Academic Positions

  • Present 2015

    Assistant Professor

    Concordia University, Concordia Institute of Information Systems Engineering (CIISE)

  • 2015 2013

    Postdoctoral Fellow

    University of Toronto, Department of Electrical and Computer Engineering

Education & Training

  • Ph.D. 2013

    Ph.D. in Electrical Engineering

    York University Department of Electrical Engineering and Computer Science

  • M.Sc.2007

    Master of Science in Biomedical Engineering

    Amirkabir University of Technology (Tehran Polytechnic)

  • B.A.2005

    Bachelor of Electrical Engineering

    University of Tehran

Bibliometrics

  •                          

Professional Service

They did not know it was impossible so they did it. Mark Twain.

Honors, Awards and Grants

  • May 2019
    Gina Cody School of Engineering and Computer Science's Research Award - Tier III
    image
    Gina Cody School of Engineering and Computer Science's Research Award received during Dean's Excellence Awards Ceremony on May 28th, 2019.
  • May 2019
    Gina Cody School of Engineering and Computer Science's Teaching Excellence Award
    image
    Gina Cody School of Engineering and Computer Science's Teaching Excellence Award received during Dean's Excellence Awards Ceremony on May 28th, 2019.
  • June 2018
    Concordia President's Excellence in Teaching Award
    image
    Recipient of Concordia President's Excellence in Teaching Award in the New Teacher Category.
  • Feb. 2014
    Eshrat Arjomandi Award for Outstanding Ph.D. Dissertation
    image
    Best Ph.D. Thesis Award from Department of Electrical Engineering and Computer Science (EECS), York University.
  • July 2012
    IEEE Information Fusion Student Paper Award
    image
    One of 10 recipients of Student Paper Awards at 15th IEEE International Conference on Information Fusion, 2012, for my paper entitled: "Decentralized Sensor Selection based on the Distributed Posterior Cramer-Rao Lower Bound"
  • Dec. 2011
    IEEE CAMSAP Student Researcher Travel Grant
    IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP 2011). The Grant was supported by the U.S. Office of Naval Research (7 recipients).

Research Summary

We live in an era of data deluge. The volume, variety, and velocity of data is exploding and the ability to process such large amounts of information promises to limit the spread of epidemics, learn the dynamics of emergent social-computational systems, and protect critical infrastructures. Of particular interest to this talk is the big data collected from Cyber-Physical Systems (CPS), which exhibit a wide range of diversities. The CPSs are engineering systems with embedded control, communication and sensing capabilities that can interact with humans through cyber space. Recently there has been a surge of interest in practical and opportunistic applications of CPSs including: (i) State prediction for analyzing contingencies and taking preventive actions against possible failures in smart power grids; (ii) Optimizing the reliability of CPSs using decentralized sensor resource management techniques, and; (iii) Surveillance applications for following a reference target in decentralized camera networks. State forecasting is the core part of all these problems, which is the focus of this talk.

Interests

  • Statistical Signal Processing
  • Systems with Non-Linear Dynamics
  • Cyber-Physical Systems
  • Distributed Agent/ Sensor Networks
  • Information Fusion
  • Large-Scale Dynamical Systems
  • Complex-Valued Systems
  • Predictive Analytics
  • Smart Grids

Prospective Students

Research Assistant Positions

  • I am seeking energetic, innovative, and hard-working graduate students interested in working with me on statistical signal/image processing, secure/event-based processing in Cyber-Physical Systems (CPS), information fusion, and communications.

  • If you are interested in joining my research group, please read my research publications and send me an email including your CV and a list of your research publications (if any). Your email should also indicate: (i) The research area of your interest and why you are interested; (ii) Your research plans (if any), e.g., prepare a research proposal, and; (iii) Your past research experiences.

  • Please note that I will respond to an email only if I am interested in your background. Otherwise, please assume that I am not interested.

  • A Successful candidate should have strong background in systems and mathematics, strong analytical skills, and familiarity with Matlab.

  • Advice for Prospective Research Students

Current Teaching

  • Winter 2019

    COEN-231: Introduction to Discrete Mathematics

    This course contains some mathematical background required in many other engineering advanced courses and many real world engineering applications. By the end of this course, students should learn a particular set of mathematical facts and how to apply them and more importantly should be able to think logically and mathematically. Five important themes are interwoven in the textbook and lectures: mathematical reasoning, combinatorial analysis, discrete structures, algorithmic thinking, and application and modeling.

    image image

    INSE-6320: Risk Analysis for Information and Systems Engineering

    This course examines the fundamental concepts, techniques and tools for risk analysis and decision making strategies in the context of information and systems engineering. This includes qualitative and quantitative risk assessment, risks in systems engineering, environmental risks, security risks; methods of risk analysis, fault trees and event trees; quantification of probabilities, use of data, models, and expert judgements; risks and decisions, interlinking risk analysis with risk management; decision analysis; system analysis and quantification; uncertainty modeling and risk measurement; and project risk management.

    image image

Previous Teaching

  • Winter 2018

    COEN-231: Introduction to Discrete Mathematics

    This course contains some mathematical background required in many other engineering advanced courses and many real world engineering applications. By the end of this course, students should learn a particular set of mathematical facts and how to apply them and more importantly should be able to think logically and mathematically. Five important themes are interwoven in the textbook and lectures: mathematical reasoning, combinatorial analysis, discrete structures, algorithmic thinking, and application and modeling.

    image image

    INSE-6310: Systems Engineering Maintenance Management

    This course teaches basic concepts, models, methods and tools in maintenance management. The related reliability concepts, deterministic replacement, preventive maintenance and condition based maintenance will be discussed. Case studies will be performed.

    image image
  • Winter 2017

    INSE-6310: Introduction to Discrete Mathematics

    This course teaches basic concepts, models, methods and tools in maintenance management. The related reliability concepts, deterministic replacement, preventive maintenance and condition based maintenance will be discussed. Case studies will be performed.

    image image
  • Fall 2016

    COEN-231: Systems Engineering Maintenance Management

    This course contains some mathematical background required in many other engineering advanced courses and many real world engineering applications. By the end of this course, students should learn a particular set of mathematical facts and how to apply them and more importantly should be able to think logically and mathematically. Five important themes are interwoven in the textbook and lectures: mathematical reasoning, combinatorial analysis, discrete structures, algorithmic thinking, and application and modeling.

    image image
  • Winter 2016

    INSE-6310: Introduction to Discrete Mathematics

    This course teaches basic concepts, models, methods and tools in maintenance management. The related reliability concepts, deterministic replacement, preventive maintenance and condition based maintenance will be discussed. Case studies will be performed.

    image
  • Fall 2012

    CSE3451: Signals and Systems

    York University, Toronto, Canada, course offered by the Departments of Computer Sciece and Engineering.

Teaching Experience as Tutorial Teaching Assistant

  • 2008 2013

    CSE4215: Mobile Communication

    York University, Toronto, Canada, course offered by the Departments of Computer Sciece and Engineering.

    CSE3451: Signals and Systems

    York University, Toronto, Canada, course offered by the Departments of Computer Sciece and Engineering.

Teaching Experience as Teaching Assistant

  • 2008 2013

    CSE1020: Introduciton to Computer Science I

    York University, Toronto, Canada, course offered by the Departments of Computer Sciece and Engineering.

    CSE1030: Introduciton to Computer Science II

    York University, Toronto, Canada, course offered by the Departments of Computer Sciece and Engineering.

    CSE1560: Introduction to Computing for Mathematics and Statistics

    York University, Toronto, Canada, course offered by the Departments of Computer Sciece and Engineering.

Filter by type:

Sort by year:

PHTNet: Characterization and Deep Mining of Involuntary Pathological Hand Tremor using Recurrent Neural Network Models

Soroosh Shahtalebi, Seyed Farokh Atashzar, Olivia Samotus, Rajni V. Patel, Mandar S. Jog, and Arash Mohammadi
Journal Paper 36 Submitted to Nature Scientific Reports, 2019.

Abstract

The global aging phenomenon has increased the number of individuals with age-related neurological movement disorders including Parkinson’s Disease (PD) and Essential Tremor (ET). Pathological Hand Tremor (PHT), which is considered among the most common motor symptoms of such disorders, can severely affect patients’ independence and quality of life. To develop advanced rehabilitation and assistive technologies, accurate estimation/prediction of nonstationary PHT is critical, however, the required level of accuracy has not yet been achieved. The lack of sizable datasets and generalizable modeling techniques that can fully represent the spectrotemporal characteristics of the PHT have been a critical bottleneck in attaining this goal. The paper addresses this unmet need through establishing a deep recurrent model to predict and eliminate the PHT component of hand motion. More specifically, we propose a machine learning-based, assumption-free, and real-time PHT elimination framework, the PHTNet, by incorporating deep bidirectional recurrent neural networks. The PHTNet is developed over a hand motion dataset of 81 ET and PD patients collected systematically in a movement disorders clinic over 3 years. The PHTNet is the first intelligent systems model developed on this scale for PHT elimination that maximizes the resolution of estimation and allows for prediction of future and upcoming sub-movements.

