Prognosis of anterior cruciate ligament reconstruction: a data-driven approach

Chandra, Abhijit; Kar, Oliva; Wu, Kuan Chuen; Hall, Michelle; Gillette, Jason C.

doi:10.1098/rspa.2014.0526

Cited by 5 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, a novel data-driven method called data-driven prognosis (DDP) was proposed by Chandra et al [111] that relies on in situ data measurements and estimates the system's failure based on the curvature information that is extracted from the system. This method was later on employed to analyze LIBs [112].…”

Section: Data-driven Prognosis (Ddp)mentioning

confidence: 99%

“…Model-based and Physics-based method Equivalent circuit model [85] Electrochemical model [61,62,77] Electrochemical-mechanical model [63,64,68,70] Mathematical model [65,72,78] Data-driven method ANN [104][105][106][107]114,115] kNN [108] DDP [111,112] SVM [113] RF [109] PF [87] BM [86,90] Hybrid method Series [129,130] Parallel [131] 4. Challenges, Perspectives, and Conclusions PHM-augmented schemes provide an essential characterization framework for evaluating the availability and reliability of SSBs.…”

Section: Categories Techniquementioning

confidence: 99%

See 1 more Smart Citation

Prognosis and Health Management (PHM) of Solid-State Batteries: Perspectives, Challenges, and Opportunities

Kouhestani

et al. 2022

Energies

View full text Add to dashboard Cite

Solid-state batteries (SSBs) have proven to have the potential to be a proper substitute for conventional lithium-ion batteries due to their promising features. In order for the SSBs to be market-ready, the prognostics and health management (PHM) of battery systems plays a critical role in achieving such a goal. PHM ensures the reliability and availability of batteries during their operational time with acceptable safety margin. In the past two decades, much of the focus has been directed towards the PHM of lithium-ion batteries, while little attention has been given to PHM of solid-state batteries. Hence, this report presents a holistic review of the recent advances and current trends in PHM techniques of solid-state batteries and the associated challenges. For this purpose, notable commonly employed physics-based, data-driven, and hybrid methods are discussed in this report. The goal of this study is to bridge the gap between liquid state and SSBs and present the crucial aspects of SSBs that should be considered in order to have an accurate PHM model. The primary focus is given to the ML-based data-driven methods and the requirements that are needed to be included in the models, including anode, cathode, and electrolyte materials.

show abstract

Section: Data-driven Prognosis (Ddp)mentioning

confidence: 99%

Section: Categories Techniquementioning

confidence: 99%

Prognosis and Health Management (PHM) of Solid-State Batteries: Perspectives, Challenges, and Opportunities

Kouhestani

et al. 2022

Energies

View full text Add to dashboard Cite

show abstract

“…The DDP algorithm developed here is also applicable to any datasets representing a conservative system. A companion paper applies similar framework for prognosis of osteo-arthritis after reconstructive surgery following ACL injury [27].…”

Section: Pdi Startedmentioning

confidence: 99%

Data-driven prognosis: a multi-physics approach verified via balloon burst experiment

Chandra

Kar

2015

Proc. R. Soc. A.

Self Cite

View full text Add to dashboard Cite

A multi-physics formulation for data-driven prognosis (DDP) is developed. Unlike traditional predictive strategies that require controlled offline measurements or 'training' for determination of constitutive parameters to derive the transitional statistics, the proposed DDP algorithm relies solely on in situ measurements. It uses a deterministic mechanics framework, but the stochastic nature of the solution arises naturally from the underlying assumptions regarding the order of the conservation potential as well as the number of dimensions involved. The proposed DDP scheme is capable of predicting onset of instabilities. Because the need for offline testing (or training) is obviated, it can be easily implemented for systems where such a priori testing is difficult or even impossible to conduct. The prognosis capability is demonstrated here via a balloon burst experiment where the instability is predicted using only online visual observations. The DDP scheme never failed to predict the incipient failure, and no false-positives were issued. The DDP algorithm is applicable to other types of datasets. Time horizons of DDP predictions can be adjusted by using memory over different time windows. Thus, a big dataset can be parsed in time to make a range of predictions over varying time horizons.

show abstract

“…15,[26][27][28][29][30][31] While gait abnormalities tend to normalize around 2 years after surgery, 17,32 changes in the loading environment that occur during these time periods may contribute to the premature development of posttraumatic knee osteoarthritis (OA). 15,28,30,31,33 Understanding how gait aberrations progress during the early months after surgery, when interventions may be most feasible, can help inform new rehabilitative strategies to mitigate asymmetries and preserve long-term joint health.…”

Section: Introductionmentioning

confidence: 99%

Knee joint biomechanics during gait improve from 3 to 6 months after anterior cruciate ligament reconstruction

Neal

Williams

Alfayyadh

et al. 2022

Journal Orthopaedic Research

View full text Add to dashboard Cite

Gait alterations after anterior cruciate ligament reconstruction (ACLR) are commonly reported and have been linked to posttraumatic osteoarthritis development. While knee gait alterations have been studied at several time points after ACLR, little is known about how these biomechanical variables change earlier than 6 months after surgery, nor is much known about how they differ over the entire stance phase of gait. The purpose of this study was to examine knee gait biomechanical variables over their entire movement pattern through stance at both 3 and 6 months after ACLR and to study the progression of interlimb asymmetry between the two postoperative time points. Thirty‐five individuals underwent motion analysis during overground walking 3 (3.2 ± 0.5) and 6 (6.4 ± 0.7) months after ACLR. Knee biomechanical variables were compared between limbs and across time points through 100% of stance using statistical parametric mapping; this included a 2 × 2 (Limb × Time) repeated measures analysis of variance and two‐tailed t‐tests. Smaller knee joint angles, moments, extensor forces, and medial compartment forces were present in the involved versus uninvolved limb. Interlimb asymmetries were present at both time points but were less prevalent at 6 months. The uninvolved limb's biomechanical variables stayed relatively consistent over time, while the involved limb's trended toward that of the uninvolved limb. Statement of Clinical Significance: Interventions to correct asymmetrical gait patterns after ACLR may need to occur early after surgery and may need to focus on multiple parts of stance phase.

show abstract

Prognosis of anterior cruciate ligament reconstruction: a data-driven approach

Cited by 5 publications

References 30 publications

Prognosis and Health Management (PHM) of Solid-State Batteries: Perspectives, Challenges, and Opportunities

Prognosis and Health Management (PHM) of Solid-State Batteries: Perspectives, Challenges, and Opportunities

Data-driven prognosis: a multi-physics approach verified via balloon burst experiment

Knee joint biomechanics during gait improve from 3 to 6 months after anterior cruciate ligament reconstruction

Contact Info

Product

Resources

About