MyMedR

Displaying publications 1 - 20 of 42 in total

Abstract:

Sort:

Optimal set of EEG features for emotional state classification and trajectory visualization in Parkinson's disease

Yuvaraj R, Murugappan M, Ibrahim NM, Sundaraj K, Omar MI, Mohamad K, et al.

Int J Psychophysiol, 2014 Dec;94(3):482-95.
PMID: 25109433 DOI: 10.1016/j.ijpsycho.2014.07.014

In addition to classic motor signs and symptoms, individuals with Parkinson's disease (PD) are characterized by emotional deficits. Ongoing brain activity can be recorded by electroencephalograph (EEG) to discover the links between emotional states and brain activity. This study utilized machine-learning algorithms to categorize emotional states in PD patients compared with healthy controls (HC) using EEG. Twenty non-demented PD patients and 20 healthy age-, gender-, and education level-matched controls viewed happiness, sadness, fear, anger, surprise, and disgust emotional stimuli while fourteen-channel EEG was being recorded. Multimodal stimulus (combination of audio and visual) was used to evoke the emotions. To classify the EEG-based emotional states and visualize the changes of emotional states over time, this paper compares four kinds of EEG features for emotional state classification and proposes an approach to track the trajectory of emotion changes with manifold learning. From the experimental results using our EEG data set, we found that (a) bispectrum feature is superior to other three kinds of features, namely power spectrum, wavelet packet and nonlinear dynamical analysis; (b) higher frequency bands (alpha, beta and gamma) play a more important role in emotion activities than lower frequency bands (delta and theta) in both groups and; (c) the trajectory of emotion changes can be visualized by reducing subject-independent features with manifold learning. This provides a promising way of implementing visualization of patient's emotional state in real time and leads to a practical system for noninvasive assessment of the emotional impairments associated with neurological disorders.
Inter-hemispheric EEG coherence analysis in Parkinson's disease: assessing brain activity during emotion processing

Yuvaraj R, Murugappan M, Ibrahim NM, Sundaraj K, Omar MI, Mohamad K, et al.

J Neural Transm (Vienna), 2015 Feb;122(2):237-52.
PMID: 24894699 DOI: 10.1007/s00702-014-1249-4

Parkinson's disease (PD) is not only characterized by its prominent motor symptoms but also associated with disturbances in cognitive and emotional functioning. The objective of the present study was to investigate the influence of emotion processing on inter-hemispheric electroencephalography (EEG) coherence in PD. Multimodal emotional stimuli (happiness, sadness, fear, anger, surprise, and disgust) were presented to 20 PD patients and 30 age-, education level-, and gender-matched healthy controls (HC) while EEG was recorded. Inter-hemispheric coherence was computed from seven homologous EEG electrode pairs (AF3-AF4, F7-F8, F3-F4, FC5-FC6, T7-T8, P7-P8, and O1-O2) for delta, theta, alpha, beta, and gamma frequency bands. In addition, subjective ratings were obtained for a representative of emotional stimuli. Interhemispherically, PD patients showed significantly lower coherence in theta, alpha, beta, and gamma frequency bands than HC during emotion processing. No significant changes were found in the delta frequency band coherence. We also found that PD patients were more impaired in recognizing negative emotions (sadness, fear, anger, and disgust) than relatively positive emotions (happiness and surprise). Behaviorally, PD patients did not show impairment in emotion recognition as measured by subjective ratings. These findings suggest that PD patients may have an impairment of inter-hemispheric functional connectivity (i.e., a decline in cortical connectivity) during emotion processing. This study may increase the awareness of EEG emotional response studies in clinical practice to uncover potential neurophysiologic abnormalities.
Emotion classification in Parkinson's disease by higher-order spectra and power spectrum features using EEG signals: a comparative study

Yuvaraj R, Murugappan M, Ibrahim NM, Omar MI, Sundaraj K, Mohamad K, et al.

