Engineering Commons^™

Artificial Intelligence (Ai) And Nuclear Features From The Fine Needle Aspirated (Fna) Tissue Samples To Recognize Breast Cancer, Rumana Islam, Mohammed Tarique

Electrical and Computer Engineering Publications

Breast cancer is one of the paramount causes of new cancer cases worldwide annually. It is a malignant neoplasm that develops in the breast cells. The early screening of this disease is essential to prevent its metastasis. A mammogram X-ray image is the most common screening tool practiced currently when this disease is suspected; all the breast lesions identified are not malignant. The invasive fine needle aspiration (FNA) of a breast mass sample is the secondary screening tool to clinically examine cancerous lesions. The visual image analysis of the stained aspirated sample imposes a challenge for the cytologist to identify …

An Investigation Of Information Structures In Dna, Joel Mohrmann

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

The information-containing nature of the DNA molecule has been long known and observed. One technique for quantifying the relationships existing within the information contained in DNA sequences is an entity from information theory known as the average mutual information (AMI) profile. This investigation sought to use principally the AMI profile along with a few other metrics to explore the structure of the information contained in DNA sequences.

Treating DNA sequences as an information source, several computational methods were employed to model their information structure. Maximum likelihood and maximum a posteriori estimators were used to predict missing bases in DNA sequences. …

Composite Style Pixel And Point Convolution-Based Deep Fusion Neural Network Architecture For The Semantic Segmentation Of Hyperspectral And Lidar Data, Kevin T. Decker, Brett J. Borghetti

Faculty Publications

Multimodal hyperspectral and lidar data sets provide complementary spectral and structural data. Joint processing and exploitation to produce semantically labeled pixel maps through semantic segmentation has proven useful for a variety of decision tasks. In this work, we identify two areas of improvement over previous approaches and present a proof of concept network implementing these improvements. First, rather than using a late fusion style architecture as in prior work, our approach implements a composite style fusion architecture to allow for the simultaneous generation of multimodal features and the learning of fused features during encoding. Second, our approach processes the higher …

Improvement On Pdp Evaluation Performance Based On Neural Networks And Sgdk-Means Algorithm, Fan Deng, Houbing Song, Zhenhua Yu, Liyong Zhang, Xi Song, Min Zhang, Zhenyu Zhang, Yu Mei

Publications

With the purpose of improving the PDP (policy decision point) evaluation performance, a novel and efficient evaluation engine, namely XDNNEngine, based on neural networks and an SGDK-means (stochastic gradient descent K-means) algorithm is proposed. We divide a policy set into different clusters, distinguish different rules based on their own features and label them for the training of neural networks by using the K-means algorithm and an asynchronous SGDK-means algorithm. Then, we utilize neural networks to search for the applicable rule. A quantitative neural network is introduced to reduce a server’s computational cost. By simulating the arrival of requests, XDNNEngine is …

A Cdzntese Gamma Spectrometer Trained By Deep Convolutional Neural Network For Radioisotope Identification, Sandeep K. Chaudhuri, Joshua W. Kleppinger, Ritwik Nag, Kaushik Roy, Rojina Panta, Forest Agostinelli, Amit Sheth, Utpal N. Roy, Ralph B. James, Krishna C. Mandal

Publications

We report the implementation of a deep convolutional neural network to train a high-resolution room-temperature CdZnTeSe based gamma ray spectrometer for accurate and precise determination of gamma ray energies for radioisotope identification. The prototype learned spectrometer consists of a NI PCI 5122 fast digitizer connected to a pre-amplifier to recognize spectral features in a sequence of data. We used simulated preamplifier pulses that resemble actual data for various gamma photon energies to train a CNN on the equivalent of 90 seconds worth of data and validated it on 10 seconds worth of simulated data.

