Computer Engineering Commons^™

Glaciernet: A Deep-Learning Approach For Debris-Covered Glacier Mapping, Zhiyuan Xie, Umesh K. Haritashya, Vijayan K. Asari, Brennan W. Young, Michael P. Bishop, Jeffrey S. Kargel

Electrical and Computer Engineering Faculty Publications

Rising global temperatures over the past decades is directly affecting glacier dynamics. To understand glacier fluctuations and document regional glacier-state trends, glacier-boundary detection is necessary. Debris-covered glacier (DCG) mapping, however, is notoriously difficult using conventional geospatial technology methods. Therefore, in this research for automated DCG mapping, we evaluate the utility of a convolutional neural network (CNN), which is a deep learning feed-forward neural network. The CNN inputs include Landsat satellite images, an Advanced Land Observation Satellite (ALOS) digital elevation model (DEM) and DEM-derived land-surface parameters. Our CNN based deep-learning approach named GlacierNet was designed by appropriately choosing the type, number …

Mitosisnet: End-To-End Mitotic Cell Detection By Multi-Task Learning, Md Zahangir Alom, Theus Aspiras, Tarek M. Taha, Tj Bowen, Vijayan K. Asari

Electrical and Computer Engineering Faculty Publications

Mitotic cell detection is one of the challenging problems in the field of computational pathology. Currently, mitotic cell detection and counting are one of the strongest prognostic markers for breast cancer diagnosis. The clinical visual inspection on histology slides is tedious, error prone, and time consuming for the pathologist. Thus, automatic mitotic cell detection approaches are highly demanded in clinical practice. In this paper, we propose an end-to-end multi-task learning system for mitosis detection from pathological images which is named"MitosisNet". MitosisNet consist of segmentation, detection, and classification models where the segmentation, and detection models are used for mitosis reference region …

A State-Of-The-Art Survey On Deep Learning Theory And Architectures, Md Zahangir Alom, Tarek M. Taha, Christopher Yakopcic, Stefan Westberg, Paheding Sidike, Mst Shamima Nasrin, Mahmudul Hasan, Brian C. Van Essen, Abdul A. S. Awwal, Vijayan K. Asari

Electrical and Computer Engineering Faculty Publications

In recent years, deep learning has garnered tremendous success in a variety of application domains. This new field of machine learning has been growing rapidly and has been applied to most traditional application domains, as well as some new areas that present more opportunities. Different methods have been proposed based on different categories of learning, including supervised, semi-supervised, and un-supervised learning. Experimental results show state-of-the-art performance using deep learning when compared to traditional machine learning approaches in the fields of image processing, computer vision, speech recognition, machine translation, art, medical imaging, medical information processing, robotics and control, bioinformatics, natural language …

Active Recall Networks For Multiperspectivity Learning Through Shared Latent Space Optimization, Theus Aspiras, Ruixu Liu, Vijayan K. Asari

Electrical and Computer Engineering Faculty Publications

Given that there are numerous amounts of unlabeled data available for usage in training neural networks, it is desirable to implement a neural network architecture and training paradigm to maximize the ability of the latent space representation. Through multiple perspectives of the latent space using adversarial learning and autoencoding, data requirements can be reduced, which improves learning ability across domains. The entire goal of the proposed work is not to train exhaustively, but to train with multiperspectivity. We propose a new neural network architecture called Active Recall Network (ARN) for learning with less labels by optimizing the latent space. This …

Deep Temporal Convolutional Networks For Short-Term Traffic Flow Forecasting, Wentian Zhao, Yanyun Gao, Tingxiang Ji, Xili Wan, Feng Ye, Guangwei Bai

Electrical and Computer Engineering Faculty Publications

To reduce the increasingly congestion in cities, it is essential for intelligent transportation system (ITS) to accurately forecast the short-term traffic flow to identify the potential congestion sites. In recent years, the emerging deep learning method has been introduced to design traffic flow predictors, such as recurrent neural network (RNN) and long short-term memory (LSTM), which has demonstrated its promising results. In this paper, different from existing work, we study the temporal convolutional network (TCN) and propose a deep learning framework based on TCN model for short-term city-wide traffic forecast to accurately capture the temporal and spatial evolution of traffic …