Noisy Hybrid Neural Network Arcitecture for Remaining Useful Life Estimation

Ali Al-Dulaimi, Soheil Zabihi, Amir Asif, and Arash Mohammadi
Journal Paper 35 Submitted to Journal of Computing and Information Science in Engineering, 2019.

Abstract

Smart manufacturing and industrial Internet of Things (IoT) have transformed the maintenance management concept from the conventional perspective of being reactive to being predictive. Recent advancements in this regard has resulted in development of effective Prognostic Health Management (PHM) frameworks, which coupled with deep learning architectures have produced sophisticated techniques for Remaining Useful Life (RUL) estimation. Accurately predicting the RUL significantly empowers the decision making process and allows deployment of advanced maintenance strategies to improve the overall outcome in a timely fashion. In light of this, the paper proposes a novel noisy deep learning architecture consisting of multiple models designed in parallel, referred to as noisy and hybrid deep architecture for remaining useful life estimation (NBLSTM). The proposed NBLSTM is designed by integration of two parallel noisy deep architectures, i.e., a noisy Convolutional Neural Network (CNN) to extract spatial features, and a noisy Bidirectional Long Short-Term Memory (BLSTM) to extract temporal information learning the dependencies of input data in both forward and backward directions. The two paths are connected through a fusion center consisting of fully connected multilayers, which combines their outputs and forms the target predicted RUL. To improve the robustness of the model, the NBLSTM is trained based on noisy input signals leading to significantly robust and enhanced generalization behavior. The proposed NBLSTM model is evaluated and tested based on the Commercial Modular Aero-Propulsion System Simulation (CMAPSS) dataset provided by NASA, illustrating state-of-the-art results in comparison to its counterparts.

STUPEFY: Set-Valued Box Particle Filtering for BLE-based Indoor Localization

Parvin Malekzadeh, Konstantinos N. Plataniotis, and Arash Mohammadi
Journal Paper 34 Submitted to Signal Processing Letters, 2019.

Abstract

With the rapid emergence of Internet of Things (IoT), we are more and more surrounded by smart connected devices with integrated sensing, processing, and communication capabilities. Bluetooth Low Energy (BLE), referred to as Bluetooth Smart, is considered as the main-stream technology to perform identification and localization/tracking in IoT applications. While single-model BLE-based tracking has been investigated from different aspects, application of multi-model (hybrid) solutions are still in their infancy. In this regard, the letter proposes a novel BLE-based tracking framework, referred to as the STUPEFY, which incorporates set-valued information within box particle filtering context. More specifically, the proposed multiple-model STUPEFY framework consists of three integrated modules, i.e., an intriguing Smoothing Module based on Kalman filtering to reduce the RSSI fluctuations and facilitate comparison of Gaussian models of the RSSI values in distribution with the learned ones; A learning-based model (Cooperation Module) utilized in an intuitive fashion to provide/construct a coarse estimate of the target’s location together with the smallest axes-aligned box containing the ellipsoid associated with each zone’s learned RSSI distribution, and; A novel set-valued box particle filtering (SBPF) approach (Micro-Localization Module). The proposed STUPEFY framework is evaluated based on real BLE datasets and results illustrate significant potentials in terms of improving overall BLE-based achievable tracking accuracy.

Mobility-Aware Femtocaching Algorithm in D2D Networks Based on Handover

Zohreh Hajiakhondi, Jamshid Abouei, Muhammad Jassemuddin, and Arash Mohammadi
Journal Paper 33 Submitted to IEEE Transactions on Vehicular Technology, 2019.

Abstract

Storing the most popular contents in local caching nodes, including Femto Access Points (FAPs) and user devices, supported by Device-to-Device (D2D) communications, is a promising solution to deal with the backhaul bottleneck and improves content download latency. Toward this goal, we present an enterprise wireless network consisting of both FAPs and Mobile Users (MUs), in which MUs communicate directly with each other via D2D communication. Despite all the benefits that came with the D2D communication, this type of connection leads to consuming the battery of users’ devices. On the other hand, regarding the fact that the user’s mobility is one of the inherent features of wireless networks, particularly in a large enterprise that femtocells operate in an open access mode, the small transmission range of FAPs leads to triggering frequent handovers. Taking the above challenges into account, we propose a novel Mobility-Aware Femtocaching scheme based on Handover (MAFH) in order to reduce the number of unnecessary handovers and increase the battery life of users’ devices. In this regard, the best caching node is selected by considering the velocity of users as decision criteria to download the required content. Moreover, a random walk model is assumed to illustrate the mobility pattern’s of users to implement a practical model. The effectiveness of the proposed MAFH algorithm is evaluated in terms of the cache hit ratio, transferred byte volume, connecting time, content delivery time, the number of handovers, and the energy consumption of clients.

A Co-Designed Incentives for an Aimed Renewable Energy Contribution and Volunteer Load Shedding

Ehsan Saeidpour Parizy, Arash Mohammadi, Ali Jahanbani Ardakani, and Kenneth A. Loparo
Journal Paper 32 Submitted to IET Renewable Power Generation, 2019.

Abstract

An unavoidable revolution is upon us changing mainstream of electricity supply from a thermal-dominant profile to a renewable-supplied grid. This revolution comes with vital benefits for sustainability of electricity generation. However, several challenges, especially at high levels of renewable energy sources (RESs) penetration, need to be addressed. In particular, and due to economic reasons and stability issues, RESs are underdogs in competition with fossil-fuel generations, unless proper incentives are provided added to consumers’ electricity bills. The other challenge is their intermittent output, which compromises the grid efficiency and increases the consumers’ electricity bill. The aforementioned issues can be resolved, using demand response, which is limited upon the load flexibility. Volunteer load-shedding could help if the consumers are willing to voluntarily shed their unnecessary loads. This paper investigates the impact of planned outage rate on the required incentive, to reach different levels of RES penetration. To illustrate the effectiveness of consumers’ contribution for integration of RESs and utility grids, their collaboration impact is explored against a numerical system constructed based on real-historical-data. The results demonstrate positive impact of consumers’ contribution by substantial reduction in the incentive. The saving margin, then, shall be used to evaluate the value of consumers’ volunteer load-shedding.

A New Quantitative Load Profile Measure for Demand Response Performance Evaluation

Ehsan Saeidpour Parizy, Ali Jahanbani Ardakani, Arash Mohammadi, and Kenneth A. Loparo
Journal Paper 31 Submitted to International Journal of Electrical Power and Energy Systems, 2019.

Abstract

This article proposes a quantitative measure of the load profile that can be used to compare demand response techniques for load shaping. This quantitative measure is a projection of the overall cost for electric power generation planning, and can be used to more effectively guide the determination of dynamic electric energy retail pricing tariffs that can improve the performance of demand response techniques from the overall generation expansion planning and utilization cost perspective. For several years, the peak to average ratio has been the popular choice to quantitatively measure the load profile, although it does not incorporate critical measures such as minimum power demand and load variation. In this paper, several load profiles are synthesized and the cost for their electricity supply is calculated. Then, the correlation coefficient between different statistical measures of the load profiles and the cost of optimal generation expansion planning and utilization is explored. Several statistical factors of the load profile that show a linear relationship with the overall cost are selected and their contribution level to the final measure is determined to form a quantitative load profile measure that accurately reflects the overall supply cost.

RQ-CEASE: A Resilient Quantized Collaborative Event-triggered Average-consensus Sampled-data Framework Under Denial of Service Attack

Amir Amini, Amir Asif, and Arash Mohammadi
Journal Paper 30 Accepted with Minor Revisions in IEEE Transactions on Systems, Man and Cybernetics: Systems, 2019.

Abstract

Referred to as the RQ-CEASE, the paper proposes a resilient framework for quantized, event-triggered, sampled-data, average consensus in multi-agent systems subject to denial of service (DoS) attacks. The DoS attacks typically attempt to block the measurement and communication channels in the network. Two different event-triggering (ET) approaches are considered in RQCEASE based on whether the ET threshold is dependent or independent of the state dynamics. For each approach, we analytically derive operating conditions (bounds) for the sampling period and ET design parameter guaranteeing the input-to-state (ISS) stability of the network under DoS attacks. In addition, upper bounds for duration and frequency of DoS attacks are derived within which the network remains operational. For each approach, the maximum possible error from the average consensus value is derived. The resilience of the two RQ-CEASE approaches to DoS attacks, as well as their steady-state consensus error, and transmission savings are compared both analytically and using simulations.

Event-triggered Performance Guaranteed Containment Control in Multi-agent Systems

Amir Amini, Arash Mohammadi, and Amir Asif
Journal Paper 29 Submitted to Journal of the Franklin Institute, 2019.

