scholarly journals Using machine learning to investigate the relationship between domains of functioning and functional mobility in older adults

PLoS ONE ◽  
2021 ◽  
Vol 16 (2) ◽  
pp. e0246397
Author(s):  
Keisuke Hirata ◽  
Makoto Suzuki ◽  
Naoki Iso ◽  
Takuhiro Okabe ◽  
Hiroshi Goto ◽  
...  
Keyword(s):  
Machine Learning ◽  
Older Adults ◽  
Knee Extension ◽  
The Body ◽  
Functional Mobility ◽  
Support Vector ◽  
Timed Up And Go ◽  
Explanatory Variables ◽  
Machine Learning Classification ◽  
Age Related

Previous studies have shown that functional mobility, along with other physical functions, decreases with advanced age. However, it is still unclear which domains of functioning (body structures, body functions, and activities) are most closely related to functional mobility. This study used machine learning classification to predict the rankings of Timed Up and Go tests based on the results of four assessments (soft lean mass, FEV1/FVC, knee extension torque, and one-leg standing time). We tested whether assessment results for each level could predict functional mobility assessments in older adults. Using support vector machines for machine learning classification, we verified that the four assessments of each level could classify functional mobility. Knee extension torque (from the body function domain) was the most closely related assessment. Naturally, the classification accuracy rate increased with a larger number of assessments as explanatory variables. However, knee extension torque remained the highest of all assessments. This extended to all combinations (of 2–3 assessments) that included knee extension torque. This suggests that resistance training may help protect individuals suffering from age-related declines in functional mobility.

scholarly journals Machine-Learning Analysis of Voice Samples Recorded through Smartphones: The Combined Effect of Ageing and Gender

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5022
Author(s):  
Francesco Asci ◽  
Giovanni Costantini ◽  
Pietro Di Leo ◽  
Alessandro Zampogna ◽  
Giovanni Ruoppolo ◽  
...  
Keyword(s):  
Machine Learning ◽  
Older Adults ◽  
Experimental Studies ◽  
Combined Effect ◽  
Support Vector ◽  
Ecological Value ◽  
Age Related ◽  
And Gender ◽  
Age Range ◽  
Learning Analysis

Background: Experimental studies using qualitative or quantitative analysis have demonstrated that the human voice progressively worsens with ageing. These studies, however, have mostly focused on specific voice features without examining their dynamic interaction. To examine the complexity of age-related changes in voice, more advanced techniques based on machine learning have been recently applied to voice recordings but only in a laboratory setting. We here recorded voice samples in a large sample of healthy subjects. To improve the ecological value of our analysis, we collected voice samples directly at home using smartphones. Methods: 138 younger adults (65 males and 73 females, age range: 15–30) and 123 older adults (47 males and 76 females, age range: 40–85) produced a sustained emission of a vowel and a sentence. The recorded voice samples underwent a machine learning analysis through a support vector machine algorithm. Results: The machine learning analysis of voice samples from both speech tasks discriminated between younger and older adults, and between males and females, with high statistical accuracy. Conclusions: By recording voice samples through smartphones in an ecological setting, we demonstrated the combined effect of age and gender on voice. Our machine learning analysis demonstrates the effect of ageing on voice.

scholarly journals Decoding age-related changes in the spatiotemporal neural processing of speech using machine learning

2019 ◽  
Author(s):  
Md Sultan Mahmud ◽  
Faruk Ahmed ◽  
Rakib Al-Fahad ◽  
Kazi Ashraf Moinuddin ◽  
Mohammed Yeasin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Older Adults ◽  
Hearing Loss ◽  
Brain Regions ◽  
Evoked Response ◽  
Support Vector ◽  
Model Parameters ◽  
Stability Selection ◽  
Degraded Speech ◽  
Age Related

ABSTRACTSpeech comprehension in noisy environments depends on complex interactions between sensory and cognitive systems. In older adults, such interactions may be affected, especially in those individuals who have more severe age-related hearing loss. Using a data-driven approach, we assessed the temporal (when in time) and spatial (where in the brain) characteristics of the cortex’s speech-evoked response that distinguish older adults with or without mild hearing loss. We used source montage to model scalp-recorded during a phoneme discrimination task conducted under clear and noise-degraded conditions. We applied machine learning analyses (stability selection and control) to choose features of the speech-evoked response that are consistent over a range of model parameters and support vector machine (SVM) classification to investigate the time course and brain regions that segregate groups and speech clarity. Whole-brain data analysis revealed a classification accuracy of 82.03% [area under the curve (AUC)=81.18%; F1-score 82.00%], distinguishing groups within ∼50 ms after speech onset (i.e., as early as the P1 wave).We observed lower accuracy of 78.39% [AUC=78.74%; F1-score=79.00%] and delayed classification performance when the speech token were embedded in noise, with group segregation at 60 ms. Separate analysis using left (LH) and right hemisphere (RH) regions showed that LH speech activity was better at distinguishing hearing groups than activity measured over the RH. Moreover, stability selection analysis identified 13 brain regions (among 1428 total spatiotemporal features from 68 regions) where source activity segregated groups with >80% accuracy (clear speech); whereas 15 regions were critical for noise-degraded speech to achieve a comparable level of group segregation (76% accuracy). Our results identify two core neural networks associated with complex speech perception in older adults and confirm a larger number of neural regions, particularly in RH and frontal lobe, are active when processing degraded speech information.