Recurrent Residual U-Net For Medical Image Segmentation, Md Zahangir Alom, Christopher Yakopcic, Mahmudul Hasan, Tarek M. Taha, Vijayan K. Asari

Electrical and Computer Engineering Faculty Publications

Deep learning (DL)-based semantic segmentation methods have been providing state-of-the-art performance in the past few years. More specifically, these techniques have been successfully applied in medical image classification, segmentation, and detection tasks. One DL technique, U-Net, has become one of the most popular for these applications. We propose a recurrent U-Net model and a recurrent residual U-Net model, which are named RU-Net and R2U-Net, respectively. The proposed models utilize the power of U-Net, residual networks, and recurrent convolutional neural networks. There are several advantages to using these proposed architectures for segmentation tasks. First, a residual unit helps when training deep …

A Survey Of Techniques For Mobile Service Encrypted Traffic Classification Using Deep Learning, Pan Wang, Xuejiao Chen, Feng Ye, Zhixin Sun

Electrical and Computer Engineering Faculty Publications

The rapid adoption of mobile devices has dramatically changed the access to various net- working services and led to the explosion of mobile service traffic. Mobile service traffic classification has been a crucial task that attracts strong interest in mobile network management and security as well as machine learning communities for past decades. However, with more and more adoptions of encryption over mobile services, it brings a lot of challenges about mobile traffic classification. Although classical machine learning approaches can solve many issues that port and payload-based methods cannot solve, it still has some limitations, such as time-consuming, costly handcrafted …

The Internet Of Energy: Architectures, Cyber Security, And Applications, Kun Wang, Yan Zhang, Song Guo, Mianxiong Dong, Rose Qingyang Hu, Lei He

Electrical and Computer Engineering Faculty Publications

The energy crisis and carbon emissions have become two critical concerns globally. As a very promising solution, the concept of Internet of Energy has appeared to tackle these challenges. The Internet of Energy is a new power generation paradigm developing a revolutionary vision of smart grids into the Internet. The communication infrastructure is an essential component for implementing the Internet of Energy. A scalable and robust communication infrastructure is crucial in both operating and maintaining smart energy systems. The wide-scale implementation and development of Internet of Energy into industrial applications should take into account the following challenges:

Chaotic Phase-Coded Waveforms With Space-Time Complementary Coding For Mimo Radar Applications, Sheng Hong, Fuhui Zhou, Yantao Dong, Zhixin Zhao, Yuhao Wang, Maosong Yan

Electrical and Computer Engineering Faculty Publications

A framework for designing orthogonal chaotic phase-coded waveforms with space-time complementary coding (STCC) is proposed for multiple-input multiple-output (MIMO) radar applications. The phase-coded waveform set to be transmitted is generated with an arbitrary family size and an arbitrary code length by using chaotic sequences. Due to the properties of chaos, this chaotic waveform set has many advantages in performance, such as anti-interference and low probability of intercept. However, it cannot be directly exploited due to the high range sidelobes, mutual interferences, and Doppler intolerance. In order to widely implement it in practice, we optimize the chaotic phase-coded waveform set from …

Advanced Recurrent Network-Based Hybrid Acoustic Models For Low Resource Speech Recognition, Jian Kang, Wei-Qiang Zhang, Wei-Wei Liu, Jia Liu, Michael T. Johnson

Electrical and Computer Engineering Faculty Publications

Recurrent neural networks (RNNs) have shown an ability to model temporal dependencies. However, the problem of exploding or vanishing gradients has limited their application. In recent years, long short-term memory RNNs (LSTM RNNs) have been proposed to solve this problem and have achieved excellent results. Bidirectional LSTM (BLSTM), which uses both preceding and following context, has shown particularly good performance. However, the computational requirements of BLSTM approaches are quite heavy, even when implemented efficiently with GPU-based high performance computers. In addition, because the output of LSTM units is bounded, there is often still a vanishing gradient issue over multiple layers. …

Fault Identification And Location For Distribution Network With Distributed Generations, Wen Fan, Yuan Liao