Abstract

In this paper, we propose a novel approach for event-triggered performance guaranteed containment control (EPiCC) in linear multi-agent systems. To extend longevity of the system and reduce the amount of data exchanges, a distributed event-triggered transmission condition is incorporated within the EPiCC implementation. A second objective of EPiCC is to co-design containment parameters, namely the control gain and transmission threshold, which collectively guarantee an exponential rate of containment. The control gain has a degree of resilience such that containment can be achieved even with some perturbation in its nominally designed value. Using the Lyapunov stability theorem, sufficient conditions for event-triggered exponential containment with resilient control gain are expressed in terms of a linear matrix inequality optimization. An objective function which incorporates the number of events and control effort is minimized to compute the design parameters. The containment design stage can be performed in a distributed fashion. The practicability of the event-triggered scheme is studied by proving the Zeno behaviour exclusion. Numerical simulations quantify the effectiveness of the proposed EPiCC algorithm for a multi-agent systems.

From Hand-Crafted to Deep Learning-based Cancer Radiomics: Challenges and Opportunities

Parnian Afshar, Arash Mohammadi, Konstantinos N. Plataniotis, Anastasia Oikonomou, and Habib Benali
Journal Paper 28 IEEE Signal Processing Magazine, vol. 36, no. 4, pp. 132-160, 2019.

Abstract

Recent advancements in signal processing (SP) and machine learning, coupled with electronic medical record keeping in hospitals and the availability of extensive sets of medical images through internal/external communication systems, have resulted in a recent surge of interest in radiomics. Radiomics, an emerging and relatively new research field, refers to extracting semiquantitative and/or quantitative features from medical images with the goal of developing predictive and/or prognostic models. In the near future, it is expected to be a critical component for integrating image-derived information used for personalized treatment. The conventional radiomics workflow is typically based on extracting predesigned features (also referred to as handcrafted or engineered features) from a segmented region of interest (ROI). Nevertheless, recent advancements in deep learning have inspired trends toward deep-learning-based radiomics (DLRs) (also referred to as discovery radiomics). In addition to the advantages of these two approaches, there are also hybrid solutions that exploit the potential of multiple data sources. Considering the variety of approaches to radiomics, further improvements require a comprehensive and integrated sketch, which is the goal of this article. This article provides a unique interdisciplinary perspective on radiomics by discussing state-of-the-art SP solutions in the context of radiomics.

HMFP-DBRNN: Real-time Hand Motion Filtering and Prediction via Deep Bidirectional RNN

Soroosh Shahtalebi, Farokh Atashzar, Rajni Patel, and Arash Mohammadi
Journal Paper 27 IEEE Robotics and Automation Letters, vol. 4, no. 2, pp. 1061-1068, April 2019.

Abstract

Pathological hand tremor (PHT) is among the most common movement symptoms of several neurological disorders including Parkinson's disease and essential tremor. Extracting PHT is of paramount importance in several engineering and clinical applications such as assistive and robotic rehabilitation technologies. In such systems, PHT is modeled as the input noise to the system and thus there is a surge of interest in estimation an compensation of the noise. Although various works in the literature have attempted to estimate and extract the PHT, in this letter, first, we argue that the ground truth signal used in existing works to optimize the performance of tremor extraction techniques is not accurate enough, and thus the performance measures for the prior techniques are not perfectly reliable. In addition, most of the existing tremor extraction techniques impose unrealistic assumptions, which are, typically, violated in practical settings. This letter proposes a novel technique that for the first time incorporates deep bidirectional recurrent neural networks as a processing tool for PHT extraction. Moreover, we devise an intuitively pleasing training strategy that enables the network to perform not only online estimation but also online prediction of the voluntary hand motion in a myopic fashion, which is currently a significantly important unmet need for rehabilitative and assistive robotic technologies designed for patients with pathological tremor.

A Multiple-Model and Hybrid~Deep Neural Network Model for Remaining Useful Life Estimation

Ali Al-Dulaimi, Soheil Zabihi, Amir Asif, and Arash Mohammadi
Journal Paper 26 Computers in Industry, vol. 108, pp. 186-196, 2019.

Abstract

Ageing critical infrastructures and valuable machineries together with recent catastrophic incidents such as the collapse of Morandi bridge calls for an urgent quest to design advanced and innovative data-driven solutions and efficiently incorporate multi-sensor streaming data sources for condition-based maintenance. Remaining Useful Life (RUL) is a crucial measure used in this regard within manufacturing and industrial systems, and its accurate estimation enables improved decision-making for operations and maintenance. Capitalizing on the recent success of multiple-model (also referred to as hybrid or mixture of experts) deep learning techniques, the paper proposes a hybrid deep neural network framework for RUL estimation, referred to as the Hybrid Deep Neural Network Model (HDNN). The proposed HDNN framework is the first hybrid deep neural network model designed for RUL estimation that integrates two deep learning models simultaneously and in a parallel fashion. More specifically, in contrary to the majority of existing data-driven prognostic approaches for RUL estimation, which are developed based on a single deep model and can hardly maintain good generalization performance across various prognostic scenarios, the proposed HDNN framework consists of two parallel paths (one LSTM and one CNN) followed by a fully connected multilayer fusion neural network which acts as the fusion centre combining the output of the two paths to form the target RUL. The HDNN uses the LSTM path to extract temporal features while simultaneously the CNN is utilized to extract spatial features. The proposed HDNN framework is tested on the NASA commercial modular aero-propulsion system simulation (C-MAPSS) dataset. Our comprehensive experiments and comparisons with several recently proposed RUL estimation methodologies developed based on the same data-sets show that the proposed HDNN framework significantly outperforms all its counterparts in the complicated prognostic scenarios with increased number of operating conditions and fault modes.

Lung Cancer Radiomics: Highlights from the IEEE Video and Image Processing Cup 2018 Student Competition

Arash Mohammadi, Parnian Afshar, Amir Asif, Keyvan Farahani, Justin Kirby, Anastasia Oikonomou, and Konstantinos N. Plataniotis
Journal Paper 25 IEEE Signal Processing Magazine, vol. 36, no. 1, pp. 164-173, Jan. 2019.

Abstract

The volume, variety, and velocity of medical imaging data are exploding, making it impractical for clinicians to properly utilize such available information resources in an efficient fashion. At the same time, the interpretation of such a large amount of medical imaging data by humans is significantly error prone, reducing the possibility of extracting informative data. The ability to process such large amounts of data promises to decipher encrypted information within medical images, develop predictive and prognosis models to design personalized diagnosis, allow comprehensive study of tumor phenotype, and allow the assessment of tissue heterogeneity for diagnosis of different types of cancers.

WAKE: Wavelet Decomposition Coupled with Adaptive Kalman Filtering for Pathological Tremor Extraction

Soroosh Shahtalebi, Farokh Atashzar, Rajni Patel, and Arash Mohammadi
Journal Paper 24 Biomedical Signal Processing and Control, vol. 48, pp. 179-188, Feb. 2019.

Abstract

Pathological Hand Tremor (PHT) is among common symptoms of several neurological movement disorders, which can significantly degrade quality of life of affected individuals. Beside pharmaceutical and surgical therapies, mechatronic technologies have been utilized to control PHTs. Most of these technologies function based on estimation, extraction, and characterization of tremor movement signals. Real-time extraction of tremor signal is of paramount importance because of its application in assistive and rehabilitative devices. In this paper, we propose a novel on-line adaptive method which can adjust the hyper-parameters of the filter to the variable characteristics of the tremor. The proposed technique (i.e., WAKE) is composed of a new adaptive Kalman filter and a wavelet transform core to provide indirect prediction of the tremor, one sample ahead of time, to be used for its suppression. In this paper, the design, implementation and evaluation of WAKE are given. The performance is evaluated on two different datasets. One dataset is recorded from patients with PHTs and the other one is a synthetic dataset, developed in this work, that simulates hand tremor under ten different conditions. The results demonstrate a significant improvement in the estimation accuracy in comparison with two well regarded techniques in literature.

Performance Constrained Distributed Event-triggered Consensus in Multi-agent Systems

Amir Amini, Amir Asif, and Arash Mohammadi
Journal Paper 23 Information Science, vol. 484, pp. 338-349, May 2019.

Abstract

The paper proposes a novel performance guaranteed sampled-data event-triggered consensus (PSEC) algorithm for linear multi-agent systems configured as directed networks. To reduce information exchanges and preserve communication resources, a sampled-data event detector is incorporated at each agent. Communication between agents is based on the fulfillment of distributed state-dependent event-triggering conditions. PSEC ensures a guaranteed exponential convergence rate and is resilient to norm-bounded uncertainties in control gains resulting from implementation distortions. The Lyapunov–Krasovskii theorem is used to incorporate the performance objectives. The design parameters, namely, the heterogeneous control gains and a transmission threshold, are simultaneously computed using a constrained convex optimization framework with linear matrix inequalities. Numerical simulations based on an experimental spacecraft formation flying multi-agent system quantify the effectiveness of the proposed PSEC approach.

