Memristive devices are promising candidates to emulate biological computing. However, the typical switching voltages (0.2-2 V) in previously described devices are much higher than the amplitude in biological counterparts. Here we demonstrate a type of diffusive memristor, fabricated from the protein nanowires harvested from the bacterium Geobacter sulfurreducens, that functions at the biological voltages of 40-100 mV. Memristive function at biological voltages is possible because the protein nanowires catalyze metallization. Artificial neurons built from these memristors not only function at biological action potentials (e.g., 100 mV, 1 ms) but also exhibit temporal integration close to that in biological neurons. The potential of using the memristor to directly process biosensing signals is also demonstrated. Designing energy efficient systems capable to directly process signals at biological voltages remains a challenge. Here, the authors propose a bio-compatible memristor device based on protein-nanowire dielectric, harvested from the bacterium Geobactor sulfurreducens, working at biological voltages.

/pdf/bioinspired-bio-voltage-memristors-57r6x0dgh8.pdf

Bioinspired bio-voltage memristors

In this paper we present a method for continuous EEG classification, where we employ nonnegative tensor factorization (NTF) to determine discriminative spectral features and use the Viterbi algorithm to continuously classily multiple mental tasks. This is an extension of our previous work on the use of nonnegative matrix factorization (NMF) for EEG classification. Numerical experiments with two data sets in BCI competition, confirm the useful behavior of the method for continuous EEG classification.

Nonnegative Tensor Factorization for Continuous EEG Classification

The advent of dedicated Deep Learning (DL) accelerators and neuromorphic processors has brought on new opportunities for applying both Deep and Spiking Neural Network (SNN) algorithms to healthcare and biomedical applications at the edge. This can facilitate the advancement of medical Internet of Things (IoT) systems and Point of Care (PoC) devices. In this paper, we provide a tutorial describing how various technologies including emerging memristive devices, Field Programmable Gate Arrays (FPGAs), and Complementary Metal Oxide Semiconductor (CMOS) can be used to develop efficient DL accelerators to solve a wide variety of diagnostic, pattern recognition, and signal processing problems in healthcare. Furthermore, we explore how spiking neuromorphic processors can complement their DL counterparts for processing biomedical signals. The tutorial is augmented with case studies of the vast literature on neural network and neuromorphic hardware as applied to the healthcare domain. We benchmark various hardware platforms by performing a sensor fusion signal processing task combining electromyography (EMG) signals with computer vision. Comparisons are made between dedicated neuromorphic processors and embedded AI accelerators in terms of inference latency and energy. Finally, we provide our analysis of the field and share a perspective on the advantages, disadvantages, challenges, and opportunities that various accelerators and neuromorphic processors introduce to healthcare and biomedical domains.

Hardware Implementation of Deep Network Accelerators Towards Healthcare and Biomedical Applications

Electrocardiogram (ECG) signal analysis has received special attention of the researchers in the recent past because of its ability to divulge crucial information about the electrophysiology of the heart and the autonomic nervous system activity in a noninvasive manner. Analysis of the ECG signals has been explored using both linear and nonlinear methods. However, the nonlinear methods of ECG signal analysis are gaining popularity because of their robustness in feature extraction and classification. The current study presents a review of the nonlinear signal analysis methods, namely, reconstructed phase space analysis, Lyapunov exponents, correlation dimension, detrended fluctuation analysis (DFA), recurrence plot, Poincare plot, approximate entropy, and sample entropy along with their recent applications in the ECG signal analysis.

/pdf/a-review-on-the-nonlinear-dynamical-system-analysis-of-nd17z6duwy.pdf

A Review on the Nonlinear Dynamical System Analysis of Electrocardiogram Signal.

