Ramakrishnan Swaminathan

In this study, an attempt has been made to distinguish between nonfatigue and fatigue conditions in surface Electromyography (sEMG) signal using the time frequency distribution obtained from analytic Bump Continuous Wavelet Transform. For the analysis, sEMG signals from biceps brachii muscle of 22 healthy subjects are acquired during isometric contraction protocol. The signals acquired is preprocessed and partitioned into ten equal segments followed by the decomposition of selected segments using analytic Bump wavelets. Further, Singular Value Decomposition is applied to the time frequency distribution matrix and the maximum singular value and entropy feature for each segment are obtained. The usefulness of both the features is estimated using the Wilcoxon sign rank test that gives higher significance with a p <.00001. It is observed that the proposed method is capable of analyzing the fatigue regions in sEMG signals.

Face detection in videos from smart cars or homes is becoming increasingly important in human-computer interaction, emotion recognition, gender and age identification, driving assistance, and vital sign measurements, as heart rate and respiratory rate is derived from the video. However, face detection suffers from variations in illumination, subject motion, different skin colors, or camera distances. We compare three algorithms for in-car application: Haar cascade classifier (HCC), histogram of oriented gradients (HoG), and a deep neural network (DNN). For evaluation, we consider the freely available "driver monitoring dataset"multimodal database (DMD) and self-collected videos recorded in a research car. We analyze run-time, accuracy, and F1-score. HoG has highest computational time as compared to HCC and DNN with 2.99 frames per second(fps), 7.00 fps, and 18.25 fps, respectively. For DMD, the F1-scores are 91.75%, 95.91%, and 99.48% for HCC, HoG, and DNN respectively, and 88.05%, 83.68%, and 99.66% for our dataset, respectively. All in all, DNN is fastest and most accurate. Moreover, we observed that DNN handles occlusions and varying illumination better than the other approaches. In conclusion, DNN can be applied successfully for in-car face detection as a first step towards real-time continuous health monitoring.

Muscle fatigue is a neuromuscular disease which occurs when the muscles fail to produce the necessary or expected potential, which is the cause for muscular forces. It could be either due to overexertion of the muscles or any excessive repetitive action [1]. It can occur to any subject - both normal as well as abnormal. The most common symptoms of this condition are localized pain, muscle twitching, trembling and muscle cramps. The detection of muscle fatigue can assist in the improvement of the performance in many fields such as clinical diagnosis and sports biomechanics and facilitates in the commercial development of various industries [2], [3]. Analysis of fatigue conditions of a muscle also plays a major role in the rehabilitation processes and kinesiology [4]. The behaviour of sEMG signals is different under non-fatigue and fatigue conditions due to energetic, metabolic, and structural variations in the muscle [5]. Hence, in this work, the differences in the muscle activity under non-fatigue and fatigue conditions as determined from recorded multichannel sEMG signals of biceps brachii and triceps brachii during dynamic contractions are studied.

In this study, an attempt has been made to evaluate the applicability of geometric features extracted from the different frequency bands of surface electromyography (sEMG) signals for detecting muscle fatigue condition. For this purpose, sEMG signals are acquired from twenty-five healthy volunteers during isometric contraction of biceps brachii muscle. The nonfatigue and fatigue segments are obtained from preprocessed signals and are separated into low frequency band (LFB: 15- 45Hz), medium frequency band (MFB: 55-95Hz) and high frequency band (HFB: 95-500Hz). The analytical representations of these signals are obtained from Hilbert Transform and the features, area and perimeter are extracted from the resultant shape. The results demonstrate that the features obtained from the three bands can differentiate nonfatigue and fatigue conditions with significant difference (p<0.05). Among the three bands, LFB achieves high sensitivity of 88% and 84% for perimeter and area feature respectively. However, sensitivity in MFB and HFB is decreased for both the features. It appears that the geometric features associated with LFB signals are more sensitive in detecting fatigue. It is interesting to note that the sensitivity is in acceptable level for low-frequency signals (15- 45Hz). However, the study has to be conducted on large population to draw a reliable conclusion.

Pedicle screw fixations are widely used to provide support and improve stability for the treatment of spinal pathologies. The effectiveness of treatment depends on the anchorage strength between the screw and bone. In this study, the influence of pedicle screw half-angle and bone quality on the displacement of fixation and stress transfer are analyzed using a 2D axisymmetric finite element model. The pedicle screw proximal half-angle is varied between 0° and 60° in steps of 10°, along with two different distal half-angles of 30° and 40°. Three bone models are considered for cancellous bone to simulate various degrees of bone quality, namely, poor, moderate and good. The mechanical properties of cortical bone are kept constant throughout the study. The material properties and boundary conditions are applied based on previous studies. Frictional contact is considered between the bone and screw. Results show that, the displacement of fixation is observed to be minimum at a proximal half angle of 0° and maximum at an angle of 60°, independent of bone quality. The highest implant displacement is observed in case of poor bone quality. All the bone model showed similar patterns of stress distribution, with high stress concentration around the first few threads. The highest peak von Mises stress is obtained at a proximal half-angle of 60°. Furthermore, the stress transfer increased with increase in proximal half-angle and bone quality, with maximum stress transfer at a proximal half-angle of 60°. It appears that, this study might aid to improve the design of pedicle screw for treatment of degenerative spinal diseases.Clinical Relevance - This study analyses the impact of bone quality on pedicle screw design

Muscle fatigue analysis is important in the diagnosis of neuromuscular diseases. Analysis of surface electromyography (sEMG) signals by non-linear probabilistic approach is useful in studying their transitions and thus the neuromuscular system. In this study, a method to visualize sEMG signals using Markov transition field (MTF) under fatigue conditions is proposed. sEMG signals are acquired from 45 healthy participants during biceps curl exercise. They are filtered and divided into ten equal segments. Markov transition matrix is constructed and corresponding MTF image is generated. The average self-transition probability is extracted and compared for both non-fatigue and fatigue segments. It is observed that the extracted feature shows high statistical significance with p value less than 0.001. The increase in average self-transition probability under fatigue condition correlates with the reduction in the degree of signal complexity. Thus, encoding of sEMG signals to images is helpful in analyzing the complexity of the neuromuscular system. Clinical Relevance- This approach may be helpful in analyzing muscle fatigue related with various myoneural conditions.

Preterm birth (gestation ≤ 37 weeks) is the leading cause of neonatal mortality and morbidity worldwide. Early diagnosis of Preterm is crucial for increasing the survival rate of infants [1]. Surface uterine Electromyography (uEMG) records the electrical activity of uterus during contraction. It quantitatively assesses the intensity, duration and frequency of uterine contractions. These contractions are characterized by a slow cyclic pattern of bursts followed by a period of quiescence [2]. Analysis of these bursts using uEMG signals has high sensitivity in detecting Preterm labor sign [3]. Significant information from these complex signals can be obtained using topological data analysis as it extracts the underlying shape characteristics of the signal [4]. Hence, in this study, an attempt has been made to differentiate Term (gestation > 37 weeks) and Preterm conditions using uEMG signals and topological features.