Electrical and Computer Engineering Commons^™

Robust And Trustworthy Deep Learning: Attacks, Defenses And Designs, Bingyin Zhao

All Dissertations

Deep neural networks (DNNs) have achieved unprecedented success in many fields. However, robustness and trustworthiness have become emerging concerns since DNNs are vulnerable to various attacks and susceptible to data distributional shifts. Attacks such as data poisoning and out-of-distribution scenarios such as natural corruption significantly undermine the performance and robustness of DNNs in model training and inference and impose uncertainty and insecurity on the deployment in real-world applications. Thus, it is crucial to investigate threats and challenges against deep neural networks, develop corresponding countermeasures, and dig into design tactics to secure their safety and reliability. The works investigated in this …

Generalized Conditional Feedback System With Model Uncertainty, Chengbo Dai, Zhiqiang Gao, Yangquan Chen, Donghai Li

Electrical and Computer Engineering Faculty Publications

Model uncertainty creates a largely open challenge for industrial process control, which causes a trade-off between robustness and performance optimality. In such a case, we propose a generalized conditional feedback (GCF) system to largely eliminate conflicts between robustness and performance optimality. This approach leverages a nominal model to design an optimal control in the virtual domain and defines an ancillary feedback controller to drive the physical process to track the trajectory of the virtual domain. The effectiveness of the proposed GCF scheme is demonstrated in a simulation for six typical industrial processes and three model-based control methods, and in a …

A Novel Physics-Assisted Genetic Algorithm For Decoupling Capacitor Optimization, Li Jiang, Ling Zhang, Shurun Tan, Da Li, Chulsoon Hwang, Jun Fan, Er Ping Li

Electrical and Computer Engineering Faculty Research & Creative Works

This article proposes a new physics-assisted genetic algorithm (PAGA) for decoupling capacitor (decap) optimization in power distribution networks (PDNs), which is a highly efficient approach to minimizing the number of decaps within an enormous search space. In the proposed PAGA method, the priority of the decap ports is first determined based on their physical loop inductances. Then, an initial solution is quickly obtained by placing decaps sequentially on the port with the highest priority. Subsequently, a GA with prior physical knowledge is developed to find better decap solutions progressively. A port removal scheme that eliminates the low-priority ports and a …

Evalattai: A Holistic Approach To Evaluating Attribution Maps In Robust And Non-Robust Models, Ian E. Nielsen, Ravi Ramachandran, Nidhal Carla Bouaynaya, Hassan M. Fathallah-Shaykh, Ghulam Rasool

Henry M. Rowan College of Engineering Faculty Scholarship

Eyes are one of the main critical organs of the body that provide our brain with the most information about the surrounding environment. Disturbance in the activity of this informational organ, resulting from different ocular diseases, could affect the quality of life, so finding appropriate methods for treating ocular disease has attracted lots of attention. This is especially due to the ineffectiveness of the conventional therapeutic method to deliver drugs into the interior parts of the eye, and the also presence of barriers such as tear film, blood-ocular, and blood-retina barriers. Recently, some novel techniques, such as different types of …

Memory-Based Adaptive Sliding Mode Load Frequency Control In Interconnected Power Systems With Energy Storage, Farhad Farivar, Octavian Bass, Daryoush Habibi

Research outputs 2022 to 2026

This paper presents a memory-based adaptive sliding mode load frequency control (LFC) strategy aimed at minimizing the impacts of exogenous power disturbances and parameter uncertainties on frequency deviations in interconnected power systems with energy storage. First, the dynamic model of the system is constructed by considering the participation of the energy storage system (ESS) in the conventional decentralized LFC model of a multiarea power system. A disturbance observer (DOB) is proposed to generate an online approximation of the lumped disturbance. In order to enhance the transient performance of the system and effectively mitigate the adverse effects of power fluctuations on …

Failure Detection In Deep Neural Networks For Medical Imaging, Sabeen Ahmed, Dimah Dera, Saud Ul Hassan, Nidhal Bouaynaya, Ghulam Rasool

Electrical and Computer Engineering Faculty Publications and Presentations

Deep neural networks (DNNs) have started to find their role in the modern healthcare system. DNNs are being developed for diagnosis, prognosis, treatment planning, and outcome prediction for various diseases. With the increasing number of applications of DNNs in modern healthcare, their trustworthiness and reliability are becoming increasingly important. An essential aspect of trustworthiness is detecting the performance degradation and failure of deployed DNNs in medical settings. The softmax output values produced by DNNs are not a calibrated measure of model confidence. Softmax probability numbers are generally higher than the actual model confidence. The model confidence-accuracy gap further increases for …

