Jatin Aggarwal

Jatin Aggarwal

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
1 July 2024 in Archives of Civil and Mechanical Engineering
Verified
Journal Article
Open access
PDF file
DCDaniel Cantero
Daniel Cantero
MSMuhammad Zohaib Sarwar
Muhammad Zohaib Sarwar
Abdollah MalekjafarianAbdollah Malekjafarian
Abdollah Malekjafarian
RCRobert Corbally
Robert Corbally
MAMehrisadat Makki Alamdari
Mehrisadat Makki Alamdari
JLJingxiao Liu
Jingxiao Liu
Drive-by bridge monitoring utilizes measured responses from passing vehicles to perform damage detection of bridge, a methodology challenged by multiple factors and operational conditions. Recently, data-driven methods have been used to improve the accuracy of drive-by monitoring. This thriving research field requires (but lacks) publicly available datasets to improve and validate its monitoring and damage detection capabilities. To foster data-driven drive-by bridge damage assessment methods, this document presents an openly available dataset consisting of numerically simulated vehicle responses crossing a range of bridge spans with various damage conditions. The dataset includes results for different monitoring scenarios, road profile conditions, vehicle models, vehicle mechanical properties and speeds. The intention is to provide a useful resource to the research community that serves as a reference set of results for testing and benchmarking new developments in the field. In addition, four recently published data-driven drive-by methods have been tested using the same dataset.

22 September 2025 in IEEE Sensors Journal
Verified
Journal Article
Closed access
JLJingxiao Liu
Jingxiao Liu
HLHaipeng Li
Haipeng Li
JLJiaxuan Li
Jiaxuan Li
DHDoyun Hwang
Doyun Hwang
JAJatin Aggarwal
Jatin Aggarwal
HNHae Young Noh
Hae Young Noh
Urban monitoring is important for maintaining safe and sustainable urban life through infrastructure assessment, resource optimization, hazard mitigation, and public safety enhancement. Vibration and seismic signals offer rich insights into urban environments, reflecting both physical and environmental conditions and societal activities. Recent advancements in Distributed Acoustic Sensing (DAS) have leveraged pre-existing telecommunication (telecom) fiber-optic networks as dense arrays of seismic and vibration sensors, providing a scalable, cost-effective, and continuous urban monitoring solution. DAS technology uses internal imperfections in fiber-optic cables to measure dynamic strain (rate), enabling fibers to capture seismic waves and structural vibrations at meter-scale intervals over tens of kilometers. By utilizing pre-existing telecom fiber networks as urban-scale sensing platforms, DAS has demonstrated broad applications ranging from seismic monitoring and subsurface imaging to urban activity detection and structural health assessment. As research and technological advancements continue, DAS is positioned to become prominent in next-generation urban sensing, supporting smarter, more resilient, and more sustainable urban planning and development. Building on these developments, this paper reviews the latest progress in urban monitoring using pre-existing telecom fiber networks as DAS systems.

15 November 2023
Verified
Conference Paper
Open access
YDYiwen Dong
Yiwen Dong
YWYuyan Wu
Yuyan Wu
JCJesse R Codling
Jesse R Codling
JAJatin Aggarwal
Jatin Aggarwal
PHPeide Huang
Peide Huang
HNHae Young Noh
Hae Young Noh
Crowd monitoring involves tracking and analyzing the behavior of large groups of people in large-scale public spaces, such as sports games. In sports stadiums, understanding audience reactions to the games and their distribution around the public facilities is important for ensuring public safety and security, enhancing the game experience, and improving crowd management. Recent crowd-crushing incidents (e.g., Kanjuruhan Stadium disaster, Seoul Halloween Stampede) have caused 100+ deaths in a single event, calling for advancements in crowd monitoring methods. Existing monitoring approaches include manual observation, wearables, video-, audio-, and WiFi-based sensing. However, few meet the practical needs due to their limitations in cost, privacy protection, and accuracy. In this paper, we introduce GameVibes, a novel method for crowd behavior monitoring using crowd-induced floor vibrations to infer audience reactions to the game (e.g., clapping, stomping, dancing) and crowd traffic (i.e., the number of people entering each door). The main benefits of GameVibes are that it allows continuous, fine-grained crowd monitoring in a cost-effective and non-intrusive way and is perceived as more privacy-friendly. Unlike monitoring an individual person, crowd monitoring involves understanding the overall behavior of a large population (typically more than 1,000), leading to high uncertainty in the vibration data. To overcome the challenge, we first establish the game and facility association to inform the context of crowd behaviors, including 1) game associations (temporal context) between the crowd reaction and the game progress and 2) facility associations (spatial context) between the crowd traffic and facility layouts. Then, we formulate the crowd monitoring problem by converting the conceptual graph of the audience-game-facility association into probabilistic game/facility association models. Through these models, GameVibes first learns the latent representations of the game progress and facility layout through neural network encoders, and then integrates heterogeneous game/facility information and vibration data to estimate crowd behaviors. This mitigates the estimation error due to the uncertainty in vibration data. To evaluate our approach, we conduct 6 real-world deployments for NCAA Pac-12 games at Stanford Maples Pavilion. Our results show that GameVibes achieves a 0.9 F-1 score in crowd reaction monitoring and 9.3 mean absolute error in crowd traffic estimation, which correspond to 10% and 12.2% error reduction, respectively, compared to the baseline methods without context-specific information.

