• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.57-64
• /
• 2023

This study analyzed the perceptions of elementary and secondary school teachers regarding the importance of SW/AI education in fostering students' fundamental knowledge and the necessity of integrating SW/AI into education. A total of 830 elementary and secondary school teachers were selected as study subjects using the judgment sampling method. The analysis of survey data revealed that elementary and secondary teachers exhibited a strong awareness of the importance and necessity of SW/AI education, irrespective of school characteristics, region, educational experience, or prior involvement in SW and AI education. Nevertheless, the primary reasons for not implementing SW/AI education were identified as excessive workload and a lack of pedagogical expertise. An analysis of opinions on the essential conditions for implementing SW/AI education revealed that workload reduction, budget support, teacher training to enhance teacher competency, content distribution, expansion of subject-linked courses, and dedicated instructional time allocation were the major influencing factors. These findings indicate a significant demand for comprehensive instructional support and teacher capacity-building programs.

• 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%.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.325-327
• /
• 2024

국내외에서 AI기반 의료 솔루션 시장은 빠른 속도로 확장 중이며 이에 따른 다양한 의학 분야에서 많은 기법을 통한 의료 AI 시스템이 등장하고 있다. 그러나 기존 다양한 AI 연구가 이뤄짐에도 아직 중환자의 징후 예측에는 많은 어려움이 있다. 또한, 중환자의 경우 현재 의료진만으로 모든 환자를 필요한 시기에 진료하기엔 어려움이 있고 환자 상태 조기 예측이 필수적임을 관련 다양한 의학 기사를 통해 쉽게 인지할 수 있다. 본 연구에서는 위와 같은 문제점을 해결하고자 중환자의 진료 결과 데이터를 활용하여 환자의 진료 후 상태를 예측하는 모델을 생성하였다. '용인시산업진흥원'에서 제공하는 60만여 건에 달하는 환자 데이터를 수집하여, 중환자 상태 징후를 조기에 예측할 수 있는 머신러닝/딥러닝 기반 알고리즘으로 구현한 여러 모델에 대해 비교했을 때 딥러닝(DNN) 기반 모델이 약 92%의 분류 정확도를 측정할 수 있었다.

• Korean Journal of Radiology
• /
• v.22 no.8
• /
• pp.1225-1239
• /
• 2021

During the past decade, researchers have investigated the use of computer-aided mammography interpretation. With the application of deep learning technology, artificial intelligence (AI)-based algorithms for mammography have shown promising results in the quantitative assessment of parenchymal density, detection and diagnosis of breast cancer, and prediction of breast cancer risk, enabling more precise patient management. AI-based algorithms may also enhance the efficiency of the interpretation workflow by reducing both the workload and interpretation time. However, more in-depth investigation is required to conclusively prove the effectiveness of AI-based algorithms. This review article discusses how AI algorithms can be applied to mammography interpretation as well as the current challenges in its implementation in real-world practice.

• Communications of Mathematical Education
• /
• v.34 no.3
• /
• pp.215-234
• /
• 2020

With the advent of the AI, the need to use AI in the field of education is widely recognized. The purpose of this study is to shed light on how prospective mathematics teachers perceive the need for AI and the role of teachers in future mathematics education. As a result, with regard to teaching, prospective teachers recognized that the use of AI in school mathematics is a demand of a new era, that various types of lesson can be implemented, and that accurate knowledge and information can be delivered. On the other hand, they recognized that AI has limitations in having cognitive and emotional interactions with students. As for mathematics learning, the prospective teachers recognized that AI can provide individualized learning, be used for supplementary learning outside of school, and stimulate students' interest in learning. However, they also said that learning through AI could undermine students' ability to think on their own. With regard to assessment, the prospective teachers recognized that AI is objective, fair and can reduce teachers' workload, but they also said that AI has limitations in evaluating students' abilities in constructed-response items and in process-focused assessment. The roles of teachers that the prospective teachers think were to conduct a lesson, emotional interaction, unstructured assessment, and counseling, and those of AI were individualized learning, rote learning, structured assessment, and administrative works.

