• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.99-104
• /
• 2022

Artificial intelligence is getting a crucial part of our lives with its incredible benefits. Machines outperform humans in recognizing objects in images, particularly in classifying people into correct age and gender groups. In this respect, age and gender classification has been one of the hot topics among computer vision researchers in recent decades. Deployment of deep Convolutional Neural Network(: CNN) models achieved state-of-the-art performance. However, the most of CNN based architectures are very complex with several dozens of training parameters so they require much computation time and resources. For this reason, we propose a new CNN-based classification algorithm with significantly fewer training parameters and training time compared to the existing methods. Despite its less complexity, our model shows better accuracy of age and gender classification on the UTKFace dataset.

• Journal of Creative Information Culture
• /
• v.7 no.2
• /
• pp.91-98
• /
• 2021

As the amount of time that elementary school students spend online increased due to Corona 19, the amount of posts, comments, and chats they write increased, and problems such as offending others' feelings or using swear words are occurring. Netiquette is being educated in elementary school, but training time is insufficient. In addition, it is difficult to expect changes in student behavior. So, technical support through natural language processing is needed. In this study, an experiment was conducted to automatically filter profanity sentences by applying them to a pre-trained language model on sentences written by elementary school students. In the experiment, chat details of elementary school 4-6 graders were collected on an online learning platform, and general sentences and profanity sentences were trained through a pre-learned language model. As a result of the experiment, as a result of classifying profanity sentences, it was analyzed that the precision was 75%. It has been shown that if the learning data is sufficiently supplemented, it can be sufficiently applied to the online platform used by elementary school students.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.173-178
• /
• 2022

Recently, a recommendation system using deep learning in social network services has been actively studied. However, in the case of a recommendation system using deep learning, the cold start problem and the increased learning time due to the complex computation exist as the disadvantage. In this paper, the user-tailored exercise routine recommendation algorithm is proposed using the user's metadata. Metadata (the user's height, weight, sex, etc.) set as the input of the model is applied to the designed model in the proposed algorithms. The exercise recommendation system model proposed in this paper is designed based on the neural collaborative filtering (NCF) algorithm using multi-layer perceptron and matrix factorization algorithm. The learning proceeds with proposed model by receiving user metadata and exercise information. The model where learning is completed provides recommendation score to the user when a specific exercise is set as the input of the model. As a result of the experiment, the proposed exercise recommendation system model showed 10% improvement in recommended performance and 50% reduction in learning time compared to the existing NCF model.

• The Korean Journal of Applied Statistics
• /
• v.35 no.4
• /
• pp.469-484
• /
• 2022

Since a large text corpus contains hundred-thousand unique words, text data is one of the typical large-dimensional data. Therefore, various feature selection methods have been proposed for dimension reduction. Feature selection methods can improve the prediction accuracy. In addition, with reduced data size, computational efficiency also can be achieved. The chi-square statistic and the information gain are two of the most popular measures for identifying interesting terms from text data. In this paper, we investigate the theoretical properties of the chi-square statistic and the information gain. We show that the two filtering metrics share theoretical properties such as non-negativity and convexity. However, they are different from each other in the sense that the information gain is prone to select more negative features than the chi-square statistic in imbalanced text data.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.725-737
• /
• 2021

Although the performance of cameras is gradually improving now, there are noise in the acquired digital images from the camera, which acts as an obstacle to obtaining high-resolution images. Traditionally, a filtering method has been used for denoising, and a convolutional neural network (CNN), one of the deep learning techniques, has been showing better performance than traditional methods in the field of image denoising, but the details in images could be lost during the learning process. In this paper, we present a CNN for image denoising, which improves image details by learning the details of the image based on wavelet transform. The proposed network uses two subnetworks for detail enhancement and noise extraction. The experiment was conducted through Gaussian noise and real-world noise, we confirmed that our proposed method was able to solve the detail loss problem more effectively than conventional algorithms, and we verified that both objective quality evaluation and subjective quality comparison showed excellent results.

