More Like this

1. Nonlinear Time-Series Prediction Using a Single MEMS Reservoir

   https://doi.org/10.1115/DETC2020-22671  

   Hasan, Mohammad H.; Alsaleem, Fadi (August 2020, 14th International Conference on Micro- and Nanosystems (MNS))

   null (Ed.)

   Abstract In this work, we show the computational potential of MEMS devices by predicting the dynamics of a 10th order nonlinear auto-regressive moving average (NARMA10) dynamical system. Modeling this system is considered complex due to its high nonlinearity and dependency on its previous values. To model the NARMA10 system, we used a reservoir computing scheme by utilizing one MEMS device as a reservoir, produced by the interaction of 100 virtual nodes. The virtual nodes are attained by sampling the input of the MEMS device and modulating this input using a random modulation mask. The interaction between virtual nodes within the system was produced through delayed feedback and temporal dependence. Using this approach, the MEMS device was capable of adequately capturing the NARMA10 response with a normalized root mean square error (NRMSE) = 6.18% and 6.43% for the training and testing sets, respectively. In practice, the MEMS device would be superior to simulated reservoirs due to its ability to perform this complex computing task in real time. 

   more » « less
2. Machine Learning Augmentation in Micro-Sensor Assemblies

   https://doi.org/10.1115/DETC2020-22665  

   Hasan, Mohammad H.; Alsaleem, Fadi; Abbasalipour, Amin; Pourkamali Anaraki, Siavash; Emad-Un-Din, Muhammad; Jafari, Roozbeh (August 2020, 14th International Conference on Micro- and Nanosystems (MNS))

   null (Ed.)

   Abstract The size and power limitations in small electronic systems such as wearable devices limit their potential. Significant energy is lost utilizing current computational schemes in processes such as analog-to-digital conversion and wireless communication for cloud computing. Edge computing, where information is processed near the data sources, was shown to significantly enhance the performance of computational systems and reduce their power consumption. In this work, we push computation directly into the sensory node by presenting the use of an array of electrostatic Microelectromechanical systems (MEMS) sensors to perform colocalized sensing-and-computing. The MEMS network is operated around the pull-in regime to access the instability jump and the hysteresis available in this regime. Within this regime, the MEMS network is capable of emulating the response of the continuous-time recurrent neural network (CTRNN) computational scheme. The network is shown to be successful at classifying a quasi-static input acceleration waveform into square or triangle signals in the absence of digital processors. Our results show that the MEMS may be a viable solution for edge computing implementation without the need for digital electronics or micro-processors. Moreover, our results can be used as a basis for the development of new types of specialized MEMS sensors (ex: gesture recognition sensors). 

   more » « less
3. Exploiting Pull-In/Pull-Out Hysteresis in Electrostatic MEMS Sensor Networks to Realize a Novel Sensing Continuous-Time Recurrent Neural Network

   https://doi.org/10.3390/mi12030268  

   H Hasan, Mohammad; Abbasalipour, Amin; Nikfarjam, Hamed; Pourkamali, Siavash; Emad-Ud-Din, Muhammad; Jafari, Roozbeh; Alsaleem, Fadi (March 2021, Micromachines)

   null (Ed.)

   The goal of this paper is to provide a novel computing approach that can be used to reduce the power consumption, size, and cost of wearable electronics. To achieve this goal, the use of microelectromechanical systems (MEMS) sensors for simultaneous sensing and computing is introduced. Specifically, by enabling sensing and computing locally at the MEMS sensor node and utilizing the usually unwanted pull in/out hysteresis, we may eliminate the need for cloud computing and reduce the use of analog-to-digital converters, sampling circuits, and digital processors. As a proof of concept, we show that a simulation model of a network of three commercially available MEMS accelerometers can classify a train of square and triangular acceleration signals inherently using pull-in and release hysteresis. Furthermore, we develop and fabricate a network with finger arrays of parallel plate actuators to facilitate coupling between MEMS devices in the network using actuating assemblies and biasing assemblies, thus bypassing the previously reported coupling challenge in MEMS neural networks. 

   more » « less
4. Modeling and Simulation of Circuit-Level Nonidealities for an Analog Computing Design Approach with Application to EEG Feature Extraction

   https://doi.org/10.1109/TCAD.2022.3170248  

   Mirchandani, Nikita; Zhang, Yuqing; Abdelfattah, Safaa; Onabajo, Marvin; Shrivastava, Aatmesh (April 2022, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems)

   This paper presents a design approach for the modeling and simulation of ultra-low power (ULP) analog computing machine learning (ML) circuits for seizure detection using EEG signals in wearable health monitoring applications. In this paper, we describe a new analog system modeling and simulation technique to associate power consumption, noise, linearity, and other critical performance parameters of analog circuits with the classification accuracy of a given ML network, which allows to realize a power and performance optimized analog ML hardware implementation based on diverse application-specific needs. We carried out circuit simulations to obtain non-idealities, which are then mathematically modeled for an accurate mapping. We have modeled noise, non-linearity, resolution, and process variations such that the model can accurately obtain the classification accuracy of the analog computing based seizure detection system. Noise has been modeled as an input-referred white noise that can be directly added at the input. Device process and temperature variations were modeled as random fluctuations in circuit parameters such as gain and cut-off frequency. Nonlinearity was mathematically modeled as a power series. The combined system level model was then simulated for classification accuracy assessments. The design approach helps to optimize power and area during the development of tailored analog circuits for ML networks with the ability to potentially trade power and performance goals while still ensuring the required classification accuracy. The simulation technique also enables to determine target specifications for each circuit block in the analog computing hardware. This is achieved by developing the ML hardware model, and investigating the effect of circuit nonidealities on classification accuracy. Simulation of an analog computing EEG seizure detection block shows a classification accuracy of 91%. The proposed modeling approach will significantly reduce design time and complexity of large analog computing systems. Two feature extraction approaches are also compared for an analog computing architecture. 

   more » « less
5. Analog Cancellation of a Known Remote Interference: Hardware Realization and Analysis

   https://doi.org/10.1109/LWC.2023.3346290  

   Doty, James M; Jackson, Robert W; Goeckel, Dennis L (March 2024, IEEE Wireless Communications Letters)

   The onset of quantum computing calls for secrecy schemes that can provide everlasting secrecy resistant to increased computational power of an adversary. One novel physical layer scheme proposes that an intended receiver capable of performing analog cancellation of a known key-based interference would hold a significant advantage in recovering small underlying messages versus an eavesdropper performing cancellation after analog-to-digital conversion. This advantage holds even if an eavesdropper later obtains the key and employs it in their digital cancellation. Inspired by this scheme, a flexible software-defined radio receiver design capable of maintaining analog cancellation ratios over 40 dB, reaching up to and over 50 dB, is implemented. Using analog cancellation levels from the hardware testbed, practical everlasting secrecy rates up to 2.0 bits/symbol are shown to be gained by receivers performing interference cancellation in analog rather than on a digital signal processor. 

   more » « less