Kenneth Sundaraj

A comparative study of the svm and k-nn machine learning algorithms for the diagnosis of respiratory pathologies using pulmonary acoustic signals

BackgroundPulmonary 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.ResultsThe pulmonary acoustic signals used in this study were obtained from the R.A.L.E lung sound database. The pulmonary acoustic signals were manually categorised into three different groups, namely normal, airway obstruction pathology, and parenchymal pathology. The mel-frequency cepstral coefficient (MFCC) features were extracted from the pre-processed pulmonary acoustic signals. The MFCC features were analysed by one-way ANOVA and then fed separately into the SVM and K-nn classifiers. The performances of the classifiers were analysed using the confusion matrix technique. The statistical analysis of the MFCC features using one-way ANOVA showed that the extracted MFCC features are significantly different (p < 0.001). The classification accuracies of the SVM and K-nn classifiers were found to be 92.19% and 98.26%, respectively.ConclusionAlthough the data used to train and test the classifiers are limited, the classification accuracies found are satisfactory. The K-nn classifier was better than the SVM classifier for the discrimination of pulmonary acoustic signals from pathological and normal subjects obtained from the RALE database.

Computer-based Respiratory Sound Analysis: A Systematic Review

Abstract Over the years, lung auscultation has been used as an effective clinical tool to monitor the state of the respiratory system. Lung auscultation provides valuable information regarding the patient’s respiratory function. Recent technical advances have led to the development of computer-based respiratory sound analysis which serves as a powerful tool to diagnose abnormalities and disorders in the lung. This paper provides a comprehensive review on computer-based respiratory sound analysis techniques employed by various researchers in the past. The search for articles related to computer-based respiratory sound analysis was carried out on electronic resources such as IEEE, Springer, Elsevier, Pub Med, and ACM digital library databases. Around 55 articles were identified and were subjected to a systematic review. In this review, we examine lung sound/lung disorder, sensor used, sensor locations, number of subjects, signal processing methods, classification methods, and statistical methods employed for the analysis of lung sounds by previous researchers. A brief discussion is undertaken on the overview from the previous works. Finally, the review is concluded by discussing the possibilities and recommendations for further improvements.

A telemedicine tool to detect pulmonary pathology using computerized pulmonary acoustic signal analysis

Respiratory sound signals are prepossessed and respiratory cycles are segmented.S-transform based statistical features were extracted.The features were classified using KNN, SVM and ELM classifier.Accuracy of 94.99%, 96.85% and 98.52% for KNN, SVM and ELM, respectively.Telemedicine software was developed using ELM classifier. BackgroundDetection and monitoring of respiratory related illness is an important aspect in pulmonary medicine. Acoustic signals extracted from the human body are considered in detection of respiratory pathology accurately. ObjectivesThe aim of this study is to develop a prototype telemedicine tool to detect respiratory pathology using computerized respiratory sound analysis. MethodsAround 120 subjects (40 normal, 40 continuous lung sounds (20 wheeze and 20 rhonchi)) and 40 discontinuous lung sounds (20 fine crackles and 20 coarse crackles) were included in this study. The respiratory sounds were segmented into respiratory cycles using fuzzy inference system and then S-transform was applied to these respiratory cycles. From the S-transform matrix, statistical features were extracted. The extracted features were statistically significant with p<0.05. To classify the respiratory pathology KNN, SVM and ELM classifiers were implemented using the statistical features obtained from of the data. ResultsThe validation showed that the classification rate for training for ELM classifier with RBF kernel was high compared to the SVM and KNN classifiers. The time taken for training the classifier was also less in ELM compared to SVM and KNN classifiers. The overall mean classification rate for ELM classifier was 98.52%. ConclusionThe telemedicine software tool was developed using the ELM classifier. The telemedicine tool has performed extraordinary well in detecting the respiratory pathology and it is well validated.

Artificial intelligence techniques used in respiratory sound analysis – a systematic review

Abstract Artificial intelligence (AI) has recently been established as an alternative method to many conventional methods. The implementation of AI techniques for respiratory sound analysis can assist medical professionals in the diagnosis of lung pathologies. This article highlights the importance of AI techniques in the implementation of computer-based respiratory sound analysis. Articles on computer-based respiratory sound analysis using AI techniques were identified by searches conducted on various electronic resources, such as the IEEE, Springer, Elsevier, PubMed, and ACM digital library databases. Brief descriptions of the types of respiratory sounds and their respective characteristics are provided. We then analyzed each of the previous studies to determine the specific respiratory sounds/pathology analyzed, the number of subjects, the signal processing method used, the AI techniques used, and the performance of the AI technique used in the analysis of respiratory sounds. A detailed description of each of these studies is provided. In conclusion, this article provides recommendations for further advancements in respiratory sound analysis.

A novel approach to detect respiratory phases from pulmonary acoustic signals using normalised power spectral density and fuzzy inference system.

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.

