Recent advances in neuroscience have revealed many principles about neural processing. In particular, many biological systems were found to reconfigure/recruit single neurons to generate multiple kinds of decisions. Such findings have the potential to advance our understanding of the design and optimization process of artificial neural networks. Previous work demonstrated that dense neural networks are needed to shape complex decision surfaces required for AI-level recognition tasks. We investigate the ability to model high dimensional recognition problems using single or several neurons networks that are relatively easier to train. By employing three datasets, we test the use of a population of single neuron networks in performing multi-class recognition tasks. Surprisingly, we find that sparse networks can be as efficient as dense networks in both binary and multi-class tasks. Moreover, single neuron networks demonstrate superior performance in binary classification scheme and competing results when combined for multi-class recognition.
Swallowing dysfunction, or dysphagia, occurs secondary to many underlying etiologies such as stroke and can lead to pneumonia. The upper esophageal sphincter (UES) is a major anatomical landmark that allows the passage of swallowed materials into the esophagus during swallowing. Delayed UES opening or reduced duration of opening can lead to the accumulation of pharyngeal residue, which can increase risk of aspiration. UES opening is observed through the inspection of radiographic exams, known as videofluoroscopy swallow studies (VFSSs), which expose patients to ionizing radiation and depend on subjective clinician interpretations. High resolution cervical auscultation (HRCA) is a non-invasive sensor-based technology that has been recently investigated to depict swallowing physiology. HRCA has been proposed for detecting UES opening duration through a deep learning framework. However, the proposed framework was only validated over swallows from patients. For such an algorithm to be robust, it has to be proven equally reliable for the detection of UES opening duration in swallows from both patients and healthy subjects. In this study, we intend to investigate the robustness of the HRCA-based framework to detect the UES opening in signals collected from a diverse population. The framework showed comparable performance regarding the UES opening detection with an average area under the ROC curve of 95%. The results indicate that the HRCA-based UES opening detection can provide superior performance on swallows from diverse populations which demonstrates the clinical potential of HRCA as a non-invasive swallowing assessment tool.
Existing radar algorithms assume stationary statistical characteristics for environment/clutter. In practical scenarios, the statistical characteristics of the clutter can dynamically change depending on where the radar is operating. Non-stationarity in the statistical characteristics of the clutter may negatively affect the radar performance. Cognitive radar that can sense the changes in the clutter statistics, learn the new statistical characteristics, and adapt to these changes has been proposed to overcome these shortcomings. We have recently developed techniques for detection of statistical changes and learning the new clutter distribution for cognitive radar. In this work, we will extend the learning component. More specifically, in our previous work, we have developed a sparse recovery based clutter distribution identification to learn the distribution of the new clutter characteristics after the detected change in the statistics of the clutter. In our method, we have built a dictionary of clutter distributions and used this dictionary in orthogonal matching pursuit to perform sparse recovery of the clutter distribution assuming that the dictionary includes the new distribution. In this work, we propose a hypothesis testing based approach to detect whether the new distribution of the clutter is included in the dictionary or not, and suggest a method to dynamically update the dictionary. We envision that the successful outcomes of this work will be of high relevance to the adaptive learning and cognitive augmentation of the radar systems that are used in remotely piloted vehicles for surveillance and reconnaissance operations.
Malia Kelsey, Richard Vincent Palumbo, Alberto Urbaneja, Murat Akcakaya, Jeannie Huang, Ian Kleckner, Lisa Feldman Barrett, Karen Quigley, Ervin Sejdic, Matthew Goodwin
Electrodermal Activity (EDA) – a peripheral index of sympathetic nervous system activity - is a primary measure used in psychophysiology. EDA is widely accepted as an indicator of physiological arousal, and it has been shown to reveal when psychologically novel events occur. Traditionally, EDA data is collected in controlled laboratory experiments. However, recent developments in wireless biosensing have led to an increase in out-of-lab studies. This transition to ambulatory data collection has introduced challenges. In particular, artifacts such as wearer motion, changes in temperature, and electrical interference can be misidentified as true EDA responses. The inability to distinguish artifact from signal hinders analyses of ambulatory EDA data. Though manual procedures for identifying and removing EDA artifacts exist, they are time consuming – which is problematic for the types of longitudinal data sets represented in modern ambulatory studies. This manuscript presents a novel technique to automatically identify and remove artifacts in EDA data using curve fitting and sparse recovery methods. Our method was evaluated using labeled data to determine the accuracy of artifact identification. Procedures, results, conclusions, and future directions are presented.
