Data Mining Practical Machine Learning Tools and Techniques

Falls in the elderly.

Wearable sensors have recently been used to evaluate biomechanical parameters of everyday movements, but few have been located at the head level. This study investigated the relative and absolute reliability (intra- and inter-session) and concurrent validity of an inertial measurement unit (IMU) embedded in smart eyeglasses during sit-to-stand (STS) movements for the measurement of maximal acceleration of the head. Reliability and concurrent validity were investigated in nineteen young and healthy participants by comparing the acceleration values of the glasses’ IMU to an optoelectronic system. Sit-to-stand movements were performed in laboratory conditions using standardized tests. Participants wore the smart glasses and completed two testing sessions with STS movements performed at two speeds (slow and comfortable) under two different conditions (with and without a cervical collar). Both the vertical and anteroposterior acceleration values were collected and analyzed. The use of the cervical collar did not significantly influence the results obtained. The relative reliability intra- and inter-session was good to excellent (i.e., intraclass correlation coefficients were between 0.78 and 0.91) and excellent absolute reliability (i.e., standard error of the measurement lower than 10% of the average test or retest value) was observed for the glasses, especially for the vertical axis. Whatever the testing sessions in all conditions, significant correlations (p < 0.001) were found for the acceleration values recorded either in the vertical axis and in the anteroposterior axis between the glasses and the optoelectronic system. Concurrent validity between the glasses and the optoelectronic system was observed. Our observations indicate that the IMU embedded in smart glasses is accurate to measure vertical acceleration during STS movements. Further studies should investigate the use of these smart glasses to assess the STS movement in unstandardized settings (i.e., clinical and/or home) and to report vertical acceleration values in an elderly population of fallers and non-fallers.

https://www.mdpi.com/1424-8220/20/18/5019/pdf

Sit-To-Stand Movement Evaluated Using an Inertial Measurement Unit Embedded in Smart Glasses—A Validation Study

Many of the existing methods for action quality assessment implement single-stage score regression networks that lack pertinence and rationality for the evaluation task. In this work, our target is to find a reasonable action quality assessment method for sports competitions that conforms to objective evaluation rules and field experience. To achieve this goal, three assessment scenarios, i.e., the overall-score-guided scenario, execution-score-guided scenario, and difficulty-level-based overall-score-guided scenario, are defined. A learning and fusion network of multiple hidden substages is proposed to assess athletic performance by segmenting videos into five substages by a temporal semantic segmentation. The feature of each video segment is extracted from the five feature backbone networks with shared weights, and a fully-connected-network-based hidden regression model is built to predict the score of each substage, fusing these scores into the overall score. We evaluate the proposed method on the UNLV-Diving dataset. The comparison results show that the proposed method based on objective evaluation rules of sports competitions outperforms the regression model directly trained on the overall score. The proposed multiple-substage network is more accurate than the single-stage score regression network and achieves state-of-the-art performance by leveraging objective evaluation rules and field experience that are beneficial for building an accurate and reasonable action quality assessment model.

Learning and fusing multiple hidden substages for action quality assessment

Accelerometer data from the performance of sit-to-stand test by elderly people

The sit-to-stand test (STS) is a simple test of function in older people that can identify people at risk of falls. The aim of this study was to develop two novel methods of evaluating performance in the STS using a low-cost RGB camera and another an instrumented chair containing load cells in the seat of the chair to detect center of pressure movements and ground reaction forces. The two systems were compared to a Kinect and a force plate. Twenty-one younger subjects were tested when performing two 5STS movements at self-selected slow and normal speeds while 16 older fallers were tested when performing one 5STS at a self-selected pace. All methods had acceptable limits of agreement with an expert for total STS time for younger subjects and older fallers, with smaller errors observed for the chair (−0.18 ± 0.17 s) and force plate (−0.19 ± 0.79 s) than for the RGB camera (−0.30 ± 0.51 s) and the Kinect (−0.38 ± 0.50 s) for older fallers. The chair had the smallest limits of agreement compared to the expert for both younger and older participants. The new device was also able to estimate movement velocity, which could be used to estimate muscle power during the STS movement. Subsequent studies will test the device against opto-electronic systems, incorporate additional sensors, and then develop predictive equations for measures of physical function.