Physiological signal based detection of driver hypovigilance using higher order spectra

ECG and EMG signals collected and these physiological signals are preprocessed.The hypovigilance features extracted from signals using HOS feature.The features were classified using KNN, LDA and QDA.Maximum accuracy of 96.75% and 92.31% for ECG and EMG signals, respectively.Feature of ECG and EMG were fused with PCA and the classification accuracy was 96%. In this work, the focus is on developing a system that can detect hypovigilance, which includes both drowsiness and inattention, using Electrocardiogram (ECG) and Electromyogram (EMG) signals. Drowsiness has been manipulated by allowing the driver to drive monotonously at a limited speed for long hours and inattention was manipulated by asking the driver to respond to phone calls and short messaging services. ECG and EMG signals along with the video recording have been collected throughout the experiment. The gathered physiological signals were preprocessed to remove noise and artifacts. The hypovigilance features were extracted from the preprocessed signals using higher order spectral features. The features were classified using k Nearest Neighbor, Linear Discriminant Analysis and Quadratic Discriminant Analysis. The bispectral features gave an overall maximum accuracy of 96.75% and 92.31% for ECG and EMG signals, respectively using k fold validation. The features of ECG and EMG signals were fused using principal component analysis to obtain the optimally combined features and the classification accuracy was 96%. A number of road accidents can be avoided if an alert is sent to a driver who is drowsy or inattentive.

Pulmonary Acoustic Signal Classification Using Autoregressive Coefficients and k-Nearest Neighbor

— Pulmonary acoustic signals provide important information of the condition of the respiratory system. It can be used to assist medical professionals as an alternative diagnosis tool. In this paper, we intend to discriminate between normal (without any pathological condition), Airway Obstruction (AO) pathology and Interstitial lung disease (ILD) pathology using pulmonary acoustic signals. The proposed method filters the heart sounds and other artifacts using a butterworth bandpass filter and windowed to 256 samples per segment. The autoregressive coefficients (AR coefficients) were extracted as features from the pulmonary acoustic signals. The extracted features are distinguished using k-nearest neighbor (k-nn) classifier. The classifier performance is analysed by using confusion matrix technique. A mean classification accuracy of 96.12% was reported for the proposed method. The performance analysis of the knn classifier using confusion matrix revealed that normal, AO and ILD pathology are classified at 94.36%, 95.18% and 94.68% classification accuracy respectively. The analysis reveals that the proposed method performs better in distinguishing between the normal, AO and ILD.Keywords—Respiratorysound,ARcoefficients,k-nearestneighbor,confusionmatrix

Adaptive neuro-fuzzy inference system for breath phase detection and breath cycle segmentation

BACKGROUND The monitoring of the respiratory rate is vital in several medical conditions, including sleep apnea because patients with sleep apnea exhibit an irregular respiratory rate compared with controls. Therefore, monitoring the respiratory rate by detecting the different breath phases is crucial. OBJECTIVES This study aimed to segment the breath cycles from pulmonary acoustic signals using the newly developed adaptive neuro-fuzzy inference system (ANFIS) based on breath phase detection and to subsequently evaluate the performance of the system. METHODS The normalised averaged power spectral density for each segment was fuzzified, and a set of fuzzy rules was formulated. The ANFIS was developed to detect the breath phases and subsequently perform breath cycle segmentation. To evaluate the performance of the proposed method, the root mean square error (RMSE) and correlation coefficient values were calculated and analysed, and the proposed method was then validated using data collected at KIMS Hospital and the RALE standard dataset. RESULTS The analysis of the correlation coefficient of the neuro-fuzzy model, which was performed to evaluate its performance, revealed a correlation strength of r = 0.9925, and the RMSE for the neuro-fuzzy model was found to equal 0.0069. CONCLUSION The proposed neuro-fuzzy model performs better than the fuzzy inference system (FIS) in detecting the breath phases and segmenting the breath cycles and requires less rules than FIS.

Hybrid markerless tracking of complex articulated motion in golf swings.

Sports video tracking is a research topic that has attained increasing attention due to its high commercial potential. A number of sports, including tennis, soccer, gymnastics, running, golf, badminton and cricket have been utilised to display the novel ideas in sports motion tracking. The main challenge associated with this research concerns the extraction of a highly complex articulated motion from a video scene. Our research focuses on the development of a markerless human motion tracking system that tracks the major body parts of an athlete straight from a sports broadcast video. We proposed a hybrid tracking method, which consists of a combination of three algorithms (pyramidal Lucas-Kanade optical flow (LK), normalised correlation-based template matching and background subtraction), to track the golfers head, body, hands, shoulders, knees and feet during a full swing. We then match, track and map the results onto a 2D articulated human stick model to represent the pose of the golfer over time. Our work was tested using two video broadcasts of a golfer, and we obtained satisfactory results. The current outcomes of this research can play an important role in enhancing the performance of a golfer, provide vital information to sports medicine practitioners by providing technically sound guidance on movements and should assist to diminish the risk of golfing injuries.

Tracheal sound reliability for wheeze data collection method: A review

The purpose of this review is to present the reliability of sound obtained from trachea for wheeze data collection method. Wheeze is the most common sign used in the detection of airway obstruction. Airway obstruction such as asthma and chronic obstructive pulmonary disease (COPD) are normally detected by the recognition of any wheezes present in lung auscultation method. The primary source of publication used is IEEE, Elsevier, Chest and others that may offered related papers to the review. Papers regarding on wheeze, and asthma had been gathered through and papers that uses tracheal as the placement of the sensor had been identified and tabulated. From all the success studies, further explanation on tracheal placement for wheeze data collection method will be discussed. Thus the reliability of the tracheal position for the sensor placement can be proved for a better automated system development for lung auscultation in the future.