Robust Learning Via Ensemble Density Propagation In Deep Neural Networks, Giuseppina Carannante, Dimah Dera, Ghulam Rasool, Nidhal Carla Bouaynaya, Lyudmila Mihaylova

Electrical and Computer Engineering Faculty Publications and Presentations

Learning in uncertain, noisy, or adversarial environments is a challenging task for deep neural networks (DNNs). We propose a new theoretically grounded and efficient approach for robust learning that builds upon Bayesian estimation and Variational Inference. We formulate the problem of density propagation through layers of a DNN and solve it using an Ensemble Density Propagation (EnDP) scheme. The EnDP approach allows us to propagate moments of the variational probability distribution across the layers of a Bayesian DNN, enabling the estimation of the mean and covariance of the predictive distribution at the output of the model. Our experiments using MNIST …

Performance Resilience Analysis Of Dynamic Feedback Controllers For Both Multiplicative And Additive Gain Perturbations, Fan Feng, Susan C. Schneider, Edwin E. Yaz

Electrical and Computer Engineering Faculty Research and Publications

In this work, a procedure is presented for performance resilience analysis of continuous-time systems controlled by full-order dynamic feedback compensators. The resilience property is defined in terms of defining maximum perturbations on both the controller and observer gains that will maintain controller and observer eigenvalues in disjoint regions in the complex plane so that the closed loop system will sustain certain performance characteristics. The desired performance is characterized by the response speed and magnitude bounds on the response. Therefore, the intersection of two regions are chosen, vertical strips and sector regions, to guarantee upper and lower bounds on the settling …

Recursive Robust Pca Or Recursive Sparse Recovery In Large But Structured Noise, Chenlu Qiu, Namrata Vaswani, Brian Lois, Leslie Hogben

Namrata Vaswani

This paper studies the recursive robust principal components analysis problem. If the outlier is the signal-of-interest, this problem can be interpreted as one of recursively recovering a time sequence of sparse vectors, St, in the presence of large but structured noise, Lt. The structure that we assume on Lt is that Lt is dense and lies in a low-dimensional subspace that is either fixed or changes slowly enough. A key application where this problem occurs is in video surveillance where the goal is to separate a slowly changing background (Lt) from moving foreground objects (St) on-the-fly. To solve the above …

A Modified Two-Degree Of Freedom-Internal Model Control Configuration For Load Frequency Control Of A Single Area Power System, Bheem Sonker, Deepak Kumar, Paulson Samuel

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, we propose a modified two degree-of-freedom internal model control structure, with dual feedback loop configuration for the load frequency control problem of a single-area power system. Our main objective is to achieve better transient and steady state performance. The predictive model of the proposed configuration is derived through the stability equation method, which preserves the stability of the model. The proposed scheme is simulated for a single-area power system with nonreheated turbine and 50% parametric uncertainty. It is observed from the responses and the performance indices that the proposed control configuration gives better results compared to well-known …

Unknown Input Observer Based On Lmi For Robust Generation Residuals, Souad Tahraoui, Abdelmadjid Meghabbar, Djamila Boubekeur

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, a method of generating robust residuals of a linear system, subject to unknown inputs, is proposed. The impact of disturbances and uncertainty may create difficulties at the decision stage of diagnosis (false alarm); this has resulted in the use of a robust observer for the unknown inputs to ensure the robustness of the system based on the unknown input observer with an optimal decoupling approach, which has a sensitivity that is minimal to unknown inputs and maximal to faults. A generation of robust residuals is then transformed into a problem of robustness/sensitivity constraints (H$_{\infty }$, H and …

Design Of Novel Devices And Circuits For Electrostatic Discharge Protection Applications In Advanced Semiconductor Technologies, Zhixin Wang

Electronic Theses and Dissertations

Electrostatic Discharge (ESD), as a subset of Electrical Overstress (EOS), was reported to be in charge of more than 35% of failure in integrated circuits (ICs). Especially in the manufacturing process, the silicon wafer turns out to be a functional ICs after numerous physical, chemical and mechanical processes, each of which expose the sensitive and fragile ICs to ESD environment. In normal end-user applications, ESD from human and machine handling, surge and spike signals in the power supply, and wrong supplying signals, will probably cause severe damage to the ICs and even the whole systems. Generally, ESD protections are evaluated …

Rbc Lifespan Uncertainty: Models And Anemia Management Robustness, Rui Dai

Masters Theses 1911 - February 2014

This thesis discusses the modeling of uncertainty of red blood cell (RBC) lifespan distribution in patients suffering from Chronic Kidney Disease(CKD) patients, whose anemia is managed through periodic dosing of erythropoietin (EPO).

