A machine-learning tool to identify bistable states from calcium imaging data.

Mapping neuronal activation using calcium imaging in vivo during behavioural tasks has advanced our understanding of nervous system function. In almost all of these studies, calcium imaging is used to infer spike probabilities because action potentials activate voltage-gated calcium channels and increase intracellular calcium levels. However, neurons not only fire action potentials, but also convey information via intrinsic dynamics such as by generating bistable membrane potential states. Although a number of tools for spike inference have been developed and are currently being used, no tool exists for converting calcium imaging signals to maps of cellular state in bistable neurons. Purkinje neurons in the larval zebrafish cerebellum exhibit membrane potential bistability, firing either tonically or in bursts. Several studies have implicated the role of a population code in cerebellar function, with bistability adding an extra layer of complexity to this code. In the present study, we develop a tool, CaMLSort, which uses convolutional recurrent neural networks to classify calcium imaging traces as arising from either tonic or bursting cells. We validate this classifier using a number of different methods and find that it performs well on simulated event rasters as well as real biological data that it had not previously seen. Moreover, we find that CaMLsort generalizes to other bistable neurons, such as dopaminergic neurons in the ventral tegmental area of mice. Thus, this tool offers a new way of analysing calcium imaging data from bistable neurons to understand how they participate in network computation and natural behaviours. KEY POINTS: Calcium imaging, compriising the gold standard of inferring neuronal activity, does not report cellular state in neurons that are bistable, such as Purkinje neurons in the cerebellum of larval zebrafish. We model the relationship between Purkinje neuron electrical activity and its corresponding calcium signal to compile a dataset of state-labelled simulated calcium signals. We apply machine-learning methods to this dataset to develop a tool that can classify the state of a Purkinje neuron using only its calcium signal, which works well on real data even though it was trained only on simulated data. CaMLsort (Calcium imaging and Machine Learning based tool to sort intracellular state) also generalizes well to bistable neurons in a different brain region (ventral tegmental area) in a different model organism (mouse). This tool can facilitate our understanding of how these neurons carry out their functions in a circuit.

Multi-Modal Point-of-Care Diagnostics for COVID-19 Based on Acoustics and Symptoms.

BACKGROUND: The COVID-19 pandemic has highlighted the need to invent alternative respiratory health diagnosis methodologies which provide improvement with respect to time, cost, physical distancing and detection performance. In this context, identifying acoustic bio-markers of respiratory diseases has received renewed interest. OBJECTIVE: In this paper, we aim to design COVID-19 diagnostics based on analyzing the acoustics and symptoms data. Towards this, the data is composed of cough, breathing, and speech signals, and health symptoms record, collected using a web-application over a period of twenty months. METHODS: We investigate the use of time-frequency features for acoustic signals and binary features for encoding different health symptoms. We experiment with use of classifiers like logistic regression, support vector machines and long-short term memory (LSTM) network models on the acoustic data, while decision tree models are proposed for the symptoms data. RESULTS: We show that a multi-modal integration of inference from different acoustic signal categories and symptoms achieves an area-under-curve (AUC) of 96.3%, a statistically significant improvement when compared against any individual modality ([Formula: see text]). Experimentation with different feature representations suggests that the mel-spectrogram acoustic features performs relatively better across the three kinds of acoustic signals. Further, a score analysis with data recorded from newer SARS-CoV-2 variants highlights the generalization ability of the proposed diagnostic approach for COVID-19 detection. CONCLUSION: The proposed method shows a promising direction for COVID-19 detection using a multi-modal dataset, while generalizing to new COVID variants.

Automatic Classification of Healthy Subjects and Patients With Essential Vocal Tremor Using Probabilistic Source-Filter Model Based Noise Robust Pitch Estimation.

Essential voice tremor (EVT) is a voice disorder resulting from dyscoordination within the laryngeal musculature. A low-frequency fluctuations of fundamental voice frequency or the strength of excitation amplitude is the main consequence of the disorder. The automatic classification of healthy control and EVT is useful tool for the clinicians. A typical automatic EVT classification involves three steps. The first step is to compute the pitch contour from the speech. The second step is to compute the features from the pitch contour, and the final step is to use a classifier to classify the features into healthy or EVT. It is shown that a high-resolution pitch contour estimated from the glottal closure instants (GCIs) is useful for EVT classification. The HPRC estimation can be very poor in the presence of noise. Hence, a probabilistic source filter model based noise robust GCI detection is used for HPRC estimation. The Empirical mode decomposition based feature extraction is used followed by a support vector machine classifier. The EVT classification performance is evaluated using recordings from 45 subjects. The proposed method is found to perform better than the baseline techniques in eight different additive noise conditions with six SNR levels.