J Integr Neurosci, 2014 Mar;13(1):89-120.
PMID: 24738541 DOI: 10.1142/S021963521450006X

Deficits in the ability to process emotions characterize several neuropsychiatric disorders and are traits of Parkinson's disease (PD), and there is need for a method of quantifying emotion, which is currently performed by clinical diagnosis. Electroencephalogram (EEG) signals, being an activity of central nervous system (CNS), can reflect the underlying true emotional state of a person. This study applied machine-learning algorithms to categorize EEG emotional states in PD patients that would classify six basic emotions (happiness and sadness, fear, anger, surprise and disgust) in comparison with healthy controls (HC). Emotional EEG data were recorded from 20 PD patients and 20 healthy age-, education level- and sex-matched controls using multimodal (audio-visual) stimuli. The use of nonlinear features motivated by the higher-order spectra (HOS) has been reported to be a promising approach to classify the emotional states. In this work, we made the comparative study of the performance of k-nearest neighbor (kNN) and support vector machine (SVM) classifiers using the features derived from HOS and from the power spectrum. Analysis of variance (ANOVA) showed that power spectrum and HOS based features were statistically significant among the six emotional states (p < 0.0001). Classification results shows that using the selected HOS based features instead of power spectrum based features provided comparatively better accuracy for all the six classes with an overall accuracy of 70.10% ± 2.83% and 77.29% ± 1.73% for PD patients and HC in beta (13-30 Hz) band using SVM classifier. Besides, PD patients achieved less accuracy in the processing of negative emotions (sadness, fear, anger and disgust) than in processing of positive emotions (happiness, surprise) compared with HC. These results demonstrate the effectiveness of applying machine learning techniques to the classification of emotional states in PD patients in a user independent manner using EEG signals. The accuracy of the system can be improved by investigating the other HOS based features. This study might lead to a practical system for noninvasive assessment of the emotional impairments associated with neurological disorders.
Fulltext On the analysis of EEG power, frequency and asymmetry in Parkinson's disease during emotion processing

Yuvaraj R, Murugappan M, Mohamed Ibrahim N, Iqbal M, Sundaraj K, Mohamad K, et al.

Behav Brain Funct, 2014;10:12.
PMID: 24716619 DOI: 10.1186/1744-9081-10-12

While Parkinson's disease (PD) has traditionally been described as a movement disorder, there is growing evidence of disruption in emotion information processing associated with the disease. The aim of this study was to investigate whether there are specific electroencephalographic (EEG) characteristics that discriminate PD patients and normal controls during emotion information processing.
Fulltext Review of emotion recognition in stroke patients

Yuvaraj R, Murugappan M, Norlinah MI, Sundaraj K, Khairiyah M

Dement Geriatr Cogn Disord, 2013;36(3-4):179-96.
PMID: 23899462 DOI: 10.1159/000353440

OBJECTIVE: Patients suffering from stroke have a diminished ability to recognize emotions. This paper presents a review of neuropsychological studies that investigated the basic emotion processing deficits involved in individuals with interhemispheric brain (right, left) damage and normal controls, including processing mode (perception) and communication channels (facial, prosodic-intonational, lexical-verbal).
METHODS: An electronic search was conducted using specific keywords for studies investigating emotion recognition in brain damage patients. The PubMed database was searched until March 2012 as well as citations and reference lists. 92 potential articles were identified.
RESULTS: The findings showed that deficits in emotion perception were more frequently observed in individuals with right brain damage than those with left brain damage when processing facial, prosodic and lexical emotional stimuli.
CONCLUSION: These findings suggest that the right hemisphere has a unique contribution in emotional processing and provide support for the right hemisphere emotion hypothesis.
SIGNIFICANCE:
This robust deficit in emotion recognition has clinical significance. The extent of emotion recognition deficit in brain damage patients appears to be correlated with a variety of interpersonal difficulties such as complaints of frustration in social relations, feelings of social discomfort, desire to connect with others, feelings of social disconnection and use of controlling behaviors.
Emotion processing in Parkinson's disease: an EEG spectral power study

Yuvaraj R, Murugappan M, Omar MI, Ibrahim NM, Sundaraj K, Mohamad K, et al.

