Hyungshin Kim
YOU?
Author Swipe
View article: Genomic and Epidemiological Dynamics of Meropenem-Resistant GPSC1-CC320<i>Streptococcus pneumoniae</i>Serotype 19A Isolates from Children Under 5 Years of Age with Invasive Infections, 2018–2024
Genomic and Epidemiological Dynamics of Meropenem-Resistant GPSC1-CC320<i>Streptococcus pneumoniae</i>Serotype 19A Isolates from Children Under 5 Years of Age with Invasive Infections, 2018–2024 Open
The global rise of multidrug-resistant (MDR) Streptococcus pneumoniae serotype 19A despite widespread pneumococcal conjugate vaccine (PCV) use poses an emerging challenge for pediatric infectious disease control. In South Korea, the detect…
View article: Simplifying Two-Stage Object Detectors for On-Board Remote Sensing
Simplifying Two-Stage Object Detectors for On-Board Remote Sensing Open
Deep learning has been applied to object detection in remotely sensed images. Typically, remote sensing object detection is performed on the ground rather than on-board due to the limited computational resources available on embedded syste…
View article: Accelerated ElasticTrainer With Elastic Layer Selection
Accelerated ElasticTrainer With Elastic Layer Selection Open
On-device training consumes a lot of training time due to the limited computing resources of edge devices. ElasticTrainer reduces training time by selecting important tensors from the model and then training them. However, selection at the…
View article: Elastic-DETR: Making Image Resolution Learnable with Content-Specific Network Prediction
Elastic-DETR: Making Image Resolution Learnable with Content-Specific Network Prediction Open
Multi-scale image resolution is a de facto standard approach in modern object detectors, such as DETR. This technique allows for the acquisition of various scale information from multiple image resolutions. However, manual hyperparameter s…
View article: Simplifying Two-Stage Detectors for On-Device Inference in Remote Sensing
Simplifying Two-Stage Detectors for On-Device Inference in Remote Sensing Open
Deep learning has been successfully applied to object detection from remotely sensed images. Images are typically processed on the ground rather than on-board due to the computation power of the ground system. Such offloaded processing cau…
View article: DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors
DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors Open
Achieving constant accuracy in object detection is challenging due to the inherent variability of object sizes. One effective approach to this problem involves optimizing input resolution, referred to as a multi-resolution strategy. Previo…
View article: A Unified Compression Framework for Efficient Speech-Driven Talking-Face Generation
A Unified Compression Framework for Efficient Speech-Driven Talking-Face Generation Open
Virtual humans have gained considerable attention in numerous industries, e.g., entertainment and e-commerce. As a core technology, synthesizing photorealistic face frames from target speech and facial identity has been actively studied wi…
View article: Development of Fault Injection Testing Tool for Spacecraft Flight Software
Development of Fault Injection Testing Tool for Spacecraft Flight Software Open
인공위성의 탑재 소프트웨어는 고신뢰성을 갖는 임베디드 소프트웨어의 특징을 갖는다. 탑재 컴퓨터의 성능이 높아지면서, 탑재 소프트웨어는 보다 복잡한 임무를 수행하게 되었다. 탑재 소프트웨어는 소프트웨어 개발 표준에 따라 개발 주기 전체적으로 고신뢰성 소프트웨어 개발기법을 적용하고 있다. 이러한 고신뢰성 소프트웨어는 개발 과정에서 다양한 형태의 테스팅을 검증과정으로 수행해야 하는데, 본 연구에서는 인공위성 탑재 소프트웨어의 강인…
View article: Soft Error Fault Injection Test for Spacecraft Flight Software
Soft Error Fault Injection Test for Spacecraft Flight Software Open
인공위성은 태양과 심우주에서 발생한 우주 방사선 환경인 지구 주위의 궤도에서 동작해야 한다. 우주방사선은 위성의 탑재 컴퓨터의 하드웨어에 SEU(Single Event Upset)라는 에러를 유발할 수 있다. SEU는 비 파괴성 오류로 일시적으로 메모리나 레지스터에 저장된 비트를 반전시키는 소프트 에러다. 인공위성 탑재 컴퓨터는 이러한 소프트 에러를 감내해야 한다. 위성의 탑재 컴퓨터는 소프트 에러가 발생하더라도 오동작을 하…
View article: Depressed Mood Prediction of Elderly People with a Wearable Band
Depressed Mood Prediction of Elderly People with a Wearable Band Open
Depression in the elderly is an important social issue considering the population aging of the world. In particular, elderly living alone who has narrowed social relationship due to bereavement and retirement are more prone to be depressed…
View article: Time-Invariant Features-Based Online Learning for Long-Term Notification Management: A Longitudinal Study
Time-Invariant Features-Based Online Learning for Long-Term Notification Management: A Longitudinal Study Open
The increasing number of daily notifications generated by smartphones and wearable devices increases mental burdens, deteriorates productivity, and results in energy waste. These phenomena are exacerbated by emerging use cases in which use…
View article: Software-Level Memory Regulation to Reduce Execution Time Variation on Multicore Real-Time Systems
Software-Level Memory Regulation to Reduce Execution Time Variation on Multicore Real-Time Systems Open
Modern real-time embedded systems are equipped with multi-core processors to execute computationally intensive tasks. In multi-core architecture, last-level cache memory is shared by cores. The shared cache becomes a non-deterministic reso…
View article: Test Case Generation Method for Increasing Software Reliability in Safety-Critical Embedded Systems
Test Case Generation Method for Increasing Software Reliability in Safety-Critical Embedded Systems Open
Finite-state machines (FSMs) and the W method have been widely used in software testing. However, the W method fails to detect post-processing errors in the implementation under test (IUT) because it ends testing when it encounters a previ…
View article: Execution Model to Reduce the Interference of Shared Memory in ARINC 653 Compliant Multicore RTOS
Execution Model to Reduce the Interference of Shared Memory in ARINC 653 Compliant Multicore RTOS Open
Multicore architecture is applied to contemporary avionics systems to deal with complex tasks. However, multicore architectures can cause interference by contention because the cores share hardware resources. This interference reduces the …
View article: Hardware Resource Analysis in Distributed Training with Edge Devices
Hardware Resource Analysis in Distributed Training with Edge Devices Open
When training a deep learning model with distributed training, the hardware resource utilization of each device depends on the model structure and the number of devices used for training. Distributed training has recently been applied to e…
View article: Reducing Smartwatch Users’ Distraction with Convolutional Neural Network
Reducing Smartwatch Users’ Distraction with Convolutional Neural Network Open
Smartwatches provide a useful feature whereby users can be directly aware of incoming notifications by vibration. However, such prompt awareness causes high distractions to users. To remedy the distraction problem, we propose an intelligen…
View article: Translated Block Optimization of Dynamic Binary Translator for Embedded System Virtualization
Translated Block Optimization of Dynamic Binary Translator for Embedded System Virtualization Open
View article: Advanced Indoor Zone Detection with Bluetooth and Ultrasound of Smartphone
Advanced Indoor Zone Detection with Bluetooth and Ultrasound of Smartphone Open
Indoor zone-based services have continuously become popular by increased prevalence of smartphones. Bluetooth and ultrasound can be used for zone detection. However, bluetooth does not guarantee precise zone detection if the signal degrade…
View article: QDroid: Mobile Application Quality Analyzer for App Market Curators
QDroid: Mobile Application Quality Analyzer for App Market Curators Open
Low quality mobile applications have damaged the user experience. However, in light of the number of applications, quality analysis is a daunting task. For that reason, QDroid is proposed, an automated quality analyzer that detects the pre…