In healthy individuals, RBCs containing hemoglobin (Hgb) are produced in the bone marrow. When oxygen carried by hemoglobin is transported to human tissues throughout the body, the kidneys sense reduced level of Hgb and secretes EPO that simulates proliferation of red cell precursors and eventually producing red blood cells. However, in CKD patients, their kidneys fail to secrete enough EPO, so that too few of RBCs are produced …

A Robust Decentralized Load Frequency Controller For Interconnected Power Systems, Lili Dong, Yao Zhang, Zhiqiang Gao

Electrical and Computer Engineering Faculty Publications

A novel design of a robust decentralized load frequency control (LFC) algorithm is proposed for an inter-connected three-area power system, for the purpose of regulating area control error (ACE) in the presence of system uncertainties and external disturbances. The design is based on the concept of active disturbance rejection control (ADRC). Estimating and mitigating the total effect of various uncertainties in real time, ADRC is particularly effective against a wide range of parameter variations, model uncertainties, and large disturbances. Furthermore, with only two tuning parameters, the controller provides a simple and easy-to-use solution to complex engineering problems in practice. Here, …

Reduction Of Torque Ripple In Dtc For Induction Motor Using Input-Output Feedback Linearization, Sebti Belkacem, Farid Naceri, Rachid Abdessemed

Turkish Journal of Electrical Engineering and Computer Sciences

Direct torque control (DTC) is known to produce fast responses and robust control in AC adjustable-speed drives. However, in the steady-state operation, notable torque, flux, and current pulsations occur. In this paper, nonlinear DTC of induction motor drives is presented based on a space vector pulse-width modulation scheme combined with the input-output feedback linearization technique. The variation of stator and rotor resistance due to changes in temperature or frequency deteriorates the performance of the DTC controller by introducing errors in the estimated flux linkage and the electromagnetic torque. This approach will not be suitable for high power drives such as …

Robust And Resilient Finite-Time Control Of A Class Of Discrete-Time Nonlinear Systems, Mohammad N. Elbsat, Edwin E. Yaz

Electrical and Computer Engineering Faculty Research and Publications

In this paper, we address the finite-time state-feedback stabilization of a class of discrete-time nonlinear systems with conic type nonlinearities, bounded feedback control gain perturbations, and additive disturbances. Sufficient conditions for the existence of a robust and resilient linear state feedback controller for this class of systems are derived. Then, using linear matrix inequality techniques, a solution for the controller gain is obtained. The developed controller is robust for all unknown nonlinearities lying in a hyper-sphere and all admissible disturbances. Moreover, it is resilient against any bounded perturbations that may alter the controller’s gain by at most a prescribed amount. …

Robust Signaling Techniques For Through Silicon Via Bundles, Krishna Chaitanya Chillara

Masters Theses 1911 - February 2014

3D circuit integration is becoming increasingly important as one of the remaining techniques for staying on Moore’s law trajectory. 3D Integrated Circuits (ICs) can be realized using the Through Silicon Via (TSV) approach. In order to extract the full benefits of 3D and for better yield, it has been suggested that the TSVs should be arranged as bundles rather than parallel TSVs. TSVs are required to route the signals through different dies in a multi-tier 3D IC. TSVs are excellent but scarce electrical conductors. Hence, it is important to utilize these resources very efficiently.

