• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.31-36
• /
• 2024

Recently, mobile apps that utilize AI technologies are increasing. In the personal mobile environment, performance degradation may occur during the training phase of large AI workload due to limitations in memory capacity. In this paper, we extract memory reference traces of AI workloads and analyze their characteristics. From this analysis, we observe that AI workloads can cause frequent storage access due to weak temporal locality and irregular popularity bias during memory write operations, which can degrade the performance of mobile devices. Based on this observation, we discuss ways to efficiently manage memory write operations of AI workloads using persistent memory-based swap devices. Through simulation experiments, we show that the system architecture proposed in this paper can improve the I/O time of mobile systems by more than 80%.

• Journal of Internet of Things and Convergence
• /
• v.10 no.4
• /
• pp.27-33
• /
• 2024

As of 2023, the number of accident victims in the domestic construction industry is 26,829, ranking second only to other businesses (service industries). The accident types of casualties in all industries were falls (29,229 people), followed by falls (14,357 people). Based on the above data, this study attaches sensors to hard hats and insoles to predict fall accidents that frequently occur at construction sites, and proposes smart safety equipment that applies a random forest algorithm based on the data collected through this. The random forest model can determine fall accidents in real time with high accuracy by generating multiple decision trees and combining the predictions of each tree. This model classifies whether a worker has had a fall accident and the type of behavior through data collected from the MPU-6050 sensor attached to the hard hat. Fall accidents that are primarily determined from hard hats are secondarily predicted through sensors attached to the insole, thereby increasing prediction accuracy. It is expected that this will enable rapid response in the event of an accident, thereby reducing worker deaths and accidents.

• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.17-23
• /
• 2020

Biometric information indicating measurement items related to human characteristics has attracted great attention as security technology with high reliability since there is no fear of theft or loss. Among these biometric information, fingerprints are mainly used in fields such as identity verification and identification. If there is a problem such as a wound, wrinkle, or moisture that is difficult to authenticate to the fingerprint image when identifying the identity, the fingerprint expert can identify the problem with the fingerprint directly through the preprocessing step, and apply the image processing algorithm appropriate to the problem. Solve the problem. In this case, by implementing artificial intelligence software that distinguishes fingerprint images with cuts and wrinkles on the fingerprint, it is easy to check whether there are cuts or wrinkles, and by selecting an appropriate algorithm, the fingerprint image can be easily improved. In this study, we developed a total of 17,080 fingerprint databases by acquiring all finger prints of 1,010 students from the Royal University of Cambodia, 600 Sokoto open data sets, and 98 Korean students. In order to determine if there are any injuries or wrinkles in the built database, criteria were established, and the data were validated by experts. The training and test datasets consisted of Cambodian data and Sokoto data, and the ratio was set to 8: 2. The data of 98 Korean students were set up as a validation data set. Using the constructed data set, five CNN-based architectures such as Classic CNN, AlexNet, VGG-16, Resnet50, and Yolo v3 were implemented. A study was conducted to find the model that performed best on the readings. Among the five architectures, ResNet50 showed the best performance with 81.51%.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.461-469
• /
• 2020

In this paper, we propose a PCA-based feature feedback method for extracting important areas of handwritten numeric data sets and face data sets. A PCA-based feature feedback method is proposed by extending the previous LDA-based feature feedback method. In the proposed method, the data is reduced to important feature dimensions by applying the PCA technique, one of the dimension reduction machine learning algorithms. Through the weights derived during the dimensional reduction process, the important points of data in each reduced dimensional axis are identified. Each dimension axis has a different weight in the total data according to the size of the eigenvalue of the axis. Accordingly, a weight proportional to the size of the eigenvalues of each dimension axis is given, and an operation process is performed to add important points of data in each dimension axis. The critical area of the data is calculated by applying a threshold to the data obtained through the calculation process. After that, induces reverse mapping to the original data in the important area of the derived data, and selects the important area in the original data space. The results of the experiment on the MNIST dataset are checked, and the effectiveness and possibility of the pattern recognition method based on PCA-based feature feedback are verified by comparing the results with the existing LDA-based feature feedback method.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.143-174
• /
• 2023

With the development of deep learning technologies, Artificial Intelligence powered Optical Character Recognition (AI-OCR) has evolved to read multiple languages from various forms of images accurately. For the financial industry, where a large number of diverse documents are processed through manpower, the potential for using AI-OCR is great. In this study, we present a configuration and a design of an AI-OCR modality for use in the financial industry and discuss the platform construction with application cases. Since the use of financial domain data is prohibited under the Personal Information Protection Act, we developed a deep learning-based data generation approach and used it to train the AI-OCR models. The AI-OCR models are trained for image preprocessing, text recognition, and language processing and are configured as a microservice architected platform to process a broad variety of documents. We have demonstrated the AI-OCR platform by applying it to financial domain tasks of document sorting, document verification, and typing assistance The demonstrations confirm the increasing work efficiency and conveniences.