Non-Circular Attacks on Phasor Measurement Units for State Estimation in Smart Grid

Arash Mohammadi and Konstantinos N. Plataniotis
Journal Paper 22 IEEE Journal of Selected Topics in Signal Processing, vol. 12, no. 4, pp. 777-789, Aug. 2018.

Abstract

With the evolution of phasor measurement units (PMUs) and the proposition to incorporate a large number of PMUs in future smart grids, it is critical to identify and prevent potential (zero-day) cyber attacks on phasor signals. The PMUs are the forefront of sensor technologies used in the smart grid and produce phasor voltage and current readings, which are complex-valued in nature. In this regard, the paper investigates potential attacks on complex-valued PMU signals and proposes the new paradigm of data-injection attacks, referred to as non-circular attacks. Existing state estimation algorithms and attack monitoring solutions assume that the PMU observations have statistical characteristics similar to that of real-valued signals. This assumption makes PMUs extremely defenseless against the proposed non-circular attacks. In this paper, we: (i) Introduce the non-circular attack model; (ii) Evaluate (both analytically and via experiments) the potential destructive nature of such attacks; (iii) Propose a Bhattacharyya distance (BD)- detector for monitoring the system against cyber attacks by transforming the detection problem to an equivalent problem of comparing innovation sequences in distribution via statistical distance measures, and; (iv) Propose a circularization approach, which enables the conventional detection algorithms to identify non-circular attacks.

Ternary Event-based State Estimation with Joint Point, Quantized, and Set-valued Measurements

Arash Mohammadi, Somayeh Davar, and Konstantinos N. Plataniotis
Journal Paper 21 IEEE Signal Processing Letter, vol. 25, no. 5, pp. 665-669, 2018.

Abstract

This letter proposes a novel ternary-event-based particle filtering (TEB-PF) framework by introducing the ternary-event-triggering mechanism coupled with a non-Gaussian fusion strategy that jointly incorporates point-valued, quantized, and set-valued measurements. In contrast to the existing binary-event-triggering solutions, the TEB-PF is a distributed state estimation architecture where the remote sensor communicates its measurements to the estimator, residing at the fusion centre, in a ternary-event-based fashion, i.e., holds on to its observation during idle epochs, transfers quantized ones during the transitional epochs, and only communicates raw observations during event epochs. Due to joint utilization of quantized and set-valued measurements in addition to the point-valued ones, the proposed TEB-PF simultaneously reduces the communication overhead, in comparison to its binary triggering counterparts, while also improving the estimation accuracy specially in low communication rates.

CEASE: A Collaborative Event-Triggered Average-Consensus Sampled-Data Framework With Performance Guarantees for Multi-Agent Systems

Amir Amini, Arash Mohammadi, and Amir Asif
Journal Paper 20 IEEE Transactions on Signal Processing, vol. 66, no. 23, pp. 6096-6109, 1 Dec.1, 2018.

Abstract

The paper proposes a distributed framework for Collaborative, Event-triggered, Average consensus, Sampled data (CEASE) algorithms for multiagent systems with two classes of performance guarantees. Referred to as the E-CEASE algorithm, the first approach ensures an exponential rate of convergence and derives associated conditions and optimal design parameters using the Lyapunov-Krasovskii stability theorem. The second approach provides a structured trade-off between the number of transmissions and rate of consensus convergence based on a guaranteed cost and is referred to as G-CEASE. The two implementations of CEASE are event-driven in the sense that agents transmit within their respective neighbourhoods only on the triggering of an event. To reduce communication and processing, the triggering condition in CEASE is monitored at discrete-time steps. Both E-CEASE and G-CEASE support switching topologies in multi-agent systems. Monte-Carlo simulations on randomized networks quantify the effectiveness of the proposed approaches.

Bayesian Optimized Spectral Filters Coupled with Ternary ECOC for Single Trial EEG Classification

Soroosh Shahtalebi, and Arash Mohammadi
Journal Paper 19 IEEE Transactions on Neural Systems & Rehabilitation Engineering, vol. 26, no. 12, pp. 2249-2259, Dec. 2018.

Abstract

Motivated by the promising emergence of Brain Computer Interfaces (BCIs) within assistive/rehabilitative systems for therapeutic applications, the paper proposes a novel Bayesian framework that simultaneously optimizes a number subject-specific filter banks and spatial filters. Referred to as the ECCSP framework, optimized double band spectra-spatial filters are derived based on Common Spatial Patterns (CSP) coupled with the error correcting output coding (ECOC) classifiers. The proposed ECCSP framework constructs optimized subject-specific spectral filters in an intuitive fashion resulting in creation of significantly discriminant features, which is a crucial requirement for any EEG-based BCI system. Through incorporation of the ECOC approach, the classification problem is then modeled as communication over a noisy channel where the misclassification error is corrected by error correction techniques borrowed from information theory. The paper also proposes a modified version of the ECOC adopted to EEG classification problems by deploying ternary class codewords to account for ambiguous EEG epochs (which is a common phenomenon due to the cocktail-party nature of brain signals). The proposed ECCSP framework and its variants are evaluated over two different datasets from the BCI Competition (i.e., BCIC-IV2a and BCIC-IV2b). The results indicate that the proposed approach significantly outperforms its state-of-the-art counterparts and introduces a robust framework for motor imagery studies.

Guest Editorial Distributed Signal Processing for Security and Privacy in Networked Cyber-Physical Systems.

Arash Mohammadi, P. Cheng, Vincenzo Piuri, Konstantinos N. Plataniotis, P. Campisi:
Journal Paper 18 IEEE Transactions on Signal and Information Processing over Networks, vol. 4, no. 1, pp. 1-3, 2018.

Abstract

The papers in this special section address distributed signal processing applications that support security and privacy in networked cyber-physical systems. Networked cyber-physical systems (CPSs) are engineering systems with integrated computational and communication capabilities that interact with humans through cyber space. The CPSs have recently emerged in several practical applications of significant engineering importance including aerospace, industrial/manufacturing process control, multimedia networks, transportation systems, power grids, and medical systems. The CPSs typically consist of both wireless and wired sensor/agent networks with different capacity/reliability levels where the emphasis is on real-time operations, and performing distributed, secure, and optimal sensing/processing is the key concern. To satisfy these requirements of the CPSs, it is of paramount importance to design innovative “Signal Processing” tools to provide unprecedented performance and resource utilization efficiency.

Event-Based Estimation With Information-Based Triggering and Adaptive Update

Arash Mohammadi and Konstantinos N. Plataniotis
Journal Paper 17 IEEE Transactions on Signal Processing, vol. 65, no. 18, pp. 4924-4939, Sept. 15, 2017

Abstract

This paper is motivated by recent advancements of cyber-physical systems and significance of managing limited communication resources in their applications. We propose an open-loop estimation strategy with an information-based triggering mechanism coupled with an adaptive event-based fusion framework. In the open-loop topology considered in this paper, a sensor transfers its measurements to a remote estimator only in occurrence of specific events (asynchronously). Each event is identified using a local stochastic triggering mechanism without incorporation of a feedback from the remote estimator and/or implementation of a local filter at the sensor level. We propose a particular stochastic triggering criterion based on the projection of local observation into the state-space, which in turn is a measure of the achievable gain in the local information state vector. Then, we investigate an unsupervised fusion model at the estimation side where the estimator blindly listens to its communication channel without having a priori information of the triggering mechanism of the sensor. An update mechanism with a Bayesian collapsing strategy is proposed to adaptively form state estimates at the estimator side in an unsupervised fashion. The estimator is adaptive in the sense that it is able to distinguish between having received an actual measurement or noise. The simulation results show that the proposed information-based triggering mechanism significantly outperforms its counterparts specifically in low communication rates, and confirms the effectiveness of the proposed unsupervised fusion methodology.

Distributed-Graph-Based Statistical Approach for Intrusion Detection in Cyber-Physical Systems

Hamidreza Sadreazami, Arash Mohammadi, Amir Asif, and Konstantinos N. Plataniotis
Journal Paper 16 IEEE Transactions on Signal and Information Processing over Networks, vol. 4, no. 1, pp. 137-147, 2018.

Abstract

Cyber-physical systems have recently emerged in several practical engineering applications where security and privacy are of paramount importance. This motivated the paper and a recent surge of interest in development of innovative and novel anomaly and intrusion detection technologies. This paper proposes a novel distributed blind intrusion detection framework by modeling sensor measurements as the target graph-signal and utilizing the statistical properties of the graph-signal for intrusion detection. To fully take into account the underlying network structure, the graph similarity matrix is constructed using both the data measured by the sensors and sensors' proximity resulting in a data-adaptive and structure-aware monitoring solution. In the proposed supervised detection framework, the magnitude of the captured data is modeled by Gaussian Markov random field and the corresponding precision matrix is estimated by learning a graph Laplacian matrix from sensor measurements adaptively. The proposed intrusion detection methodology is designed based on a modified Bayesian likelihood ratio test and the closed-form expressions are derived for the test statistic. Finally, temporal analysis of the network behavior is established by computing the Bhattacharyya distance between the measurement distributions at the consecutive time instants. Experiments are conducted to evaluate the performance of the proposed method and to compare it with that of the state-of-the-art methods. The results show that the proposed intrusion detection framework provides a detection performance superior to those provided by the other existing schemes.