With the advent of dedicated Deep Learning (DL) accelerators and neuromorphic processors, new opportunities are emerging for applying deep and Spiking Neural Network (SNN) algorithms to healthcare and biomedical applications at the edge. This can facilitate the advancement of the medical Internet of Things (IoT) systems and Point of Care (PoC) devices. In this paper, we provide a tutorial describing how various technologies ranging from emerging memristive devices, to established Field Programmable Gate Arrays (FPGAs), and mature Complementary Metal Oxide Semiconductor (CMOS) technology can be used to develop efficient DL accelerators to solve a wide variety of diagnostic, pattern recognition, and signal processing problems in healthcare. Furthermore, we explore how spiking neuromorphic processors can complement their DL counterparts for processing biomedical signals. After providing the required background, we unify the sparsely distributed research on neural network and neuromorphic hardware implementations as applied to the healthcare domain. In addition, we benchmark various hardware platforms by performing a biomedical electromyography (EMG) signal processing task and drawing comparisons among them in terms of inference delay and energy. Finally, we provide our analysis of the field and share a perspective on the advantages, disadvantages, challenges, and opportunities that different accelerators and neuromorphic processors introduce to healthcare and biomedical domains. This paper can serve a large audience, ranging from nanoelectronics researchers, to biomedical and healthcare practitioners in grasping the fundamental interplay between hardware, algorithms, and clinical adoption of these tools, as we shed light on the future of deep networks and spiking neuromorphic processing systems as proponents for driving biomedical circuits and systems forward.

Characterization of phase space trajectories for Brain-Computer Interface

We present DiSH-Sim, a simulator for large discrete models of biological signal transduction pathways, capable of simulating networks with multi-valued elements in both deterministic and stochastic manner. We focus on order of update and thus incorporate information about timing, taking into account that biological processes are not synchronized and certain biochemical changes occur slower than others. Another feature of our simulator is the use of grouped rules to model multi-valued elements and delays. The DiSH-Sim is publicly available and is being used to validate discrete cancer microenvironment and infectious disease models. It is also incorporated within a large architecture that includes natural language processing tools that read biological literature to assemble logical models. This paper demonstrates the functionalities and ease of use of DiSH-Sim, making it a very useful tool for discrete modeling.

DiSH Simulator: Capturing Dynamics of Cellular Signaling with Heterogeneous Knowledge

In this paper, we present DiSH, a simulator for large discrete models of biological signal transduction pathways, capable of simulating networks with multi-valued elements in both deterministic and stochastic manner. The simulator incorporates the timing of molecular reactions, which are often not synchronized and occur in random order, and it also takes into account the difference between slow and fast reactions. DiSH also allows for changes in conditions during simulations, combined deterministic and stochastic changes, and it uses the concept of delays in models, similar to delays in digital circuits. DiSH is publicly available and has been used to study intra- and inter-cellular models of several diseases. It is also being used as part of a larger architecture including natural language processing tools that read biological literature, automated model assembly tools, and formal model analysis tools.

Dish simulator: capturing dynamics of cellular signaling with heterogeneous knowledge

Biological literature is rich in mechanistic information that can be utilized to construct executable models of complex systems to increase our understanding of health and disease. However, the literature is vast and fragmented, and therefore, automation of information extraction from papers and of model assembly from the extracted information is necessary. We describe here our approach for translating machine reading outputs, obtained by reading biological signaling literature, to discrete models of cellular networks. We use outputs from three different reading engines, and demonstrate the translation of different features using examples from cancer literature. We also outline several issues that still arise when assembling cellular network models from state-of-the-art reading engines. Finally, we illustrate the details of our approach with a case study in pancreatic cancer.

Khaled Sayed

Papers

Characterization of phase space trajectories for Brain-Computer Interface

DiSH Simulator: Capturing Dynamics of Cellular Signaling with Heterogeneous Knowledge

Dish simulator: capturing dynamics of cellular signaling with heterogeneous knowledge

Recipes for Translating Big Data Machine Reading to Executable Cellular Signaling Models

Compensatory hepatic adaptation accompanies permanent absence of intrahepatic biliary network due to YAP1 loss in liver progenitors.