Electrical and Computer Engineering Faculty Publications

Power distribution networks with distributed generations may experience faults. It is essential to promptly locate the fault for fast repair and restoration. This paper presents a novel method for identifying the faulted section and accurate location of faults that occur on power distribution grid. Appropriate matrices are set up to represent meter locations on the grid and the topology of the grid. The voltage and current measurements obtained are utilized to decide the fault sections. Then fault location is determined by solving equations that link measurements and fault locations through bus impedance matrix. The method is applicable to both single …

A Fast And Robust Extrinsic Calibration For Rgb-D Camera Networks, Po-Chang Su, Ju Shen, Wanxin Xu, Sen-Ching S. Cheung, Ying Luo

Electrical and Computer Engineering Faculty Publications

From object tracking to 3D reconstruction, RGB-Depth (RGB-D) camera networks play an increasingly important role in many vision and graphics applications. Practical applications often use sparsely-placed cameras to maximize visibility, while using as few cameras as possible to minimize cost. In general, it is challenging to calibrate sparse camera networks due to the lack of shared scene features across different camera views. In this paper, we propose a novel algorithm that can accurately and rapidly calibrate the geometric relationships across an arbitrary number of RGB-D cameras on a network. Our work has a number of novel features. First, to cope …

Datanet: Deep Learning Based Encrypted Network Traffic Classification In Sdn Home Gateway, Pan Wang, Feng Ye, Xuejiao Chen, And Yi Qian

Electrical and Computer Engineering Faculty Publications

A smart home network will support various smart devices and applications, e.g., home automation devices, E-health devices, regular computing devices, and so on. Most devices in a smart home access the Internet through a home gateway (HGW). In this paper, we propose a software-defined- network (SDN)-HGW framework to better manage distributed smart home networks and support the SDN controller of the core network. The SDN controller enables efficient network quality-of-service management based on real-time traffic monitoring and resource allocation of the core network. However, it cannot provide network management in distributed smart homes. Our proposed SDN-HGW extends the control to …

Handwritten Bangla Character Recognition Using The State-Of-The-Art Deep Convolutional Neural Networks, Md Zahangir Alom, Paheding Sidike, Mahmudul Hasan, Tarek M. Taha, Vijayan K. Asari

Electrical and Computer Engineering Faculty Publications

In spite of advances in object recognition technology, handwritten Bangla character recognition (HBCR) remains largely unsolved due to the presence of many ambiguous handwritten characters and excessively cursive Bangla handwritings. Even many advanced existing methods do not lead to satisfactory performance in practice that related to HBCR. In this paper, a set of the state-of-the-art deep convolutional neural networks (DCNNs) is discussed and their performance on the application of HBCR is systematically evaluated. The main advantage of DCNN approaches is that they can extract discriminative features from raw data and represent them with a high degree of invariance to object …

On-Chip Training Of Memristor Crossbar Based Multi-Layer Neural Networks, Raqibul Hasan, Tarek M. Taha, Christopher Yakopcic

Electrical and Computer Engineering Faculty Publications

Memristor crossbar arrays carry out multiply-add operations in parallel in the analog domain, and so can enable neuromorphic systems with high throughput at low energy and area consumption. On-chip training of these systems have the significant advantage of being able to get around device variability and faults. This paper presents on-chip training circuits for multi-layer neural networks implemented using a single crossbar per layer and two memristors per synapse. Using two memristors per synapse provides double the synaptic weight precision when compared to a design that uses only one memristor per synapse. Proposed on-chip training system utilizes the back propagation …

On The Simulation And Mitigation Of Anisoplanatic Optical Turbulence For Long Range Imaging, Russell C. Hardie, Daniel A. Lemaster

Electrical and Computer Engineering Faculty Publications

We describe a numerical wave propagation method for simulating long range imaging of an extended scene under anisoplanatic conditions. Our approach computes an array of point spread functions (PSFs) for a 2D grid on the object plane. The PSFs are then used in a spatially varying weighted sum operation, with an ideal image, to produce a simulated image with realistic optical turbulence degradation. To validate the simulation we compare simulated outputs with the theoretical anisoplanatic tilt correlation and differential tilt variance. This is in addition to comparing the long- and short-exposure PSFs, and isoplanatic angle. Our validation analysis shows an …

Identity‐Based Schemes For A Secured Big Data And Cloud Ict Framework In Smart Grid System, Feng Ye, Yi Qian, Rose Qingyang Hu

