A5082634431- Traffic Prediction and Management Techniques
- Traffic control and management
- Transportation Planning and Optimization
- Autonomous Vehicle Technology and Safety
- Human Mobility and Location-Based Analysis
- Data Management and Algorithms
- Traffic and Road Safety
- Transportation and Mobility Innovations
- Mechanical Circulatory Support Devices
- Time Series Analysis and Forecasting
- Cardiovascular Function and Risk Factors
- Human-Automation Interaction and Safety
- Hydraulic and Pneumatic Systems
- Ferroelectric and Piezoelectric Materials
- Plasma Diagnostics and Applications
- Silicon Carbide Semiconductor Technologies
- Energy Load and Power Forecasting
- Fuzzy Logic and Control Systems
- Cardiac Structural Anomalies and Repair
- Fuel Cells and Related Materials
- Education, Safety, and Science Studies
- Smart Parking Systems Research
- Technology and Data Analysis
- Machine Fault Diagnosis Techniques
- Power System Reliability and Maintenance
University of Minnesota
2023-2025
Korea University
2004-2024
Sejong University
2017-2024
McGill University
2022-2023
SK Group (South Korea)
2023
Korea Advanced Institute of Science and Technology
2017-2022
New York University
2018
Seoul National University of Science and Technology
2014
Focus (Germany)
2014
Faculty of Media
2014
Nowadays, Automated Vehicle (AV) technology is gaining attention as a candidate to improve the efficiency of Bus Rapid Transit (BRT) systems. However, there are still some challenges in AV including limited perception range and lack cooperation capability mixed traffic situations with drivers. The emerging Connected Vehicles (CAVs) Cooperative Intelligent Transportation System (C-ITS) offer an unprecedented opportunity solve such challenges. As result, this study presents framework for BRT...
As the number of various positioning sensors and location-based devices increase, a huge amount spatial temporal information data is collected accumulated. These are expressed as trajectory by connecting points in chronological sequence, these contain movement any moving object. Particularly, this study, urban vehicle prediction studied using vehicles traffic network. In previous work, Recurrent Neural Network model for proposed. For further improvement model, we propose Attention-based...
As data produced by multimedia explodes and demand for storage increases, the most important topics NAND-Flash memory field are continuous performance improvements cost/bit reduction. To improve performance, features to quality of service (QoS) as well read/write [1] required. reduce cost/bit, number stacked layers needs increase, while pitch between decreases. It is necessary manage increasing WL resistance a decreased stack pitch. overcome these challenges, this paper presents techniques...
A fuzzy logic controller for a rotary, turbodynamic left ventricular assist system was developed to optimize the delivery of blood flow without inducing suction in ventricle. The is based on pulsatility through pump and assumes that natural heart still able produce some pumping action. To avoid use transducers, which are not reliable long term use, estimates using model device. tested computer simulation, mock circulatory system, animal experiments. Simulation studies suggest more robust...
Abstract: Hemodynamic control of left ventricular assist devices (LVADs) is generally a complicated problem due to diverse operating environments and the variability patients: both changes in circulatory metabolic parameters as well disturbances that require adjustment point. This challenge especially acute with turbodynamic blood pumps. article presents pulsatility ratio controller for LVAD provides proper perfusion according physiological demands patient, while avoiding adverse conditions....
This paper proposes a deep learning approach to and predicting network-wide vehicle movement patterns in urban networks. Inspired by recent success sequence data using recurrent neural networks (RNN), specifically language modeling that predicts the next words sentence given previous words, this research aims apply RNN predict locations vehicle’s trajectory, locations, viewing trajectory as set of network vocabulary human language. To extract finite “locations,” study partitions into...
In transportation systems and autonomous vehicles, intelligent agents must understand the future motion of traffic participants to effectively plan trajectories. At same time, is inherently uncertain. this paper, we propose TrajFlow, a generative framework for estimating occupancy density participants. Our utilizes causal encoder extract semantically meaningful embeddings observed trajectory, as well normalizing flow decode these determine most likely location at some time point in future....