Int J Neurosci, 2014 Jul;124(7):491-502.
PMID: 24168328 DOI: 10.3109/00207454.2013.860527

Although an emotional deficit is a common finding in Parkinson's disease (PD), its neurobiological mechanism on emotion recognition is still unknown. This study examined the emotion processing deficits in PD patients using electroencephalogram (EEG) signals in response to multimodal stimuli.
Fulltext Effect of Forearm Postures and Elbow Joint Angles on Elbow Flexion Torque and Mechanomyography in Neuromuscular Electrical Stimulation of the Biceps Brachii

Uwamahoro R, Sundaraj K, Feroz FS

Sensors (Basel), 2023 Sep 29;23(19).
PMID: 37836995 DOI: 10.3390/s23198165

Neuromuscular electrical stimulation plays a pivotal role in rehabilitating muscle function among individuals with neurological impairment. However, there remains uncertainty regarding whether the muscle's response to electrical excitation is affected by forearm posture, joint angle, or a combination of both factors. This study aimed to investigate the effects of forearm postures and elbow joint angles on the muscle torque and MMG signals. Measurements of the torque around the elbow and MMG of the biceps brachii (BB) muscle were conducted in 36 healthy subjects (age, 22.24 ± 2.94 years; height, 172 ± 0.5 cm; and weight, 67.01 ± 7.22 kg) using an in-house elbow flexion testbed and neuromuscular electrical stimulation (NMES) of the BB muscle. The BB muscle was stimulated while the forearm was positioned in the neutral, pronation, or supination positions. The elbow was flexed at angles of 10°, 30°, 60°, and 90°. The study analyzed the impact of the forearm posture(s) and elbow joint angle(s) on the root-mean-square value of the torque (TQRMS). Subsequently, various MMG parameters, such as the root-mean-square value (MMGRMS), the mean power frequency (MMGMPF), and the median frequency (MMGMDF), were analyzed along the longitudinal, lateral, and transverse axes of the BB muscle fibers. The test-retest interclass correlation coefficient (ICC21) for the torque and MMG ranged from 0.522 to 0.828. Repeated-measure ANOVAs showed that the forearm posture and elbow flexion angle significantly influenced the TQRMS (p < 0.05). Similarly, the MMGRMS, MMGMPF, and MMGMDF showed significant differences among all the postures and angles (p < 0.05). However, the combined main effect of the forearm posture and elbow joint angle was insignificant along the longitudinal axis (p > 0.05). The study also found that the MMGRMS and TQRMS increased with increases in the joint angle from 10° to 60° and decreased at greater angles. However, during this investigation, the MMGMPF and MMGMDF exhibited a consistent decrease in response to increases in the joint angle for the lateral and transverse axes of the BB muscle. These findings suggest that the muscle contraction evoked by NMES may be influenced by the interplay between actin and myosin filaments, which are responsible for muscle contraction and are, in turn, influenced by the muscle length. Because restoring the function of limbs is a common goal in rehabilitation services, the use of MMG in the development of methods that may enable the real-time tracking of exact muscle dimensional changes and activation levels is imperative.
Fulltext Assessment of muscle activity using electrical stimulation and mechanomyography: a systematic review

Uwamahoro R, Sundaraj K, Subramaniam ID

Biomed Eng Online, 2021 Jan 03;20(1):1.
PMID: 33390158 DOI: 10.1186/s12938-020-00840-w

