Journal of Computational and Theoretical Nanoscience最新文献

{"title":"Interactive Webtoon System Using VR 360 Cam and Face Detection","authors":"Hyeongjin Kim, Sunjin Yu","doi":"10.1166/jctn.2021.9608","DOIUrl":"https://doi.org/10.1166/jctn.2021.9608","url":null,"abstract":"VR 360 Cam is an emerging device. By combining this with the rising webtoon industry, we want to show people an immersive webtoon. Based on the python language, face detection was performed from images received in real time from VR 360 Cam through dlib, a machine learning library that\u0000 supports python. The VR 360 Cam performs trekking on the detected face to receive each detected position value, and is converted into a natural face through rectification to be shown to the audience. The exhibition, which performed face detection from the VR 360 Cam, and showed the image of\u0000 the person’s face mapped to the audience, drew meaningful results. Unlike cameras such as webcams, VR 360 Cam has a wider viewing angle, allowing more people to interact. Existing webcams can only interact with one person at a time because it is impossible to interact with more people\u0000 due to a narrow angle when one person enters. On the other hand, interaction with multiple people is possible through VR 360 Cam. Various exhibitions were possible.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41371872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Short Term Power Load Forecasting Based on Deep Neural Networks","authors":"Geum-Seong Lee, Gwang-Hyun Kim","doi":"10.1166/jctn.2021.9622","DOIUrl":"https://doi.org/10.1166/jctn.2021.9622","url":null,"abstract":"The purpose of this study is to find the most appropriate forecasting method by applying the machine learning and deep learning techniques that have recently been representing an outstanding performance in various fields to power load forecasting and evaluating their performance. Forecasting\u0000 model has been realized by using logistic regression, decision tree, support vector machine (SVM) algorithm as the machine learning technique, and deep neural network (DNN) algorithm as deep learning technique and compared with each other. In order to find the most appropriate method for power\u0000 load forecasting, the performance of machine learning and deep learning model was compared and evaluated. Performance was evaluated by realizing total 7 forecasting models including 3 machine learning-based single forecasting models, 1 deep learning-based single forecasting model, and 3 complex\u0000 forecasting models. As for complex forecasting model, forecasting rate turned out to be 96.91% for logistic regression-based complex forecasting model, 97.08% for decision tree-based complex forecasting model, and 96.43% for support vector machine-based forecasting model that the complex forecasting\u0000 model combined with decision tree and deep neural network represented the most outstanding performance. With this study, it is anticipated to precisely forecast power load saving the electronic energy while preparing for a plan to efficiently distribute and utilize energy in connection with\u0000 smart grid technology such as Energy Storage System (ESS) or Energy Management System (EMS).","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44638823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Stock Price Prediction by Using BLSTM (Bidirectional Long Short Term Memory)","authors":"Sunghyuck Hong, Jungsoo Han","doi":"10.1166/jctn.2021.9603","DOIUrl":"https://doi.org/10.1166/jctn.2021.9603","url":null,"abstract":"Currently, many researchers are working on stock price prediction system by using deep learning algorithms. Stock market is completely random, and there is no pattern. Even though, a pattern in stock market could be found, it will not be last for a long time because the stock market\u0000 will adopt a new situation and the strategy is no longer available on already changed stock market. There are many auto trading programs such as a trading bot on stock market. However, they are literally trade stocks based on human’s direction or rules. It will not affect any changes,\u0000 and it keeps working as what rules are set up from the initial status on the stock market. Stock price depends on volume of total sales, stock news, revenue, total asset, big buyer’s position and so on. There are many aspects for affecting stock price, and it changes all the time. Therefore,\u0000 it keeps monitoring stock market and makes a decision whether buy or sell at the right time for earning profits. This research uses Bidirectional Long Short-Term Memory (BLSTM) to predict stock price in the near future. BLSTM is more accurate than LSTM which is one directional. In addition,\u0000 stock market is like a living creature. Data to manipulate stock price must be inputted and analyzed consistently. Therefore, stock price can be predicted by consistent monitoring with BLSTM.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46465158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Environmental Factor-Based Segmentation of Images in Natural Environments","authors":"Seok-Woo Jang","doi":"10.1166/jctn.2021.9583","DOIUrl":"https://doi.org/10.1166/jctn.2021.9583","url":null,"abstract":"The robust segmentation of color images in a natural environment without specific constraints such as lighting or background is very important in the field of image processing and computer vision. In this paper, an environmentally adaptive image segmentation method using color invariant\u0000 is proposed. The proposed method introduces a number of color invariant, such as W, C, U, N, and H, and automatically detects factors in the surrounding environment in which images such as lighting, shading, and highlights are taken. The image is then effectively split based on the edge by\u0000 selecting the color invariant optimal for the detected environmental factors. In the experiment, we implemented the proposed edge-based image segmentation algorithm. Various image data taken in general environments without specific constraints were utilized as input images of the suggested\u0000 system. In this study, various kinds of color images taken in different environments were tested, and each color invariant was extracted from the experiments that best expressed the environmental changes around them. As a result, a largest number of images were determined to have a change\u0000 in the intensity of lighting, followed by highlights and shadows. In addition, there were a few images that determined that no special state environmental changes existed. As the results of the experiment show visually, the existing method did not correctly remove shadows and did not detect\u0000 some areas of the circular shape. In addition, the existing method can also be found to be partially inaccurate in edge detection in many areas. On the other hand, the proposed method confirmed stable segmentation of images. The proposed color invariant-based image segmentation algorithm is\u0000 expected to be useful in various pattern recognition areas such as face tracking, mobile object detection, gesture recognition, motion understanding, etc.