• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.57-58
• /
• 2022

Sleep apnea (SA) is a common chronic sleep disorder that disrupts breathing during sleep. Clinically, the standard for diagnosing SA involves nocturnal polysomnography (PSG). However, this requires expert human intervention and considerable time, which limits the availability of SA diagnoses in public health sectors. Therefore, ECG-based methods for SA detection have been proposed to automate the PSG procedure and reduce its discomfort. We propose a preprocessing method to convert the one-dimensional time series of ECG into two-dimensional images using the Gramian Angular Field (GAF) algorithm, extract temporal features, and use a two-dimensional convolutional neural network for classification. The results of this study demonstrated that the proposed method can perform SA detection with specificity, sensitivity, accuracy, and area under the curve (AUC) of 88.89%, 81.50%, 86.11%, and 0.85, respectively. Our experimental results show that SA is successfully classified by extracting preprocessing transforms with temporal features.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.4
• /
• pp.751-756
• /
• 2024

The accuracy of the model and the explanation of the results are important factors that should be considered simultaneously Recently, applications of explainable artificial intelligence are increasing, and it is especially widely applied in the financial field where interpretation of results is important. In this paper, we compare the performance of open API credit evaluation data using various machine learning techniques. In addition, existing financial logic is verified through explainable artificial intelligence technologies, SHAP and LIME. Accordingly, it is expected to demonstrate the applicability of machine learning in the financial market.

• Journal of muscle and joint health
• /
• v.29 no.1
• /
• pp.50-59
• /
• 2022

Purpose: This qualitative study aimed to explore the experiences of patients with diabetes provided with medication monitoring using an artificial intelligence-based smartwatch. Methods: Giorgi's descriptive phenomenological methodology was applied to collect and analyze data from November 9 to December 23, 2021. The study samples were recruited by convenience sampling, and even patients with diabetes participated in in-depth interviews via video conference and telephone calls or face-to-face visits. Results: Ten sub-themes and four themes were finally revealed. The four themes were as follows: journey with unfamiliar devices, a less-than-acceptable smartwatch, insufficient functions and content for patients with diabetes to use, and efforts for regular medication behaviors and daily monitoring of patient's health conditions. Conclusion: To effectively manage diabetic conditions using digital healthcare technologies, nursing interventions were needed to identify personal needs and consider technological, psychological, aesthetic, and socioeconomic aspects of wearable devices.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.4
• /
• pp.97-115
• /
• 2023

In South Korea, chronic kidney disease(CKD) impacts around 4.6 million adults, leading to a high reliance on hemodialysis. For effective dialysis, vascular access is crucial, with decisions about vascular surgeries often made during dialysis sessions. Anticipating these needs could improve dialysis quality and patient comfort. This study investigates the use of Artificial Intelligence(AI) to predict the timing of surgeries for dialysis vessels, an area not extensively researched. We've developed an AI algorithm using predictive maintenance methods, transitioning from machine learning to a more advanced deep learning approach with Long Short-Term Memory(LSTM) models. The algorithm processes variables such as venous pressure, blood flow, and patient age, demonstrating high effectiveness with metrics exceeding 0.91. By shortening the data collection intervals, a more refined model can be obtained. Implementing this AI in clinical practice could notably enhance patient experience and the quality of medical services in dialysis, marking a significant advancement in the treatment of CKD.

• Clinical Endoscopy
• /
• v.57 no.3
• /
• pp.302-308
• /
• 2024

With incessant advances in information technology and its implications in all domains of our lives, artificial intelligence (AI) has emerged as a requirement for improved machine performance. This brings forth the query of how this can benefit endoscopists and improve both diagnostic and therapeutic endoscopy in each part of the gastrointestinal tract. Additionally, it also raises the question of the recent benefits and clinical usefulness of this new technology in daily endoscopic practice. There are two main categories of AI systems: computer-assisted detection (CADe) for lesion detection and computer-assisted diagnosis (CADx) for optical biopsy and lesion characterization. Quality assurance is the next step in the complete monitoring of high-quality colonoscopies. In all cases, computer-aided endoscopy is used, as the overall results rely on the physician. Video capsule endoscopy is a unique example in which a computer operates a device, stores multiple images, and performs an accurate diagnosis. While there are many expectations, we need to standardize and assess various software packages. It is important for healthcare providers to support this new development and make its use an obligation in daily clinical practice. In summary, AI represents a breakthrough in digestive endoscopy. Screening for gastric and colonic cancer detection should be improved, particularly outside expert centers. Prospective and multicenter trials are mandatory before introducing new software into clinical practice.