Acquiring swallowing accelerometry signals using a comprehensive sensing scheme may be a desirable approach for monitoring swallowing safety for longer periods of time. However, it needs to be insured that signal characteristics can be recovered accurately from compressed samples. In this paper, we considered this issue by examining the effects of the number of acquired compressed samples on the calculated swallowing accelerometry signal features. We used tri-axial swallowing accelerometry signals acquired from seventeen stroke patients (106 swallows in total). From acquired signals, we extracted typically considered signal features from time, frequency and time-frequency domains. Next, we compared these features from the original signals (sampled using traditional sampling schemes) and compressively sampled signals. Our results have shown we can obtain accurate estimates of signal features even by using only a third of original samples.
Emerging methods for the spectral analysis of graphs are analyzed in this paper, as graphs are currently used to study interactions in many fields from neuroscience to social networks. There are two main approaches related to the spectral transformation of graphs. The first approach is based on the Laplacian matrix. The graph Fourier transform is defined as an expansion of a graph signal in terms of eigenfunctions of the graph Laplacian. The calculated eigenvalues carry the notion of frequency of graph signals. The second approach is based on the graph weighted adjacency matrix, as it expands the graph signal into a basis of eigenvectors of the adjacency matrix instead of the graph Laplacian. Here, the notion of frequency is then obtained from the eigenvalues of the adjacency matrix or its Jordan decomposition. In this paper, advantages and drawbacks of both approaches are examined. Potential challenges and improvements to graph spectral processing methods are considered as well as the generalization of graph processing techniques in the spectral domain. Its generalization to the time-frequency domain and other potential extensions of classical signal processing concepts to graph datasets are also considered. Lastly, it is given an overview of the compressive sensing on graphs concepts.
Analog sparse signals resulting from biomedical and sensing network applications are typically non–stationary with frequency–varying spectra. By ignoring that the maximum frequency of their spectra is changing, uniform sampling of sparse signals collects unnecessary samples in quiescent segments of the signal. A more appropriate sampling approach would be signal–dependent. Moreover, in many of these applications power consumption and analog processing are issues of great importance that need to be considered. In this paper we present a signal dependent non–uniform sampler that uses a Modified Asynchronous Sigma Delta Modulator which consumes low–power and can be processed using analog procedures. Using Prolate Spheroidal Wave Functions (PSWF) interpolation of the original signal is performed, thus giving an asynchronous analog to digital and digital to analog conversion. Stable solutions are obtained by using modulated PSWFs functions. The advantage of the adapted asynchronous sampler is that range of frequencies of the sparse signal is taken into account avoiding aliasing. Moreover, it requires saving only the zero–crossing times of the non–uniform samples, or their differences, and the reconstruction can be done using their quantized values and a PSWF–based interpolation. The range of frequencies analyzed can be changed and the sampler can be implemented as a bank of filters for unknown range of frequencies. The performance of the proposed algorithm is illustrated with an electroencephalogram (EEG) signal.
Swallowing accelerometry is a promising tool for non-invasive assessment of swallowing difficulties. A recent contribution showed that swallowing accelerometry signals for healthy swallows and swallows indicating laryn- geal penetration or tracheal aspiration have different time-frequency structures, which may be problematic for compressive sensing schemes based on time-frequency dictionaries. In this paper, we examined the effects of dif- ferent swallows on the accuracy of a compressive sensing scheme based on modulated discrete prolate spheroidal sequences. We utilized tri-axial swallowing accelerometry signals recorded from four patients during routinely schedule videofluoroscopy exams. In particular, we considered 77 swallows approximately equally distributed between healthy swallows and swallows presenting with some penetration/aspiration. Our results indicated that the swallow type does not affect the accuracy of a considered compressive sensing scheme. Also, the results con- firmed previous findings that each individual axis contributes different information. Our findings are important for further developments of a device which is to be used for long-term monitoring of swallowing difficulties.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.