• Journal of the Korea Society of Computer and Information
• /
• v.23 no.4
• /
• pp.147-153
• /
• 2018

In this paper, we propose an efficient WBC 14-Diff classification which performs using the WBC-ResNet-152, a type of CNN model. The main point of view is to use Super-pixel for the segmentation of the image of WBC, and to use ResNet for the classification of WBC. A total of 136,164 blood image samples (224x224) were grouped for image segmentation, training, training verification, and final test performance analysis. Image segmentation using super-pixels have different number of images for each classes, so weighted average was applied and therefore image segmentation error was low at 7.23%. Using the training data-set for training 50 times, and using soft-max classifier, TPR average of 80.3% for the training set of 8,827 images was achieved. Based on this, using verification data-set of 21,437 images, 14-Diff classification TPR average of normal WBCs were at 93.4% and TPR average of abnormal WBCs were at 83.3%. The result and methodology of this research demonstrates the usefulness of artificial intelligence technology in the blood cell image classification field. WBC-ResNet-152 based morphology approach is shown to be meaningful and worthwhile method. And based on stored medical data, in-depth diagnosis and early detection of curable diseases is expected to improve the quality of treatment.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.31-36
• /
• 2019

Unsupervised neural networks have not caught enough attention until Generative Adversarial Network (GAN) was proposed. By using both the generator and discriminator networks, GAN can extract the main characteristic of the original dataset and produce new data with similarlatent statistics. However, researchers understand fully that training GAN is not easy because of its unstable condition. The discriminator usually performs too good when helping the generator to learn statistics of the training datasets. Thus, the generated data is not compelling. Various research have focused on how to improve the stability and classification accuracy of GAN. However, few studies delve into how to improve the training efficiency and to save training time. In this paper, we propose a novel optimizer, named FAST-ADAM, which integrates the Lookahead to ADAM optimizer to train the generator of a semi-supervised generative adversarial network (SSGAN). We experiment to assess the feasibility and performance of our optimizer using Canadian Institute For Advanced Research - 10 (CIFAR-10) benchmark dataset. From the experiment results, we show that FAST-ADAM can help the generator to reach convergence faster than the original ADAM while maintaining comparable training accuracy results.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.11
• /
• pp.75-84
• /
• 2018

Social engineering attack means to get information of Social engineering attack means to get information of opponent without technical attack or to induce opponent to provide information directly. In particular, social engineering does not approach opponents through technical attacks, so it is difficult to prevent all attacks with high-tech security equipment. Each company plans employee education and social training as a countermeasure to prevent social engineering. However, it is difficult for a security officer to obtain a practical education(training) effect, and it is also difficult to measure it visually. Therefore, to measure the social engineering threat, we use the results of social engineering training result to calculate the risk by system asset and propose a attack graph based probability. The security officer uses the results of social engineering training to analyze the security threats by asset and suggests a framework for quick security response. Through the framework presented in this paper, we measure the qualitative social engineering threats, collect system asset information, and calculate the asset risk to generate probability based attack graphs. As a result, the security officer can graphically monitor the degree of vulnerability of the asset's authority system, asset information and preferences along with social engineering training results. It aims to make it practical for companies to utilize as a key indicator for establishing a systematic security strategy in the enterprise.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.294-300
• /
• 2022

The article highlights the European experience of innovative educational technologies of training management specialists. Based on existing strategies, relevant in the European educational space, the introduction of regulatory elements to maintain a balance between the traditional and innovative format of the educational process, which is typical for the Ukrainian education system is proposed. The article aims to single out educational and technological innovations into a separate cluster of managerial training at different levels in the context of the principles of the modern synergetic sociocultural paradigm. The main objectives of the work are to develop settings to ensure the effective functioning of innovative educational technologies. Among the synergetic principles of educational technologies, providing the formation of necessary competencies of future managers, are: self-organization, interdisciplinarity, nonlinearity, individuality, and technologization. The methods used in the scientific study can be attributed to the group of scientific synergetic methodology. So, the training of specialists in management, implemented in the European practice assumes the use of new educational strategies. These technologies provide both the necessary skills of different levels (hard-soft-digital skills) and the observance of value components (solidarity, ethics, inclusiveness, openness).

