified generator network which is given inputs noise, character class, and style, which help us to calculate losses separately for the character class labels and character style labels. We show that adding the character style vector on top of the character class vector separately gives the model rich information about the font and enables us to explicitly specify not only the character class but also the character style that we want the model to generate.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.3
• /
• pp.717-729
• /
• 2021

This paper examines the efficacy of the default risk factor in an emerging market context using the Fama-French five-factor model. Our aim is to test whether the Fama-French five-factor model augmented with a default risk factor improves the predictability of returns of portfolios sorted on the firm's characteristics as well as on industry. The default risk factor is constructed by estimating the probability of default using a hybrid version of dynamic panel probit and artificial neural network (ANN) to proxy default risk. This study also provides evidence on the temporal stability of risk premiums obtained using the Fama-MacBeth approach. Using a sample of 3,806 firm-year observations on non-financial listed companies of Pakistan over 2006-2015 we found that the augmented model performed better when tested across size-investment-default sorted portfolios. The investment factor contains some default-related information, but default risk is independently priced and bears a significantly positive risk premium. The risk premiums are also found temporally stable over the full sample and more recent sample period 2010-2015 as evidence by the Fama-MacBeth regressions. The finding suggests that the default risk factor is not a useless factor and due to mispricing, default risk anomaly prevails in the Pakistani equity market.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.1
• /
• pp.54-60
• /
• 2021

AR (Augmented Reality) is a technology that provides virtual content to the real world and provides additional information to objects in real-time through 3D content. In the past, a high-performance device was required to experience AR, but it was possible to implement AR more easily by improving mobile performance and mounting various sensors such as ToF (Time-of-Flight). Also, the importance of mobile augmented reality is growing with the commercialization of high-speed wireless Internet such as 5G. Thus, this paper proposes a system that can provide AR services via GNN (Graph Neural Network) using cameras and sensors on mobile devices. ToF of mobile devices is used to capture depth maps. A 3D point cloud was created using RGB images to distinguish specific colors of objects. Point clouds created with RGB images and Depth Map perform downsampling for smooth communication between mobile and server. Point clouds sent to the server are used for 3D object detection. The detection process determines the class of objects and uses one point in the 3D bounding box as an anchor point. AR contents are provided through app and web through class and anchor of the detected object.

• Journal of Positioning, Navigation, and Timing
• /
• v.10 no.1
• /
• pp.55-66
• /
• 2021

In this paper, we propose a signal propagation modeling technique for generating a positioning fingerprint DB based on Long Term Evolution (LTE) signals. When a DB is created based on the location-based signal information collected in an urban area, gaps in the DB due to uncollected areas occur. The spatial interpolation method for filling the gaps has limitations. In addition, the existing gap filling technique through signal propagation modeling does not reflect the signal attenuation characteristics according to directions occurring in urban areas by considering only the signal attenuation characteristics according to distance. To solve this problem, this paper proposes a Deep Neural Network (DNN)-based signal propagation functionalization technique that considers distance and direction together. To verify the performance of this technique, an experiment was conducted in Seocho-gu, Seoul. Based on the acquired signals, signal propagation characteristics were modeled for each method, and Root Mean Squared Errors (RMSE) was calculated using the verification data to perform comparative analysis. As a result, it was shown that the proposed technique is improved by about 4.284 dBm compared to the existing signal propagation model. Through this, it can be confirmed that the DNN-based signal propagation model proposed in this paper is excellent in performance, and it is expected that the positioning performance will be improved based on the fingerprint DB generated through it.

• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.3-13
• /
• 2021

We propose a moire artifacts removal algorithm for screen-shot images using multiple domain learning. First, we estimate clean preliminary images by exploiting complementary information of the moire artifacts in pixel value and frequency domains. Next, we estimate a clean edge map of the input moire image by developing a clean edge predictor. Then, we refine the pixel and frequency domain outputs to further improve the quality of the results using the estimated edge map as the guide information. Finally, the proposed algorithm obtains the final result by merging the two refined results. Experimental results on a public dataset demonstrate that the proposed algorithm outperforms conventional algorithms in quantitative and qualitative comparison.

• Journal of Korea Multimedia Society
• /
• v.24 no.2
• /
• pp.274-284
• /
• 2021

Customized services to a sleep induction for better sleepcare are more effective because of different satisfaction levels to users. The EOG data measured at the frontal lobe when a person blinks his eyes can be used as biometric data because it has different values for each person. The accuracy of measurement is degraded by a noise source, such as toss and turn. Therefore, it is necessary to analyze the noisy data and remove them from normal EOG by filtering. There are low-pass filtering and high-pass filtering as filtering using a frequency band. However, since filtering within a frequency band range is also required for more effective performance, we propose a machine learning model for the filtering of EOG data in this paper as the second filtering method. In addition, optimal values of parameters such as the depth of the hidden layer, the number of nodes of the hidden layer, the activation function, and the dropout were found through experiments, to improve the performance of the machine learning filtering model, and the filtering performance of 95.7% was obtained. Eventually, it is expected that it can be used for effective user identification services by using filtering model for EOG data.