Ramakrishnan Swaminathan

In this work, an attempt has been made to analyze the influence of the frequencies bands in uterine electromyography (uEMG) signals on the detection of preterm birth. The signals recorded from the women's abdomen during pregnancy are considered in this study. The signals are subjected to preprocessing using digital bandpass Butterworth filter and decomposed into different frequency bands namely, 0.3-1.0 Hz (F1), 1.0-2.0 Hz (F2) and 2.0-3.0Hz (F3). Spectral features namely, peak magnitude, peak frequency, mean frequency and median frequency are extracted from the power spectrum. Classification models namely, k-nearest neighbor, support vector machine and random forest are employed to distinguish the term and preterm conditions. The results show that the features extracted from these frequency bands are able to differentiate term and preterm condition. Particularly, the frequency band F3 performs better than other frequency bands. The features associated with these frequencies along with random forest classification model achieves a maximum accuracy of 75.2%. Thus, these measures could be used to accurately detect the preterm birth well in advance. © 2021 European Federation for Medical Informatics (EFMI) and IOS Press.

In this work, automated abnormality detection using keypoint information from Speeded-Up Robust feature (SURF) and Scale Invariant Feature Transform (SIFT) descriptors in chest Radiographic (CR) images is investigated and compared. Computerized image analysis using artificial intelligence is crucial to detect subtle and non-specific alterations of Tuberculosis (TB). For this, the healthy and TB CRs are subjected to lung field segmentation. SURF and SIFT keypoints are extracted from the segmented lung images. Statistical features from keypoints, its scale and orientation are computed. Discrimination of TB from healthy is performed using SVM. Results show that the SURF and SIFT methods are able to extract local keypoint information in CRs. Linear SVM is found to perform better with precision of 88.9% and AUC of 91% in TB detection for combined features. Hence, the application of keypoint techniques is found to have clinical relevance in the automated screening of non-specific TB abnormalities using CRs. © 2021 European Federation for Medical Informatics (EFMI) and IOS Press.

In this work, an attempt has been made to classify various emotional states in Electrodermal Activity (EDA) signals using modified Hjorth features and non-parametric classifiers. For this, the EDA signals are collected from a publicly available online database. The EDA is decomposed into SCL (Skin Conductance Level) and SCR (Skin Conductance Response). Five features, namely activity, mobility, complexity, chaos, and hazard, collectively known as modified Hjorth features, are extracted from SCR and SCL. Four non-parametric classifiers, namely, random forest, k-nearest neighbor, support vector machine, and rotation forest, are used for the classification. The results demonstrate that the proposed approach can classify the emotional states in EDA. Most of the features exhibit statistical significance in discriminating emotional states. It is found that the combination of modified Hjorth features and rotation forest is most accurate in classifying the emotional states. Thus, the result demonstrates that this method can recognize valence and arousal dimensions under various clinical conditions. © 2021 European Federation for Medical Informatics (EFMI) and IOS Press.

In this study, an attempt has been made to differentiate Alzheimer's Disease (AD) stages in structural Magnetic Resonance (MR) images using single inception module network. For this, T1-weighted MR brain images of AD, mild cognitive impairment and Normal Controls (NC) are obtained from a public database. From the images, significant features are extracted and classified using an inception module network. The performance of the model is computed and analyzed for different input image sizes. Results show that the single inception module is able to classify AD stages using MR images. The end-to-end network differentiates AD from NC with 85% precision. The model is found to be effective for varied sizes of input images. Since the proposed approach is able to categorize AD stages, single inception module networks could be used for the automated AD diagnosis with minimum medical expertise. © 2021 European Federation for Medical Informatics (EFMI) and IOS Press.

Recognition of the emotions demonstrated by human beings plays a crucial role in healthcare and human-machine interface. This paper reports an attempt to classify emotions using a spectral feature from facial electromyography (facial EMG) signals in the valence affective dimension. For this purpose, the facial EMG signals are obtained from the DEAP dataset. The signals are subjected to Short-Time Fourier Transform, and the peak frequency values are extracted from the signal in intervals of one second. Support vector machine (SVM) classifier is used for the classification of the features extracted. The extracted feature can classify the signals in the valence dimension with an accuracy of 61.37%. The proposed feature could be used as an added feature for emotion recognition, and this method of analysis could be extended to myoelectric control applications. © 2021 European Federation for Medical Informatics (EFMI) and IOS Press.

Emotions are essential for the intellectual ability of human beings defined by perception, concentration, and actions. Electroencephalogram (EEG) responses have been studied in different lobes of the brain for emotion recognition. An attempt has been made in this work to identify emotional states using time-domain features, and probabilistic random forest based decision fusion. The EEG signals are collected for this from an online public database. The prefrontal and frontal electrodes, namely Fp1, Fp2, F3, F4, and Fz are considered. Eleven features are extracted from each electrode, and subjected to a probabilistic random forest. The probabilities are employed to Dempster-Shafer's (D-S) based evidence theory for electrode selection using decision fusion. Results demonstrate that the method suggested is capable of classifying emotional states. The decision fusion based electrode selection appears to be most accurate (arousal F-measure = 77.9%) in classifying the emotional states. The combination of Fp2, F3, and F4 electrodes yields higher accuracy for characterizing arousal (65.1%) and valence (57.9%) dimension. Thus, the proposed method can be used to select the critical electrodes for the classification of emotions. © 2021 European Federation for Medical Informatics (EFMI) and IOS Press.

In this, study, we have investigated to identify the muscle fatigue using spatial maps of High-Density Electromyography (HDEMG). The experiment involves subjects performing plantar flexion at 40% maximum voluntary contraction until fatigue. During the experiment, HDEMG signal was recorded from the tibialis anterior muscle. The monopolar and bipolar spatial intensity maps were extracted from the HDEMG signal. The random forest classifier with different tree configurations was tested to distinguish nonfatigue and fatigue condition. The results indicate that selected electrodes from the differential intensity map results in an accuracy of 83.3% with the number of trees set at 17. This method of spatial analysis of HDEMG signals may be extended to assess fatigue in real life scenarios. © 2021 European Federation for Medical Informatics (EFMI) and IOS Press.

In this study, an attempt has been made to differentiate Drug Resistant Tuberculosis (DR-TB) in chest X-rays using projection profiling and mediastinal features. DR-TB is a condition which is non-responsive to at least one of anti-TB drugs. Mediastinum variations can be considered as significant image biomarkers for detection of DR-TB. Images are obtained from a public database and are contrast enhanced using coherence filtering. Projection profiling is used to obtain the feature lines from which the mediastinal and thoracic indices are computed. Classification of Drug Sensitive (DS-TB) and DR-TB is performed using three classifiers. Results show that the mediastinal features are found to be statistically significant. Support vector machine with quadratic kernel is able to provide better classification performance values of greater than 93%. Hence, the automated analysis of mediastinum could be clinically significant in differentiation of DR-TB. © 2021 European Federation for Medical Informatics (EFMI) and IOS Press.