arXiv subjects

Jinwoo Lee

Publications and source records attributed to Jinwoo Lee.

26 records · Page 2Linked to original sources

arXiv2024

Intelligent upper-limb exoskeleton integrated with soft wearable bioelectronics and deep-learning for human intention-driven strength augmentation based on sensory feedback

The age and stroke-associated decline in musculoskeletal strength degrades the ability to perform daily human tasks using the upper extremities. Although there are a few examples of exoskeletons, they need manual operations due to the absence of sensor feedback and no intention prediction of movements. Here, we introduce an intelligent upper-limb exoskeleton system that uses cloud-based deep learning to predict human intention for strength augmentation. The embedded soft wearable sensors provide sensory feedback by collecting real-time muscle signals, which are simultaneously computed to determine the user's intended movement. The cloud-based deep-learning predicts four upper-limb joint motions with an average accuracy of 96.2% at a 200-250 millisecond response rate, suggesting that the exoskeleton operates just by human intention. In addition, an array of soft pneumatics assists the intended movements by providing 897 newton of force and 78.7 millimeter of displacement at maximum. Collectively, the intent-driven exoskeleton can augment human strength by 5.15 times on average compared to the unassisted exoskeleton. This report demonstrates an exoskeleton robot that augments the upper-limb joint movements by human intention based on a machine-learning cloud computing and sensory feedback.

cs.RO↗

arXiv2023

Novel Smart N95 Filtering Facepiece Respirator with Real-time Adaptive Fit Functionality and Wireless Humidity Monitoring for Enhanced Wearable Comfort

The widespread emergence of the COVID-19 pandemic has transformed our lifestyle, and facial respirators have become an essential part of daily life. Nevertheless, the current respirators possess several limitations such as poor respirator fit because they are incapable of covering diverse human facial sizes and shapes, potentially diminishing the effect of wearing respirators. In addition, the current facial respirators do not inform the user of the air quality within the smart facepiece respirator in case of continuous long-term use. Here, we demonstrate the novel smart N-95 filtering facepiece respirator that incorporates the humidity sensor and pressure sensory feedback-enabled self-fit adjusting functionality for the effective performance of the facial respirator to prevent the transmission of airborne pathogens. The laser-induced graphene (LIG) constitutes the humidity sensor, and the pressure sensor array based on the dielectric elastomeric sponge monitors the respirator contact on the face of the user, providing the sensory information for a closed-loop feedback mechanism. As a result of the self-fit adjusting mode along with elastomeric lining, the fit factor is increased by 3.20 and 5 times at average and maximum respectively. We expect that the experimental proof-of-concept of this work will offer viable solutions to the current commercial respirators to address the limitations.

eess.SP↗

arXiv2023

Exploring Train and Test-Time Augmentations for Audio-Language Learning

In this paper, we aim to unveil the impact of data augmentation in audio-language multi-modal learning, which has not been explored despite its importance. We explore various augmentation methods at not only train-time but also test-time and find out that proper data augmentation can lead to substantial improvements. Specifically, applying our proposed audio-language paired augmentation PairMix, which is the first multi-modal audio-language augmentation method, outperforms the baselines for both automated audio captioning and audio-text retrieval tasks. To fully take advantage of data augmentation, we also present multi-level test-time augmentation (Multi-TTA) for the test-time. We successfully incorporate the two proposed methods and uni-modal augmentations and achieve 47.5 SPIDEr on audio captioning, which is an 18.2% relative increase over the baseline. In audio-text retrieval, the proposed methods also show an improvement in performance as well.

cs.SD↗

arXiv2022

Optimal Parking Planning for Shared Autonomous Vehicles

Parking is a crucial element of the driving experience in urban transportation systems. Especially in the coming era of Shared Autonomous Vehicles (SAVs), parking operations in urban transportation networks will inevitably change. Parking stations will serve as storage places for unused vehicles and depots that control the level-of-service of SAVs. This study presents an Analytical Parking Planning Model (APPM) for the SAV environment to provide broader insights into parking planning decisions. Two specific planning scenarios are considered for the APPM: (i) Single-zone APPM (S-APPM), which considers the target area as a single homogeneous zone, and (ii) Two-zone APPM (T-APPM), which considers the target area as two different zones, such as city center and suburban area. S-APPM offers a closed-form solution to find the optimal density of parking stations and parking spaces and the optimal number of SAV fleets, which is beneficial for understanding the explicit relationship between planning decisions and the given environments, including demand density and cost factors. In addition, to incorporate different macroscopic characteristics across two zones, T-APPM accounts for inter- and intra-zonal passenger trips and the relocation of vehicles. We conduct a case study to demonstrate the proposed method with the actual data collected in Seoul Metropolitan Area, South Korea. Sensitivity analyses with respect to cost factors are performed to provide decision-makers with further insights. Also, we find that the optimal densities of parking stations and spaces in the target area are much lower than the current situations.