Integrating Urban Air Mobility (UAM) into airspace managed by Traffic Control (ATC) poses significant challenges, particularly in congested terminal environments. This study proposes a framework to assess the feasibility of UAM route integration using probabilistic aircraft trajectory prediction. By leveraging conditional Normalizing Flows, predicts short-term distributions conventional aircraft, enabling vehicles dynamically adjust speeds and maintain safe separations. The methodology was...
Deep-learning-based multivariate and multistep-ahead traffic forecasting models are typically trained with the mean squared error (MSE) or absolute (MAE) as loss function in a sequence-to-sequence setting, simply assuming that errors follow an independent isotropic Gaussian Laplacian distributions. However, such assumptions often unrealistic for real-world tasks, where probabilistic distribution of spatiotemporal is very complex strong concurrent correlations across both sensors horizons...
This paper proposes a dynamic regression (DR) framework that enhances existing deep spatiotemporal models by incorporating structured learning for the error process in traffic forecasting. The relaxes assumption of time independence modeling series base model (i.e., well-established forecasting model) using matrix-variate autoregressive (AR) model. AR is integrated into training redesigning loss function. newly designed function based on likelihood nonisotropic term, enabling to generate...
Multiple sclerosis (MS) is a chronic inflammatory disease affecting the central nervous system that involves immune-mediated demyelination and axonal degeneration. Clinical imaging techniques play critical role in diagnosing assessing prognosis of MS. Magnetic resonance has been most frequently used to visualize detect acute active lesions, which are key indicators clinical course illness. Previous research also highlighted effectiveness translocator protein 18-kDa (TSPO) positron emission...
This paper presents a model for identification of an axial pump. It aims to provide flow and pressure difference estimates the pump as well parameters characteristics without using sensors.
Parking is a crucial element of the driving experience in urban transportation systems. Especially coming era Shared Autonomous Vehicles (SAVs), parking operations networks will inevitably change. stations serve as storage places for unused vehicles and depots that control level-of-service SAVs. This study presents an Analytical Planning Model (APPM) SAV environment to provide broader insights into planning decisions. Two specific scenarios are considered APPM: (i) Single-zone APPM (S-APPM),...
Heart assist devices are blood pumps used to augment the cardiac output of patients with left ventricular failure. A new generation being evaluated for human use is based on turbo-hydrodynamic methods pumping, which offer several advantages over reciprocating, pulsatile in current devices. However, pose a more difficult control problem because their sensitivity circulatory load and other patient cardiovascular parameters. The paper describes design structure regulate operation these...
Covers advancements in spacecraft and tactical strategic missile systems, including subsystem design application, mission analysis, materials structures, developments space sciences, processing manufacturing, operations, applications of technologies to other fields.
The safety of urban transportation systems is considered a public health issue worldwide, and many researchers have contributed to improving it. Connected automated vehicles (CAVs) cooperative intelligent (C-ITSs) are solutions ensure the using various sensors communication devices. However, realizing data flow framework, including collection, transmission, processing, in South Korea challenging, as CAVs produce massive amount every minute, which cannot be transmitted via existing networks....
Originally, decision and control of the lane change vehicle is on human driver. It mainly used to increase individual's benefit such as decreasing travel time. However, selfish lane-changing behavior can sometimes make a negative impact overall traffic flow. As autonomous technology develops, modeling changing action well making falls within category vehicles. In this study, we focused for vehicles considering flow, accordingly, propose system whole The predicts future situation using Cell...
With the increasing demand for urban traffic simulation, mesoscopic model takes center stage with its advantage that can simulate a large network less computational cost and gets information of individual vehicles. This study proposes simulation called Agent-based Mesoscopic Cell Transmission Model (AMCTM). It models both longitudinal lateral movement The is based on (CTM) implements signal by adjusting amount flow between cells according to signal. includes mandatory lane-change allow...
Freeways which are designed for high-speed vehicular traffic seems to have some problems with the sections inclines due performance drop in accelerations of heavy trucks and high occupancy vehicles (HOVs). To complement this problem, installing auxiliary lane laterally separate low speed from vehicles. This is called a climbing lane. There mainly two types lane: 1) pocket type 2) overtaking In Korea, many located near urban area, leading attentions on performances at various input flow...