Prediction of diabetic foot ulcer progression: a computational study

Machine learning assisted classification between diabetic polyneuropathy and healthy subjects using plantar pressure and temperature data: a feasibility study

Automated and early detection of diabetics with polyneuropathy in an ambulatory health monitoring setup may reduce the major risk factors for diabetic patients. Increased and localized plantar pressure associated with impaired pain and temperature is a combination of developing foot ulcers in subjects with polyneuropathy. Although many interesting research works have been reported in this area, most of them emphasize on signal acquisition process and plantar pressure distribution in the foot region. In this work, a machine learning assisted low complexity technique was developed using plantar pressure and temperature signals which will classify between diabetic polyneuropathy and healthy subjects. Principal component analysis (PCA) and maximum relevance minimum redundancy (mRMR) methods were used for feature extraction and selection respectively followed by k-NN classifier for binary classification. The proposed technique was evaluated with 100 min of publicly available annotated data from 43 subjects and provides blind test accuracy, sensitivity, precision, F1-score, and area under curve (AUC) of 99.58%, 99.50%, 99.44%, 99.47% and 99.56% respectively. A low resource hardware implementation in ARM v6 controller required an average memory usage of 81.2 kB and latency of 1.31 s to process 9 s pressure and temperature data collected from 16 sensor channels for each of the foot region.

A high-fidelity biomechanical modeling framework for injury prediction during frontal car crash

Injuries arising from car crashes are ubiquitous across the globe and account for over 1.3 million fatalities annually. 93% of mortalities are observed in middle- and low-income countries owing to the lack of infrastructure in the safety assessment of car designs. It is therefore imperative to predict the extent of injuries to the occupants during car crashes, which would lead to safer vehicle design. To date, conventional computational testing methods use Hybrid III dummies, which fail to reproduce fracture and tear injuries. In this work, a full-frontal collision of a vehicle against a rigid wall with a highly biofidelic human body model of an occupant was simulated for the first time to investigate fractures and tears using a novel fracture modeling technique. Fractures were observed in ribs (5-7), which occurred at stresses of 120 MPa at the left lateral vertebrosternal region. In the lower extremity, tears in the ligaments at 70.80 MPa, and fractures in the tibia and femur at 236 MPa were quantified. Stresses in the skull were limited to 11 MPa, indicating a possibility of concussion rather than fractures. The developed computational model would be indispensable for car manufacturers to test the crash impact on the human body at all possible accident scenarios accurately, which will help design better solutions for automotive injury mitigation.

Biomechanical modeling of footwear-fluid-floor interaction during slips

Slips and falls are among the major concerns for public safety. Slipping risks can be reduced by ensuring adequate traction at the shoe-floor interface. The outsole design of footwear is a critical factor to maintain sufficient shoe-floor traction in the presence of slippery contaminants such as water or oil. While the role of floorings and contaminants on footwear traction has been studied widely, limited works have investigated the role of footwear outsole geometry and tread patterns on shoe-floor traction. In this work, eight footwear outsole designs and their traction performance were tested on a common flooring with water contamination, through the development of a novel fluid-structure interaction based computational framework. Induced fluid pressure, mass flow rates, and contact areas were quantified across the outsole patterns, and their effect on footwear friction was investigated. The study results were validated using mechanical slip testing experiments. The results indicated that the outsoles which had horizontal treads or untreaded heel regions can lead to drastic reduction of footwear friction. Also, contact area alone was quantified to be a poor choice in estimating the traction performance of footwear on water contaminated floorings. Such novel study results have not been reported to date, and are anticipated to provide important guidelines to footwear manufacturers to evaluate and optimize footwear tread parameters which would help in reducing the risk of slips.