Iterative Graph-Based Filtering for Image Abstraction and Stylization

Hamidreza Sadreazami, Amir Asif, and Arash Mohammadi
Journal Paper 15 IEEE Transactions on Circuits and Systems, vol. 65-II, no. 2, pp. 251-255, 2018.

Abstract

In this brief, motivated by the recent advances in graph signal processing, we address the problem of image abstraction and stylization. A novel unified graph-based multi-layer framework is proposed to perform iterative filtering without requiring any weight updates. The proposed graph-based filtering approach is shown to be superior to other existing methods due to iteratively using the filtered Laplacian in order to enhance the smoothened image signal at each layer. In order to render real images into painterly style ones and create a simple stylized format from color images, the low-contrast regions of an image are first smoothened using the proposed iterative graph filters in either vertex or spectral domains. The abstracted image is then quantized and sharpened using the proposed iterative highpass graph filter. The effectiveness of the graph-based image stylization method is verified through several experiments. It is shown that the proposed method can yield significantly improved visual quality for stylized images as compared to other existing methods.

Attack Detection/Isolation via a Secure Multi-Sensor Fusion Framework for Cyber-Physical Systems

Arash Mohammadi Chun Yang, and Qing-wei Chen
Journal Paper 14 Complexity, 2018.

Abstract

Motivated by rapid growth of cyberphysical systems (CPSs) and the necessity to provide secure state estimates against potential data injection attacks in their application domains, the paper proposes a secure and innovative attack detection and isolation fusion framework. The proposed multisensor fusion framework provides secure state estimates by using ideas from interactive multiple models (IMM) combined with a novel fuzzy-based attack detection/isolation mechanism. The IMM filter is used to adjust the system’s uncertainty adaptively via model probabilities by using a hybrid state model consisting of two behaviour modes, one corresponding to the ideal scenario and one associated with the attack behaviour mode. The state chi-square test is then incorporated through the proposed fuzzy-based fusion framework to detect and isolate potential data injection attacks. In other words, the validation probability of each sensor is calculated based on the value of the chi-square test. Finally, by incorporation of the validation probability of each sensor, the weights of its associated subsystem are computed. To be concrete, an integrated navigation system is simulated with three types of attacks ranging from a constant bias attack to a non-Gaussian stochastic attack to evaluate the proposed attack detection and isolation fusion framework.

Improper Complex-Valued Bhattacharyya Distance

Arash Mohammadi and Konstantinos N. Plataniotis
Journal Paper 13 IEEE Transactions on Neural Networks and Learning Systems, vol. 27, no. 5, pp. 1049-1064, 2016.

Abstract

Motivated by application of complex-valued signal processing techniques in statistical pattern recognition, classification, and Gaussian mixture (GM) modeling, this paper derives analytical expressions for computing the Bhattacharyya coefficient/distance (BC/BD) between two improper complex-valued Gaussian distributions. The BC/BD is one of the most widely used statistical measures for evaluating class separability in classification problems, feature extraction in pattern recognition, and for GM reduction (GMR) purposes. The BC provides an upper bound on the Bayes error, which is commonly known as the best criterion to evaluate feature sets. Although the computation of the BC/BD between real-valued signals is a well-known result, it has not yet been extended to the case of improper complex-valued Gaussian densities. This paper addresses this gap. We analyze the role of the pseudocovariance matrix, which characterizes the noncircularity of the signal, and show that it carries critical second-order statistical information for computing the BC/BD. We derive upper and lower bounds on the BD in terms of the eigenvalues of the covariance and pseudocovariance matrices of the underlying densities. The theoretical bounds are then used to introduce the concept of β -dominance in the context of statistical distance measures. The BC is pseudometric, since it fails to satisfy the triangle inequality. Using the Matusita distance (a full-metric variant of the BC), we propose an intuitively pleasing indirect distance measure for comparing two general GMs. Finally, we investigate the application of the proposed BC/BD measures for GMR purposes and develop two BC-based GMR algorithms.

Multi-Sensor Fusion with Interaction Multiple Model and Chi-Square Test Tolerant Filter

Chun Yang, Arash Mohammadi, Qingwei Chen,
Journal Paper 12 Sensors, vol. 16, no. 11, 2016.

Abstract

Motivated by the key importance of multi-sensor information fusion algorithms in the state-of-the-art integrated navigation systems due to recent advancements in sensor technologies, telecommunication, and navigation systems, the paper proposes an improved and innovative fault-tolerant fusion framework. An integrated navigation system is considered consisting of four sensory sub-systems, i.e., Strap-down Inertial Navigation System (SINS), Global Navigation System (GPS), the Bei-Dou2 (BD2) and Celestial Navigation System (CNS) navigation sensors. In such multi-sensor applications, on the one hand, the design of an efficient fusion methodology is extremely constrained specially when no information regarding the system’s error characteristics is available. On the other hand, the development of an accurate fault detection and integrity monitoring solution is both challenging and critical. The paper addresses the sensitivity issues of conventional fault detection solutions and the unavailability of a precisely known system model by jointly designing fault detection and information fusion algorithms. In particular, by using ideas from Interacting Multiple Model (IMM) filters, the uncertainty of the system will be adjusted adaptively by model probabilities and using the proposed fuzzy-based fusion framework. The paper also addresses the problem of using corrupted measurements for fault detection purposes by designing a two state propagator chi-square test jointly with the fusion algorithm. Two IMM predictors, running in parallel, are used and alternatively reactivated based on the received information form the fusion filter to increase the reliability and accuracy of the proposed detection solution. With the combination of the IMM and the proposed fusion method, we increase the failure sensitivity of the detection system and, thereby, significantly increase the overall reliability and accuracy of the integrated navigation system. Simulation results indicate that the proposed fault tolerant fusion framework provides superior performance over its traditional counterparts.

Distributed Widely Linear Multiple-Model Adaptive Estimation

Arash Mohammadi and Konstantinos N. Plataniotis
Journal Paper 11 IEEE Transactions on Signal and Information Processing over Networks, vol. 1, no. 3, pp. 164-179, 2015.

Abstract

The paper considers the problem of estimating the state of a complex-valued stochastic hybrid system observed distributively using an agent/sensor network (AN/SN) with complex-valued (possibly noncircular) observations. In several distributed estimation problems, a suitable model to describe the underlying system is unknown a priori, i.e., distributed state estimation with structural uncertainty. Motivated by application of widely linear processing techniques in such problems, the paper proposes a class of distributed multiple-model adaptive estimation algorithms, referred to as the CD/MMAE. By incorporating the particular structure of the complex-valued observations on the second moment, first we develop two hierarchical CD/MMAE implementations and then use them as the building blocks and develop a diffusion-based hybrid estimator for decentralized estimation without incorporation of a fusion centre. The paper derives a new form of the adaptation law and a new form of information fusion, which takes advantage of the full second-order statistical properties of the underlying observations. Convergence properties of the proposed diffusion-based CD/MMAE are then investigated. We show that the adaptive weight of all local nodes converges to the true mode with probability one. Simulation results indicate that the proposed hybrid estimators provide improved performance and convergence properties over their traditional counterparts.

Structure-Induced Complex Kalman Filter for Decentralized Sequential Bayesian Estimation

Arash Mohammadi and Konstantinos N. Plataniotis
Journal Paper 10 IEEE Signal Processing Letters, vol. 22, no. 9, pp. 1419-1423, 2015.

Abstract

The letter considers a multi-sensor state estimation problem configured in a decentralized architecture where local complex statistics are communicated to the central processing unit for fusion instead of the raw observations. Naive adaptation of the augmented complex statistics to develop a decentralized state estimation algorithm results in increased local computations, and introduces extensive communication overhead, making it practically unattractive. The letter proposes a structure-induced complex Kalman filter framework with reduced communication overhead. In order to further reduce the local computations, the letter proposes a non-circularity criterion which allows each node to examine the non-circularity of its local observations. A local sensor node disregards its extra second-order statistical information when the non-circularity coefficient is small. In cases where the local observations are highly non-circular, an intuitively pleasing circularization approach is proposed to avoid computation and communication of the pseudo-covariance matrices. Simulation results indicate that the proposed structured-induced complex Kalman filter (SCKF) provides significant performance improvements over its traditional counterparts.

Improper Complex-Valued Multiple-Model Adaptive Estimation

Arash Mohammadi and Konstantinos N. Plataniotis
Journal Paper 9 IEEE Transactions on Signal Processing, vol. 63, no. 6, pp. 1528-1542, 2015.