Noise Robust Detection of Fundamental Heart Sound using Parametric Mixture Gaussian and Dynamic Programming.

In this work, we propose an unsupervised algorithm for fundamental heart sound detection. We propose to detect the heart sound candidates using the stationary wavelet transforms and group delay. We further propose an objective function to select the candidates. The objective function has two parts. We model the energy contour of S1/S2 sound using the Gaussian mixture function (GMF). The goodness of fit for the GMF is used as the first part of the objective function. The second part of the objective function captures the consistency of the heart sounds' relative location. We solve the objective function efficiently using dynamic programming. We evaluate the algorithm on Michigan HeartSound and Murmur database. We also assess the algorithm's performance using the three different additive noises- white Gaussian noise (AWGN), Student-t noise, and impulsive noise. The experiments demonstrate that the proposed method performs better than baseline in both clean and noisy conditions. We found that the proposed method is robust in the case of AWGN noise and student-t distribution noise. But its performance reduces in case of impulsive noise.

Unsegmented Heart Sound Classification Using Hybrid CNN-LSTM Neural Networks.

Cardiac Auscultation, an integral part of the physical examination of a patient, is essential for early diagnosis of cardiovascular diseases (CVDs). The ability to accurately diagnose the heart sounds requires experience and expertise, which is lacking in doctors in the early years of clinical practice. Thus, there is a need for an automatic diagnostic tool that would aid medical practitioners with their diagnosis. We propose novel hybrid architectures for classification of unsegmented heart sounds to normal and abnormal classes. We propose two methods, with and without the conventional feature extraction step in the classification pipeline. We demonstrate that the F score using the approach with conventional feature extraction is 1.25 (absolute) more than using a baseline implementation on the Physionet dataset. We also introduce a mechanism to tag predictions as unsure and compare results with a varying threshold.

Two step convolutional neural network for automatic glottis localization and segmentation in stroboscopic videos.

Precise analysis of the vocal fold vibratory pattern in a stroboscopic video plays a key role in the evaluation of voice disorders. Automatic glottis segmentation is one of the preliminary steps in such analysis. In this work, it is divided into two subproblems namely, glottis localization and glottis segmentation. A two step convolutional neural network (CNN) approach is proposed for the automatic glottis segmentation. Data augmentation is carried out using two techniques :  1) Blind rotation (WB), 2) Rotation with respect to glottis orientation (WO). The dataset used in this study contains stroboscopic videos of 18 subjects with Sulcus vocalis, in which the glottis region is annotated by three speech language pathologists (SLPs). The proposed two step CNN approach achieves an average localization accuracy of 90.08% and a mean dice score of 0.65.

Closed-set speaker conditioned acoustic-to-articulatory inversion using bi-directional long short term memory network.

Estimating articulatory movements from speech acoustic representations is known as acoustic-to-articulatory inversion (AAI). In this work, a speaker conditioned AAI (SC AAI) is proposed using a bi-directional LSTM neural network, where training is performed by pooling acoustic-articulatory data from multiple speakers along with their corresponding speaker identity information. For this work, 7.24 h of multi-speaker acoustic-articulatory data are collected from 20 speakers speaking 460 English sentences. Experiments with 20 speakers indicate that the SC AAI model performs better than SD AAI model with an improvement of correlation coefficient by 0.036 (absolute) between the original and estimated articulatory movements.

Trend Statistics Network and Channel invariant EEG Network for sleep arousal study.

Sleep is a very important part of life. Lack of sleep or sleep disorder can cause a negative impact on day to day life and can have long term serious consequences. In this work, we propose an end-to-end trainable neural network for automated sleep arousal scoring. The network consists of two main parts. Firstly, a trend statistics network computes the moving average of the filtered signals at different scales. Secondly, we propose a channel invariant EEG network to detect the arousals in any Electroencephalography (EEG) channel. Finally, we combine the features from various channels through a convolution network and a bi-directional long short-term memory to predict the probability of arousal. Further, we propose an objective function that uses only respiratory effort related arousal (RERA) and non-arousal regions to optimize the network. We also propose a method to estimate the respiratory disturbance index (RDI) from the probability predicted by the network. Evaluation on Physionet Challenge 2018 database shows that the proposed method detects RERA with mean area under the precision-recall curve (AUPRC) of 0.50 in a 10-fold cross validation setup. The mean absolute error of RDI prediction is 6.11, while a two-class RDI severity prediction yields a specificity of 75% and a sensitivity of 83%.