Zip Load Modeling For Single And Aggregate Loads And Cvr Factor Estimation, Yiqi Zhang, Yuan Liao, Evan S. Jones, Nicholas Jewell, Dan M. Ionel

Electrical and Computer Engineering Presentations

ZIP load modeling has been used in various power system applications. The aggregate load modeling is common practice in utility companies. However, little research has been done on the theoretical formulation of the aggregate load. This paper formulates the aggregate ZIP load model using the single ZIP load model. The factors that may affect aggregate ZIP load estimation are studied. Common ZIP parameter estimation methods including least squares method, optimization method and neural network method have been used in this paper to estimate ZIP parameters. The case studies are based on the IEEE 13-bus and 34-bus system built in OpenDSS. …

Deep Learning Control For Digital Feedback Systems: Improved Performance With Robustness Against Parameter Change, Nuha A. S. Alwan, Zahir M. Hussain

Research outputs 2014 to 2021

Training data for a deep learning (DL) neural network (NN) controller are obtained from the input and output signals of a conventional digital controller that is designed to provide the suitable control signal to a specified plant within a feedback digital control system. It is found that if the DL controller is sufficiently deep (four hidden layers), it can outperform the conventional controller in terms of settling time of the system output transient response to a unit-step reference signal. That is, the DL controller introduces a damping effect. Moreover, it does not need to be retrained to operate with a …

Admittance Method For Estimating Local Field Potentials Generated In A Multi-Scale Neuron Model Of The Hippocampus, Clayton S. Bingham, Javad Paknahad, Christopher Bc Girard, Kyle Loizos, Jean-Marie C. Bouteiller, Dong Song, Gianluca Lazzi, Theodore W. Berger

Engineering Faculty Articles and Research

Significant progress has been made toward model-based prediction of neral tissue activation in response to extracellular electrical stimulation, but challenges remain in the accurate and efficient estimation of distributed local field potentials (LFP). Analytical methods of estimating electric fields are a first-order approximation that may be suitable for model validation, but they are computationally expensive and cannot accurately capture boundary conditions in heterogeneous tissue. While there are many appropriate numerical methods of solving electric fields in neural tissue models, there isn't an established standard for mesh geometry nor a well-known rule for handling any mismatch in spatial resolution. Moreover, the …

Greentpu: Predictive Design Paradigm For Improving Timing Error Resilience Of A Near-Threshold Tensor Processing Unit, Pramesh Pandey, Prabal Basu, Koushik Chakraborty, Sanghamitra Roy

Electrical and Computer Engineering Faculty Publications

The emergence of hardware accelerators has brought about several orders of magnitude improvement in the speed of the deep neural-network (DNN) inference. Among such DNN accelerators, the Google tensor processing unit (TPU) has transpired to be the best-in-class, offering more than 15\times speedup over the contemporary GPUs. However, the rapid growth in several DNN workloads conspires to escalate the energy consumptions of the TPU-based data-centers. In order to restrict the energy consumption of TPUs, we propose GreenTPU - a low-power near-threshold (NTC) TPU design paradigm. To ensure a high inference accuracy at a low-voltage operation, GreenTPU identifies the patterns in …

Short-Term Solar Power Prediction Using An Rbf Neural Network, Jianwu Zeng, Wei Qiao

Department of Electrical and Computer Engineering: Faculty Publications

This paper proposes a radial basis function (RBF) neural network-based model for short-term solar power prediction (SPP). Instead of predicting solar power directly, the model predicts transmissivity, which is then used to obtain solar power according to the extraterrestrial radiation. The proposed model uses a novel two-dimensional (2D) representation for hourly solar radiation and uses historical transmissivity, sky cover, relative humidity and wind speed as the input. Simulation studies are carried out to validate the proposed model for shortterm SPP by using the data obtained from the National Solar Radiation Database (NSRDB). The performance of the RBF neural network is …

Eeg Artifact Removal Using A Wavelet Neural Network, Hoang-Anh T. Nguyen, John Musson, Jiang Li, Frederick Mckenzie, Guangfan Zhang, Roger Xu, Carl Richey, Tom Schnell, Thomas E. Pinelli (Ed.)

Electrical & Computer Engineering Faculty Publications

In this paper we developed a wavelet neural network. (WNN) algorithm for Electroencephalogram (EEG) artifact removal without electrooculographic (EOG) recordings. The algorithm combines the universal approximation characteristics of neural network and the time/frequency property of wavelet. We compared the WNN algorithm with the ICA technique and a wavelet thresholding method, which was realized by using the Stein's unbiased risk estimate (SURE) with an adaptive gradient-based optimal threshold. Experimental results on a driving test data set show that WNN can remove EEG artifacts effectively without diminishing useful EEG information even for very noisy data.

