• Electronics and Telecommunications Trends
• /
• v.34 no.1
• /
• pp.98-110
• /
• 2019

Machine learning has been applied to medical imaging and has shown an excellent recognition rate. Recently, there has been much interest in preventive medicine. If data are accessible, machine learning packages can be used easily in digital healthcare fields. However, it is necessary to prepare the data in advance, and model evaluation and tuning are required to construct a reliable model. On average, these processes take more than 80% of the total effort required. In this study, we describe the basic concepts of machine learning, pre-processing and visualization of datasets, feature engineering for reliable models, model evaluation and tuning, and the latest trends in popular machine learning frameworks. Finally, we survey a explainable machine learning analysis tool and will discuss the future direction of machine learning.

• Electronics and Telecommunications Trends
• /
• v.34 no.1
• /
• pp.111-122
• /
• 2019

As society develops, the demand for safety and security services increases. Developed nations such as the United States use advanced technology to lower crime rate and promote intelligent security services. First, this article examines intelligent systems that are used for monitoring and detecting crimes and dangerous situations. Recently, we have been studying technologies that enable preemptive responses through prediction of crime and hazardous situations. In this paper, we examine the cases of security services based on a crime/risk prediction model and explain the structure and major technologies of an intelligent security system. In addition, we propose a direction for technological development for achieving future security services.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.32-42
• /
• 2019

The performance of machine learning algorithms significantly depends on how a configuration of hyperparameters is identified and how a neural network architecture is designed. However, this requires expert knowledge of relevant task domains and a prohibitive computation time. To optimize these two processes using minimal effort, many studies have investigated automated machine learning in recent years. This paper reviews the conventional random, grid, and Bayesian methods for hyperparameter optimization (HPO) and addresses its recent approaches, which speeds up the identification of the best set of hyperparameters. We further investigate existing neural architecture search (NAS) techniques based on evolutionary algorithms, reinforcement learning, and gradient derivatives and analyze their theoretical characteristics and performance results. Moreover, future research directions and challenges in HPO and NAS are described.

• Clinical and Experimental Pediatrics
• /
• v.62 no.4
• /
• pp.113-118
• /
• 2019

Inappropriate antibiotic use is the most important factor causing increased bacterial resistance to antibiotics, thus affecting patient outcomes. Multidrug-resistant bacteria have become a serious public health threat, causing significant morbidity and mortality worldwide. In Korea, the burden of antibiotic-resistant bacteria has become an important public health issue. There is increasing evidence of overuse and misuse of antibiotics in Korea, as observed in cohorts with large sample sizes. Antibiotic use among children should receive particular attention because of the frequency of community-associated infections among this population and the elevated risk of transmission. Recent studies from Korea have demonstrated that the use of broad-spectrum antibiotics, either for inpatient or outpatient treatment, has increased among many age groups, especially children. In this review, we aim to describe the patterns of antibiotic prescription and evaluate recent trends in antibiotic use among children. Coordinated efforts toward communication and education in order to address misunderstandings regarding antibiotic use, involving interprofessional antimicrobial stewardship programs, are required in the near future.

• Electronics and Telecommunications Trends
• /
• v.34 no.5
• /
• pp.91-98
• /
• 2019

Optical frequency comb generators have been investigated as a signal source capable of generating highly stabilized ultrafast pulse lasers. The precise control of the optical frequency comb spacing by RF clock signals has led to a revolutionary paradigm shift in the precise measurement of time and frequency. Optical frequency combs also have advantages such as stable frequency spacing, stable number of lines, and robustness. Owing to these characteristics, optical frequency combs have been applied to the fields of high precision optical clock, communication, spectroscopy, waveform generation, and astronomy. In this article, we introduce the properties (i.e., generation methods, advantages, and so on) of various optical frequency combs, and discuss the expected future technological trends and applications.

• Electronics and Telecommunications Trends
• /
• v.34 no.5
• /
• pp.113-126
• /
• 2019

Based on the accumulation of medical big data, advances in medical artificial intelligence technology facilitate the timely treatment of disease through the reading the medical images and the increase of prediction speed and accuracy of diagnoses. In addition, these advances are expected to spark significant innovations in reducing medical costs and improving care quality. There are already approximately 40 FDA approved products in the US, and more than 10 products with K-FDA approval in Korea. Medical applications and services based on artificial intelligence are expected to spread rapidly in the future. Furthermore, the evolution of medical artificial intelligence technology is expanding the boundaries or limits of various related issues such as reference standards and specifications, ethical and clinical validation issues, and the harmonization of international regulatory systems.

• Electronics and Telecommunications Trends
• /
• v.34 no.3
• /
• pp.55-64
• /
• 2019

In drone-assisted wireless sensor networks, drones collect data from sensors in an energy-efficient manner and quickly distribute urgent information to sensor nodes. This article introduces recent communication and security schemes for drone-assisted wireless sensor networks. For the communication schemes, we introduce data collection optimization schemes, drone position and movement optimization schemes, and drone flight path optimization schemes. For the security schemes, we introduce authentication and key management schemes, cluster formation schemes, and cluster head election schemes. Then, we present some enhancement methodologies for these communication and security schemes. As a conclusion, we present some interesting future work items.

• Electronics and Telecommunications Trends
• /
• v.36 no.4
• /
• pp.145-153
• /
• 2021

Data imputation is a crucial issue in data analysis because quality data are highly correlated with the performance of AI models. Particularly, it is difficult to collect quality time-series data for uncertain situations (for example, electricity blackout, delays for network conditions). Thus, it is necessary to research effective methods of time-series data imputation. Many studies on time-series data imputation can be divided into 5 parts, including statistical based, matrix-based, regression-based, deep learning (RNN and GAN) based methodologies. This study reviews and organizes these methodologies. Recently, deep learning-based imputation methods are developed and show excellent performance. However, it is associated to some computational problems that make it difficult to use in real-time system. Thus, the direction of future work is to develop low computational but high-performance imputation methods for application in the real field.

• Journal of Contemporary Eastern Asia
• /
• v.19 no.2
• /
• pp.1-19
• /
• 2020

Trends toward an influx of new migrants have been pronounced in East Asia through a development we call the third round of migrant incorporation. At the same time, other features of East Asian societies, such as strong levels of ethnic nationalism, have changed little, posing challenges to multiculturalism. In this introduction to this special issue, we review the latest research trends broadly concerning multiculturalism, migrant groups that have received little attention, racism and xenophobia. We first discuss the state of migrant incorporation in East Asia and the limits of multiculturalism in this region, where various features of the developmental state persist. We then introduce research on voices opposing multiculturalism in East Asia. This introduction highlights what is peculiar―and ordinary―about migrant incorporation and the associated challenges in East Asia.

• Electronics and Telecommunications Trends
• /
• v.36 no.4
• /
• pp.13-22
• /
• 2021

Among the activities of 3GPP for operating 5G-based unmanned aerial vehicles, we introduce several use cases of UAVs in 5G mobile communication such as radio access node onboard UAV, simultaneous support data transmission for UAVs and eMBB users, autonomous UAVs controlled by AI, isolated deployment of radio access through UAV, and separation of UAV service area. From this, we further summarize 5G mobile communication requirements for UAVs, including definition and operational criteria of UAS, UAS remote identification requirements, UAS usage requirements, and performance requirements. Finally, regarding 5G mobile communication-based UAS connectivity, identification and tracking support, we discuss the 3GPP UAV architecture, seven major problems, the proposed solutions to each problem, and propose the results for future specification work.