In high performance 3D ICs, signaling …

On The Performance Of Svd-Dwt Based Digital Video Watermarking Technique With Semi-Blind Detector, Tarzan Basaruddin, Della Maulidiya

Makara Journal of Technology

On the Performance of SVD-DWT Based Digital Video Watermarking Technique with Semi-Blind Detector. This paper presents a watermarking technique for digital video. The proposed scheme is developed based on the work of Ganic and Chan which took the virtue of SVD and DWT. While the previous works of Chan has the blind detector property, our attempt is to develop a scheme with semi-blind detector, by using the merit of the DWT-SDV technique proposed by Ganic which was originally applied to still image. Overall, our experimental results show that our proposed scheme has a very good imperceptibility and is reasonably robust …

Frsmc Design For The Steering Control And Diving Control Of Underwater Vehicles, Tzu-Chun Kuo, Ying-Jeh Huang, Hung-Hsiu Yu

Journal of Marine Science and Technology

A robust control method is proposed for the steering and diving control systems of autonomous underwater vehicles. Heading angle and heave position tracking are achieved. All the closed-loop poles in the sliding mode can be placed by using the sliding mode and root locus techniques. Fuzzy logic technique is further employed to effectively tune the control law. Parameter variation and external disturbance such as various vehicle speeds and the ocean current effect are overcome.

Load Frequency Control Of Multiple-Area Power Systems, Yao Zhang

ETD Archive

In an interconnected power system, as a power load demand varies randomly, both area frequency and tie-line power interchange also vary. The objectives of load frequency control (LFC) are to minimize the transient deviations in theses variables (area frequency and tie-line power interchange) and to ensure their steady state errors to be zeros. When dealing with the LFC problem of power systems, unexpected external disturbances, parameter uncertainties and the model uncertainties of the power system pose big challenges for controller design. Active disturbance rejection control (ADRC), as an increasingly popular practical control technique, has the advantages of requiring little information …

Optimal Robust Fault Detection, Nike Liu

LSU Doctoral Dissertations

This dissertation gives complete, analytic, and optimal solutions to several robust fault detection problems for both continuous and discrete linear systems that have been considered in the research community in the last twenty years. It is shown that several well-recognized robust fault detection problems, such as H_minus\H_2, H_2\ H_infinity and H_infinity\H_infinity problems, have a very simple optimal solution in an observer form by solving a standard algebraic Riccati equation. The optimal solutions to some other robust fault detection problems, such as H_minus\H_2 and H_2\H_2 problems are also given. In addition, it is shown that some well-studied and seeming sensible optimization …

Clock-Free Nanowire Crossbar Architecture Based On Null Convention Logic (Ncl), Ravi Bonam, Shikha Chaudhary, Yadunandana Yellambalase, Minsu Choi

Electrical and Computer Engineering Faculty Research & Creative Works

There have been numerous nanowire crossbar architectures proposed till date, although all of them are envisioned to be synchronous (i.e., clocked). The clock is an important part in a circuit and it needs to be connected to all the components to synchronize their operation. Considering non-deterministic nature of nanoscale integration, realizing them on a nano wire crossbar system would be quite cumbersome. Unlike the conventional clocked counterparts, a new clock-free crossbar architecture is proposed to resolve the issues with clocked counterparts in this paper, where the use of clock is eliminated from the architecture. This has been done by implementing …

A Measure Of Robustness Against Multiple Kinds Of Perturbations, Shoukat Ali, Behdis Eslamnour

Electrical and Computer Engineering Faculty Research & Creative Works

Parallel and distributed heterogeneous computing systems may operate in an environment that undergoes unpredictable changes causing certain system performance features to degrade. Such systems need robustness to guarantee limited degradation despite fluctuations in the behavior of its component parts or environment. Our previous work in this area presented a method for generating a measure of robustness for a given system. However, the focus of that approach was on a scenario where all perturbations were of the same kind, e.g., all perturbations were in message sizes or computation times, but not both message sizes and computation times. This paper gives an …

Estimative Current Mode Control Technique For Dc-Dc Converters Operating In Discontinuous Conduction Mode, Mehdi Ferdowsi, Ali Emadi

Electrical and Computer Engineering Faculty Research & Creative Works

A new control technique for DC-DC converters is introduced and applied to a boost converter operating in discontinuous conduction mode (DCM). In contrast to conventional control methods, the principal idea of the proposed control scheme is to obtain samples of the required signals and estimate the required switch-on time. The proposed technique is applicable to any converter operating in DCM, including power factor correctors (PFC), however, this letter mainly focuses on boost topology. In this letter, the main mathematical concept of a new control algorithm is introduced, as well as the robustness investigation of the proposed method with simulation and …

Measuring The Robustness Of A Resource Allocation, Shoukat Ali, A. A. Maciejewski, Howard Jay Siegel, Jong-Kook Kim