Abstract

Motivated by the problem of estimating the discrete and continuous states of an improper complex-valued stochastic hybrid system, the paper proposes a class of widely linear (augmented) multiple model adaptive estimation algorithms, referred to as the C/MMAE. We show that for an improper complex-valued signal, pseudo-covariance of the innovation sequence is not zero and, therefore, carries useful statistical information regarding the unknown behaviour mode of the hybrid system. A new Bayesian law is, therefore, derived as a function of the pseudo-covariance of the innovation sequence and used to compute the probability that a hypothesized model is in effect at a certain time. We show that the C/MMAE, which uses the new Bayesian law and utilizes the complete second-order statistical characterization of the complex-valued innovation sequence, convergencies faster than its counterpart, which only uses the conventional covariance of the innovation sequence. In order to simplify the computational complexity, we develop two circularized versions of the C/MMAE using a preprocessing step, referred to as the circularizing filter (CF). The CF is incorporated to convert the improper observations/innovations into the proper ones in order to reduce the computational complexity of the hypothesis testing step. Finally, an interacting version of the C/MMAE, referred to as C/IMM, is developed for improper complex-valued systems with Markovian switching coefficients. Simulation results indicate that the proposed hybrid estimators provide improved performance and convergence properties over their traditional counterparts.

Complex-Valued Gaussian Sum Filter for Nonlinear Filtering of Non-Gaussian/Non-Circular Noise

Arash Mohammadi and Konstantinos N. Plataniotis
Journal Paper 8 IEEE Signal Processing Letters, vol. 22, no. 4, pp. 440-444, 2015.

Abstract

Distributed Consensus + Innovation Particle Filtering for Bearing/Range Tracking with Communication Constraints

Arash Mohammadi and Amir Asif
Journal Paper 7 IEEE Transactions on Signal Processing, vol. 63, no. 3, pp. 620-635, 2015.

Abstract

Consensus-based Distributed Dynamic Sensor Selection in Decentralised Sensor Networks Using the Posterior Cramer-Rao Lower Bound

Arash Mohammadi and Amir Asif
Journal Paper 6 Signal Processing, vol. 108, pp. 558-575, 2015.

Abstract

Full and Reduced-order Distributed Bayesian Estimation: Analytical Performance Bounds

Arash Mohammadi and Amir Asif
Journal Paper 5 IEEE Transaction on Aerospace and Electronic Systems, vol. 50, issue 4, pp. 2468-2488, 2014.

Abstract

A Distributed Particle Filtering Approach for Multiple Acoustic Source Tracking Using an Acoustic Vector Sensor Network

Xionghu Zhong, Arash Mohammadi, A. B. Premkumar, and Amir Asif
Journal Paper 4 Signal Processing, 108, pp. 589-603, 2015.

Abstract

Distributed Particle Filter Implementation with Intermittent/Irregular Consensus Convergence

Arash Mohammadi, and Amir Asif
Journal Paper 3 IEEE Transactions on Signal Processing, vol. 61, no. 10, pp. 2572-2587, May 15, 2013.

Abstract

Decentralized Conditional Posterior Cramer-Rao Lower Bound for Nonlinear Distributed Estimation

Arash Mohammadi, and Amir Asif
Journal Paper 2 IEEE Signal Processing Letters, vol. 20, no. 2, pp. 165-168, Feb. 2013.

Abstract

Reconstruction of Missing Features by Means of Multivariate Laplace Distribution (MLD) for Noise Robust Speech Recognition

Arash Mohammadi, and Farshad Almasganj
Journal Paper 1 Expert Systems with Applications, vol. 38, no. 4, pp. 3918-3930, 2011.

Abstract

Secure State Estimation in Industrial Control Systems

Arash Mohammadi and Konstantinos N. Plataniotis
Book Chapter 2 CRC Press | March 18, 2016 | ISBN: 9781498734738
image

Cyber Security for Industrial Control Systems: from the Viewpoint of Close-Loop

Motivated by recent evolution of cutting-edge sensor technologies with complex-valued measurements, this chapter analyzes attack models and diagnostic solutions for monitoring industrial control systems against complex-valued cyber attacks. By capitalizing on the knowledge that the existing detection and closed loop estimation algorithms ignore the full second-order statistical properties of the received measurements, we show that an adversary can attack the system by maximizing the correlations between the real and imaginary parts of the reported measurements. Consequently, the adversary can pass the conventional attack detection methodologies and change the underlying system beyond repair.

In ths chapter, the first section surveys recent developments in secure closed-loop state estimation methodologies, and then reviews the fundamentals of complex-valued signals and their applications. Second section highlights the drawbacks of~the state-of-the-art estimation methodologies and illustrates their vulnerability to cyber attacks. In the third section, first we review the existing attack models and then introduce the non-circular attack model. The forth section first surveys the state-of-the-art attack detection diagnostics and shows how to transform cyber-attack detection problem into the problem of comparing statistical distance measures between probability distributions. Fifth section provides illustrative examples followed by future research directions and conclusions.

Consensus-based Particle Filter Implementations for Distributed Non-linear Systems

Arash Mohammadi, Amir Asif
Book Chapter 1 Nova Science Publishers | November, 2012 | ISBN: 978-1-61942-898-0
image

Nonlinear Estimation and Applications to Industrial Systems Control

The chapter proposes three consensus-based, distributed implementations of the particle filter for non-linear state estimation problems with non-Gaussian excitation. Our approaches range from a simple but still intuitive approach, referred to as the global likelihood constrained implementation of the particle filter (GLC/DPF), included to illustrate the underlying concepts to near-optimal distributed approaches. The unscented, consensusbased, distributed implementation of the particle filter (UCD/DPF) is the second approach that couples the unscented Kalman filter (UKF) with the particle filter such that the UKF estimates the Gaussian approximation of the proposal distribution, which is then used as the proposal distribution in the particle filter. The UCD/DPF requires each node to wait until consensus is reached before running the next iteration of the particle filter and is suitable for networks where communication is relatively inexpensive as compared to sensing. The third approach is the global channel filter based distributed particle filter (GCF/DPF), which does not require the consensus algorithms to converge between two consecutive observations. These approaches are successfully tested by running simulations of bearings-only tracking (BOT) applications of moving targets arising in radar surveillance, underwater submarine tracking, and robotics.

Adaptive Subject-Specific Bayesian Spectral Filtering for Single Trial EEG Classification

Mahsa Mirgholami, SorooshShahtalebi, Raika Karimi, Amir Asif and Arash Mohammadi
Conference Papers 76Submitted to IEEE Global Signal Processing Conference (GlobalSip), 2019.

Abstract

Study on Novel Designs with Reduced Fatigue for Steady State Motion Visual Evoked Potentials

Raika Karimi, Laura Rosero, Mahsa Mirgholami, Amir Asif and Arash Mohammadi
Conference Papers 75Submitted to IEEE Global Signal Processing Conference (GlobalSip), 2019.

Abstract

sEMG-Based Hand Gesture Recognition via Dilated Convolutional Neural Networks

Elahe Rahimian, Soheil Zabihi, S.F. Atashzar, Amir Asif and Arash Mohammadi
Conference Papers 74Submitted to IEEE Global Signal Processing Conference (GlobalSip), 2019.

Abstract

Training of Deep Bidirectional RNNs for Hand Motion Filtering via Multimodal Data Fusion

Soroosh Shahtalebi, S.F. Atashzar, R.V. Patel, and Arash Mohammadi
Conference Papers 73Submitted to IEEE Global Signal Processing Conference (GlobalSip), 2019.

Abstract

NBLSTM: A Noisy Parallel Hybrid Model of CNN and BLSTM for Remaining Useful Life Estimation

Ali Al-Dulaimi, Soheil Zabihi, Amir Asif, and Arash Mohammadi
Conference Papers 72Submitted to IEEE Global Signal Processing Conference (GlobalSip), 2019.

Abstract

Gaussian Mixture-Based Indoor Localization via Bluetooth Low Energy Sensors

Parvin Malekzadeh, Mohammad Salimibeni, MohammadAmin Atashi, M. Barbulescu, K.N. Plataniotis and Arash Mohammadi
Conference Papers 71 Submitted to IEEE Sensors Conference, 2019.

Abstract

Event-Triggered Monitoring/Communication of Inertial Measurement Unit for IoT Applications

Mohammad Salimibeni, Parvin Malekzadeh, MohammadAmin Atashi, M. Barbulescu, K.N. Plataniotis and Arash Mohammadi
Conference Papers 70 Submitted to IEEE Sensors Conference, 2019.

Abstract

Orientation Detection and Multiple Modeling of RSSI Values via BLE Sensors for Indoor Localiztion within IoT Applications

MohammadAmin Atashi, Parvin Malekzadeh, Mohammad Salimibeni, M. Barbulescu, K.N. Plataniotis and Arash Mohammadi
Conference Papers 69 Submitted to IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2019.

Abstract

Parallel Deep Network Arcitecture for sEMG-Based Hand Gesture Recognition

Elahe Rahimian, Soheil Zabihi, Amir Asif, and Arash Mohammadi
Conference Papers 68 Submitted to IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2019.