Automatic intonation classification using temporal patterns in utterance-level pitch contour and perceptually motivated pitch transformation.

Second language learners of British English (BE) are typically trained for four intonation classes: Glide-up, Glide-down, Dive, and Take-off. Automatic four-way intonation classification could be useful to evaluate a learner's pronunciation. However, such automatic classification is challenging without having manually annotated tones, typically considered in intonation analysis and classification tasks. In this, a three-dimensional feature sequence is proposed representing temporal patterns in the utterance-level f0 contour using a perceptually motivated pitch transformation. Hidden Markov model based classification experiments conducted using a training material for teaching BE intonation demonstrate the benefit of the proposed approach over the baseline scheme considered.

A Heart Rate Driven Kalman Filter for Continuous Arousal Trend Monitoring.

This paper proposes a continuous and unsupervised approach of monitoring the arousal trend of an individual from his heart rate using Kalman Filter. The state-space model of the filter characterizes the baseline arousal condition. Deviations from this baseline model are used to recognize the arousal trend. A publicly available dataset, DECAF, comprising the physiological responses of 30 subjects while watching 36 movie clips inducing different emotions, is used to validate the proposed technique. For each clip, annotations of arousal given by experts per second are used to quantify the ground truth of arousal change. Experimental results suggest that the proposed algorithm achieves a median correlation of 0.53 between the computed and expected arousal levels which is significantly higher than that achievable by the state-of-the-art technique.

A Maximum Likelihood Formulation To Exploit Heart Rate Variability for Robust Heart Rate Estimation From Facial Video.

The problem of estimating the heart rate (HR) from a racial video is considered. A typical approach for this problem is to use independent component analysis (ICA) on the red, blue, green intensity prof iles averaged over the facial region. This provides estimates of the underlying source signals, whose spectral peaks are used to predict HR in every analysis window. In this work, we propose a maximum likelihood formulation to optimally select a source signal in each window such that the predicted HR trajectory not only corresponds to the most likely spectral peaks but also ensures a realistic HR variability (HRV) across analysis windows. The likelihood function is efficiently optimized using dynamic programming in a manner similar to Viterbi decoding. The proposed scheme for HR estimation is denoted by vICA. The performance of vICA is compared with a typical ICA approach as well as a recently proposed sparse spectral peak tracking (SSPT) technique that ensures that the predicted HR does not vary drastically across analysis windows. Experiments are performed in a five fold setup using racial videos of 15 subjects recorded using two types of smartphones (Samsung Galaxy and iPhone) at three different distances (6inches, lfoot, 2feet) between the phone camera and the subject. Mean absolute error (MAE) between the original and predicted HR reveals that the proposed vICA scheme performs better than the best of the baseline schemes, namely SSPT by -8.69%, 52.77% and 8.00% when Samsung Galaxy phone was used at a distance of 6inches, lfoot, and 2feet respectively. These improvements are 12.13%, 13.59% and 18.34% when iPhone was used. This, in turn, suggests that the HR predicted from a racial video becomes more accurate when the smoothness of HRV is utilized in predicting the HR trajectory as done in the proposed vICA.

Comparison of Cough, Wheeze and Sustained Phonations for Automatic Classification Between Healthy Subjects and Asthmatic Patients.

In this work, we consider the task of automatic classification of asthmatic patients and healthy subjects using voice stimuli. Cough and wheeze have been used as voice stimuli for this classification task in the past. In this work, we focus on sustained phonations, namely /aː/, /iː/, /uː/, /eɪ/, /o℧/ and compare their classification performances with the cough and wheeze. Classification experiments using 35 asthmatic patients and 36 healthy subjects show that sustained vowel /iː/ achieves the highest classification accuracy of 80.79% among five vowels considered. However, it is found to be higher and lower than the classification accuracies of 78.72% and 90.25% obtained using cough and wheeze respectively. This suggests that for speech-based asthma classification, /iː/ would be a better choice compared to other vowels considered in this work. However, when non-speech sounds are included for classification, wheeze is a better choice than sustained /iː/.

