Arun Kumar

Arun Kumar

Auto-generated profile, based on publicly available information

Arun Kumar

Department of Computer Science and Engineering, University of California, San Diego, La Jolla, CA, USA

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
10 February 2025 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
KLKyle Luoma
Kyle Luoma
AKArun Kumar
Arun Kumar
Large Language Models (LLMs) have revolutionized Natural Language to SQL (NL-to-SQL), dominating most NL-to-SQL benchmarks. But LLMs still face limitations due to hallucinations, semantic ambiguity, and lexical mismatches between an NL query and the database schema. Naturally, a lot of work in the ML+DB intersection aims to mitigate such LLM limitations. In this work, we shine the light on a complementary data-centric question: How should DB schemas evolve in this era of LLMs to boost NL-to-SQL? The intuition is that more NL-friendly schema identifiers can help LLMs work better with DBs. We dive deeper into this seemingly obvious, but hitherto underexplored and important, connection between schema identifier ''naturalness'' and the behavior of LLM-based NL-to-SQL by creating a new integrated benchmark suite we call SNAILS. SNAILS has 4 novel artifacts: (1) A collection of real-world DB schemas not present in prior NL-to-SQL benchmarks; (2) A set of labeled NL-SQL query pairs on our collection not seen before by public LLMs; (3) A notion of naturalness level for schema identifiers and a novel labeled dataset of modified identifiers; and (4) AI artifacts to automatically modify identifier naturalness. Using SNAILS, we perform a comprehensive empirical evaluation of the impact of schema naturalness on LLM-based NL-to-SQL accuracy, and present a method for improving LLM-based NL-to-SQL with natural views. Our results reveal statistically significant correlations across multiple public LLMs from OpenAI, Meta, and Google on multiple databases using both zero-shot prompting as well as more complex NL-to-SQL workflows: DIN SQL, and CodeS. We present several fine-grained insights and discuss pathways for DB practitioners to better exploit LLMs for NL-to-SQL.

2 August 2024 in JMIR Rehabilitation and Assistive Technologies
Verified
Journal Article
Open access
ALAudrey Lee
Audrey Lee
EWElijah Wyckoff
Elijah Wyckoff
EFEmilia Farcas
Emilia Farcas
JGJob G Godino
Job G Godino
KPkevin patrick
kevin patrick
SGSara Gombatto
Sara Gombatto
Background: Low back pain (LBP) is a significant public health problem that can result in physical disability and financial burden for the individual and society. Physical therapy is effective for managing LBP and includes evaluation of posture and movement, interventions directed at modifying posture and movement, and prescription of exercises. However, physical therapists have limited tools for objective evaluation of low back posture and movement and monitoring of exercises, and this evaluation is limited to the time frame of a clinical encounter. There is a need for a valid tool that can be used to evaluate low back posture and movement and monitor exercises outside the clinic. To address this need, a fabric-based, wearable sensor, Motion Tape (MT), was developed and adapted for a low back use case. MT is a low-profile, disposable, self-adhesive, skin-strain sensor developed by spray coating piezoresistive graphene nanocomposites directly onto commercial kinesiology tape. Objective: The objectives of this study were to (1) validate MT for measuring low back posture and movement and (2) assess the acceptability of MT for users. Methods: A total of 10 participants without LBP were tested. A 3D optical motion capture system was used as a reference standard to measure low back kinematics. Retroreflective markers and a matrix of MTs were placed on the low back to measure kinematics (motion capture) and strain (MT) simultaneously during low back movements in the sagittal, frontal, and axial planes. Cross-correlation coefficients were calculated to evaluate the concurrent validity of MT strain in reference motion capture kinematics during each movement. The acceptability of MT was assessed using semistructured interviews conducted with each participant after laboratory testing. Interview data were analyzed using rapid qualitative analysis to identify themes and subthemes of user acceptability. Results: Visual inspection of concurrent MT strain and kinematics of the low back indicated that MT can distinguish between different movement directions. Cross-correlation coefficients between MT strain and motion capture kinematics ranged from –0.915 to 0.983, and the strength of the correlations varied across MT placements and low back movement directions. Regarding user acceptability, participants expressed enthusiasm toward MT and believed that it would be helpful for remote interventions for LBP but provided suggestions for improvement. Conclusions: MT was able to distinguish between different low back movements, and most MTs demonstrated moderate to high correlation with motion capture kinematics. This preliminary laboratory validation of MT provides a basis for future device improvements, which will also involve testing in a free-living environment. Overall, users found MT acceptable for use in physical therapy for managing LBP.

21 October 2024
Verified
Conference Paper
Open access
XZXiuwen Zheng
Xiuwen Zheng
AKArun Kumar
Arun Kumar
AGAmarnath Gupta
Amarnath Gupta
Data analytics applications today often require processing heterogeneous data from different data models, including relational, graph, and text data, for more holistic analytics. While query optimization for single data models, especially relational data, has been studied for decades, there is surprisingly little work on query optimization for cross-model data analytics. Cross-model query optimization can benefit from the long line of prior work in query optimization in the relational realm, wherein cost-based and/or machine learning-based (ML-based) optimizers are common. Both approaches require a large and diverse set of query workloads to measure, tune, and evaluate a query optimizer. To the best of our knowledge, there are still no large public cross-model benchmark workloads, a significant obstacle for systems researchers in this space. In this paper, we take a step toward filling this research gap by generating new query workloads spanning relational and graph data, which are ubiquitous in analytics applications. Our approach leverages large language models (LLMs) via different prompting strategies to generate queries and proposes new rule-based post-processing methods to ensure query correctness. We evaluate the pros and cons of each strategy and perform an in-depth analysis by categorizing the syntactic and semantic errors of the generated queries. So far, we have produced over 4000 correct cross-model queries, the largest set ever. Our code, prompts, data, and query workloads will all be released publicly.