Abstract

Explainable Capsule Networks for Cancer Radiomics

Parnian Afshar, K.N. Plataniotis, and Arash Mohammadi
Conference Papers 67ACCEPTED in 2019 IEEE International Conference on Image Processing(ICIP), 2019.

Abstract

Level-based Single Trial EEG Classification based on Wavelet Decomposition of Signals

Soroosh Shahtalebi and Arash Mohammadi
Conference Papers 66IEEE International Engineering in Medicine and Biology Conference (EMBC), 2019.

Abstract

Multiple Model BLE-based Tracking via Validation of RSSI Fluctuations Under Different Conditions

MohammadAmin Atashi, Mohammad Salimibeni, Parvin Malekzadeh, M. Barbulescu, K.N. Plataniotis and Arash Mohammadi
Conference Papers 65 IEEE International Conference on Information Fusion, 2019.

Abstract

Resilient Event-triggered Average Consensus Under Denial of Service Attack and Uncertain Network

Amir Amini, A. Azarbahram, Amir Asif, and Arash Mohammadi
Conference Papers 64 IEEE International Conference on Control, Decision and Information Technologies (CoDIT), 2019.

Abstract

Capsule Networks for Brain Tumor Classification based on MRI Images and Course Tumor Boundaries

Parnian Afshar, K.N. Plataniotis, and Arash Mohammadi
Conference Papers 63 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019.

Abstract

Belief Condensation Filtering for RSSI-based State Estimation in Indoor Localization

Shervin Mehryar, Parvin Malekzadeh, S. Mazuelas, P. Spachos, K. N. Plataniotis, and Arash Mohammadi
Conference Papers 62IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019.

Abstract

Quantized Event-Triggered Sampled-Data Average Consensus with Guaranteed Rate of Convergence

Amir Amini, Amir Asif, and Arash Mohammadi
Conference Papers 61 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019.

Abstract

Hybrid Deep Neural Network Framework for Estimating Remaining Useful Life in Prognostic Health Management Industrial Applications

Ali Al-Dulaimi, Soheil Zabihi, Amir Asif, and Arash Mohammadi
Conference Papers 60 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019.

Abstract

Performance Constrained Distributed Event-triggered Consensus in Multi-agent Systems

Amir Amini, Amir Asif, and Arash Mohammadi
Conference Papers 59IEEE American Control Conference (ACC), 2019.

Abstract

Improving the Performance of Motor Imagery EEG-based BCIs via an Adaptive Epoch Trimming Mechanism

Golnar Kalantar, Mahsa Mirgholami, Amir Asif, and Arash Mohammadi
Conference Papers 58 IEEE Global Signal Processing Conference (GlobalSip), 2018.

Abstract

Designing Optimal Thresholds for Ternary Event-based State Estimation via Multi Objective Particle Swarm Optimizer

Somayeh Davar and Arash Mohammadi
Conference Papers 57 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS), 2018.

Abstract

Brain Tumor Classification via Capsule Nets

Parnian Afshar, Arash Mohammadi, and K.N. Plataniotis
Conference Papers 56 IEEE International Conference on Image Processing (ICIP), pp. 3129-3133, 2018.

Abstract

Improved Explainability of Capsule Networks: Relevance Path by Agreement

Atefeh Shahroudnejad, Parnian Afshar, Arash Mohammadi, and K.N. Plataniotis
Conference Papers 55 IEEE Global Signal Processing Conference (GlobalSip), 2018.

Abstract

CARISI: Convolutional Autoencoder-based Inter-Slice Interpolation of Brain Tumor Images

Parnian Afshar, Atefeh Shahroudnejad, Arash Mohammadi, and K.N. Plataniotis
Conference Papers 54 IEEE International Conference on Image Processing (ICIP), pp. 1458-1462, 2018.

Abstract

Analyzing the Effect of Bluetooth Low Energy (BLE) with Randomized MAC Addresses in IoT Applications

Golnar Kalantar, Arash Mohammadi, and Nima Sadrieh
Conference Papers 53 IEEE International Conference on Internet of Things (iThings), 2018.

Abstract

Graph-based Model of EEG Signals via Functional Clustering and Total Variation Measure for Brain Computer Interfacing

Golnar Kalantar, and Arash Mohammadi
Conference Papers 52 IEEE International Engineering in Medicine and Biology Conference (EMBC), pp. 4603-4606, 2018.

Abstract

Interactive Multiple Model Particle Filters for Generalized Degradation Path Modeling

Ali Al-Dulaimi, Arash Mohammadi, and Amir Asif
Conference Papers 51 Institute of Industrial & Systems Engineers (IISE) Annual Conference \& Expo, 2018.

Abstract

Autonomous and self-aware systems, Autonomous Vehicles, Event-triggered estimation, Particle filtering

Somayeh Davar, Arash Mohammadi, and K.N. Plataniotis
Conference Papers 50 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6578-6582, 2018.

Abstract

Resilient Event-Triggered Consensus with Exponential Convergence in Multi-agent Systems

Amir Amini, Amir Asif, and Arash Mohammadi
Conference Papers 49 IEEE American Control Conference (ACC), pp. 2889-2896, 2018.

Abstract

A Bayesian Framework to Optimize Double Band Spectra Spatial Filters for Motor Imagery Classification

Soroosh Shahtalebi and Arash Mohammadi
Conference Papers 48 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 871-875, 2018.

Abstract

Multiple-Model and Reduced-Order Kalman Filtering for Pathological Hand Tremor Extraction

Vahid Khorasani, Arash Mohammadi, S.F. Atashzar, R. Patel
Conference Papers 47 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 940-944, 2018.

Abstract

WAKE-BPAT: Wavelet-based Adaptive Kalman Filtering for Blood Pressure Estimation via Fusion of Pulse Arrival Times

Golnar Kalantar, S.K. Mukhopadhyay, F. Marefat, P. Mohseni, and Arash Mohammadi
Conference Papers 46 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 945-949, 2018.

Abstract

An Event-triggered Average Consensus Algorithm with Performance Guarantees for Distributed Sensor Networks

Amir Amini, Amir Asif, and Arash Mohammadi
Conference Papers 45 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3409-3413, 2018.

Abstract

A Robust Event-Triggered Consensus Strategy for Linear Multi-agent Systems with Uncertain Network Topology

Amir Amini, Amir Asif, and Arash Mohammadi
Conference Papers 44 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3659-3663, 2018.

Abstract

Real-Time and Event-Triggered Object Detection, Recognition, and Tracking

D. Blizzard, Somayeh Davar, and Arash Mohammadi
Conference Papers 43 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS), 2017.

Abstract

Progressive Fusion of Multi-rate Motor Imagery Classification for Brain Computer Interfaces

T. Maloney, Golnar Kalantar, and Arash Mohammadi
Conference Papers 42 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS), 2017.

Abstract

A Late Adaptive Graph-Based Edge-Aware Filtering with Iterative Weight Updating Process

H. Sadreazami, Amir Asif, and Arash Mohammadi
Conference Papers 41 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS), 2017.

Abstract

Interactive Gaussian-Sum Filtering for Estimating Systematic Risk in Financial Econometrics

Arash Mohammadi, X.P. Zhang, and K.N. Plataniotis
Conference Papers 40 IEEE Global Signal Processing Conference (GlobalSip), 2017.

Abstract

Adaptive Dimentionality Reduction Method using Graph-based Spectral Decomposition for Motor Imagery-based Brain-Computer Interfaces

Golnar Kalantar, H. Sadreazami, Arash Mohammadi, and Amir. Asif
Conference Papers 39 IEEE Global Signal Processing Conference (GlobalSip), 2017.

Abstract

A Guaranteed Cons LMI-based Approach for Event-Triggered Average Consensus in Multi-Agent Networks

Amir Amini, Amir Asif, and Arash Mohammadi
Conference Papers 38 IEEE Global Signal Processing Conference (GlobalSip), 2017.

Abstract

Dynamic Estimation Strategy for E-BMFLC Filters in Analyzing Pathological Hand Tremors

Vahid Khorasani, Arash Mohammadi, S.F. Atashzar, R. Patel
Conference Papers 37 IEEE Global Signal Processing Conference (GlobalSip), 2017.

Abstract

A Multi-rate and Auto-Adjustable Wavelet Decomposition Framework for Pathological Hand Tremor Extraction

Soroosh Shahtalebi, Arash Mohammadi, S.F. Atashzar, and R. Patel
Conference Papers 36 IEEE Global Signal Processing Conference (GlobalSip), 2017.

Abstract

Ternary ECOC Classifiers Coupled with Optimized Saptio-Spectral Patterns for Multiclass Motor Imagery Classification

Soroosh Shahtalebi and Arash Mohammadi
Conference Papers 35 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2017.

Abstract

Error Correction Output Codding Coupled with the CSP for Motor Imagery BCI

Soroosh Shahtalebi and Arash Mohammadi
Conference Papers 34 European Signal Processing Conference (EUSIPCO), 2017.