Electrical and Computer Engineering Faculty Publications

Smart grid is an intelligent cyber physical system (CPS). The CPS generates a massive amount of data for efficient grid operation. In this paper, a big data‐driven, cloud‐based information and communication technology (ICT) framework for smart grid CPS is proposed. The proposed ICT framework deploys hybrid cloud servers to enhance scalability and reliability of smart grid communication infrastructure. Because the data in the ICT framework contains much privacy of customers and important data for automated controlling, the security of data transmission must be ensured. In order to secure the communications over the Internet in the system, identity‐based schemes are proposed …

Identity-Based Schemes For A Secured Big Data And Cloud Ict Framework In Smart Grid System, Feng Ye, Yi Qian, Rose Qingyang Hu

Electrical and Computer Engineering Faculty Publications

Smart grid is an intelligent cyber physical system (CPS). The CPS generates a massive amount of data for efficient grid operation. In this paper, a big data-driven, cloud-based information and communication technology (ICT) framework for smart grid CPS is proposed. The proposed ICT framework deploys hybrid cloud servers to enhance scalability and reliability of smart grid communication infrastructure. Because the data in the ICT framework contains much privacy of customers and important data for automated controlling, the security of data transmission must be ensured. In order to secure the communications over the Internet in the system, identity-based schemes are proposed …

Recursive Non-Local Means Filter For Video Denoising With Poisson-Gaussian Noise, Redha A. Almahdi, Russell C. Hardie

Electrical and Computer Engineering Faculty Publications

In this paper, we describe a new recursive Non-Local means (RNLM) algorithm for video denoising that has been developed by the current authors. Furthermore, we extend this work by incorporating a Poisson-Gaussian noise model. Our new RNLM method provides a computationally efficient means for video denoising, and yields improved performance compared with the single frame NLM and BM3D benchmarks methods. Non-Local means (NLM) based methods of denoising have been applied successfully in various image and video sequence denoising applications. However, direct extension of this method from 2D to 3D for video processing can be computationally demanding. The RNLM approach takes …

Analysis Of Various Classification Techniques For Computer Aided Detection System Of Pulmonary Nodules In Ct, Barath Narayanan Narayanan, Russell C. Hardie, Temesguen Messay

Electrical and Computer Engineering Faculty Publications

Lung cancer is the leading cause of cancer death in the United States. It usually exhibits its presence with the formation of pulmonary nodules. Nodules are round or oval-shaped growth present in the lung. Computed Tomography (CT) scans are used by radiologists to detect such nodules. Computer Aided Detection (CAD) of such nodules would aid in providing a second opinion to the radiologists and would be of valuable help in lung cancer screening. In this research, we study various feature selection methods for the CAD system framework proposed in FlyerScan. Algorithmic steps of FlyerScan include (i) local contrast enhancement (ii) …

Histogram Of Oriented Phase (Hop): A New Descriptor Based On Phase Congruency, Hussin Ragb, Vijayan K. Asari

Electrical and Computer Engineering Faculty Publications

In this paper we present a low level image descriptor called Histogram of Oriented Phase based on phase congruency concept and the Principal Component Analysis (PCA). Since the phase of the signal conveys more information regarding signal structure than the magnitude, the proposed descriptor can precisely identify and localize image features over the gradient based techniques, especially in the regions affected by illumination changes. The proposed features can be formed by extracting the phase congruency information for each pixel in the image with respect to its neighborhood. Histograms of the phase congruency values of the local regions in the image …

Diffractive Propagation And Recovery Of Modulated (Including Chaotic) Electromagnetic Waves Through Uniform Atmosphere And Modified Von Karman Phase Turbulence, Monish Ranjan Chatterjee, Fathi H.A. Mohamed

Electrical and Computer Engineering Faculty Publications

In a parallel approach to recently-used transfer function formalism, a study involving diffraction of modulated electromagnetic (EM) waves through uniform and phase-turbulent atmospheres is reported in this paper. Specifically, the input wave is treated as a modulated optical carrier, represented by use of a sinusoidal phasor with a slowly timevarying envelope. Using phasors and (spatial) Fourier transforms, the complex phasor wave is transmitted across a uniform or turbulent medium using the Kirchhoff-Fresnel integral and the random phase screen.

