Younho Nam

Dr. Younho Nam

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 September 2023 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Verified
Journal Article
Open access
JKJiha Kim
Jiha Kim
YNYounho Nam
Younho Nam
JLJungeun Lee
Jungeun Lee
YSYoung-Joo Suh
Young-Joo Suh
IHInseok Hwang
Inseok Hwang
Although many works bring exercise monitoring to smartphone and smartwatch, inertial sensors used in such systems require device to be in motion to detect exercises. We introduce ProxiFit, a highly practical on-device exercise monitoring system capable of classifying and counting exercises even if the device stays still. Utilizing novel proximity sensing of natural magnetism in exercise equipment, ProxiFit brings (1) a new category of exercise not involving device motion such as lower-body machine exercise, and (2) a new off-body exercise monitoring mode where a smartphone can be conveniently viewed in front of the user during workouts. ProxiFit addresses common issues of faint magnetic sensing by choosing appropriate preprocessing, negating adversarial motion artifacts, and designing a lightweight yet noise-tolerant classifier. Also, application-specific challenges such as a wide variety of equipment and the impracticality of obtaining large datasets are overcome by devising a unique yet challenging training policy. We evaluate ProxiFit on up to 10 weight machines (5 lower- and 5 upper-body) and 4 free-weight exercises, on both wearable and signage mode, with 19 users, at 3 gyms, over 14 months, and verify robustness against user and weather variations, spatial and rotational device location deviations, and neighboring machine interference.

8 October 2023
Verified
Conference Paper
Open access
JKJiha Kim
Jiha Kim
YNYounho Nam
Younho Nam
JLJungeun Lee
Jungeun Lee
Young-Joo SuhYoung-Joo Suh
Young-Joo Suh
IHInseok Hwang
Inseok Hwang
Although many works bring exercise monitoring to smartphones and smartwatches, inertial sensors used in such systems require the device to be in motion to detect exercises. We demonstrate our full paper ProxiFit, a practical on-device exercise monitoring system capable of classifying and counting exercises despite the device being still. ProxiFit remotely detects adjacent exercises with magnetic field fluctuations induced by the motions of ferrous exercise equipment. Novel proximal sensing nature of ProxiFit (1) extends coverage of wearable exercise monitoring to exercises that do not involve device motion such as lower-body machine exercise, and (2) brings a new off-body exercise monitoring mode with line-of-sight screen visibility, namely signage mode, to a smartphone mounted in front of the user.

8 December 2025 in Sensors
Verified
Journal Article
Open access
PDF file
YNYounho Nam
Younho Nam
SSSu Yeon Shim
Su Yeon Shim
KSKyeong Su Shin
Kyeong Su Shin
Young-Joo SuhYoung-Joo Suh
Young-Joo Suh
Monitoring the condition of belt conveyor idlers is critical for ensuring safe and efficient operation of industrial conveying systems. However, existing methods often suffer from limited scalability and delayed fault detection, particularly under variable environmental conditions. In this work, we propose MIRA, a transformer-based framework for monitoring idler roller anomalies, which detects and localizes faults using acoustic and vibration signals collected from low-cost sensors. MIRA employs a masked transformer-based autoencoder trained in an unsupervised manner to reconstruct normal patterns and detect deviations via reconstruction error. MIRA can also infer the fault location, enabling spatially aware anomaly detection without the need for labeled data. We validated the system on a custom-built conveyor belt testbed equipped with sensor units, each measuring sound and two-axis vibration signals. We evaluated MIRA on four types of idler faults across 14 roller locations and 6 belt speeds. The results show that MIRA achieves an anomaly detection accuracy of 98.70% and a fault localization accuracy of 96.09%, demonstrating its robustness and practical applicability in complex operational settings.

14 December 2024 in Sensors
Verified
Journal Article
Open access
PDF file
KSKyeong Su Shin
Kyeong Su Shin
YNYounho Nam
Younho Nam
Young-Joo SuhYoung-Joo Suh
Young-Joo Suh
Belt conveyor idlers are freely rotating idlers supporting the belt of a conveyor, and can induce severe frictional damage to the belt as they fail. Therefore, fast and accurate detection of idler faults is crucial for the effective maintenance of belt conveyor systems. In this article, we implement and evaluate the performance of an idler stall detection system based on a multivariate deep learning model using accelerometers and microphone sensor data. Emphasis is place on the scalability of the system, as large belt conveyor installations can span multiple kilometers, potentially requiring hundreds or even thousands of sensor units to monitor. The accuracy of the proposed system are analyzed and reported, along with its network bandwidth and energy requirements. The results suggest that while implementing accurate large-scale idler stall detection is feasible, careful consideration must be paid to observing the available network bandwidth and energy budget in order to avoid prolonged downtimes.

22 May 2026 in IEEE Sensors Journal
Verified
Journal Article
Closed access
KSKyeong Su Shin
Kyeong Su Shin
YNYounho Nam
Younho Nam
Young-Joo SuhYoung-Joo Suh
Young-Joo Suh
Conveyor belt failures can inflict significant financial losses on operators by stalling operations. However, belt monitoring systems for preventing such failures are not widely adopted due to their cost and maintenance burden. To address this issue, we propose a Wi-Fi sensing–based conveyor belt wear monitoring system that continuously monitors changes in belt thickness to enable early detection or prediction of failures. By transmitting Wi-Fi frames through the belt and monitoring changes in Wi-Fi channel state information (CSI) caused by the dielectric properties of the belt material, the belt thickness can be estimated. As the belt wears and thins, Wi-Fi signals are less affected by its dielectric properties. Therefore, using a machine learning–based regressor, belt thickness can be estimated from CSI measurements. We validate this proposed approach through a prototype implementation on a conveyor belt testbed. A belt was intentionally ground down to various thicknesses and then installed on the testbed. Wi-Fi sensor units were mounted on the testbed, and data samples were collected. Using the obtained samples, we trained a multilayer perceptron–based belt thickness estimation model and achieved a root mean square error of 0.2292 mm. The proposed system offers a cost-effective and low-maintenance alternative to conventional belt monitoring solutions, as it does not require active electronic components to be mounted directly on the belt conveyor.

23 July 2025 in Electronics
Verified
Journal Article
Open access
PDF file
MKMinseok Kim
Minseok Kim
YNYounho Nam
Younho Nam
JKJinyou Kim
Jinyou Kim
Young-Joo SuhYoung-Joo Suh
Young-Joo Suh
Accurate heading direction tracking is essential for immersive VR/AR, spatial audio rendering, and robotic navigation. Existing IMU-based methods suffer from drift and vibration artifacts, vision-based approaches require LoS and raise privacy concerns, and RF techniques often need dedicated infrastructure. We propose UDirEar, a COTS UWB device-based system that estimates user heading using solely high-level UWB information like distance and unit direction. By initializing an EKF with each user’s constant interaural distance, UDirEar compensates for the earbuds’ roto-translational motion without additional sensors. We evaluate UDirEar on a step-motor-driven dummy head against an IMU-only baseline (MAE 30.8°), examining robustness across dummy head–initiator distances, elapsed time, EKF calibration conditions, and NLoS scenarios. UDirEar achieves a mean absolute error of 3.84° and maintains stable performance under all tested conditions.