Effect of source filter interaction on isolated vowel-consonant-vowel perception.

Source-filter interaction explains the drop in pitch in voiced consonant due to constriction in the vocal tract during vowel-consonant-vowel (VCV) production. In this work, a perceptual study is conducted where the pitch contour in the voiced consonant region is modified to four different levels and a listening test is performed to assess the naturalness of the VCVs synthesized with the modified pitch contour. The listening test with 30 listeners shows no statistically significant difference between the naturalness of the original and synthesized VCVs with modified pitch indicating that pitch drop due to source-filter interaction may not be critical for the perceived naturalness of VCVs.

Reconstruction of articulatory movements during neutral speech from those during whispered speech.

A transformation function (TF) that reconstructs neutral speech articulatory trajectories (NATs) from whispered speech articulatory trajectories (WATs) is investigated, such that the dynamic time warped (DTW) distance between the transformed whispered and the original neutral articulatory movements is minimized. Three candidate TFs are considered: an affine function with a diagonal matrix ( Ad) which reconstructs one NAT from the corresponding WAT, an affine function with a full matrix ( Af) and a deep neural network (DNN) based nonlinear function which reconstruct each NAT from all WATs. Experiments reveal that the transformation could be approximated well by Af, since it generalizes better across subjects and achieves the least DTW distance of 5.20 (±1.27) mm (on average), with an improvement of 7.47%, 4.76%, and 7.64% (relative) compared to that with Ad, DNN, and the best baseline scheme, respectively. Further analysis to understand the differences in neutral and whispered articulation reveals that the whispered articulators exhibit exaggerated movements in order to reconstruct the lip movements during neutral speech. It is also observed that among the articulators considered in the study, the tongue exhibits a higher precision and stability while whispering, implying that subjects control their tongue movements carefully in order to render an intelligible whispered speech.

A frame selective dynamic programming approach for noise robust pitch estimation.

The principles of the existing pitch estimation techniques are often different and complementary in nature. In this work, a frame selective dynamic programming (FSDP) method is proposed which exploits the complementary characteristics of two existing methods, namely, sub-harmonic to harmonic ratio (SHR) and sawtooth-wave inspired pitch estimator (SWIPE). Using variants of SHR and SWIPE, the proposed FSDP method classifies all the voiced frames into two classes-the first class consists of the frames where a confidence score maximization criterion is used for pitch estimation, while for the second class, a dynamic programming (DP) based approach is proposed. Experiments are performed on speech signals separately from KEELE, CSLU, and PaulBaghsaw corpora under clean and additive white Gaussian noise at 20, 10, 5, and 0 dB SNR conditions using four baseline schemes including SHR, SWIPE, and two DP based techniques. The pitch estimation performance of FSDP, when averaged over all SNRs, is found to be better than those of the baseline schemes suggesting the benefit of applying smoothness constraint using DP in selected frames in the proposed FSDP scheme. The VuV classification error from FSDP is also found to be lower than that from all four baseline schemes in almost all SNR conditions on three corpora.

Dissociating meditation proficiency and experience dependent EEG changes during traditional Vipassana meditation practice.

Meditation, as taught by most schools of practice, consists of a set of heterogeneous techniques. We wanted to assess if EEG profiles varied across different meditation techniques, proficiency levels and experience of the practitioners. We examined EEG dynamics in Vipassana meditators (Novice, Senior meditators and Teachers) while they engaged in their traditional meditation practice (concentration, mindfulness and loving kindness in a structured manner) as taught by S.N. Goenka. Seniors and Teachers (vs Novices) showed trait increases in delta (1-4 Hz), theta-alpha (6-10 Hz) and low-gamma power (30-40 Hz) at baseline rest; state-trait increases in low-alpha (8-10 Hz) and low-gamma power during concentrative and mindfulness meditation; and theta-alpha and low-gamma power during loving-kindness meditation. Permutation entropy and Higuchi fractal dimension measures further dissociated high proficiency from duration of experience as only Teachers showed consistent increase in network complexity from baseline rest and state transitions between the different meditation states.

Similar Biologics: Global Opportunities and Issues.