• ETRI Journal
• /
• v.44 no.3
• /
• pp.476-490
• /
• 2022

With the recent advances in technology, automatic speech recognition (ASR) has been widely used in real-world applications. The efficiency of converting large amounts of speech into text accurately with limited resources has become more vital than ever. In this study, we propose a method to rapidly recognize a large speech database via a transformer-based end-to-end model. Transformers have improved the state-of-the-art performance in many fields. However, they are not easy to use for long sequences. In this study, various techniques to accelerate the recognition of real-world speeches are proposed and tested, including decoding via multiple-utterance-batched beam search, detecting end of speech based on a connectionist temporal classification (CTC), restricting the CTC-prefix score, and splitting long speeches into short segments. Experiments are conducted with the Librispeech dataset and the real-world Korean ASR tasks to verify the proposed methods. From the experiments, the proposed system can convert 8 h of speeches spoken at real-world meetings into text in less than 3 min with a 10.73% character error rate, which is 27.1% relatively lower than that of conventional systems.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.6-10
• /
• 2023

High-potential data can be predicted and stored in the cache to prevent cache misses, thus reducing the processor's request and wait times. As a result, the processor can work non-stop, hiding memory latency. By utilizing the temporal/spatial locality of memory access, the prefetcher introduced to improve the performance of these computers predicts the following memory address will be accessed. We propose a prefetcher that applies the GRU model, which is advantageous for handling time series data. Display the currently accessed address in binary and use it as training data to train the Gated Recurrent Unit model based on the difference (delta) between consecutive memory accesses. Finally, using a GRU model with learned memory access patterns, the proposed data prefetcher predicts the memory address to be accessed next. We have compared the model with the multi-layer perceptron, but our prefetcher showed better results than the Multi-Layer Perceptron.

• Journal of Internet of Things and Convergence
• /
• v.8 no.6
• /
• pp.21-26
• /
• 2022

This study aims to enhance the cultivation of SW·AI basic competencies of middle school students by forming and distributing SW·AI education programs for middle school students who form the basis of their lives. In addition, by planning SW·AI education programs in connection with the regular curriculum, it is intended to serve as a cornerstone for the public education of SW·AI education that will be implemented from 2025. To this end, the concept of SW and AI in middle school was first defined and a plan to link software/artificial intelligence learning factors to the regular curriculum was proposed, and based on this, SW·AI education programs for middle school students were prepared. Based on literature research, the understanding of artificial intelligence technology, the value of data, and the use of artificial intelligence technology in real life were set as SW·AI education contents, and educational programs were organized by linking them with the current middle school curriculum. All SW·AI education was organized in the form of practice rather than theory so that classes could be conducted centered on participants, and the purpose of the course was to cultivate the ability to use artificial intelligence technology in real life based on understanding artificial intelligence technology.

• International Journal of Advanced Culture Technology
• /
• v.10 no.1
• /
• pp.36-41
• /
• 2022

Cyberbullying and digital drama are on the rise among students. Therefore, this paper proposes an educational program that can enhance students' ability to use artificial intelligence(AI) technology and develop the power to respond to digital drama. In order to understand the effect of the proposed education program, this education was applied on a trial basis to 205 middle school students residing in South Korea. Moreover, the change of coping ability to the digital drama was observed before and after education. After applying for the educational program, the students' empathy(t=-5.506, p<0.001), peer conflict resolution(t=-3.842, p<0.01), and peer mediation(t=-4.213, p<0.001) improved, and did not significantly affect their anger control ability(t=-0.272, p>0.05). The educational program proposed in this paper uses AI to make it more attractive for students familiar with digital devices to participate in education and increase their educational concentration. This paper has its limitations as it is a study only for middle school students in South Korea. However, it is significant that the educational program proposed in this paper prevented the recently increased digital drama and led to a crucial change in coping ability.

• 한국정보교육학회:학술대회논문집
• /
• 2021.08a
• /
• pp.31-36
• /
• 2021

In the era of the 4th industrial revolution represented by AI technology, various AI education is being conducted in the education field. However, AI education in the educational field is mostly one-off project education or teacher-centered education. In order to practice student-centered, field-oriented education, an artificial intelligence education program was developed based on design thinking. The AI education program based on design thinking will improve understanding and ability to use AI through the process of solving everyday problems with AI, and will develop the ability to create new values beyond understanding AI. It is expected that various AI education will take place in the educational field through design thinking-based artificial intelligence education programs.