• ETRI Journal
• /
• v.32 no.1
• /
• pp.160-162
• /
• 2010

For the acoustic models of embedded speech recognition systems, hidden Markov models (HMMs) are usually quantized and the original full space distributions are represented by combinations of a few quantized distribution prototypes. We propose a maximum likelihood objective function to train the quantized distribution prototypes. The experimental results show that the new training algorithm and the link structure adaptation scheme for the quantized HMMs reduce the word recognition error rate by 20.0%.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.3
• /
• pp.120-124
• /
• 2021

Recently, human attribute recognition (HAR) attracts a lot of attention due to its wide application in video surveillance systems. Recent deep-learning-based solutions for HAR require time-consuming training processes. In this paper, we propose a post-processing technique that utilizes the historical video frames to improve prediction results without invoking re-training or modifying existing deep-learning-based classifiers. Experiment results on a large-scale benchmark dataset show the effectiveness of our proposed method.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.397-398
• /
• 2022

본 논문에서는 SK텔레콤에서 진행하는 디지털 선도기업 아카데미 FLYAI의 교육과정을 설계하고 개발한다. 이 교육과정은 Project Based Learning(272시간)과 Product Based Learning(128시간)으로 구성하여 총 400시간을 교육하도록 설계한다. 특히 Product Based Learning의 AI-Hackathon(80시간)에서는 SK텔레콤 각 부서에서 제안하는 제픔을 기획하고 개발하는 과정으로 SK텔레콤 AI 개발자들이 멘토로 참여함으로써 기업 현장의 경험을 체험할 수 있도록 개발한다.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.11-20
• /
• 2024

While artificial neural networks are adept at identifying patterns, they can struggle to distinguish between actual correlations and false associations between extracted facial features and criminal behavior within the training data. These associations may not indicate causal connections. Socioeconomic factors, ethnicity, or even chance occurrences in the data can influence both facial features and criminal activity. Consequently, the artificial neural network might identify linked features without understanding the underlying cause. This raises concerns about incorrect linkages and potential misclassification of individuals based on features unrelated to criminal tendencies. To address this challenge, we propose a novel region-based training approach for artificial neural networks focused on criminal propensity detection. Instead of solely relying on overall facial recognition, the network would systematically analyze each facial feature in isolation. This fine-grained approach would enable the network to identify which specific features hold the strongest correlations with criminal activity within the training data. By focusing on these key features, the network can be optimized for more accurate and reliable criminal propensity prediction. This study examines the effectiveness of various algorithms for criminal propensity classification. We evaluate YOLO versions YOLOv5 and YOLOv8 alongside VGG-16. Our findings indicate that YOLO achieved the highest accuracy 0.93 in classifying criminal and non-criminal facial features. While these results are promising, we acknowledge the need for further research on bias and misclassification in criminal justice applications

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.1075-1087
• /
• 2020

Aviation ICT technology is a convergence technology between aviation and electronics, and has a wide variety of applications, including navigation and education. Among them, in the field of aerial pilot training, there are many problems such as the possibility of accidents during training and the lack of coping skills for various situations. This raises the need for a simulated pilot training system similar to actual training. In this paper, pilot training data were collected in pilot training system using VR/AR to increase immersion in flight training, and Customized Pilot Training Platform with Collaborative Deep Learning in VR/AR Environment that can recommend effective training courses to pilots is proposed. To verify the accuracy of the recommendation, the performance of the proposed collaborative deep learning algorithm with the existing recommendation algorithm was evaluated, and the flight test score was measured based on the pilot's training data base, and the deviations of each result were compared. The proposed service platform can expect more reliable recommendation results than previous studies, and the user survey for verification showed high satisfaction.

• Journal of Korea Multimedia Society
• /
• v.24 no.2
• /
• pp.328-335
• /
• 2021

In the era of 'Untact', virtual reality-based job training platforms are actively being used as part of non-face-to-face education for students with developmental disabilities. Because the people with developmental disabilities may lack sufficient cognitive abilities, it is difficult to conduct untact training seamlessly without the help of a third party. Therefore, it is necessary for training programs to identify the right timing to provide help so that the training can be continued. This research analyzed the visual attention of students with developmental disabilities in virtual reality-based job training program in order to determine the point of time when an intervention is required by the trainee. Results showed that students who completed the mission tended to have intense visual attention on a small number of objects for a certain period of time; the visual attention of the students who failed tended to shift erratically among multiple objects.