1 March 2024 in JMIR Preprints
Verified
Preprint
Open access
ALAudrey Lee
Audrey Lee
EWElijah Wyckoff
Elijah Wyckoff
EFEmilia Farcas
Emilia Farcas
JGJob G Godino
Job G Godino
KPkevin patrick
kevin patrick
SGSara Gombatto
Sara Gombatto
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Low back pain (LBP) is a significant public health problem that can result in physical disability and financial burden for the individual and society. Physical therapy is effective for managing LBP and includes evaluation of posture and movement, interventions directed at modifying posture and movement, and prescription of exercises. However, physical therapists have limited tools for objective evaluation of low back posture and movement and monitoring of exercises, and this evaluation is limited to the time frame of a clinical encounter. There is a need for a valid tool that can be used to evaluate low back posture and movement and monitor exercises outside the clinic. To address this need, a fabric-based, wearable sensor, Motion Tape (MT), was developed and adapted for a low back use case. MT is a low-profile, disposable, self-adhesive, skin-strain sensor developed by spray coating piezoresistive graphene nanocomposites directly onto commercial kinesiology tape. Objective: The objectives of this study were to (1) validate MT for measuring low back posture and movement and (2) assess the acceptability of MT for users. Methods: A total of 10 participants without LBP were tested. A 3D optical motion capture system was used as a reference standard to measure low back kinematics. Retroreflective markers and a matrix of MTs were placed on the low back to measure kinematics (motion capture) and strain (MT) simultaneously during low back movements in the sagittal, frontal, and axial planes. Cross-correlation coefficients were calculated to evaluate the concurrent validity of MT strain in reference motion capture kinematics during each movement. The acceptability of MT was assessed using semistructured interviews conducted with each participant after laboratory testing. Interview data were analyzed using rapid qualitative analysis to identify themes and subthemes of user acceptability. Results: Visual inspection of concurrent MT strain and kinematics of the low back indicated that MT can distinguish between different movement directions. Cross-correlation coefficients between MT strain and motion capture kinematics ranged from –0.915 to 0.983, and the strength of the correlations varied across MT placements and low back movement directions. Regarding user acceptability, participants expressed enthusiasm toward MT and believed that it would be helpful for remote interventions for LBP but provided suggestions for improvement. Conclusions: MT was able to distinguish between different low back movements, and most MTs demonstrated moderate to high correlation with motion capture kinematics. This preliminary laboratory validation of MT provides a basis for future device improvements, which will also involve testing in a free-living environment. Overall, users found MT acceptable for use in physical therapy for managing LBP.

1 January 2026 in Journal for the Measurement of Physical Behaviour
Verified
Journal Article
Closed access
PDF file
JMJasmine Morales
Jasmine Morales
RZRong W. Zablocki
Rong W. Zablocki
SHSheri J. Hartman
Sheri J. Hartman
AKArun Kumar
Arun Kumar
AKAnimesh Kumar
Animesh Kumar
LNLoki Natarajan
Loki Natarajan
Background : Sedentary behavior (SB) is a risk factor for cardiometabolic disease. Existing cut points of hip-worn accelerometers to quantify SB underestimate sedentary bout durations by ignoring posture. To address this, we previously developed Convolutional Neural Network Hip Accelerometer Posture (CHAP), a deep-learning algorithm that predicts sitting and breaks from sitting. In this study, we applied CHAP to a randomized controlled trial to externally validate its accuracy for classifying sitting versus nonsitting and estimating intervention-related changes in SB. Methods : CHAP was applied to 30-Hz triaxial hip-worn ActiGraph-GT3X+ (AG) accelerometer data from free-living postmenopausal women who are overweight (≥55 years) in the Rise for Health RCT ( n = 406). CHAP-predicted SB accuracy (e.g., sensitivity) and daily pattern metrics (e.g., total sedentary time) were compared with a ground-truth device activPAL (AP) and standard cut-point method (AG100) at two timepoints for intervention arms—Healthy Living (control), Reduce Sitting, and Increase Transitions. Results : CHAP’s SB accuracy metrics were above 84.8%. Mean (standard error, p values) intervention effect estimates (mean change, intervention minus controls) from generalized estimating equation models for (a) total sedentary time were AP 65.1 min/day (16.2, p < .001), CHAP 38.2 min/day (15.4, p = .013), and AG100 0.28 min/day (13.9, p = .98; Reduce Sitting); (b) breaks from SB were AP 22/day (4.3, p < .001), CHAP 4/day (1.5, p = .003), and AG100 <1/day (2.1, p = .860; Increase Transitions). Conclusions : This study validated CHAP on an independent cohort. CHAP exhibited high prediction accuracy, and although less sensitive than AP, CHAP detected changes in SB more effectively than AG100. Thus, CHAP could make a strong contribution to SB intervention research.