6 May 2025
Verified
Conference Paper
Open access
JGJulia Gersey
Julia Gersey
JAJatin Aggarwal
Jatin Aggarwal
JZJiale Zhang
Jiale Zhang
JCJesse Codling
Jesse Codling
PZPei Zhang
Pei Zhang
Assessing urban infrastructure and environment quality at scale remains a challenge. This work presents a multimodal sensing framework that integrates computer vision-based infrastructure analysis with mobile air quality monitoring to explore urban conditions beyond the camera's field of view. A vehicle-mounted system captures video data for semantic segmentation of roads and buildings while an air intake unit collects temperature, humidity, CO2, TVOC, and AQI levels. A preliminary test drive in Ann Arbor demonstrated expected correlations between CO2 and TVOC spikes in dense urban areas, providing a proof of concept for linking environmental sensing with visual urban analysis. Future work will refine sensor calibration, adaptive sampling strategies, and predictive modeling to improve accuracy and scalability.

12 September 2023
Verified
Conference Paper
Open access
PDF file
JAJatin Aggarwal
Jatin Aggarwal
JLJingxiao Liu
Jingxiao Liu
HNHae Young Noh
Hae Young Noh
Bridge health monitoring (BHM) is important to detect damages in the early stages to avoid loss of human life and any disruption in the continuous bridge operations. Driveby vehicle-based BHM approaches provide more scalable monitoring as compared to manual inspection and fixed sensors on bridges. Each vehicle can pass multiple bridges and can be used for monitoring multiple bridges. In our prior work, we developed a method that can diagnose damage in multiple bridges while eliminating the burden of collecting labeled data from all the bridges. It is achieved by learning features that are sensitive to damage and invariant across bridges. However, in real-world scenarios, vehicles passing the bridge possess varying properties such as suspension system, driving speed, and vehicle mass. Since the vibration signal obtained from the vehicle depends on the vehicle’s properties, these variabilities in vehicle properties lead to inaccurate damage prediction of the bridge even for the same damage state. To overcome these challenges, we introduce a Bootstrapping-enhanced Vehicle - Bridge-Invariant (BeVBI) approach for robust drive-by BHM. It reduces the vibration signal variation due to varying vehicle properties through bootstrapping-based mean estimations. Specifically, vibration signals obtained from vehicles (with varying vehicle properties) passing the bridge are randomly aggregated with replacement (i.e., bootstrapping) and averaged. Based on the central limit theorem, averaging the aggregated signals (bootstrapped signals) reduces signal variability due to vehicle properties by the square root of the number of aggregated signals. Further, these bootstrapped signals are used to predict the damage on multiple bridges by adopting an unsupervised domain learning algorithm. The performance of the above approach is evaluated using a numerical vehicle bridge interaction dataset with two different bridges and 4800 drive-by vehicles having different dynamic properties and speeds. Our approach is successful in diagnosing multiple bridges while being robust to varying vehicle properties. It performs 1.45x better in the detection and localization of damage and 1.75x better in the quantification of damage as compared to baseline methods (MCNN and HierMUD).

21 August 2026 in Nature Communications
Verified
Journal Article
Open access
PDF file
JLJingxiao Liu
Jingxiao Liu
JAJatin Aggarwal
Jatin Aggarwal
DHDoyun Hwang
Doyun Hwang
JLJigu Lee
Jigu Lee
YWYuyan Wu
Yuyan Wu
HNHae Young Noh
Hae Young Noh
Aging bridges pose significant risks to public safety. Although existing sensing technologies offer a potential solution for structural health monitoring, the high cost and complexity of installing and maintaining sensing systems have limited their scalability and long-term deployment. Here, we present a scalable and cost-effective approach that turns pre-existing telecommunication (telecom) fiber-optic cables into a dense array of dynamic strain sensors to continuously monitor bridges. Using telecom fibers, we retrieve guided wavefields across bridge superstructures, which was impossible with existing sensing technologies due to their limited scalability and the prohibitive cost of ultra-dense sensor arrays required to capture meter-scale wavelengths. We also estimate quasi-static displacements with millimeter-level accuracy and extract modal parameters. These results demonstrate that our approach is robust to noise from imperfect fiber-bridge coupling, a limitation inherent to the non-dedicated nature of telecom fibers used as sensors. Furthermore, we demonstrated the effectiveness of this approach through field evaluations across six bridges in the United States and South Korea. Because telecom fibers are widely deployed and co-located with civil infrastructure systems, this study introduces a new sensing paradigm that leverages existing fiber-optic networks to enable large-scale, real-time structural monitoring without the cost and logistical burden of dedicated sensors.