This research has proved that mechanomyographic (MMG) signals can be used for evaluating muscle performance. Stimulation of the lost physiological functions of a muscle using an electrical signal has been determined crucial in clinical and experimental settings in which voluntary contraction fails in stimulating specific muscles. Previous studies have already indicated that characterizing contractile properties of muscles using MMG through neuromuscular electrical stimulation (NMES) showed excellent reliability. Thus, this review highlights the use of MMG signals on evaluating skeletal muscles under electrical stimulation. In total, 336 original articles were identified from the Scopus and SpringerLink electronic databases using search keywords for studies published between 2000 and 2020, and their eligibility for inclusion in this review has been screened using various inclusion criteria. After screening, 62 studies remained for analysis, with two additional articles from the bibliography, were categorized into the following: (1) fatigue, (2) torque, (3) force, (4) stiffness, (5) electrode development, (6) reliability of MMG and NMES approaches, and (7) validation of these techniques in clinical monitoring. This review has found that MMG through NMES provides feature factors for muscle activity assessment, highlighting standardized electromyostimulation and MMG parameters from different experimental protocols. Despite the evidence of mathematical computations in quantifying MMG along with NMES, the requirement of the processing speed, and fluctuation of MMG signals influence the technique to be prone to errors. Interestingly, although this review does not focus on machine learning, there are only few studies that have adopted it as an alternative to statistical analysis in the assessment of muscle fatigue, torque, and force. The results confirm the need for further investigation on the use of sophisticated computations of features of MMG signals from electrically stimulated muscles in muscle function assessment and assistive technology such as prosthetics control.
Fulltext Association of anthropometric parameters with amplitude and crosstalk of mechanomyographic signals during forearm flexion, pronation and supination torque tasks

Talib I, Sundaraj K, Lam CK

Sci Rep, 2019 11 07;9(1):16166.
PMID: 31700129 DOI: 10.1038/s41598-019-52536-4

This study aimed to quantify the association of four anthropometric parameters of the human arm, namely, the arm circumference (CA), arm length (LA), skinfold thickness (ST) and inter-sensor distance (ISD), with amplitude (RMS) and crosstalk (CT) of mechanomyography (MMG) signals. Twenty-five young, healthy, male participants were recruited to perform forearm flexion, pronation and supination torque tasks. Three accelerometers were employed to record the MMG signals from the biceps brachii (BB), brachialis (BRA) and brachioradialis (BRD) at 80% maximal voluntary contraction (MVC). Signal RMS was used to quantify the amplitude of the MMG signals from a muscle, and cross-correlation coefficients were used to quantify the magnitude of the CT among muscle pairs (BB & BRA, BRA & BRD, and BB & BRD). For all investigated muscles and pairs, RMS and CT showed negligible to low negative correlations with CA, LA and ISD (r = -0.0001--0.4611), and negligible to moderate positive correlations with ST (r = 0.004-0.511). However, almost all of these correlations were statistically insignificant (p > 0.05). These findings suggest that RMS and CT values for the elbow flexor muscles recorded and quantified using accelerometers appear invariant to anthropometric parameters.
Analysis of the crosstalk in mechanomyographic signals along the longitudinal, lateral and transverse axes of elbow flexor muscles during sustained isometric forearm flexion, supination and pronation exercises

Talib I, Sundaraj K, Lam CK

J Musculoskelet Neuronal Interact, 2020 06 01;20(2):194-205.
PMID: 32481235

OBJECTIVE: To analyse the influence of muscle fibre axis on the degree of crosstalk in mechanomyographic (MMG) signals during sustained isometric forearm flexion, pronation and supination exercises performed at 80% maximum voluntary contraction (MVC) at an elbow joint angle of 90°.
METHODS: MMG signals in longitudinal, lateral and transverse directions of muscle fibres were recorded from the elbow flexors of twenty-five male subjects using triaxial accelerometers. Cross-correlation coefficients were used to quantify the degree of crosstalk in all nine possible pairs of fibre axes, all muscle pairs and all exercises.
RESULTS: MMG root mean square (RMS) was statistically significant among the fibre axes (p<0.05, η2=0.17- 0.34) except for biceps brachii and brachioradialis in supination and brachialis in flexion. Overall mean crosstalk values in the three muscle pairs (biceps brachii & brachialis, brachialis & brachioradialis and brachioradialis & biceps brachii) were found to be 6.09-52.17%, 4.01-61.42% and 2.16-51.85%, respectively. Crosstalk values showed statistical significance among all nine axes pairs (p<0.05, η2=0.16-0.51) except for biceps brachii & brachialis during pronation. The transverse axes pair generated the lowest mean crosstalk values (2.16-9.14%).
CONCLUSION: MMG signals recorded using accelerometers from the transverse axes of muscle fibres in the elbow flexors are unique and yield the least amount of crosstalk.
Crosstalk in Mechanomyographic Signals From Elbow Flexor Muscles During Submaximal to Maximal Isometric Flexion, Pronation, and Supination Torque Tasks