scholarly journals Isokinetic eccentric exercise substantially improves mobility, muscle strength and size, but not postural sway metrics in older adults, with limited regression observed following a detraining period

2020 ◽  
Vol 120 (11) ◽  
pp. 2383-2395 ◽  
Author(s):  
Anthony David Kay ◽  
Anthony John Blazevich ◽  
Millie Fraser ◽  
Lucy Ashmore ◽  
Mathew William Hill
Keyword(s):  
Older Adults ◽  
Muscle Strength ◽  
Eccentric Exercise ◽  
Perceived Exertion ◽  
Postural Sway ◽  
Vastus Lateralis ◽  
Functional Mobility ◽  
Timed Up And Go ◽  
Age Related ◽  
Training Programmes

Abstract Introduction Eccentric exercise can reverse age-related decreases in muscle strength and mass; however, no data exist describing its effects on postural sway. As the ankle may be more important for postural sway than hip and knee joints, and with older adults prone to periods of inactivity, the effects of two 6-week seated isokinetic eccentric exercise programmes, and an 8-week detraining period, were examined in 27 older adults (67.1 ± 6.0 years). Methods Neuromuscular parameters were measured before and after training and detraining periods with subjects assigned to ECC (twice-weekly eccentric-only hip and knee extensor contractions) or ECCPF (identical training with additional eccentric-only plantarflexor contractions) training programmes. Results Significant (P < 0.05) increases in mobility (decreased timed-up-and-go time [− 7.7 to − 12.0%]), eccentric strength (39.4–58.8%) and vastus lateralis thickness (9.8–9.9%) occurred after both training programmes, with low-to-moderate weekly rate of perceived exertion (3.3–4.5/10) reported. No significant change in any postural sway metric occurred after either training programme. After 8 weeks of detraining, mobility (− 8.2 to − 11.3%), eccentric strength (30.5–50.4%) and vastus lateralis thickness (6.1–7.1%) remained significantly greater than baseline in both groups. Conclusion Despite improvements in functional mobility, muscle strength and size, lower-limb eccentric training targeting hip, knee and ankle extensor muscle groups was not sufficient to influence static balance. Nonetheless, as the beneficial functional and structural adaptations were largely maintained through an 8-week detraining period, these findings have important implications for clinical exercise prescription as the exercise modality, low perceived training intensity, and adaptive profile are well suited to the needs of older adults.

scholarly journals Multisensory integration involved in the body perception of community-dwelling older adults

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
M. Hide ◽  
Y. Ito ◽  
N. Kuroda ◽  
M. Kanda ◽  
W. Teramoto
Keyword(s):  
Older Adults ◽  
Multisensory Integration ◽  
Fall Risk ◽  
Community Dwelling ◽  
The Body ◽  
Risk Of Falling ◽  
Body Perception ◽  
Rubber Hand ◽  
Timed Up And Go ◽  
Community Dwelling Older Adults

AbstractThis study investigates how the multisensory integration in body perception changes with increasing age, and whether it is associated with older adults’ risk of falling. For this, the rubber hand illusion (RHI) and rubber foot illusion (RFI) were used. Twenty-eight community-dwelling older adults and 25 university students were recruited. They viewed a rubber hand or foot that was stimulated in synchrony or asynchrony with their own hidden hand or foot. The illusion was assessed by using a questionnaire, and measuring the proprioceptive drift and latency. The Timed Up and Go Test was used to classify the older adults into lower and higher fall-risk groups. No difference was observed in the RHI between the younger and older adults. However, several differences were observed in the RFI. Specifically, the older adults with a lower fall-risk hardly experienced the illusion, whereas those with a higher fall-risk experienced it with a shorter latency and no weaker than the younger adults. These results suggest that in older adults, the mechanism of multisensory integration for constructing body perception can change depending on the stimulated body parts, and that the risk of falling is associated with multisensory integration.