Adaptive Dynamic Programming-Based Optimal Control Of Unknown Affine Nonlinear Discrete-Time Systems, Travis Dierks, Balaje T. Thumati, S. Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

Discrete time approximate dynamic programming (ADP) techniques have been widely used in the recent literature to determine the optimal or near optimal control policies for nonlinear systems. However, an inherent assumption of ADP requires at least partial knowledge of the system dynamics as well as the value of the controlled plant one step ahead. in this work, a novel approach to ADP is attempted while relaxing the need of the partial knowledge of the nonlinear system. the proposed methodology entails a two-part process: online system identification and offline optimal control training. First, in the identification process, a neural network (NN) …

Optimal Control Of Unknown Affine Nonlinear Discrete-Time Systems Using Offline-Trained Neural Networks With Proof Of Convergence, Travis Dierks, Balaje T. Thumati, S. Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

The optimal control of linear systems accompanied by quadratic cost functions can be achieved by solving the well-known Riccati equation. However, the optimal control of nonlinear discrete-time systems is a much more challenging task that often requires solving the nonlinear Hamilton-Jacobi-Bellman (HJB) equation. in the recent literature, discrete-time approximate dynamic programming (ADP) techniques have been widely used to determine the optimal or near optimal control policies for affine nonlinear discrete-time systems. However, an inherent assumption of ADP requires the value of the controlled system one step ahead and at least partial knowledge of the system dynamics to be known. in …

Hybrid Committee Classifier For A Computerized Colonic Polyp Detection System, Jiang Li, Jianhua Yao, Nicholas Petrick, Ronald M. Summers, Amy K. Hara, Joseph M. Reinhardt (Ed.), Josien P.W. Pluim (Ed.)

Electrical & Computer Engineering Faculty Publications

We present a hybrid committee classifier for computer-aided detection (CAD) of colonic polyps in CT colonography (CTC). The classifier involved an ensemble of support vector machines (SVM) and neural networks (NN) for classification, a progressive search algorithm for selecting a set of features used by the SVMs and a floating search algorithm for selecting features used by the NNs. A total of 102 quantitative features were calculated for each polyp candidate found by a prototype CAD system. 3 features were selected for each of 7 SVM classifiers which were then combined to form a committee of SVMs classifier. Similarly, features …

Neural Network Detection And Identification Of Electronic Devices Based On Their Unintended Emissions, Haixiao Weng, Xiaopeng Dong, Xiao Hu, Daryl G. Beetner, Todd H. Hubing, Donald C. Wunsch

Electrical and Computer Engineering Faculty Research & Creative Works

Electromagnetic emissions were measured from several radio receivers to demonstrate the possibility of detecting and identifying these devices based on their unintended emissions. Radiated fields from the different radio receivers have unique characteristics that can be used to identify these devices by analyzing time-frequency plots of measured radiation. A neural network was also developed for automated device detection.

Synthesis Of Electromagnetic Devices With A Novel Neural Network, Heriberto Jose Delgado, Michael Thursby, Fredric M. Ham

Electrical Engineering and Computer Science Faculty Publications

A novel Artificial Neural Network (ANN) is presented, which has been designed for computationally intensive problems, and applied to the optimization of electromagnetic devices such as antennas and microwave devices. The ANN exploits a unique number representation in conjunction with a more standard neural network architecture. An ANN consisting of a hetero-associative memory provided a very efficient method of computing the necessary geometrical values for the devices, when used in conjunction with a new randomization process. The number representation used provides significant insight into this new method of fault-tolerant computing. Further work is needed to evaluate the potential of this …

Model Predictive Control Of Cstr Based On Local Model Networks, Ruiyao Gao, Aidan O'Dwyer, Eugene Coyle

Conference papers

A non-linear predictive controller is presented. It judiciously combines predictive controllers with a local model network utilizing a neural-network-like gating system. It avoids the time consuming quadratic optimization calculation, which is normally necessary in non-linear predictive control. A controller simulation on a Continuous Stirred Tank Reactor (CSTR) case study was shown to be satisfactory both in terms of set point tracking and regulation performance over the entire operating range. Moreover, the inherent integration action in the local predictive controller provides zero static offsets.