Talib I, Sundaraj K, Lam CK

J Biomech Eng, 2021 01 01;143(1).
PMID: 32691054 DOI: 10.1115/1.4047850

This study analyzed the crosstalk in mechanomyographic (MMG) signals from elbow flexors during isometric muscle actions from 20% to 100% maximum voluntary isometric contraction (MVIC). Twenty-five young, healthy, male participants performed the isometric elbow flexion, forearm pronation, and supination tasks at an elbow joint angle of 90 deg. The MMG signals from the biceps brachii (BB), brachialis (BRA), and brachioradialis (BRD) muscles were recorded using accelerometers. The cross-correlation coefficient was used to quantify the crosstalk in MMG signals, recorded in a direction transverse to muscle fiber axis, among the muscle pairs (P1: BB and BRA, P2: BRA and BRD, and P3: BB and BRD). In addition, the MMG RMS and MPF were quantified. The mean normalized RMS and mean MPF exhibited increasing (r > 0.900) and decreasing (r
A review on crosstalk in myographic signals

Talib I, Sundaraj K, Lam CK, Hussain J, Ali MA

Eur J Appl Physiol, 2019 Jan;119(1):9-28.
PMID: 30242464 DOI: 10.1007/s00421-018-3994-9

PURPOSE: Crosstalk in myographic signals is a major hindrance to the understanding of local information related to individual muscle function. This review aims to analyse the problem of crosstalk in electromyography and mechanomyography.
METHODS: An initial search of the SCOPUS database using an appropriate set of keywords yielded 290 studies, and 59 potential studies were selected after all the records were screened using the eligibility criteria. This review on crosstalk revealed that signal contamination due to crosstalk remains a major challenge in the application of surface myography techniques. Various methods have been employed in previous studies to identify, quantify and reduce crosstalk in surface myographic signals.
RESULTS: Although correlation-based methods for crosstalk quantification are easy to use, there is a possibility that co-contraction could be interpreted as crosstalk. High-definition EMG has emerged as a new technique that has been successfully applied to reduce crosstalk.
CONCLUSIONS: The phenomenon of crosstalk needs to be investigated carefully because it depends on many factors related to muscle task and physiology. This review article not only provides a good summary of the literature on crosstalk in myographic signals but also discusses new directions related to techniques for crosstalk identification, quantification and reduction. The review also provides insights into muscle-related issues that impact crosstalk in myographic signals.
A systematic review of muscle activity assessment of the biceps brachii muscle using mechanomyography

Talib I, Sundaraj K, Lam CK, Sundaraj S

J Musculoskelet Neuronal Interact, 2018 12 01;18(4):446-462.
PMID: 30511949

This systematic review aims to categorically analyses the literature on the assessment of biceps brachii (BB) muscle activity through mechanomyography (MMG). The application of our search criteria to five different databases identified 319 studies. A critical review of the 48 finally selected records, revealed the diversity of protocols and parameters that are employed in MMG-based assessments of BB muscle activity. The observations were categorized into the following: muscle torque, fatigue, strength and physiology. The available information on the muscle contraction protocol, sensor(s), MMG signal parameters and obtained results were then tabulated based on these categories for further analysis. The review affirms that - 1) MMG is suitable for skeletal muscle activity assessment and can be employed potentially for further investigation of the BB muscle activity and condition (e.g., force, torque, fatigue, and contractile properties), 2) a majority of the records focused on static contractions of the BB, and the analysis of dynamic muscle contractions using MMG is thus a research gap, and 3) very few studies have focused on the analysis of BB muscle activity under externally stimulated contractions. Taken together, the findings of this review on BB activity assessment using MMG affirm the potential of MMG as an alternative tool.
Fulltext Analysis of anthropometrics and mechanomyography signals as forearm flexion, pronation and supination torque predictors