• Journal of Broadcast Engineering
• /
• v.19 no.5
• /
• pp.578-589
• /
• 2014

Window image is displayed through a monitor screen when we execute the application programs on the computer. This includes webpage, video player and a number of applications. The webpage delivers a variety of information by various types in comparison with other application. Unlike a natural image captured from a camera, the window image like a webpage includes diverse components such as text, logo, icon, subimage and so on. Each component delivers various types of information to users. However, the components with different characteristic need to be divided locally, because text and image are served by various type. In this paper, we divide window images into many sub blocks, and classify each divided region into background, text and subimage. The detected subimages can be applied into 2D-to-3D conversion, image retrieval, image browsing and so forth. There are many subimage classification methods. In this paper, we utilize AdaBoost for verifying that the machine learning-based algorithm can be efficient for subimage detection. In the experiment, we showed that the subimage detection ratio is 93.4 % and false alarm is 13 %.

• Archives of design research
• /
• v.19 no.1 s.63
• /
• pp.15-26
• /
• 2006

As the interest and use of computer have been increased among elderly users according to the entry to the aging society, the issue of universal design for computer usability was brought forward. Especially, it is widely recognized that universal UI(User Interlace) design on MS windows is important. The objective of this study is to conceptualize Universal GUI design on MS windows which can be used more easily and intuitively by novice users such as elderly and housewives. Especially, the solution for Universal GUI design on MS windows was developed by reflecting elderly users' needs because elderly users is the group with more difficulties than other user groups in learning and using MS windows. First, elderly user's needs was collected by participant observation as a teaching assistant in computer dass for elderly people for 4 weeks. Secondly, the experimental test and in-depth interview was implemented to find difficulties factors and needs in addition to participant observation. Based on the findings, the new GUI design solution was suggested. The design solution consists of ideas in several categories such as setting default, simplification of function for easy conceptual model making, customization of function and working environment, and intuitive GUI in interaction process. The new MS windows GUI design can be accessed by novice mode when user login in window XP. This study has the significance in finding elderly users detailed needs through in-depth and long term participant observation. However, the usability of the suggested prototype needs to be verified to various user groups besides elderly users in the future.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.3
• /
• pp.31-38
• /
• 2017

In this paper, we propose a system which estimates Manhattan coordinate systems for urban scene images using a convolutional neural network (CNN). Estimating the Manhattan coordinate system from an image under the Manhattan world assumption is the basis for solving computer graphics and vision problems such as image adjustment and 3D scene reconstruction. We construct a CNN that estimates Manhattan coordinate systems based on GoogLeNet [1]. To train the CNN, we collect about 155,000 images under the Manhattan world assumption by using the Google Street View APIs and calculate Manhattan coordinate systems using existing calibration methods to generate dataset. In contrast to PoseNet [2] that trains per-scene CNNs, our method learns from images under the Manhattan world assumption and thus estimates Manhattan coordinate systems for new images that have not been learned. Experimental results show that our method estimates Manhattan coordinate systems with the median error of $3.157^{\circ}$ for the Google Street View images of non-trained scenes, as test set. In addition, compared to an existing calibration method [3], the proposed method shows lower intermediate errors for the test set.

• Journal of the Korean Chemical Society
• /
• v.50 no.2
• /
• pp.141-152
• /
• 2006

In this study computer assisted instruction materials for the ‘Solution' chapter in high school chemistry II textbook were developed based on a view of particle and analyze the effect of the materials on 10th and 11th high school students. The contents of developed materials are dissolution, vapor pressure, the change of boiling point and freezing point, osmosis, and so on which are the major contents of Solution chapter in high school chemistry II textbook. Materials were developed with using animation and simulation for students understanding of the phenomena with a particle view point. Many phenomena in a solution were not simplified by colligative property of solution, but tried to explain by the concept of attraction between solute and solvent molecules. This computer assisted learning materials were developed using Flash 5.0 and Flash 6.0 Action Script. Educational effects of the materials on 10th and 11th grade students represented statistically meaningful increase of concept understanding. Especially the materials were effective to the transition stage or formal stage students in 10th grade and formal stage or the natural science major students in 11th grade.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.621-628
• /
• 2021

This paper proposes a method to calibrate a thermal camera with three different perspectives. In particular, the intrinsic parameters of the camera and re-projection errors were provided to quantify the accuracy of the calibration result. Three lenses of the camera capture the same image, but they are not overlapped, and the image resolution is worse than the one captured by the RGB camera. In computer vision, camera calibration is one of the most important and fundamental tasks to calculate the distance between camera (s) and a target object or the three-dimensional (3D) coordinates of a point in a 3D object. Once calibration is complete, the intrinsic and the extrinsic parameters of the camera(s) are provided. The intrinsic parameters are composed of the focal length, skewness factor, and principal points, and the extrinsic parameters are composed of the relative rotation and translation of the camera(s). This study estimated the intrinsic parameters of thermal cameras that have three lenses of different perspectives. In particular, image enhancement based on a deep learning algorithm was carried out to improve the quality of the calibration results. Experimental results are provided to substantiate the proposed method.