Electrical and Computer Engineering Faculty Research & Creative Works

Parallel and distributed systems may operate in an environment that undergoes unpredictable changes causing certain system performance features to degrade. Such systems need robustness to guarantee limited degradation despite fluctuations in the behavior of its component parts or environment. This research investigates the robustness of an allocation of resources to tasks in parallel and distributed systems. The main contributions are 1) a mathematical description of a metric for the robustness of a resource allocation with respect to desired system performance features against multiple perturbations in multiple system and environmental conditions, and 2) a procedure for deriving a robustness metric for …

Watermarking Using Decimal Sequences, Navneet Kumar Mandhani

LSU Master's Theses

This thesis introduces the use of decimal sequences in watermarking to hide information for authentication. The underlying system is based on code division multiple access (CDMA), which is a form of spread spectrum communication. Different algorithms for the use of decimal sequences have been formulated for use in black and white images. The watermark is spread across the carrier image by using the d- sequences of optimal period and retrieval is made by the use of correlation. Matlab version 6.5 was used to implement the algorithms discussed in this thesis. The advantage of using d-sequences over PN sequences is that …

Application Of Speech Recognition To African Elephant (Loxodonta Africana) Vocalizations, Patrick J. Clemins, Michael T. Johnson

Dr. Dolittle Project: A Framework for Classification and Understanding of Animal Vocalizations

This paper presents a novel application of speech processing research, classification of African elephant vocalizations. Speaker identification and call classification experiments are performed on data collected from captive African elephants in a naturalistic environment. The features used for classification are 12 mel-frequency cepstral coefficients plus log energy computed using a shifted filter bank to emphasize the infrasound range of the frequency spectrum used by African elephants. Initial classification accuracies of 83.8% for call classification and 88.1% for speaker identification were obtained. The long-term goal of this research is to develop a universal analysis framework and robust feature set for animal …

Adaptive-Critic-Based Optimal Neurocontrol For Synchronous Generators In A Power System Using Mlp/Rbf Neural Networks, Jung-Wook Park, Ganesh K. Venayagamoorthy, Ronald G. Harley

Electrical and Computer Engineering Faculty Research & Creative Works

This paper presents a novel optimal neurocontroller that replaces the conventional controller (CONVC), which consists of the automatic voltage regulator and turbine governor, to control a synchronous generator in a power system using a multilayer perceptron neural network (MLPN) and a radial basis function neural network (RBFN). The heuristic dynamic programming (HDP) based on the adaptive critic design technique is used for the design of the neurocontroller. The performance of the MLPN-based HDP neurocontroller (MHDPC) is compared with the RBFN-based HDP neurocontroller (RHDPC) for small as well as large disturbances to a power system, and they are in turn compared …

Implementation Of Adaptive Critic-Based Neurocontrollers For Turbogenerators In A Multimachine Power System, Ganesh K. Venayagamoorthy, Donald C. Wunsch, Ronald G. Harley

Electrical and Computer Engineering Faculty Research & Creative Works

This paper presents the design and practical hardware implementation of optimal neurocontrollers that replace the conventional automatic voltage regulator (AVR) and the turbine governor of turbogenerators on multimachine power systems. The neurocontroller design uses a powerful technique of the adaptive critic design (ACD) family called dual heuristic programming (DHP). The DHP neurocontroller's training and testing are implemented on the Innovative Integration M67 card consisting of the TMS320C6701 processor. The measured results show that the DHP neurocontrollers are robust and their performance does not degrade unlike the conventional controllers even when a power system stabilizer (PSS) is included, for changes in …

Adaptive Critic Based Neurocontroller For Turbogenerators With Global Dual Heuristic Programming, Ganesh K. Venayagamoorthy, Donald C. Wunsch, Ronald G. Harley

Electrical and Computer Engineering Faculty Research & Creative Works

Turbogenerators are nonlinear time varying systems. This paper presents the design of a neurocontroller for such a turbogenerator that augments/replaces the traditional automatic voltage regulator (AVR) and the turbine governor using a novel technique based on the adaptive critic designs (ACDs) with emphasis on global dual heuristic programming (GDHP). Simulation results are presented to show that the neurocontroller derived with the GDHP approach is robust and its performance is better when compared with that derived with other neural network technique, especially when system conditions and configuration changes.