Hybrid learning control for improving suppression of hand tremor

As’arry, Azizan; Zain, Mohd; Mailah, Musa; Hussein, Mohamed

doi:10.1177/0954411913494325

Cited by 15 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The inaccuracy in the detection of PD might have some possible reasons that include the variability in the severity of PD across patients, the sensor’s intrinsic uncertainty, and the fact that some patients may consciously or subconsciously suppress their tremors during the experiment. In previous studies, [ 37 ] and [ 38 ], PD tremor is considered and reported as a single frequency signal, and the fundamental frequency ranges between 4 to 12 Hz. However, the results in [ 30 ] showed that PD tremor consists of several harmonics.…”

Section: Discussionmentioning

confidence: 99%

Telemonitoring Parkinson’s disease using machine learning by combining tremor and voice analysis

et al. 2020

View full text Add to dashboard Cite

Background With the growing number of the aged population, the number of Parkinson’s disease (PD) affected people is also mounting. Unfortunately, due to insufficient resources and awareness in underdeveloped countries, proper and timely PD detection is highly challenged. Besides, all PD patients’ symptoms are neither the same nor they all become pronounced at the same stage of the illness. Therefore, this work aims to combine more than one symptom (rest tremor and voice degradation) by collecting data remotely using smartphones and detect PD with the help of a cloud-based machine learning system for telemonitoring the PD patients in the developing countries. Method This proposed system receives rest tremor and vowel phonation data acquired by smartphones with built-in accelerometer and voice recorder sensors. The data are primarily collected from diagnosed PD patients and healthy people for building and optimizing machine learning models that exhibit higher performance. After that, data from newly suspected PD patients are collected, and the trained algorithms are evaluated to detect PD. Based on the majority-vote from those algorithms, PD-detected patients are connected with a nearby neurologist for consultation. Upon receiving patients’ feedback after being diagnosed by the neurologist, the system may update the model by retraining using the latest data. Also, the system requests the detected patients periodically to upload new data to track their disease progress. Result The highest accuracy in PD detection using offline data was $$98.3\%$$ 98.3 % from voice data and $$98.5\%$$ 98.5 % from tremor data when used separately. In both cases, k-nearest neighbors (kNN) gave the highest accuracy over support vector machine (SVM) and naive Bayes (NB). The application of maximum relevance minimum redundancy (MRMR) feature selection method showed that by selecting different feature sets based on the patient’s gender, we could improve the detection accuracy. This study’s novelty is the application of ensemble averaging on the combined decisions generated from the analysis of voice and tremor data. The average accuracy of PD detection becomes $$99.8\%$$ 99.8 % when ensemble averaging was performed on majority-vote from kNN, SVM, and NB. Conclusion The proposed system can detect PD using a cloud-based system for computation, data preserving, and regular monitoring of voice and tremor samples captured by smartphones. Thus, this system can be a solution for healthcare authorities to ensure the older population’s accessibility to a better medical diagnosis system in the developing countries, especially in the pandemic situation like COVID-19, when in-person monitoring is minimal.

show abstract

Section: Discussionmentioning

confidence: 99%

Telemonitoring Parkinson’s disease using machine learning by combining tremor and voice analysis

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In this research, the I and D actions were excluded because both actions could cause the current control system to amplify the measurement, making the control system unable to run properly, thus producing no significant result. The variations of P values were set in the range of maximum voltage that the LVCA can experienced [16], [21], [22].…”

Section: Designing Controller 21 P Controllermentioning

confidence: 99%

“…Herrnstadt and Menon used proportional-integral-derivative (PID) controller to obtain 99.8% tremor vibration reduction [15]. Besides that, As'arry et al had also managed to achieve 98.25% tremor vibration reduction using PI+AFCAIL [16]. Meanwhile, Stone et al and Lavu and Gupta obtained 20% to 60% tremor suppression in 6-13 Hz bandwidth and 83.4% tremor suppression respectively by using PID [17], [18].…”

mentioning

confidence: 99%

Active tremor control in human-like hand tremor using fuzzy logic

Jamaludin

As’arry

Musab

et al. 2021

IJEECS

View full text Add to dashboard Cite

Tremoris the vibration in sinusoidal orientation that is experienced regularly by a person with Parkinson’s disease (PD), which disturbs their daily activities. One solution that may be used to counter this tremor effect is by developing an active tremor control system in LabVIEW for linear voice coil actuator (LVCA), where the system uses proportional (P) controller and various types of fuzzy logic controller (FLC) as a hybrid controller to reduce tremor vibration. From this research, it can be concluded that the best controller for tremor reduction is the P+FLC 1st set of rules, compared to P+FLC 2nd set of rules, and P controller only, with the highest percentage of 88.39% of tremor reduction with the actual tremor vibration of PD patients as the reference result. The P+FLC 2nd set of rules has the highest percentage of tremor reduction with a value of 86.81%, whereas P controller only has the highest tremor reduction percentage of 67.10%. This percentage of tremor reduction is based on the power spectral density (PSD) values, in which it represents the intensity of the tremor vibration. This experimental study can be used as an initial step for researchers and engineers to design and develop an anti-tremor device in the future.

show abstract

“…This frequency range is selected properly to conserve the frequencies interest of a tremor which is in a range of 3-12Hz [4] and at the same time eliminate the noise. The signal processing and control part were done with LabVIEW graphical user interface software package and for faster online control, a low level programming environment is necessary to reduce computational buffering [5].…”

Section: System Descriptionmentioning

confidence: 99%