The invention and use of a large number of biologics during the last three decades for treating various deficiencies and chronic disorders has resulted in great benefit to human health. Abundant use of these biologics has been considerably constrained due to the reasons of their increased prices, charged by the inventors up to the time up to which their use were/are protected by intellectual property rights (IPR).Some of these biologics are presently being manufactured by the existing and newer companies as "similar biologics" after the IPR on these products have expired and as a result the prices of several such medicines are coming down."Similar biologics" are also referred to as "biosimilars" and other related names in different parts of the world. The regulatory authorities of different countries have authorized use of "similar biologics" based on comparative evaluation of each of such medicines with the inventor's biologics; these are approved when considered to be closely similar to the inventor's biologics in properties, quality and efficacy. By 2020, a dozen of "inventor's biologicals" having estimated market sale-value of over USD 79 billion are going out of protection of IPR. This would drive entrepreneurs to enter in to the field and the prices are going to crash considerably due to market competition. In course of time more "biosimilars" would go out of IPR. Different proactive governments and the regulatory agencies all over the world are trying to harness the existing and future opportunities by creating regulatory guidelines to ease faster authorization for use of "similar biologics" in their territories. Up to the present time, a small number of "similar biologics" have been approved for use in different countries all over the major parts of the world. More efficient technologies for manufacture of "similar biologics" are also getting developed. Together, these efforts are anticipated to ease the availability of "similar biologics" at more affordable prices to the users/ payers the world over. This article is open to POST-PUBLICATION REVIEW. Registered readers (see "For Readers") may comment by clicking on ABSTRACT on the issue's contents page.

Speaker verification based on the fusion of speech acoustics and inverted articulatory signals.

We propose a practical, feature-level and score-level fusion approach by combining acoustic and estimated articulatory information for both text independent and text dependent speaker verification. From a practical point of view, we study how to improve speaker verification performance by combining dynamic articulatory information with the conventional acoustic features. On text independent speaker verification, we find that concatenating articulatory features obtained from measured speech production data with conventional Mel-frequency cepstral coefficients (MFCCs) improves the performance dramatically. However, since directly measuring articulatory data is not feasible in many real world applications, we also experiment with estimated articulatory features obtained through acoustic-to-articulatory inversion. We explore both feature level and score level fusion methods and find that the overall system performance is significantly enhanced even with estimated articulatory features. Such a performance boost could be due to the inter-speaker variation information embedded in the estimated articulatory features. Since the dynamics of articulation contain important information, we included inverted articulatory trajectories in text dependent speaker verification. We demonstrate that the articulatory constraints introduced by inverted articulatory features help to reject wrong password trials and improve the performance after score level fusion. We evaluate the proposed methods on the X-ray Microbeam database and the RSR 2015 database, respectively, for the aforementioned two tasks. Experimental results show that we achieve more than 15% relative equal error rate reduction for both speaker verification tasks.

Co-registration of speech production datasets from electromagnetic articulography and real-time magnetic resonance imaging.

This paper describes a spatio-temporal registration approach for speech articulation data obtained from electromagnetic articulography (EMA) and real-time Magnetic Resonance Imaging (rtMRI). This is motivated by the potential for combining the complementary advantages of both types of data. The registration method is validated on EMA and rtMRI datasets obtained at different times, but using the same stimuli. The aligned corpus offers the advantages of high temporal resolution (from EMA) and a complete mid-sagittal view (from rtMRI). The co-registration also yields optimum placement of EMA sensors as articulatory landmarks on the magnetic resonance images, thus providing richer spatio-temporal information about articulatory dynamics.

Phyto-extracts in wound healing.

Data generated through systematic investigation, carried out on the evaluation of phyto-extracts on wound healing research during the last 20 years have been compiled. About 450 plant species having wound healing properties have been identified. The present knowledge of the wound healing process comprise coagulation, inflammation, proliferation, formation and accumulation of fibrous tissues, collagen deposition, epithelialization, contraction of wound with formation of granulation tissues, remodeling and maturation. The constituents of the plant extracts modulate one or more of the above stages. It was the endeavor to identify the active constituents responsible for antimicrobial activity, free radical scavenging properties, stimulators of enhanced collagen production and/or angiogenesis promoters with identification of lead scaffold chemical structures. Multiple phytochemicals concentrated and blended in optimal concentrations, are expected to be available in future years to carry out multi-tasking efforts in wound healing as more knowledge about the properties of the key constituents are unveiled.