A Two-Stage Machine Learning Classification Approach to Identify Extremism in Arabic Opinions

2021 ◽  
Vol 10 (2) ◽  
pp. 736-745
Keyword(s):  
Machine Learning ◽  
Binary Classification ◽  
Feature Selection Method ◽  
Support Vector ◽  
Two Stage ◽  
Machine Learning Classification ◽  
Second Stage ◽  
Testing Data ◽  
Stage Classification ◽  
Positive Dataset

The increased usage of the Internet and social networks allowed and enabled people to express their views, which have generated an increasing attention lately. Sentiment Analysis (SA) techniques are used to determine the polarity of information, either positive or negative, toward a given topic, including opinions. In this research, we have introduced a machine learning approach based on Support Vector Machine (SVM), Naïve Bayes (NB) and Random Forest (RF) classifiers, to find and classify extreme opinions in Arabic reviews. To achieve this, a dataset of 1500 Arabic reviews was collected from Google Play Store. In addition, a two-stage Classification process was applied to classify the reviews. In the first stage, we built a binary classifier to sort out positive from negative reviews. In the second stage, however we applied a binary classification mechanism based on a set of proposed rules that distinguishes extreme positive from positive reviews, and extreme negative from negative reviews. Four major experiments were conducted with a total of 10 different sub experiments to fulfill the two-stage process using different X-validation schemas and Term Frequency-Inverse Document Frequency feature selection method. Obtained results have indicated that SVM was the best during the first stage classification with 30% testing data, and NB was the best with 20% testing data. The results of the second stage classification indicated that SVM has scored better results in identifying extreme positive reviews when dealing with the positive dataset with an overall accuracy of 68.7% and NB showed better accuracy results in identifying extreme negative reviews when dealing with the negative dataset, with an overall accuracy of 72.8%.

scholarly journals Effects of Periodic Task-Specific Test Feedback on Physical Performance in Older Adults Undertaking Band-Based Resistance Exercise

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Ryuichi Hasegawa ◽  
Mohammod Monirul Islam ◽  
Ryuji Watanabe ◽  
Naoki Tomiyama ◽  
Dennis R. Taaffe
Keyword(s):  
Older Adults ◽  
Physical Performance ◽  
Functional Mobility ◽  
Muscle Performance ◽  
Timed Up And Go ◽  
Feedback Group ◽  
Specific Test ◽  
Periodic Task ◽  
Test Feedback ◽  
Home Based

The purpose of this study was to determine the effects of periodic task-specific test feedback on performance improvement in older adults undertaking community- and home-based resistance exercises (CHBRE). Fifty-two older adults (65–83 years) were assigned to a muscular perfsormance feedback group (MPG,n=32) or a functional mobility feedback group (FMG,n=20). Both groups received exactly the same 9-week CHBRE program comprising one community-based and two home-based sessions per week. Muscle performance included arm curls and chair stands in 30 seconds, while functional mobility was determined by the timed up and go (TUG) test. MPG received fortnightly test feedback only on muscle performance and FMG received feedback only on the TUG. Following training, there was a significant (P<0.05) interaction for all performance tests with MPG improving more for the arm curls (MPG 31.4%, FMG 15.9%) and chair stands (MPG 33.7%, FMG 24.9%) while FMG improved more for the TUG (MPG-3.5%, FMG-9.7%). Results from this nonrandomized study suggest that periodic test feedback during resistance training may enhance task-specific physical performance in older persons, thereby augmenting reserve capacity or potentially reducing the time required to recover functional abilities.

scholarly journals Applying Machine Learning for Improving Performance Classification on Driving Behavior

2021 ◽  
Vol 4 (1) ◽  
pp. 8
Author(s):  
Ahmad Iwan Fadli ◽  
Selo Sulistyo ◽  
Sigit Wibowo
Keyword(s):  
Machine Learning ◽  
Traffic Accident ◽  
Large Scale ◽  
Detection System ◽  
Difficult Problem ◽  
Sensor Data ◽  
Driving Safety ◽  
Support Vector ◽  
Classification Methods ◽  
Machine Learning Classification

Traffic accident is a very difficult problem to handle on a large scale in a country. Indonesia is one of the most populated, developing countries that use vehicles for daily activities as its main transportation.  It is also the country with the largest number of car users in Southeast Asia, so driving safety needs to be considered. Using machine learning classification method to determine whether a driver is driving safely or not can help reduce the risk of driving accidents. We created a detection system to classify whether the driver is driving safely or unsafely using trip sensor data, which include Gyroscope, Acceleration, and GPS. The classification methods used in this study are Random Forest (RF) classification algorithm, Support Vector Machine (SVM), and Multilayer Perceptron (MLP) by improving data preprocessing using feature extraction and oversampling methods. This study shows that RF has the best performance with 98% accuracy, 98% precision, and 97% sensitivity using the proposed preprocessing stages compared to SVM or MLP.

scholarly journals Classifications of Breast Cancer Diagnosis using Machine Learning

2020 ◽  
Vol 14 ◽  
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Random Forest ◽  
Breast Cancer Diagnosis ◽  
Performance Comparison ◽  
Support Vector ◽  
Breast Cancer Dataset ◽  
K Nearest Neighbors ◽  
Cancer Dataset ◽  
Machine Learning Classification