Separation Of Infrasound Signals Using Independent Component Analysis, Fredric M. Ham, Sungin Park, Joseph C. Wheeler

Electrical Engineering and Computer Science Faculty Publications

An important element of monitoring compliance of the Comprehensive Nuclear-Test-Ban Treaty (CTBT) is an infrasound network. For reliable monitoring, it is important to distinguish between nuclear explosions and other sources of infrasound. This will require signal (event) classification after a detection is made. We have demonstrated the feasibility of using neural networks to classify various infrasonic events. However, classification of these events can be made more reliably with enhanced quality of the recorded infrasonic signals. One means of improving the quality of the infrasound signals is to remove background noise. This can be carried out by performing signal separation using …

Discrimination Of Volcano Activity And Mountain-Associated Waves Using Infrasonic Data And A Backpropagation Neural Network, Fredric M. Ham, Thomas A. Leeney, Heather M. Canady, Joseph C. Wheeler

Electrical Engineering and Computer Science Faculty Publications

An integral part of the Comprehensive Nuclear Test Ban Treaty monitoring is an international infrasonic monitoring network that is capable of detecting and verifying nuclear explosions. Reliable detection of such events must be made from data that may contain other sources of infrasonic phenomena. Infrasonic waves can also result from volcanic eruptions, mountain associated waves, auroral waves, earthquakes, meteors, avalanches, severe weather, quarry blasting, high-speed aircraft, gravity waves, and microbaroms. This paper shows that a feedforward multi-layer neural network discriminator, trained by backpropagation, is capable of distinguishing between two unique infrasonic events recorded from single station recordings with a relatively …

Extension Of The Generalized Hebbian Algorithm For Principal Component Extraction, Fredric M. Ham, Inho Kim

Electrical Engineering and Computer Science Faculty Publications

Principal component analysis (PCA) plays an important role in various areas. In many applications it is necessary to adaptively compute the principal components of the input data. Over the past several years, there have been numerous neural network approaches to adaptively extract principal components for PCA. One of he most popular learning rules for training a single-layer linear network for principal component extraction is Sanger's generalized Hebbian algorithm (GHA). We have extended the GHA (EGHA) by including a positive-definite symmetric weighting matrix in the representation error-cost function that is used to derive the learning rule to train the network. The …

Estimation Of Surface Snow Properties Using Combined Millimeter-Wave Backscatter And Near-Infrared Reflectance Measurements, Ram M. Narayanan, Sandy R. Jackson

Department of Electrical and Computer Engineering: Faculty Publications

Knowledge of surficial snow properties such as grain size, surface roughness, and free-water content provides clues to the metamorphic state of snow on the ground, which in turn yields information on weathering processes and climatic activity. Remote sensing techniques using combined concurrent measurements of near-infrared passive reflectance and millimeter-wave radar backscatter show promise in estimating the above snow parameters. Near-infrared reflectance is strongly dependent on snow grain size and free-water content, while millimeter-wave backscatter is primarily dependent on free-water content and, to some extent, on the surface roughness. A neural-network based inversion algorithm has been developed that optimally combines near-infrared …

The Application Of Neural Networks To Optimal Robot Trajectory Planning, Daniel J. Simon

Electrical and Computer Engineering Faculty Publications

Interpolation of minimum jerk robot joint trajectories through an arbitrary number of knots is realized using a hardwired neural network. Minimum jerk joint trajectories are desirable for their similarity to human joint movements and their amenability to accurate tracking. The resultant trajectories are numerical rather than analytic functions of time. This application formulates the interpolation problem as a constrained quadratic minimization problem over a continuous joint angle domain and a discrete time domain. Time is discretized according to the robot controller rate. The neuron outputs define the joint angles (one neuron for each discrete value of time) and the Lagrange …