• Journal of the Semiconductor & Display Technology
• /
• v.20 no.2
• /
• pp.121-125
• /
• 2021

Cloud service has the characteristic that it must be always available and that it must be able to respond immediately to user requests. This study suggests a method for constructing a proactive and autonomous quality and performance management system to meet these characteristics of cloud services. To this end, we identify quantitative measurement factors for cloud service quality and performance management, define a structure for applying a time series framework to cloud service application quality and performance management for proactive management, and then use big data and artificial intelligence for autonomous management. The flow of data processing and the configuration and flow of big data and artificial intelligence platforms were defined to combine intelligent technologies. In addition, the effectiveness was confirmed by applying it to the cloud service quality and performance management system through a case study. Using the methodology presented in this study, it is possible to improve the service management system that has been managed artificially and retrospectively through various convergence. However, since it requires the collection, processing, and processing of various types of data, it also has limitations in that data standardization must be prioritized in each technology and industry.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.11
• /
• pp.305-310
• /
• 2021

Artificial intelligence technology in the medical field initially focused on analysis and algorithm development, but it is gradually changing to web application development for service as a product. This paper describes a Urinary Stone segmentation model in abdominal CT images and an artificial intelligence web application based on it. To implement this, a model was developed using U-Net, a fully-convolutional network-based model of the end-to-end method proposed for the purpose of image segmentation in the medical imaging field. And for web service development, it was developed based on AWS cloud using a Python-based micro web framework called Flask. Finally, the result predicted by the urolithiasis segmentation model by model serving is shown as the result of performing the AI web application service. We expect that our proposed AI web application service will be utilized for screening test.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.57-66
• /
• 2023

In this study, we propose a novel research framework for the recommendation system that can estimate the user's emotional state and reflect it in the recommendation process by applying deep learning techniques and emotion AI (artificial intelligence). To this end, we build an emotion classification model that classifies each of the seven emotions of angry, disgust, fear, happy, sad, surprise, and neutral, respectively, and propose a model that can reflect this result in the recommendation process. However, in the general emotion classification data, the difference in distribution ratio between each label is large, so it may be difficult to expect generalized classification results. In this study, since the number of emotion data such as disgust in emotion image data is often insufficient, correction is made through augmentation. Lastly, we propose a method to reflect the emotion prediction model based on data through image augmentation in the recommendation systems.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.3
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.3
• /
• pp.63-67
• /
• 2024

Recently, artificial intelligence (AI) workloads encompassing various industries such as smart logistics, FinTech, and entertainment are being executed on the cloud. In this paper, we address the scheduling issues of various AI workloads on a multi-tenant cloud system composed of heterogeneous GPU clusters. Traditional scheduling decreases GPU utilization in such environments, degrading system performance significantly. To resolve these issues, we present a new scheduling approach utilizing genetic algorithm-based optimization techniques, implemented within a process-based event simulation framework. Trace driven simulations with diverse AI workload traces collected from Alibaba's MLaaS cluster demonstrate that the proposed scheduling improves GPU utilization compared to conventional scheduling significantly.

• The KIPS Transactions:PartB
• /
• v.11B no.1
• /
• pp.117-124
• /
• 2004

This paper proposes an efficient algorithm of NaiveBayes without loss of its accuracy. The proposed method uses the transposition of category vectors, and minimizes the computation of the probability of NaiveBayes. The proposed method was implemented on the existing framework of the text categorization, so called, AI::Categorizer and it was compared with the conventional NaiveBayes with the well-known data, Router-21578. The comparisons show that the proposed method outperforms NaiveBayes about two times with respect to the executing time.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.227-241
• /
• 2021

Object detection techniques based on deep learning such as YOLO have high detection performance and precision in a single channel video stream. In order to expand to multiple channel object detection in real-time, however, high-performance hardware is required. In this paper, we propose a novel back-end server framework, a real-time AI vision platform (RAVIP), which can extend the object detection function from single channel to simultaneous multi-channels, which can work well even in low-end server hardware. RAVIP assembles appropriate component modules from the RODEM (real-time object detection module) Base to create per-channel instances for each channel, enabling efficient parallelization of object detection instances on limited hardware resources through continuous monitoring with respect to resource utilization. Through practical experiments, RAVIP shows that it is possible to optimize CPU, GPU, and memory utilization while performing object detection service in a multi-channel situation. In addition, it has been proven that RAVIP can provide object detection services with 25 FPS for all 16 channels at the same time.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.192-195
• /
• 2021

AI 모델 서비스 제공에 강제되는 높은 메모리 사용량을 해결하기 위해 일반적으로 클라우드 컴퓨팅 기술을 이용한다. 클라우드 기반 서비스는 개발자로 하여금 메모리 사용량에 대한 걱정을 덜어주고 서비스 이용자에게는 편리하게 양질의 서비스를 제공받을 수 있게 한다. 하지만 보안 대책이 미흡한 클라우드 서비스는 서비스를 제공받아 얻는 이익만을 생각하기에는 보안사고로 인한 피해가 막대할 수 있다. AI 기술이 인간의 삶에 깊이 파고든 현 상황에서 우리가 대부분 이용하는 클라우드에 기반 서비스의 보안 문제는 그 중요도가 굉장히 높다고 할 수 있다. 이를 위해 본 논문에서는 클라우드 기반 머신러닝 서비스를 분석하여 어떤 공격이 이루어질 수 있는지 분석하고 그에 대한 연구된 방어법들의 효과를 확인하여 효과적인 것들을 선별하고 접목시키는 시도를 한다.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.28 no.1
• /
• pp.1-21
• /
• 2024

This review comprehensively explores the evolution, theoretical underpinnings, variations, and applications of diffusion models. Originating as a generative framework, diffusion models have rapidly ascended to the forefront of machine learning research, owing to their exceptional capability, stability, and versatility. We dissect the core principles driving diffusion processes, elucidating their mathematical foundations and the mechanisms by which they iteratively refine noise into structured data. We highlight pivotal advancements and the integration of auxiliary techniques that have significantly enhanced their efficiency and stability. Variants such as bridges that broaden the applicability of diffusion models to wider domains are introduced. We put special emphasis on the ability of diffusion models as a crucial foundation model, with modalities ranging from image, 3D assets, and video. The role of diffusion models as a general foundation model leads to its versatility in many of the downstream tasks such as solving inverse problems and image editing. Through this review, we aim to provide a thorough and accessible compendium for both newcomers and seasoned researchers in the field.

• Journal of information and communication convergence engineering
• /
• v.22 no.1
• /
• pp.7-13
• /
• 2024

User preferences and ratings may be anticipated by recommendation systems, which are widely used in social networking, online shopping, healthcare, and even energy efficiency. Constructing trustworthy recommender systems for various applications, requires the analysis and mining of vast quantities of user data, including demographics. This study focuses on holding elections with vague voter and candidate preferences. Collaborative user ratings are used by filtering algorithms to provide suggestions. To avoid information overload, consumers are directed towards items that they are more likely to prefer based on the profile data used by recommender systems. Better interactions between governments, residents, and businesses may result from studies on recommender systems that facilitate the use of e-government services. To broaden people's access to the democratic process, the concept of "e-democracy" applies new media technologies. This study provides a framework for an electronic voting advisory system that uses machine learning.