A Classification Model Utilizing Facial Landmark Tracking to Determine Sentence Types for American Sign Language Recognition.

The deaf and hard of hearing community relies on American Sign Language (ASL) as their primary mode of communication, but communication with others who do not know ASL can be difficult, especially during emergencies where no interpreter is available. As an effort to alleviate this problem, research in computer vision based real time ASL interpreting models is ongoing. However, most of these models are hand shape (gesture) based and lack the integration of facial cues, which are crucial in ASL to convey tone and distinguish sentence types. Thus, the integration of facial cues in computer vision based ASL interpreting models has the potential to improve performance and reliability. In this paper, we introduce a simple, computationally efficient facial expression based classification model that can be used to improve ASL interpreting models. This model utilizes the relative angles of facial landmarks with principal component analysis and a Random Forest Classification tree model to classify frames taken from videos of ASL users signing a complete sentence. The model classifies the frames as statements or assertions. The model was able to achieve an accuracy of 86.5%.

A geometric approach to quantifying the neuromodulatory effects of persistent inward currents on individual motor unit discharge patterns.

Objective.All motor commands flow through motoneurons, which entrain control of their innervated muscle fibers, forming a motor unit (MU). Owing to the high fidelity of action potentials within MUs, their discharge profiles detail the organization of ionotropic excitatory/inhibitory as well as metabotropic neuromodulatory commands to motoneurons. Neuromodulatory inputs (e.g. norepinephrine, serotonin) enhance motoneuron excitability and facilitate persistent inward currents (PICs). PICs introduce quantifiable properties in MU discharge profiles by augmenting depolarizing currents upon activation (i.e. PIC amplification) and facilitating discharge at lower levels of excitatory input than required for recruitment (i.e. PIC prolongation).Approach. Here, we introduce a novel geometric approach to estimate neuromodulatory and inhibitory contributions to MU discharge by exploiting discharge non-linearities introduced by PIC amplification during time-varying linear tasks. In specific, we quantify the deviation from linear discharge ('brace height') and the rate of change in discharge (i.e. acceleration slope, attenuation slope, angle). We further characterize these metrics on a simulated motoneuron pool with known excitatory, inhibitory, and neuromodulatory inputs and on human MUs (number of MUs; Tibialis Anterior: 1448, Medial Gastrocnemius: 2100, Soleus: 1062, First Dorsal Interosseus: 2296).Main results. In the simulated motor pool, we found brace height and attenuation slope to consistently indicate changes in neuromodulation and the pattern of inhibition (excitation-inhibition coupling), respectively, whereas the paired MU analysis (ΔF) was dependent on both neuromodulation and inhibition pattern. Furthermore, we provide estimates of these metrics in human MUs and show comparable variability in ΔFand brace height measures for MUs matched across multiple trials.Significance. Spanning both datasets, we found brace height quantification to provide an intuitive method for achieving graded estimates of neuromodulatory and inhibitory drive to individual MUs. This complements common techniques and provides an avenue for decoupling changes in the level of neuromodulatory and pattern of inhibitory motor commands.

Multimodal parameter spaces of a complex multi-channel neuron model.

One of the most common types of models that helps us to understand neuron behavior is based on the Hodgkin-Huxley ion channel formulation (HH model). A major challenge with inferring parameters in HH models is non-uniqueness: many different sets of ion channel parameter values produce similar outputs for the same input stimulus. Such phenomena result in an objective function that exhibits multiple modes (i.e., multiple local minima). This non-uniqueness of local optimality poses challenges for parameter estimation with many algorithmic optimization techniques. HH models additionally have severe non-linearities resulting in further challenges for inferring parameters in an algorithmic fashion. To address these challenges with a tractable method in high-dimensional parameter spaces, we propose using a particular Markov chain Monte Carlo (MCMC) algorithm, which has the advantage of inferring parameters in a Bayesian framework. The Bayesian approach is designed to be suitable for multimodal solutions to inverse problems. We introduce and demonstrate the method using a three-channel HH model. We then focus on the inference of nine parameters in an eight-channel HH model, which we analyze in detail. We explore how the MCMC algorithm can uncover complex relationships between inferred parameters using five injected current levels. The MCMC method provides as a result a nine-dimensional posterior distribution, which we analyze visually with solution maps or landscapes of the possible parameter sets. The visualized solution maps show new complex structures of the multimodal posteriors, and they allow for selection of locally and globally optimal value sets, and they visually expose parameter sensitivities and regions of higher model robustness. We envision these solution maps as enabling experimentalists to improve the design of future experiments, increase scientific productivity and improve on model structure and ideation when the MCMC algorithm is applied to experimental data.