eess.SY↗

arXiv2021

CTRL-C: Camera calibration TRansformer with Line-Classification

Single image camera calibration is the task of estimating the camera parameters from a single input image, such as the vanishing points, focal length, and horizon line. In this work, we propose Camera calibration TRansformer with Line-Classification (CTRL-C), an end-to-end neural network-based approach to single image camera calibration, which directly estimates the camera parameters from an image and a set of line segments. Our network adopts the transformer architecture to capture the global structure of an image with multi-modal inputs in an end-to-end manner. We also propose an auxiliary task of line classification to train the network to extract the global geometric information from lines effectively. Our experiments demonstrate that CTRL-C outperforms the previous state-of-the-art methods on the Google Street View and SUN360 benchmark datasets.

cs.CV↗

arXiv2020

Neural Geometric Parser for Single Image Camera Calibration

We propose a neural geometric parser learning single image camera calibration for man-made scenes. Unlike previous neural approaches that rely only on semantic cues obtained from neural networks, our approach considers both semantic and geometric cues, resulting in significant accuracy improvement. The proposed framework consists of two networks. Using line segments of an image as geometric cues, the first network estimates the zenith vanishing point and generates several candidates consisting of the camera rotation and focal length. The second network evaluates each candidate based on the given image and the geometric cues, where prior knowledge of man-made scenes is used for the evaluation. With the supervision of datasets consisting of the horizontal line and focal length of the images, our networks can be trained to estimate the same camera parameters. Based on the Manhattan world assumption, we can further estimate the camera rotation and focal length in a weakly supervised manner. The experimental results reveal that the performance of our neural approach is significantly higher than that of existing state-of-the-art camera calibration techniques for single images of indoor and outdoor scenes.

cs.CV↗

arXiv2012

Hidden Complexity in the Isomerization Dynamics of Holliday Junctions

A plausible consequence of rugged energy landscapes of biomolecules is that functionally competent folded states may not be unique, as is generally assumed. Indeed, molecule-to-molecule variations in the dynamics of enzymes and ribozymes under folding conditions have recently been identified in single molecule experiments. However, systematic quantification and the structural origin of the observed complex behavior remain elusive. Even for a relatively simple case of isomerization dynamics in Holliday Junctions (HJs), molecular heterogeneities persist over a long observation time (Tobs ~ 40 sec). Here, using concepts in glass physics and complementary clustering analysis, we provide a quantitative method to analyze the smFRET data probing the isomerization in HJ dynamics. We show that ergodicity of HJ dynamics is effectively broken; as a result, the conformational space of HJs is partitioned into a folding network of kinetically disconnected clusters. While isomerization dynamics in each cluster occurs rapidly as if the associated conformational space is fully sampled, distinct patterns of time series belonging to different clusters do not interconvert on Tobs. Theory suggests that persistent heterogeneity of HJ dynamics is a consequence of internal multiloops with varying sizes and flexibilities frozen by Mg2+ ions. An annealing experiment using Mg2+ pulse that changes the Mg2+ cocentration from high to low to high values lends support to this idea by explicitly showing that interconversions can be driven among trajectories with different patterns.

cond-mat.soft↗

arXiv2009

F. John's stability conditions vs. A. Carasso's SECB constraint for backward parabolic problems

In order to solve backward parabolic problems F. John [{\it Comm. Pure. Appl. Math.} (1960)] introduced the two constraints "$\|u(T)\|\le M$" and $\|u(0) - g \| \le δ$ where $u(t)$ satisfies the backward heat equation for $t\in(0,T)$ with the initial data $u(0).$ The {\it slow-evolution-from-the-continuation-boundary} (SECB) constraint has been introduced by A. Carasso in [{\it SIAM J. Numer. Anal.} (1994)] to attain continuous dependence on data for backward parabolic problems even at the continuation boundary $t=T$. The additional "SECB constraint" guarantees a significant improvement in stability up to $t=T.$ In this paper we prove that the same type of stability can be obtained by using only two constraints among the three. More precisely, we show that the a priori boundedness condition $\|u(T)\|\le M$ is redundant. This implies that the Carasso's SECB condition can be used to replace the a priori boundedness condition of F. John with an improved stability estimate. Also a new class of regularized solutions is introduced for backward parabolic problems with an SECB constraint. The new regularized solutions are optimally stable and we also provide a constructive scheme to compute. Finally numerical examples are provided.

math.NA↗