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42114269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a Digilog Learning Model for Training on the Principles of Artificial Intelligence Learning in Elementary Education","authors":"Yu-Hyun Hwang, Namje Park","doi":"10.1166/jctn.2021.9625","DOIUrl":"https://doi.org/10.1166/jctn.2021.9625","url":null,"abstract":"The importance of nurturing human resources who will lead the 4th Industrial Revolution is increasing, and artificial intelligence is a core factor of innovative technologies. Therefore, developing various and interesting teaching methods for principles of artificial intelligence is\u0000 necessary. This article suggests teaching principles of artificial intelligence by convergence of digital and analogue, called digilog. Students get to know how machines can learn and operate, which is digital, with paper worksheets and several physical teaching aids, which are analogue. In\u0000 digilog way, students figure out the principles of image recognition. There are two methods, MAX and filtration box. The principles of artificial intelligence are too abstract to understand for elementary learners who are yet at concrete operational period, according to Piaget. Therefore,\u0000 the convergence of digital and analogue is effective for teaching and learning about artificial intelligence in elementary education. Elementary learners examine colorful virtual images in their worksheet and use their hands and pencils to trace artificial intelligence’s work. They end\u0000 up with figuring out how artificial intelligence compresses inserted images into smaller reference images step by step. With the offered method and developing more diverse digilog elements, elementary learners’ knowledge and experiences necessary for the future society will be increased.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48469850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Implementation of Photoplethysmography Measurement System Based on Convolution Neural Network for Personalized Exercise Intensity","authors":"Ji-Su Lee, Ji-Yun Seo, Yun-Hong Noh, Do-Un Jeong","doi":"10.1166/jctn.2021.9591","DOIUrl":"https://doi.org/10.1166/jctn.2021.9591","url":null,"abstract":"With increasing interest in health, many people are exercising to lose weight, prevent disease, and improve cardiorespiratory function. For effective exercise, users should proceed with appropriate intensity depending on their physical strength. The system implemented in this paper\u0000 classifies exercise intensity according to PPG signal using CNN training model for objective exercise intensity classification. The PPG signal was measured after exercise through the PPG sensor, and the training data set was constructed that based on the interval between P-peaks. The\u0000 training data set is trained on the CNN model to classify the three exercise intensity according to the PPG signal. In order to analyze the accuracy of the implemented CNN training model, the performance evaluation of the classification evaluation metrics and the exercise intensity classification\u0000 monitoring system was performed. First, the performance evaluation of the CNN model for classifying exercise intensity was conducted. In the performance evaluation, the classification evaluation metrics was calculated according to the training result, the recall rate representing the percentage\u0000 of successful prediction among the actual correct answers, the precision representing the actual correct answer rate among the predicted data, and the F 1 score representing the harmonic average of recall and precision were confirmed. As a result of CNN training model classification\u0000 evaluation metrics, it was the accuracy was 99.3%, the recall rate was 99.9%, the precision was 99.8%, and the F 1 score was 99.4%. Second, to evaluate the performance of the exercise intensity classification monitoring system, jump rope experiment was conducted with 5 subjects. The\u0000 experiment measured PPG at the end of each set after low, moderate, and high intensity jump rope. The classification accuracy was analyzed by entering the measured PPG data into the CNN model 50 times each. As a result of the experiment, the accuracy of low intensity was 98%, moderate intensity\u0000 was 93.6%, and high intensity was 97.6%, confirming a total accuracy of 96.4%. Some errors are thought to have occurred due to the fact that the data located at the boundary line between the exercise intensity was classified incorrectly. In future studies, we would like to conduct a study\u0000 of exercise intensity monitoring system that can be applied to various exercises by measuring acceleration signals for each exercise together.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46966799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dimming Level Improvement Method Through Simple Mapping Error Correction Code in Visible Light Communication","authors":"Doohee Han, Kyujin Lee","doi":"10.1166/jctn.2021.9610","DOIUrl":"https://doi.org/10.1166/jctn.2021.9610","url":null,"abstract":"Since the visible light communication (VLC) has to perform the functions of communication and illumination at the same time, a method for communication as well as lighting is needed. In this paper, when text data is transmitted through visible light communication, the level of illumination\u0000 dimming according to the frequency of occurrence of alphabets in sentences is analyzed, and a method of improving the dimming level and Bit Error Rate (BER) performance through error correction codes generated during data transmission is studied. Visible light communication systems must perform\u0000 both communication and lighting functions, so not only communication but also a method for the lighting role is needed. When transferring data (transfer text), the frequency of occurrence of alphabets in sentences is different. Depending on the frequency of occurrence of these alphabetic characters,\u0000 if there are many ‘0’s in the code to be transmitted, the dimming level will be lowered and flicker will occur. Also, when a 1-bit error occurs, the alphabet code itself is changed. To solve this problem, an error correction code using parity bits has been added. Through this,\u0000 it was confirmed that the overall dimming level and Bit Error Rate (BER) performance were improved. Also, in visible light communication, the function of lighting is closely related to the performance of the overall system. As we have seen above, when there is a continuous zero period, the\u0000 function of the lighting is severely degraded. This reduces the performance of the entire system, not just the lighting. Therefore, the dimming level and BER performance were improved by improving the performance through the algorithm and error correction code to improve the overall dimming\u0000 level.