Breast Cancer (BC) is amongst the most common and leading causes of deaths in women throughout the world. Recently, classification and data analysis tools are being widely used in the medical field for diagnosis, prognosis and decision making to help lower down the risks of people dying or suffering from diseases. Advanced machine learning methods have proven to give hope for patients as this has helped the doctors in early detection of diseases like Breast Cancer that can be fatal, in support with providing accurate outcomes. However, the results highly depend on the techniques used for feature selection and classification which will produce a strong machine learning model. In this paper, a performance comparison is conducted using four classifiers which are Multilayer Perceptron (MLP), Support Vector Machine (SVM), K-Nearest Neighbors (KNN) and Random Forest on the Wisconsin Breast Cancer dataset to spot the most effective predictors. The main goal is to apply best machine learning classification methods to predict the Breast Cancer as benign or malignant using terms such as accuracy, f-measure, precision and recall. Experimental results show that Random forest is proven to achieve the highest accuracy of 99.26% on this dataset and features, while SVM and KNN show 97.78% and 97.04% accuracy respectively. MLP shows the least accuracy of 94.07%. All the experiments are conducted using RStudio as the data mining tool platform.

Tremor Identification Using Machine Learning in Parkinson's Disease

2019 ◽  
pp. 128-151
Author(s):  
Angana Saikia ◽  
Vinayak Majhi ◽  
Masaraf Hussain ◽  
Sudip Paul ◽  
Amitava Datta
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Support Vector Machine ◽  
Parkinson's Disease ◽  
Discriminant Analysis ◽  
Learning Algorithms ◽  
The Body ◽  
Machine Learning Algorithms ◽  
Support Vector

Tremor is an involuntary quivering movement or shake. Characteristically occurring at rest, the classic slow, rhythmic tremor of Parkinson's disease (PD) typically starts in one hand, foot, or leg and can eventually affect both sides of the body. The resting tremor of PD can also occur in the jaw, chin, mouth, or tongue. Loss of dopamine leads to the symptoms of Parkinson's disease and may include a tremor. For some people, a tremor might be the first symptom of PD. Various studies have proposed measurable technologies and the analysis of the characteristics of Parkinsonian tremors using different techniques. Various machine-learning algorithms such as a support vector machine (SVM) with three kernels, a discriminant analysis, a random forest, and a kNN algorithm are also used to classify and identify various kinds of tremors. This chapter focuses on an in-depth review on identification and classification of various Parkinsonian tremors using machine learning algorithms.

scholarly journals Towards Using the Instrumented Timed Up-and-Go Test for Screening of Sensory System Performance for Balance Control in Older Adults

Sensors ◽  
2019 ◽  
Vol 19 (3) ◽  
pp. 622 ◽  
Author(s):  
Thomas Gerhardy ◽  
Katharina Gordt ◽  
Carl-Philipp Jansen ◽  
Michael Schwenk
Keyword(s):  
Older Adults ◽  
System Performance ◽  
Fall Risk ◽  
Balance Control ◽  
Sensory System ◽  
Sensory Systems ◽  
Community Dwelling ◽  
Functional Mobility ◽  
Timed Up And Go ◽  
Community Dwelling Older Adults

Background: Decreasing performance of the sensory systems’ for balance control, including the visual, somatosensory and vestibular system, is associated with increased fall risk in older adults. A smartphone-based version of the Timed Up-and-Go (mTUG) may allow screening sensory balance impairments through mTUG subphases. The association between mTUG subphases and sensory system performance is examined. Methods: Functional mobility of forty-one community-dwelling older adults (>55 years) was measured using a validated mTUG. Duration of mTUG and its subphases ‘sit-to-walk’, ‘walking’, ‘turning’, ‘turn-to-sit’ and ‘sit-down’ were extracted. Sensory systems’ performance was quantified by validated posturography during standing (30 s) under different conditions. Visual, somatosensory and vestibular control ratios (CR) were calculated from posturography and correlated with mTUG subphases. Results: Vestibular CR correlated with mTUG total time (r = 0.54; p < 0.01), subphases ‘walking’ (r = 0.56; p < 0.01), and ‘turning’ (r = 0.43; p = 0.01). Somatosensory CR correlated with mTUG total time (r = 0.52; p = 0.01), subphases ‘walking’ (r = 0.52; p < 0.01) and ‘turning’ (r = 0.44; p < 0.01). Conclusions: Supporting the proposed approach, results indicate an association between specific mTUG subphases and sensory system performance. mTUG subphases ‘walking’ and ‘turning’ may allow screening for sensory system deterioration. This is a first step towards an objective, detailed and expeditious balance control assessment, however needing validation in a larger study.

Sign in / Sign up

Export Citation Format

Share Document