• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.91-98
• /
• 2022

In this study, Pukyong National University's floating population survey and analysis were conducted using Raspberry Pie, an open source hardware, and object detection algorithms based on deep learning technology. After collecting images using Raspberry Pie, the person detection of the collected images using YOLO3's IMAGEAI and YOLOv5 models was performed, and Haar-like features and HOG models were used for accuracy comparison analysis. As a result of the analysis, the smallest floating population was observed due to the school anniversary. In general, the floating population at the entrance was larger than the floating population at the exit, and both the entrance and exit were found to be greatly affected by the school's anniversary and events.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.2
• /
• pp.181-186
• /
• 2022

Poisson-Boltzmann equation (PBE) is used to model problems arising from various disciplinary including bio-pysics and colloid chemistry. Therefore, to predict a numerical solution of PBE is an important issue. The authors proposed deep learning based methods to solve PBE while the computational time to generate finite element method (FEM) solutions were bottlenecks of the algorithms. In this work, we shorten the generation time of FEM solutions in two directions. First, we experimentally find certain penalty parameter in a bilinear form. Second, we applied algebraic multigrids methods to the algebraic system so that condition number is bounded regardless of the meshsize. In conclusion, we have reduced computation times to solve algebraic systems for PBE. We expect that algebraic multigrids methods can be further employed in various disciplinary to generate deep learning samples.

• Journal of Software Assessment and Valuation
• /
• v.17 no.2
• /
• pp.143-150
• /
• 2021

There is a need for an artificial intelligent technology that can reduce various types of safety accidents by analyzing the risk factors that cause safety accidents in industrial site. In this paper, user safety profiling methods are proposed that can prevent safety accidents in advance by specifying and modeling user information data related to safety accidents. User information data is classified into normal and abnormal conditions through deep learning based artificial intelligence analysis. As a result of verifying user safety profiling technology using more than 10 types of industrial field data, 93.6% of user safety profiling accuracy was obtained.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.374-376
• /
• 2021

For the diagnosis of cancer-related diseases in clinical practice, pathological examination using biopsy is essential after basic diagnosis using imaging equipment. In order to proceed with such a biopsy, the assistance of an oncologist, clinical pathologist, etc. with specialized knowledge and the minimum required time are essential for confirmation. In recent years, research related to the establishment of a system capable of automatic classification of cancer cells using artificial intelligence is being actively conducted. However, previous studies show limitations in the type and accuracy of cells based on a limited algorithm. In this study, we propose a method to identify a total of 4 cancer cells through a convolutional neural network, a kind of deep learning. The optical images obtained through cell culture were learned through EfficientNet after performing pre-processing such as identification of the location of cells and image segmentation using OpenCV. The model used various hyper parameters based on EfficientNet, and trained InceptionV3 to compare and analyze the performance. As a result, cells were classified with a high accuracy of 96.8%, and this analysis method is expected to be helpful in confirming cancer.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.463-465
• /
• 2021

Currently, the inspection method printed on food packages and boxes is to sample only a few products and inspect them with human eyes. Such a sampling inspection has the limitation that only a small number of products can be inspected. Therefore, accurate inspection using a camera is required. This paper proposes a deep learning object recognition technology model, which is an artificial intelligence technology, as a method for detecting the defects of expiration date printed on the product packaging. Using the Faster R-CNN (region convolution neural network) model, the color images, converted gray images, and converted binary images of the printed expiration date are trained and then tested, and each detection rates are compared. The detection performance of expiration date printed on the package by the proposed method showed the same detection performance as that of conventional vision-based inspection system.

• Journal of Multimedia Information System
• /
• v.7 no.1
• /
• pp.41-44
• /
• 2020

In autonomous driving, object recognition based on machine learning is one of the core software technologies. In particular, the object recognition using deep learning becomes an essential element for autonomous driving software to operate. In this paper, we introduce a drivable area detection method based on Region-based CNN model to support autonomous driving. To effectively detect the drivable area, we used the BDD dataset for model training and demonstrated its effectiveness. As a result, our R-CNN model using BDD datasets showed interesting results in training and testing for detection of drivable areas.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.2
• /
• pp.50-58
• /
• 2019

