The science of solving clinical problems by analyzing images generated in clinical practice is known as medical image analysis. The aim is to extract information in an affective and efficient manner for improved clinical diagnosis. The recent advances in the field of biomedical engineering has made medical image analysis one of the top research and development area. One of the reason for this advancement is the application of machine learning techniques for the analysis of medical images. Deep learning is successfully used as a tool for machine learning, where a neural network is capable of automatically learning features. This is in contrast to those methods where traditionally hand crafted features are used. The selection and calculation of these features is a challenging task. Among deep learning techniques, deep convolutional networks are actively used for the purpose of medical image analysis. This include application areas such as segmentation, abnormality detection, disease classification, computer aided diagnosis and retrieval.

No abstract

Automatic detection and classification of life-threatening arrhythmia plays an important part in dealing with various cardiac conditions. In this paper, a novel method for classification of various types of arrhythmia using morphological and dynamic features is presented. Discrete wavelet transform (DWT) is applied on each heart beat to obtain the morphological features. It provides better time and frequency resolution of the electrocardiogram (ECG) signal, which helps in decoding important information of a quasiperiodic ECG using variable window sizes. RR interval information is used as a dynamic feature. The nonlinear dynamics of RR interval are captured using Teager energy operator, which improves the arrhythmia classification. Moreover, to remove redundancy, DWT subbands are subjected to dimensionality reduction using independent component analysis, and a total of twelve coefficients are selected as morphological features. These hybrid features are combined and fed to a neural network to classify arrhythmia. The proposed algorithm has been tested over MIT-BIH arrhythmia database using 13724 beats and MIT-BIH supraventricular arrhythmia database using 22151 beats. The proposed methodology resulted in an improved average accuracy of 99.75% and 99.84% for class- and subject-oriented scheme, respectively, using three-fold cross validation.

Emotion recognition in real-time using electroencephalography (EEG) signals play a key role in human-computer interaction and affective computing. The existing emotion recognition models, that use stimuli such as music and pictures in controlled lab settings and limited number of emotion classes, have low ecological validity. Moreover, for effective emotion recognition identifying significant EEG features and electrodes is important. In our proposed model, we use the DEAP dataset consisting of physiological signals collected from 32 participants as they watched 40 movie (each of 60 seconds) clips. The main objective of this study is to explore multi-domain (time, wavelet, and frequency) features and hence, identify the set of stable features which contribute towards emotion classification catering to a larger number of emotion classes. Our proposed model is able to identify nine classes of emotions including happy, pleased, relaxed, excited, neutral, calm, distressed, miserable, and depressed with an average accuracy of 65.92%. Towards this end, we use support vector machine as a classifier along with 10-fold and leave-one-out cross-validation techniques. We achieve a significant emotion classification accuracy which could be vital towards developing solutions for affective computing and deal with a larger number of emotional states.

Emotion recognition has increased the potential of affective computing by getting an instant feedback from users and thereby, have a better understanding of their behavior. Physiological sensors have been used to recognize human emotions in response to audio and video content that engages single (auditory) and multiple (two: auditory and vision) human senses, respectively. In this study, human emotions were recognized using physiological signals observed in response to tactile enhanced multimedia content that engages three (tactile, vision, and auditory) human senses. The aim was to give users an enhanced real-world sensation while engaging with multimedia content. To this end, four videos were selected and synchronized with an electric fan and a heater, based on timestamps within the scenes, to generate tactile enhanced content with cold and hot air effect respectively. Physiological signals, i.e., electroencephalography (EEG), photoplethysmography (PPG), and galvanic skin response (GSR) were recorded using commercially available sensors, while experiencing these tactile enhanced videos. The precision of the acquired physiological signals (including EEG, PPG, and GSR) is enhanced using pre-processing with a Savitzky-Golay smoothing filter. Frequency domain features (rational asymmetry, differential asymmetry, and correlation) from EEG, time domain features (variance, entropy, kurtosis, and skewness) from GSR, heart rate and heart rate variability from PPG data are extracted. The K nearest neighbor classifier is applied to the extracted features to classify four (happy, relaxed, angry, and sad) emotions. Our experimental results show that among individual modalities, PPG-based features gives the highest accuracy of 78.57 % as compared to EEG- and GSR-based features. The fusion of EEG, GSR, and PPG features further improved the classification accuracy to 79.76 % (for four emotions) when interacting with tactile enhanced multimedia.