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48329719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Single Image Super Resolution Using Multiple Re-Evaluation Process","authors":"Hyun-Ho Han, Sang Hun Lee","doi":"10.1166/jctn.2021.9607","DOIUrl":"https://doi.org/10.1166/jctn.2021.9607","url":null,"abstract":"In this paper, we proposed improved single image super resolution using multiple re-evaluation Process model for use in various image processing fields. The proposed method generates the first super resolution using the input image, and analyzes the change for each region by comparing\u0000 the features of previous image and super resolution result. According to the analyzed features, the feature map for generate n-th super resolution was selected for improved detail. After then, next generate super resolution using previous super resolution result as input image. This\u0000 process is repeated for final result. The existing single image super resolution method has two areas to be improved. First, it minimizes artifacts or staircases, which are unnecessary details that can be created during the super resolution process. Second, it is necessary to consider the\u0000 input image because it affects the result depending on the quality of input image used in the super resolution process. Therefore, in order to minimize unnecessary details, the proposed method analyzed the feature map from the generated super resolution result and applied it according to the\u0000 amount of change. In addition, aimed to gradually improve the input image to be used in the super resolution process by using the super resolution generated in the previous step. By comparing and evaluating the proposed method with the conventional single image super resolution method with\u0000 PSNR and SSIM, it is improved by about 3%.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46040222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Proposal of Classified Music Recommendation Model Based on Social Media","authors":"Kyoung-Rock Chung, Koo-Rack Park, Young-Suk Chung","doi":"10.1166/jctn.2021.9576","DOIUrl":"https://doi.org/10.1166/jctn.2021.9576","url":null,"abstract":"With the spread of smartphones, it has become common to always listen to music like background music, so it is necessary to create a music database that meets individual needs. By creating a music database using data from social media, music is classified in a different way from collaborative\u0000 filtering, which is mainly used by existing music source providing platforms. Various other hashtags attached to posts with music titles used as hashtags are collected using web crawling, and music is classified based on the collected hashtags to reflect actual listeners’ opinions on\u0000 music. It uses crawling to find posts on social media with music titles tagged as hashtags, then collects other hashtags attached to those posts. Hashtags collected by performing the same task with multiple music titles are collected, analyzed, and statistics are then classified to determine\u0000 when and where the music fits. On social media, the feelings of the person who posted the post and the conditions such as the time zone, place, weather, and situation where the post was posted are reflected as hashtags. By analyzing the hashtags attached to the music title, it is possible\u0000 to build a social media-based music database in which the opinions of various people are reflected as collective intelligence. It is possible to derive different results from existing collaborative filtering based on the past listening records of users of the platform used by most of the sound\u0000 source providing platforms. Even if music titles are not written in complete form on social media hashtags, we plan to research them so that they can be used to build a database.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45221941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computer-Vision-Based Advanced Optical Music Recognition System","authors":"Minhoon Lee, Ho-Kyoung Kim, Mikyeong Moon, Seung-Min Park","doi":"10.1166/jctn.2021.9626","DOIUrl":"https://doi.org/10.1166/jctn.2021.9626","url":null,"abstract":"Computer vision is an artificial intelligence technology that studies techniques for extracting information from images. Several studies have been performed to identify and edit music scores using computer vision. This study proposes a system to identify musical notes and print arranged\u0000 music. Music is produced by general rules; consequently, the components of music have specific patterns. There are four approaches in pattern recognition that can be used classify images using patterns. Our proposed method of identifying music sheets is as follows. Several pretreatment processes\u0000 (image binary, noise and staff elimination, image resizing) are performed to aid the identification. The components of the music sheet are identified by statistical pattern recognition. Applying an artificial intelligence model (Markov chain) to extracted music data aids in arranging the data.\u0000 From applying the pattern recognition technique, a recognition rate of 100% was shown for music sheets of low complexity. The components included in the recognition rate are signs, notes, and beats. However, there was a low recognition rate for some music sheet and can be addressed by adding\u0000 a classification to the navigation process. To increase the recognition rate of the music sheet with intermediate complexity, it is necessary to refine the pre-processing process and pattern recognition algorithm. We will also apply neural network-based models to the arrangement process.","PeriodicalId":15416,"journal":{"name":"Journal of Computational and Theoretical Nanoscience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48127876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}