Anish Mitra

Bio: Anish Mitra is an academic researcher from George Mason University. The author has contributed to research in topics: Spike (software development) & Spike train. The author has an hindex of 2, co-authored 4 publications receiving 11 citations.

Motion based markerless gait analysis using standard events of gait and ensemble Kalman filtering.

Abstract: We present a novel approach to gait analysis using ensemble Kalman filtering which permits markerless determination of segmental movement. We use image flow analysis to reliably compute temporal and kinematic measures including the translational velocity of the torso and rotational velocities of the lower leg segments. Detecting the instances where velocity changes direction also determines the standard events of a gait cycle (double-support, toe-off, mid-swing and heel-strike). In order to determine the kinematics of lower limbs, we model the synergies between the lower limb motions (thigh-shank, shank-foot) by building a nonlinear dynamical system using CMUs 3D motion capture database. This information is fed into the ensemble Kalman Filter framework to estimate the unobserved limb (upper leg and foot) motion from the measured lower leg rotational velocity. Our approach does not require calibrated cameras or special markers to capture movement. We have tested our method on different gait sequences collected from the sagttal plane and presented the estimated kinematics overlaid on the original image frames. We have also validated our approach by manually labeling the videos and comparing our results against them.

A systems identification approach to estimating the connectivity in a neuronal population model.

Abstract: Mapping the brain and its complex networked structure has been one of the most researched topics in the last decade and continues to be the path towards understanding brain diseases. In this paper we present a new approach to estimating the connectivity between neurons in a network model. We use systems identification techniques for nonlinear dynamic models to compute the synaptic connections from other pre-synaptic neurons in the population. We are able to show accurate estimation even in the presence of model error and inaccurate assumption of post-synaptic potential dynamics. This allows to compute the connectivity matrix of the network using a very small time window of membrane potential data of the individual neurons. The specificity and sensitivity measures for randomly generated networks are reported.

A new technique to optimize single neuron models using experimental spike train data

Abstract: We propose a new method for fitting model parameters to the neural spike train obtained from an experimental neuron. Due to the uncertainty associated with measuring the accurate voltage in a noisy environment, it is essential to develop methods that rely solely on the interspike intervals (ISI). Existing techniques do not provide a smooth and continuous cost function and optimal estimation of model parameters is difficult. In this paper we formulate a new cost function using the spike times of the neuron and determine the analytical gradient with respect to the model parameters. The optimal parameters are calculated using gradient based optimization techniques. We first use data generated by models to establish the accuracy of our technique. We also optimize the model to fit an experimental spike train of a biological neuron. We are able to find the optimal parameter set using a hybrid algorithm which is a combination of the gradient descent method and global optimization techniques.

Prediction of single neuron spiking activity using an optimized nonlinear dynamic model

Abstract: The increasing need of knowledge in the treatment of brain diseases has driven a huge interest in understanding the phenomenon of neural spiking. Researchers have successfully been able to create mathematical models which, with specific parameters, are able to reproduce the experimental neuronal responses. The spiking activity is characterized using spike trains and it is essential to develop methods for parameter estimation that rely solely on the spike times or interspike intervals (ISI). In this paper we describe a new technique for optimization of a single neuron model using an experimental spike train from a biological neuron. We are able to fit model parameters using the gradient descent method. The optimized model is then used to predict the activity of the biological neuron and the performance is quantified using a spike distance measure.

Human Actions Analysis: Templates Generation, Matching and Visualization Applied to Motion Capture of Highly-Skilled Karate Athletes.

Abstract: The aim of this paper is to propose and evaluate the novel method of template generation, matching, comparing and visualization applied to motion capture (kinematic) analysis. To evaluate our approach, we have used motion capture recordings (MoCap) of two highly-skilled black belt karate athletes consisting of 560 recordings of various karate techniques acquired with wearable sensors. We have evaluated the quality of generated templates; we have validated the matching algorithm that calculates similarities and differences between various MoCap data; and we have examined visualizations of important differences and similarities between MoCap data. We have concluded that our algorithms works the best when we are dealing with relatively short (2–4 s) actions that might be averaged and aligned with the dynamic time warping framework. In practice, the methodology is designed to optimize the performance of some full body techniques performed in various sport disciplines, for example combat sports and martial arts. We can also use this approach to generate templates or to compare the correct performance of techniques between various top sportsmen in order to generate a knowledge base of reference MoCap videos. The motion template generated by our method can be used for action recognition purposes. We have used the DTW classifier with angle-based features to classify various karate kicks. We have performed leave-one-out action recognition for the Shorin-ryu and Oyama karate master separately. In this case, 100 % actions were correctly classified. In another experiment, we used templates generated from Oyama master recordings to classify Shorin-ryu master recordings and vice versa. In this experiment, the overall recognition rate was 94.2 % , which is a very good result for this type of complex action.

Upper extremity movement reliability and validity of the Kinect version 2.

Abstract: Purpose: Studies have shown that marker-less motion detection systems, such as the first generation Kinect (Kinect 1), have good reliability and potential for clinical application. Studies of the s...

Controllability Analysis of Functional Brain Networks

Abstract: Network control theory has recently emerged as a promising approach for understanding brain function and dynamics. By operationalizing notions of control theory for brain networks, it offers a fundamental explanation for how brain dynamics may be regulated by structural connectivity. While powerful, the approach does not currently consider other non-structural explanations of brain dynamics. Here we extend the analysis of network controllability by formalizing the evolution of neural signals as a function of effective inter-regional coupling and pairwise signal covariance. We find that functional controllability characterizes a region's impact on the capacity for the whole system to shift between states, and significantly predicts individual difference in performance on cognitively demanding tasks including those task working memory, language, and emotional intelligence. When comparing measurements from functional and structural controllability, we observed consistent relations between average and modal controllability, supporting prior work. In the same comparison, we also observed distinct relations between controllability and synchronizability, reflecting the additional information obtained from functional signals. Our work suggests that network control theory can serve as a systematic analysis tool to understand the energetics of brain state transitions, associated cognitive processes, and subsequent behaviors.

Motion Capture Systems for Jump Analysis

Abstract: This paper presents several methods used in motion capture to measure jumps. The traditional systems to acquire jump information are force plates, but they are very expensive to most people. Amateur sports enthusiasts that want to improve their performance, do not have enough money to spend in professional systems (\(\pm 20.000\) EUR). The price reduction of electronic devices, specifically the inertial measurement units (IMU), are generating new methods of motion capture. In this paper we present the state-of-art motion capture systems for this purpose, from the classical force plates to latest released IMUs. Noise reduction techniques, as an inherent part of motion capture systems, will be reviewed.