• The Journal of the Korea Contents Association
• /
• v.21 no.7
• /
• pp.134-143
• /
• 2021

Recently, with the development of mobile devices and social media services, contents recommendation schemes have been studied. They are typically applied to the job curation systems. Most existing university education content recommendation schemes only recommend the most frequently taken subjects based on the student's school and major. Therefore, they do not consider the type or field of employment that each student wants. In this paper, we propose a university educational contents recommendation scheme for job curation services. The proposed scheme extracts companies that a user is interested in by analyzing his/her activities in the job curation system. The proposed scheme selects graduates or mentors based on the reliability and similarity of graduates who have been employed at the companies of interest. The proposed scheme recommends customized subjects, comparative subjects, and autonomous activity lists to users through collaborative filtering.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.7
• /
• pp.989-995
• /
• 2022

Currently, the demand for image processing is increasing due to the development of IT technology, and active research is being conducted. Since image data generates image noise due to various external causes, and thus degrades the performance of the image, noise removal is essential. Salt and Pepper noise is a representative image noise, and various studies are being conducted to remove it. Existing algorithms include A-TMF, AFMF, LIWF, but these have the disadvantage that their performance is somewhat insufficient. Therefore, in this paper, we propose an algorithm that performs filtering using linear interpolation with effective pixels existing around the central pixel only in case of noise after performing noise judgment in order to efficiently remove salt and pepper noise. In order to judge the performance of the proposed algorithm, it was compared using the processed image of the previously studied algorithm and PSNR.

• Journal of Practical Engineering Education
• /
• v.14 no.1
• /
• pp.99-108
• /
• 2022

As the demand for kiosks increases, more users complain of discomfort. Accordingly, a kiosk that enables easy menu selection and order by producing a voice-based interactive service is produced and provided in the form of a web. It implements voice functions based on the Annyang API and SpeechSynthesis API, and understands the user's intention through Dialogflow. And discuss how to implement this process based on Rest API. In addition, the recommendation system is applied based on collaborative filtering to improve the low consumer accessibility of existing kiosks, and to prevent infection caused by droplets during the use of voice recognition services, it provides the ability to check the wearing of masks before using the service.

• Journal of the Korea Society for Simulation
• /
• v.19 no.1
• /
• pp.161-171
• /
• 2010

Sensor Networks are often deployed in unattended environments, thus leaving these networks vulnerable to false data injection attacks in which an adversary injects forged reports into the network through compromised nodes. Such attacks by compromised sensors can cause not only false alarms but also the depletion of the finite amount of energy in a battery powered network. Ye et al. proposed the Statistical En-route Filtering scheme to overcome this threat. In statistical en-route filtering scheme, all the intermediate nodes perform verification as event reports created by center of stimulus node are forwarded to the base station. This paper applies a probabilistic verification method to the Static Statistical En-route Filtering for energy efficiency. It is expected that the farther from the base station an event source is, the higher energy efficiency is achieved.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.3
• /
• pp.203-211
• /
• 2019

The purpose of this study was to investigate the relations between sensory processing and sleep disturbances and to investigate the effect of sensory processing on sleep disorder in preschool children with developmental disorder. This study was conducted for 110 children with developmental disorder in developmental clinic and rehabilitation hospital in Gwang Ju from June to August, 2017. The final 109 data were analyzed. Sensory processing and Sleep disturbances were measured using the Shortened sensory profile(SSP) and Korean-the Children's Sleep Habits Questionnaire(K-CSHQ). Statistical analysis was performed using descriptive analysis, Pearson correlation analysis, and multiple regression analysis were performed. Children with developmental disorder had problems with sensory processing and sleep habits. Sensory processing was related to sleep habit and most important factors of sensory processing influencing sleep was taste/olfactory sensitivity, auditory filtering. Conclusion: In order to help children with developmental disorder with sleep problem, it is necessary to consider the sensory processing especially taste/olfactory sensitivity, auditory filtering.