Abstract

Event-based Particle Filtering with Point and Set-valued Measurements

Somayeh Davar and Arash Mohammadi
Conference Papers 33 European Signal Processing Conference (EUSIPCO), 2017.

Abstract

Multi-Sensor and Information-Based Event Triggered Distributed Estimation

Somayeh Davar and Arash Mohammadi
Conference Papers 32 International Conference on Distributed Computing in Sensor Systems (DCOSS), 2017.

Abstract

Event-based Consensus for a class of heterogeneous multi-agent systems: An LMI approach

Amir Amini, Arash Mohammadi, and A. Asif
Conference Papers 31 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017.

Abstract

Generalized Degradation Model for Health Management of Mission Critical Systems

Ali Al-Dulaimi, Arash Mohammadi, and A. Asif
Conference Papers 30 Institute of Industrial & Systems Engineers (IISE) Annual Conference & Expo, 2017.

Abstract

Data-Adaptive Color Image Denoising and Enhancement Using Graph-Based Filtering

H. Sadreazami, A. Asif, and Arash Mohammadi
Conference Papers 29 IEEE International Symposium on Circuits & Systems (ISCAS), 2017.

Abstract

Data-driven Image Stylization Using Graph-based Filtering

H. Sadreazami, A. Asif, and Arash Mohammadi
Conference Papers 28 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), 2017.

Abstract

Diffusive Particle Filtering for Distributed Multisensor Estimation

Arash Mohammadi, and Amir Asif
Conference Papers 27 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2016.

Abstract

Widely-Linear Gaussian Sum Filter

Arash Mohammadi, and K.N. Plataniotis
Conference Papers 26 IEEE Sensor Array & Multichannel Signal Processing Workshop (SAM), Special Session on Non-Circular Signals & Widely Linear Processing, 2016.

Abstract

Secure Estimation Against Complex-valued Attacks

Arash Mohammadi, A. Margoosian, and K.N. Plataniotis
Conference Papers 25 IEEE Statistical Signal Processing (SSP), 2016.

Abstract

Distributed Particle Filter Implementations with Minimal Consensus Runs

Arash Mohammadi, and Amir Asif
Conference Papers 24 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 4-9, Florence, Italy, 2014.

Abstract

Reduced Order Distributed Particle Filter for Electric Power Grids

Amir Asif, Arash Mohammadi and S. Saxena
Conference Papers 23 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 4-9, Florence, Italy, 2014.

Abstract

A Distributed Particle Filter for Acoustic Source Tracking Using an Acoustic Vector Sensor Network

Xionghu Zhong, Arash Mohammadi, A. B. Premkumar, and Amir Asif
Conference Papers 22 IEEE International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP), 2014.

Abstract

Full Order Nonlinear Distributed Estimation in Intermittently Connected Networks

Arash Mohammadi and Amir Asif
Conference Papers 21 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 6327-6331, May 26-31, Vancouver, Canada, 2013.

Abstract

Decentralized Computation of the Conditional Posterior Cramer-Rao Lower Bound: Application to Adaptive Sensor Selection

Arash Mohammadi, and Amir Asif
Conference Papers 20 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 5278-5282, May 26-31, Vancouver, Canada, 2013.

Abstract

Acoustic Source Tracking in a Reverberant Environment Using a Pairwise Synchronous Microphone Network

Xionghu Zhong, Arash Mohammadi, W. Wan, A. B. Premkumar, and Amir Asif
Conference Papers 19IEEE International Conference on Information Fusion (FUSION), Istanbul, Turkey, 2013.

Abstract

Decentralized Bayesian Estimation with Quantized Observations: Theoretical Performance Bounds

Arash Mohammadi, Amir Asif, Xionghu Zhong, and A. B. Premkumar
Conference Papers 18 IEEE International Conference on Distributed Computing in Sensor Systems (DCOSS), Cambridge, MA, pp. 149-156, 2013.

Abstract

Decentralized Sensor Selection based on the Distributed Posterior Cramer-Rao Lower Bound

Arash Mohammadi and Amir Asif
Conference Papers 17 IEEE International Conference on Information Fusion (FUSION), Singapore, pp. 1668-1675, 2012.

Abstract

Theoretical Performance Bounds for Reduced-order Linear and Nonlinear Distributed Estimation

Arash Mohammadi and Amir Asif
Conference Papers 16 IEEE Global Telecommunications Conference (GLOBECOM), Anaheim, CA, pp. 3929–3935, 2012.

Abstract

A Constraint Sufficient Statistics based Distributed Particle Filter for Bearing Only Tracking

Arash Mohammadi and Amir Asif
Conference Papers 15 IEEE International Communications Conference (ICC), Ottawa, Canada, pp. 3670-3675, June 12-15, 2012.

Abstract

Distributed State Estimation for Large-scale Nonlinear Systems: A Reduced Order Particle Filter Implementation

Arash Mohammadi and Amir Asif
Conference Papers 14 IEEE Statistical Signal Processing (SSP), Arbor, MI, pp. 249-252, 2012.

Abstract

Full Order Distributed Particle Filters for Intermittent Connections: Feedback From Fusion Filters to Local Filters Improves Performanc

Arash Mohammadi and Amir Asif
Conference Papers 13 IEEE Statistical Signal Processing (SSP), Arbor, MI, pp. 524-527, 2012.

Abstract

Distributed Posterior Cramer-Rao Lower Bound for Nonlinear Sequential Bayesian Estimation

Arash Mohammadi and Amir Asif
Conference Papers 12IEEE Sensor Array and Multichannel Signal Processing (SAM), pp. 509-512, 2012.

Abstract

A Consensus/Fusion based Distributed Implementation of the Particle Filter

Arash Mohammadi and Amir Asif
Conference Papers 11 IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, San Juan, Puerto Rico, pp. 285-288, Dec. 2011.

Abstract

Consensus-Based Distributed Unscented Particle Filter

Arash Mohammadi and Amir Asif
Conference Papers 10 IEEE Statistical Signal Processing (SSP), Nice, France, pp. 237-240, 2011.

Abstract

Distributed Particle Filtering for Large Scale Dynamical Systems

Arash Mohammadi and Amir Asif
Conference Papers 9 IEEE International Multi-topic Conference (INMIC), vol. 1, pp. 1-5, Dec. 2009.

Abstract

Missing Feature Reconstruction with Multivariate Laplace Distribution (MLD) for Noise Robust Phoneme Recognition

Arash Mohammadi, Farshad Almasganj, A. Taherkhani, and F. Naderkhani
Conference Papers 8 IEEE International Symposium on Communications, Control, and Signal Processing (ISCCSP), pp pp 836-840, March 12-14, 2008.

Abstract

Incomplete Spectrogram Reconstruction with Kalman Filter for Noise Robust Speech Recognition

Arash Mohammadi Farshad Almasganj, S.N. Sadrieh, and A. Zandi
Conference Papers 7 IEEE International Symposium on Communications, Control, and Signal Processing (ISCCSP), pp 814-818, March 12-14, 2008.

Abstract

Using Phoneme Segmentation in Conjunction with Missing Feature Approaches for Noise Robust Speech Recognition

Arash Mohammadi, Farshad Almasganj, A. Taherkhani, and F. Naderkhani
Conference Papers 6 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), pp 297-301, December 15-18, 2007.

Abstract

Investigation of Probability Distribution of Speech Signals in Mel Filter Bank Domain

Arash Mohammadi and Farshad Almasganj
Conference Papers 5 Proceeding of (IKT), 2007.

Abstract

Design of Chaotic Neural Network for Robust Phoneme Recognition

A. Taherkhani, S. A. Seyyedsalehi, Arash Mohammadi, and H. Davande
Conference Papers IEEE World Congress on Computational Intelligence (IWCCI), pp 3500-3504, June 1-6, 2008.

Abstract

Design of a Chaotic Neural Network by Using Chaotic Nodes and NDRAM Network

A. Taherkhani, S. A. Seyyedsalehi, Arash Mohammadi and M.H. Moradi
Conference Papers 3 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), pp 1171-1175, December 15-18, 2007.

Abstract

A New Method for Summation of short time CAF's Based on RLCS Motion

S. N. Sadrieh1, R. Saadat and Arash Mohammadi
Conference Papers 2 IEEE ICEE, 2008.

Abstract

Design of Chaotic Neural Network for Robust Phoneme Recognition

A. Taherkhani, S. A. Seyyedsalehi and Arash Mohammadi
Conference Papers 1 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), 2008.

Abstract

Contact & Meet Me

I would be happy to talk to you if you need my assistance in your research or would like to collaborate on potential research projects. Please feel free to contact me using the contact information on the right. I would also be happy to meet you in person at my office, please drop me an e-mail to arrange a meeting time. My office information is as follows:

1515 Rue Ste-Catherine, Montreal, QC, Canada, H3G-2W1.

My office is located in EV009.187

  •    office: (514) 848-2424 ext. 2712
  •    arashmoh "at" encs.concordia.ca
  •    arash.mohammadi "at" concordia.ca
  •    ca.linkedin.com/in/arash