Talib I, Sundaraj K, Hussain J, Lam CK, Ahmad Z

Sci Rep, 2022 Sep 27;12(1):16086.
PMID: 36168025 DOI: 10.1038/s41598-022-20223-6

This study aimed to analyze anthropometrics and mechanomyography (MMG) signals as forearm flexion, pronation, and supination torque predictors. 25 young, healthy, male participants performed isometric forearm flexion, pronation, and supination tasks from 20 to 100% maximal voluntary isometric contraction (MVIC) while maintaining 90° at the elbow joint. Nine anthropometric measures were recorded, and MMG signals from the biceps brachii (BB), brachialis (BRA), and brachioradialis (BRD) muscles were digitally acquired using triaxial accelerometers. These were then correlated with torque values. Significant positive correlations were found for arm circumference (CA) and MMG root mean square (RMS) values with flexion torque. Flexion torque might be predicted using CA (r = 0.426-0.575), a pseudo for muscle size while MMGRMS (r = 0.441), an indication of muscle activation.
A survey on automated wheeze detection systems for asthmatic patients

Shaharum SM, Sundaraj K, Palaniappan R

Bosn J Basic Med Sci, 2012 Nov;12(4):249-55.
PMID: 23198941

The purpose of this paper is to present an evidence of automated wheeze detection system by a survey that can be very beneficial for asthmatic patients. Generally, for detecting asthma in a patient, stethoscope is used for ascertaining wheezes present. This causes a major problem nowadays because a number of patients tend to delay the interpretation time, which can lead to misinterpretations and in some worst cases to death. Therefore, the development of automated system would ease the burden of medical personnel. A further discussion on automated wheezes detection system will be presented later in the paper. As for the methodology, a systematic search of articles published as early as 1985 to 2012 was conducted. Important details including the hardware used, placement of hardware, and signal processing methods have been presented clearly thus hope to help and encourage future researchers to develop commercial system that will improve the diagnosing and monitoring of asthmatic patients.
Initial assessment of facial nerve paralysis based on motion analysis using an optical flow method

Samsudin WS, Sundaraj K, Ahmad A, Salleh H

Technol Health Care, 2016 Mar 14;24(2):287-94.
PMID: 26578273 DOI: 10.3233/THC-151103

An initial assessment method that can classify as well as categorize the severity of paralysis into one of six levels according to the House-Brackmann (HB) system based on facial landmarks motion using an Optical Flow (OF) algorithm is proposed. The desired landmarks were obtained from the video recordings of 5 normal and 3 Bell's Palsy subjects and tracked using the Kanade-Lucas-Tomasi (KLT) method. A new scoring system based on the motion analysis using area measurement is proposed. This scoring system uses the individual scores from the facial exercises and grades the paralysis based on the HB system. The proposed method has obtained promising results and may play a pivotal role towards improved rehabilitation programs for patients.
Drowsiness detection during different times of day using multiple features

Sahayadhas A, Sundaraj K, Murugappan M

Australas Phys Eng Sci Med, 2013 Jun;36(2):243-50.
PMID: 23719977 DOI: 10.1007/s13246-013-0200-6

Driver drowsiness has been one of the major causes of road accidents that lead to severe trauma, such as physical injury, death, and economic loss, which highlights the need to develop a system that can alert drivers of their drowsy state prior to accidents. Researchers have therefore attempted to develop systems that can determine driver drowsiness using the following four measures: (1) subjective ratings from drivers, (2) vehicle-based measures, (3) behavioral measures and (4) physiological measures. In this study, we analyzed the various factors that contribute towards drowsiness. A total of 15 male subjects were asked to drive for 2 h at three different times of the day (00:00-02:00, 03:00-05:00 and 15:00-17:00 h) when the circadian rhythm is low. The less intrusive physiological signal measurements, ECG and EMG, are analyzed during this driving task. Statistically significant differences in the features of ECG and sEMG signals were observed between the alert and drowsy states of the drivers during different times of day. In the future, these physiological measures can be fused with vision-based measures for the development of an efficient drowsiness detection system.
Fulltext Detecting driver drowsiness based on sensors: a review

