• Journal of IKEEE
• /
• v.21 no.2
• /
• pp.136-141
• /
• 2017

In this paper, we propose an algorithm for memory optimization to apply deep learning to PC. The proposed algorithm minimizes the memory and computation processing time by reducing the amount of computation processing and data required in the conventional deep learning structure in a general PC. The algorithm proposed in this paper consists of three steps: a convolution layer configuration process using a random filter with discriminating power, a data reduction process using PCA, and a CNN structure creation using SVM. The learning process is not necessary in the convolution layer construction process using the discriminating random filter, thereby shortening the learning time of the overall deep learning. PCA reduces the amount of memory and computation throughput. The creation of the CNN structure using SVM maximizes the effect of reducing the amount of memory and computational throughput required. In order to evaluate the performance of the proposed algorithm, we experimented with Yale University's Extended Yale B face database. The results show that the algorithm proposed in this paper has a similar performance recognition rate compared with the existing CNN algorithm. And it was confirmed to be excellent. Based on the algorithm proposed in this paper, it is expected that a deep learning algorithm with many data and computation processes can be implemented in a general PC.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.4
• /
• pp.319-326
• /
• 2015

Recently in the fields o f stochastic optimal control ( SOC) and reinforcemnet l earning (RL), there have been a great deal of research efforts for the problem of finding data-based sub-optimal control policies. The conventional theory for finding optimal controllers via the value-function-based dynamic programming was established for solving the stochastic optimal control problems with solid theoretical background. However, they can be successfully applied only to extremely simple cases. Hence, the data-based modern approach, which tries to find sub-optimal solutions utilizing relevant data such as the state-transition and reward signals instead of rigorous mathematical analyses, is particularly attractive to practical applications. In this paper, we consider a couple of methods combining the modern SOC strategies and approximate inference together with machine-learning-based data treatment methods. Also, we apply the resultant methods to a variety of application domains including financial engineering, and observe their performance.

• Journal of Service Research and Studies
• /
• v.3 no.2
• /
• pp.53-60
• /
• 2013

Datamining from the large data in the form of various techniques for obtaining information have been developed. In recent years one of the most sought areas of pattern recognition and machine learning method is created with most of existing learning algorithms based on categorical attributes to a rule or decision model. However, the real-world data, it may consist of numeric attributes in many cases. In addition it contains attributes with numerical values to the normal categorical attribute. In this case, therefore, it is required processes in order to use the data to learn an appropriate value for the type attribute. In this paper, the domain of the numeric attributes are divided into several segments using learning algorithm techniques of discritization. It is described Clustering with other data mining techniques. Large amount of first cluster with characteristics is similar records from the database into smaller groups that split multiple given finite patterns in the pattern space. It is close to each other of a set of patterns that together make up a bunch. Among the set without specifying a particular category in a given data by extracting a pattern. It will be described similar grouping of data clustering technique to classify the data.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.1
• /
• pp.23-33
• /
• 2020

Recently, high-resolution images can be easily acquired using UAV (Unmanned Aerial Vehicle), so that it is possible to produce small area observation and spatial information at low cost. In particular, research on the generation of cover maps in crop production areas is being actively conducted for monitoring the agricultural environment. As a result of comparing classification performance by applying RF(Random Forest), SVM(Support Vector Machine) and CNN(Convolutional Neural Network), deep learning classification method has many advantages in image classification. In particular, land cover classification using satellite images has the advantage of accuracy and time of classification using satellite image data set and pre-trained parameters. However, UAV images have different characteristics such as satellite images and spatial resolution, which makes it difficult to apply them. In order to solve this problem, we conducted a study on the application of deep learning algorithms that can be used for analyzing agricultural lands where UAV data sets and small-scale composite cover exist in Korea. In this study, we applied DeepLab V3 +, FC-DenseNet (Fully Convolutional DenseNets) and FRRN-B (Full-Resolution Residual Networks), the semantic image classification of the state-of-art algorithm, to UAV data set. As a result, DeepLab V3 + and FC-DenseNet have an overall accuracy of 97% and a Kappa coefficient of 0.92, which is higher than the conventional classification. The applicability of the cover classification using UAV images of small areas is shown.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.11 no.4
• /
• pp.371-376
• /
• 2017

In this paper, we propose an algorithm that can recognize the pattern regardless of the sensor position when performing EMG pattern recognition using circular EMG system equipment. Fourteen features were extracted by using the data obtained by measuring the eight channel EMG signals of six motions for 1 second. In addition, 112 features extracted from 8 channels were analyzed to perform principal component analysis, and only the data with high influence was cut out to 8 input signals. All experiments were performed using k-NN classifier and data was verified using 5-fold cross validation. When learning data in machine learning, the results vary greatly depending on what data is learned. EMG Accuracy of 99.3% was confirmed when using the learning data used in the previous studies. However, even if the position of the sensor was changed by only 22.5 degrees, it was clearly dropped to 67.28% accuracy. The accuracy of the proposed method is 98% and the accuracy of the proposed method is about 98% even if the sensor position is changed. Using these results, it is expected that the convenience of the users using the circular EMG system can be greatly increased.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.4
• /
• pp.847-857
• /
• 2018