• Journal of Korean Society of Archives and Records Management
• /
• v.23 no.4
• /
• pp.179-200
• /
• 2023

Records management institutions in Korea generally face a situation where they lack the workforce to manage the vast amount of electronic records. If electronic records management tasks and archival information services can be automated and intelligentized, the workload can be reduced and the service satisfaction of users can be improved. Therefore, this study proposes to utilize "generative AI" technology in records management practice. To achieve this, the study first examined previous research that aimed to intelligently automate various tasks in the field of records management. The fundamental concepts of generative AI were subsequently outlined, and domestic cases of generative AI applications were investigated. Next, the scope of applying generative AI to the field of records management was defined, and specific utilization strategies were proposed based on this. Regarding the strategies, the effectiveness was verified by presenting results from applying commercial generative AI services or citing examples from other fields. Lastly, the benefits and implications of using generative AI technology in the field of records management, as well as limitations that must be addressed in advance, were presented. This study holds significance in that it identified tasks within the field of records management where generative AI technology can be integrated and proposed effective utilization strategies tailored to those tasks.

• Journal of Internet Computing and Services
• /
• v.11 no.1
• /
• pp.1-13
• /
• 2010

It is not easy to set RED(Random Early Detection) parameter according to environment in managing Network Device. Especially, it is more difficult to set parameter in the case of maintaining the constant service rate according to the change of environment. In this paper, we hypothesize the router that has Multi-core CPU in output queue and propose AI RED(Artificial Intelligence RED), which directly induces Genetic Algorithm of Artificial Intelligence in the output queue that is appropriate to the optimization of parameter according to RED environment, which is automatically adaptive to workload. As a result, AI RED Is simpler and finer than FuRED(Fuzzy-Logic-based RED), and RED parameter that AI RED searches through simulations is more adaptive to environment than standard RED parameter, providing the effective service. Consequently, the automation of management of RED parameter can provide a manager with the enhancement of efficiency in Network management.

• 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.

• Korean Journal of Radiology
• /
• v.23 no.10
• /
• pp.1009-1018
• /
• 2022

Objective: This study aimed to investigate the feasibility of using artificial intelligence (AI) to identify normal chest radiography (CXR) from the worklist of radiologists in a health-screening environment. Materials and Methods: This retrospective simulation study was conducted using the CXRs of 5887 adults (mean age ± standard deviation, 55.4 ± 11.8 years; male, 4329) from three health screening centers in South Korea using a commercial AI (Lunit INSIGHT CXR3, version 3.5.8.8). Three board-certified thoracic radiologists reviewed CXR images for referable thoracic abnormalities and grouped the images into those with visible referable abnormalities (identified as abnormal by at least one reader) and those with clearly visible referable abnormalities (identified as abnormal by at least two readers). With AI-based simulated exclusion of normal CXR images, the percentages of normal images sorted and abnormal images erroneously removed were analyzed. Additionally, in a random subsample of 480 patients, the ability to identify visible referable abnormalities was compared among AI-unassisted reading (i.e., all images read by human readers without AI), AI-assisted reading (i.e., all images read by human readers with AI assistance as concurrent readers), and reading with AI triage (i.e., human reading of only those rendered abnormal by AI). Results: Of 5887 CXR images, 405 (6.9%) and 227 (3.9%) contained visible and clearly visible abnormalities, respectively. With AI-based triage, 42.9% (2354/5482) of normal CXR images were removed at the cost of erroneous removal of 3.5% (14/405) and 1.8% (4/227) of CXR images with visible and clearly visible abnormalities, respectively. In the diagnostic performance study, AI triage removed 41.6% (188/452) of normal images from the worklist without missing visible abnormalities and increased the specificity for some readers without decreasing sensitivity. Conclusion: This study suggests the feasibility of sorting and removing normal CXRs using AI with a tailored cut-off to increase efficiency and reduce the workload of radiologists.

• Journal of Internet of Things and Convergence
• /
• v.8 no.6
• /
• pp.85-92
• /
• 2022

Demand for big data analysis and AI developers is increasing, but there is a lack of an education base to supply them. In this paper, by developing a cloud-based artificial intelligence education platform, the goal was to establish an environment in which practical practical training can be efficiently learned at low cost at educational institutions and IT companies. The development of the education platform was carried out by planning scenarios for each user, architecture design, screen design, implementation of development functions, and hardware construction. This training platform consists of a containerized workload, service management platform, lecture and development platform for instructors and students, and secured cloud stability through real-time alarm system and age test, CI/CD development environment, and reliability through docker image distribution. The development of this education platform is expected to expand opportunities to enter new businesses in the education field and contribute to fostering working-level human resources in the AI and big data fields.