/pdf/a-comparison-of-four-approaches-to-evaluate-the-sit-to-stand-4mudzqjsfz.pdf

A Comparison of Four Approaches to Evaluate the Sit-to-Stand Movement

The Sit-to-Stand (STS) is a widely used test of physical function to screen older people at risk of falls and frailty and is also one of the most important components of standard screening for sarcopenia. There have been many recent studies in which instrumented versions of the STS (iSTS) have been developed to provide additional parameters that could improve the accuracy of the STS test. This systematic review aimed to identify whether an iSTS is a viable alternative to a standard STS to identify older people at risk of falling, frailty, and sarcopenia. A total of 856 articles were found using the search strategy developed, with 12 articles retained in the review after screening based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Six studies evaluated the iSTS in fallers, five studies in frailty and only one study in both fallers and frailty. The results showed that power and velocity parameters extracted from an iSTS have the potential to improve the accuracy of screening when compared to a standard STS. Future work should focus on standardizing the segmentation of the STS into phases to enable comparison between studies and to develop devices integrated into the chair used for the test to improve usability.

https://www.mdpi.com/2306-5354/7/4/139/pdf

Instrumented analysis of the sit-to-stand movement for geriatric screening: a systematic review

The aim of this study was to investigate whether parameters from an instrumented one-leg stance on a force plate test could provide relevant information related to fall risk in older people. Twenty-five community dwelling older people and 25 young subjects performed a one-leg stance while standing on a force plate, with parameters related to transferring weight onto one leg and postural sway in singe-leg stance evaluated. Older participants were classified as being at risk of falling if their performance did not meet one of the previously-established cut-offs for the Five Times Sit-To-Stand and Timed-Up-and-Go tests. Eleven older participants were classified as having a risk of falls. The only significant difference between groups during the weight transfer phase was in the mediolateral displacement, with the fall risk group having less sway than the other groups, signifying a more precautionary approach. With respect to postural sway, both the younger subjects and the no fall risk group stabilised sufficiently to decrease their sway compared to initial values after four and six seconds, respectively. In contrast, the fall risk group was unable to stabilise during the one-leg stance, and continued to sway throughout the 10-sec recording period. These findings suggest that the normal one-leg stance test might not be suitable to detect fall risk. In contrast, an instrumented version of the test could provide valuable additional information that could identify risk of falling in older people.

/pdf/a-pilot-study-to-detect-balance-impairment-in-older-adults-1lkgz4affs.pdf

A Pilot Study to Detect Balance Impairment in Older Adults Using an Instrumented One-Leg Stance Test.

Automated clinical tests that assess quality of geriatric screening tests such as the Five-Times-Sit- To-Stand (5STS) and the Timed-Up-and-Go (TUG) are being designed to assess the decline in functional ability of elderly. The existing techniques to assess the quality of these physical activities include sensor-based techniques including body mounted sensors, force sensors and, vision and imaging sensors. These sensors have their own advantages and disadvantages towards the task of clinical assessment. In this work, we introduce a fusion- based technique to combine multiple sensors leveraging advantages of individual sensors, in such a way that the resulting assessment is more accurate. We evaluate our technique for 5STS test using a fusion of a chair and RGB sensors. In a test of 15 older people, there was no significant difference in performance between the two sensors, obtaining 76% and 73% for the RGB and chair, respectively. However, a significant improvement was obtained for the fusion technique, with 90% accuracy for all the phases of the STS test. The proposed fusion technique was observed to be better than the individual sensor assessment.

A Fusion-Based Approach to Identify the Phases of the Sit-to-Stand Test in Older People

Cardiovascular disorders (CVD) are the key cause of mortality worldwide. One in three male premature deaths and one in five female premature deaths are thought to be attributable to Cardiovascular disorders. Early prediction of CVDs may help to attenuate the disease, potentially lowering death rates. The existence of cardiac disease can be predicted using machine learning approaches; however, the effectiveness of the classifiers may be enhanced by applying PCA, relief feature selection, and data transformation techniques. The objective of employing data transformation, PCA, and relief feature selection approaches is to enhance classifier performance and increase the interpretability and ability of classifiers to predict heart disease. Heart disease anticipating is a challenging problem in the field of healthcare. This uses popular supervised machine learning (ML) algorithms including k-NN, LR, DT, RF, SVM, and ANN to help healthcare practitioners and specialists easily identify the prevalence of heart-related illnesses in patients. In these trials, data transformation is achieved using PCA, normalized features, and relief techniques, and RF surpasses all other classifiers with a prediction accuracy of 90%, followed by ANN and DT with AUCs of 87% and 86%, respectively. SVM and Naive Bayes classifiers were shown to be lesser effective at predicting heart disease.

Brajesh K. Shukla

Papers

A Comparison of Four Approaches to Evaluate the Sit-to-Stand Movement

Instrumented analysis of the sit-to-stand movement for geriatric screening: a systematic review

A Pilot Study to Detect Balance Impairment in Older Adults Using an Instrumented One-Leg Stance Test.

A Fusion-Based Approach to Identify the Phases of the Sit-to-Stand Test in Older People

Improving Heart Disease Prediction of Classifiers with Data Transformation using PCA and Relief Feature Selection