As the number of malicious code increases steeply, cyber attack victims targeting corporations, public institutions, financial institutions, hospitals are also increasing. Accordingly, academia and security industry are conducting various researches on malicious code detection. In recent years, there have been a lot of researches using machine learning techniques including deep learning. In the case of research using Convolutional Neural Network, ResNet, etc. for classification of malicious code, it can be confirmed that the performance improvement is higher than the existing classification method. However, one of the characteristics of the target attack is that it is custom malicious code that makes it operate only for a specific company, so it is not a form spreading widely to a large number of users. Since there are not many malicious codes of this kind, it is difficult to apply the previously studied machine learning or deep learning techniques. In this paper, we propose a method to classify malicious codes when the amount of samples is insufficient such as targeting type malicious code. As a result of the study, we confirmed that the accuracy of 97% can be achieved even with a small amount of data by applying the Memory Augmented Neural Networks model.

• Journal of Korean Library and Information Science Society
• /
• v.52 no.3
• /
• pp.313-334
• /
• 2021

This study aimed to analyze AI research trends related to elementary, middle, and high school education. To this end, the related literature was collected from the SCOPUS database and the publication period of the collected literature was from 1974 to March 2021, with 154 journal papers and 571 conference papers. Research trends were analyzed based on the co-occurrences analysis technique of 4,521 words of author keyword and index keyword included in these papers. As a result of the analysis, big data, data mining, data science and deep learning were found as the latest research trends with machine learning and there was a difference between elementary, middle and high school education. It can be seen that elementary school had a lot of robot-related research, middle school had a lot of game and data-related research, and high school had various and in-depth research. In discussion, we mapped the top 50 words common to elementary, middle, and high schools with the 'Artificial Intelligence Basics' curriculum of Korean Government and '5 Big Ideas' of the United States Government so that AI research can be viewed at a glance.

• Convergence Security Journal
• /
• v.21 no.1
• /
• pp.191-200
• /
• 2021

Artificial intelligence technology is developing in an environment where a lot of data is produced due to the development of computing technology, a cloud environment that can store data, and the spread of personal mobile phones. Among these artificial intelligence technologies, the deep neural network provides excellent performance in image recognition and image classification. There have been many studies on image detection for forest fires and fire prevention using such a deep neural network, but studies on detection of cigarette smoking were insufficient. Meanwhile, military units are establishing surveillance systems for various facilities through CCTV, and it is necessary to detect smoking near ammunition stores or non-smoking areas to prevent fires and explosions. In this paper, by reflecting experimentally optimized numerical values such as activation function and learning rate, we did the detection of smoking pictures and non-smoking pictures in two cases. As experimental data, data was constructed by crawling using pictures of smoking and non-smoking published on the Internet, and a machine learning library was used. As a result of the experiment, when the learning rate is 0.004 and the optimization algorithm Adam is used, it can be seen that the accuracy of 93% and F1-score of 94% are obtained.

• Journal of Digital Convergence
• /
• v.17 no.8
• /
• pp.249-255
• /
• 2019

Type 2 diabetes mellitus(T2DM) is included in metabolic disorders characterized by hyperglycemia, which causes many complications, and requires long-term treatment resulting in massive medical expenses each year. There have been many studies to solve this problem, but the existing studies have not been accurate by learning and predicting the data at specific time point. Thus, this study proposed a model using RNN to increase the accuracy of prediction of T2DM. This work propose a T2DM prediction model based on Korean Genome and Epidemiology study(Ansan, Anseong Korea). We trained all of the data over time to create prediction model of diabetes. To verify the results of the prediction model, we compared the accuracy with the existing machine learning methods, LR, k-NN, and SVM. Proposed prediction model accuracy was 0.92 and the AUC was 0.92, which were higher than the other. Therefore predicting the onset of T2DM by using the proposed diabetes prediction model in this study, it could lead to healthier lifestyle and hyperglycemic control resulting in lower risk of diabetes by alerted diabetes occurrence.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.1
• /
• pp.53-62
• /
• 2021

After the first to present projected moving pictures to audiences, the film industry has been reshaping along with technological advancements. Through the full-scale introduction of visual effects-oriented post-production and digital technologies in the film-making process, the film industry has not only undergone significant changes in the production, but is also embracing the cutting edge technologies broadly and expanding the scope of industry. Not long after the change to digital cinema, the concept of artificial intelligence, first known at the Dartmouth summer research project in 1956, before the digitalization of film, is expected to bring about a big transformation in the film industry once again. Large volume of clear digital data from digital film-making makes easy to apply recent artificial intelligence technologies represented by machine learning and deep learning. The use of artificial intelligence techniques is prominent around major visual effects studios due to automate many laborious, time-consuming tasks currently performed by artists. This study aims to predict how artificial intelligence technology will change the film industry in the future through analysis of visual effects production cases using artificial intelligence technology as a production tool and to discuss the industrial potential of artificial intelligence as visual effects technology.