Sahayadhas A, Sundaraj K, Murugappan M

Sensors (Basel), 2012 Dec 07;12(12):16937-53.
PMID: 23223151 DOI: 10.3390/s121216937

In recent years, driver drowsiness has been one of the major causes of road accidents and can lead to severe physical injuries, deaths and significant economic losses. Statistics indicate the need of a reliable driver drowsiness detection system which could alert the driver before a mishap happens. Researchers have attempted to determine driver drowsiness using the following measures: (1) vehicle-based measures; (2) behavioral measures and (3) physiological measures. A detailed review on these measures will provide insight on the present systems, issues associated with them and the enhancements that need to be done to make a robust system. In this paper, we review these three measures as to the sensors used and discuss the advantages and limitations of each. The various ways through which drowsiness has been experimentally manipulated is also discussed. We conclude that by designing a hybrid drowsiness detection system that combines non-intrusive physiological measures with other measures one would accurately determine the drowsiness level of a driver. A number of road accidents might then be avoided if an alert is sent to a driver that is deemed drowsy.
A novel approach to detect respiratory phases from pulmonary acoustic signals using normalised power spectral density and fuzzy inference system

Palaniappan R, Sundaraj K, Sundaraj S, Huliraj N, Revadi SS

Clin Respir J, 2016 Jul;10(4):486-94.
PMID: 25515741 DOI: 10.1111/crj.12250

BACKGROUND: Monitoring respiration is important in several medical applications. One such application is respiratory rate monitoring in patients with sleep apnoea. The respiratory rate in patients with sleep apnoea disorder is irregular compared with the controls. Respiratory phase detection is required for a proper monitoring of respiration in patients with sleep apnoea.
AIMS: To develop a model to detect the respiratory phases present in the pulmonary acoustic signals and to evaluate the performance of the model in detecting the respiratory phases.
METHODS: Normalised averaged power spectral density for each frame and change in normalised averaged power spectral density between the adjacent frames were fuzzified and fuzzy rules were formulated. The fuzzy inference system (FIS) was developed with both Mamdani and Sugeno methods. To evaluate the performance of both Mamdani and Sugeno methods, correlation coefficient and root mean square error (RMSE) were calculated.
RESULTS: In the correlation coefficient analysis in evaluating the fuzzy model using Mamdani and Sugeno method, the strength of the correlation was found to be r = 0.9892 and r = 0.9964, respectively. The RMSE for Mamdani and Sugeno methods are RMSE = 0.0853 and RMSE = 0.0817, respectively.
CONCLUSION: The correlation coefficient and the RMSE of the proposed fuzzy models in detecting the respiratory phases reveals that Sugeno method performs better compared with the Mamdani method.
Fulltext A comparative study of the SVM and K-nn machine learning algorithms for the diagnosis of respiratory pathologies using pulmonary acoustic signals

Palaniappan R, Sundaraj K, Sundaraj S

BMC Bioinformatics, 2014;15:223.
PMID: 24970564 DOI: 10.1186/1471-2105-15-223

Pulmonary acoustic parameters extracted from recorded respiratory sounds provide valuable information for the detection of respiratory pathologies. The automated analysis of pulmonary acoustic signals can serve as a differential diagnosis tool for medical professionals, a learning tool for medical students, and a self-management tool for patients. In this context, we intend to evaluate and compare the performance of the support vector machine (SVM) and K-nearest neighbour (K-nn) classifiers in diagnosis respiratory pathologies using respiratory sounds from R.A.L.E database.

Filters

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links