The clear and specific objective of this study is to design a false news discriminator algorithm for news articles transmitted on a text-based basis and an architecture that builds it into a system (H/W configuration with Hadoop-based in-memory technology, Deep Learning S/W design for bigdata and SNS linkage). Based on learning data on actual news, the government will submit advanced "fake news" test data as a result and complete theoretical research based on it. The need for research proposed by this study is social cost paid by rumors (including malicious comments) and rumors (written false news) due to the flood of fake news, false reports, rumors and stabbings, among other social challenges. In addition, fake news can distort normal communication channels, undermine human mutual trust, and reduce social capital at the same time. The final purpose of the study is to upgrade the study to a topic that is difficult to distinguish between false and exaggerated, fake and hypocrisy, sincere and false, fraud and error, truth and false.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.49 no.1
• /
• pp.85-94
• /
• 2022

This retrospective study aimed to evaluate the difference in measurement between conventional orthodontic analysis and artificial intelligence orthodontic analysis in pediatric and adolescent patients aged 7 - 15 with the mixed and permanent dentition. A total of 60 pediatric and adolescent patients (30 mixed dentition, 30 permanent dentition) who underwent lateral cephalometric radiograph for orthodontic diagnosis were randomly selected. Seventeen cephalometric landmarks were identified, and 22 measurements were calculated by 1 examiner, using both conventional analysis method and deep learning-based analysis method. Errors due to repeated measurements were assessed by Pearson's correlation coefficient. For the mixed dentition group and the permanent dentition group, respectively, a paired t-test was used to evaluate the difference between the 2 methods. The difference between the 2 methods for 8 measurements were statistically significant in mixed dentition group: APDI, SNA, SNB, Mandibular plane angle, LAFH (p < 0.001), Facial ratio (p = 0.001), U1 to SN (p = 0.012), and U1 to A-Pg (p = 0.021). In the permanent dentition group, 4 measurements showed a statistically significant difference between the 2 methods: ODI (p = 0.020), Wits appraisal (p = 0.025), Facial ratio (p = 0.026), and U1 to A-Pg (p = 0.001). Compared with the time-consuming conventional orthodontic analysis, the deep learning-based cephalometric system can be clinically acceptable in terms of reliability and validity. However, it is essential to understand the limitations of the deep learning-based programs for orthodontic analysis of pediatric and adolescent patients and use these programs with the proper assessment.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.640-645
• /
• 2021

The deep learning based end-to-end TTS system consists of Text2Mel module that generates spectrogram from text, and vocoder module that synthesizes speech signals from spectrogram. Recently, by applying deep learning technology to the TTS system the intelligibility and naturalness of the synthesized speech is as improved as human vocalization. However, it has the disadvantage that the inference speed for synthesizing speech is very slow compared to the conventional method. The inference speed can be improved by applying the non-autoregressive method which can generate speech samples in parallel independent of previously generated samples. In this paper, we introduce FastSpeech, FastSpeech 2, and FastPitch as Text2Mel technology, and Parallel WaveGAN, Multi-band MelGAN, and WaveGlow as vocoder technology applying non-autoregressive method. And we implement them to verify whether it can be processed in real time. Experimental results show that by the obtained RTF all the presented methods are sufficiently capable of real-time processing. And it can be seen that the size of the learned model is about tens to hundreds of megabytes except WaveGlow, and it can be applied to the embedded environment where the memory is limited.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.2
• /
• pp.93-98
• /
• 2016

For accurate precipitation forecasts the choice of weather factors and prediction method is very important. Recently, machine learning has been widely used for forecasting precipitation, and artificial neural network, one of machine learning techniques, showed good performance. In this paper, we suggest a new method for forecasting precipitation using DBN, one of deep learning techniques. DBN has an advantage that initial weights are set by unsupervised learning, so this compensates for the defects of artificial neural networks. We used past precipitation, temperature, and the parameters of the sun and moon's motion as features for forecasting precipitation. The dataset consists of observation data which had been measured for 40 years from AWS in Seoul. Experiments were based on 8-fold cross validation. As a result of estimation, we got probabilities of test dataset, so threshold was used for the decision of precipitation. CSI and Bias were used for indicating the precision of precipitation. Our experimental results showed that DBN performed better than MLP.