Some preliminary results are presented comparing non-chaotic and chaotic information transmission through turbulence, outlining possible improvement in performance utilizing the robust features …

Differential Tilt Variance Effects Of Turbulence In Imagery: Comparing Simulation With Theory, Daniel A. Lemaster, Russell C. Hardie, Szymon Gladysz, Matthew D. Howard, Michael Armand Rucci, Matthew E. Trippel, Jonathan D. Power, Barry K. Karch

Electrical and Computer Engineering Faculty Publications

Differential tilt variance is a useful metric for interpreting the distorting effects of turbulence in incoherent imaging systems. In this paper, we compare the theoretical model of differential tilt variance to simulations. Simulation is based on a Monte Carlo wave optics approach with split step propagation. Results show that the simulation closely matches theory. The results also show that care must be taken when selecting a method to estimate tilts.

Large-Area Object Search And Recovery Using Sector-Based Aerial Acousto-Optic Scanning And Reflection Sensing, Monish Ranjan Chatterjee, Salaheddeen G. Bugoffa

Electrical and Computer Engineering Faculty Publications

A sector-based angular scanning system intended to identify and spatially locate relatively small objects scattered over a large terrain is described in this paper. The system is modeled as a planar surface on the horizontal (XY) plane, with an acousto-optic Bragg cell on board an unmanned aerial vehicle (UAV) operating in the XZ plane.

The Bragg cell is excited by a chirped RF signal with a designed frequency ramp. As the scanning beam reflects off the horizontal surface, a detector placed strategically at a suitable altitude (in the analysis shown to be on board the UAV itself) picks up the …

A New Architecture For Application-Aware Cognitive Multihop Wireless Networks, Trenton Evans, Kossivi Tossou, Feng Ye, Zhihui Shu, Yi Qian, Yaoqing Yang, Hamid Sharif

Electrical and Computer Engineering Faculty Publications

In this article, we propose a new architecture for AC-MWN. Cognitive radio is a technique to adaptively use the spectrum so that the resource can be used more efficiently in a low-cost way. A multihop wireless network can be deployed quickly and flexibly without fixed infrastructure. In our proposed new architecture, we study backbone routing schemes with network cognition, and a routing scheme with network coding and spectrum adaptation. A testbed is implemented to test the proposed schemes for AC-MWN. In addition to basic measurements, we implement a video streaming application based on the proposed AC-MWN architecture using cognitive radios. …

A Real-Time Information Based Demand-Side Management System In Smart Grid, Feng Ye, Yi Qian, Rose Qingyang Hu

Electrical and Computer Engineering Faculty Publications

In this paper, we study a real-time information based demand-side management (DSM) system with advanced communication networks in smart grid. DSM can smooth peak-to-average ratio (PAR) of power usage in the grid, which in turn reduces the waste of fuel and the emission of greenhouse gas. We first target to minimize PAR with a centralized scheme. To motivate power suppliers, we further propose another centralized scheme targeting minimum power generation cost. However, customers may not be motivated by a centralized scheme since such a scheme requires total control and privacy from them. A centralized scheme also requires too much real-time …

An Adaptive Security Protocol For A Wireless Sensor‐Based Monitoring Network In Smart Grid Transmission Lines, Xuping Zhang, Feng Ye, Sucheng Fan, Jinghong Guo, Guoliang Xu, Yi Qian

Electrical and Computer Engineering Faculty Publications

In this paper, we propose a new security protocol for a wireless sensor network, which is designed for monitoring long range power transmission lines in smart grid. Part of the monitoring network is composed of optical fiber composite over head ground wire (OPGW), thus it can be secured with conventional security protocol. However, the wireless sensor network between two neighboring OPGW gateways remains vulnerable. Our proposed security protocol focuses on the wireless sensor network part, it provides mutual authentication, data integrity, and data confidentiality for both uplink and downlink transmissions between the sensor nodes and the OPGW gateway. Besides, our …

A High Performance Ceramic-Polymer Separator For Lithium Batteries, Jitendra Kumar, Padmakar Kichambare, Amarendra K. Rai, Rabi Bhattacharya, Stanley J. Rodrigues, Guru Subramanyam

Electrical and Computer Engineering Faculty Publications

A three-layered (ceramic-polymer-ceramic) hybrid separator was prepared by coating ceramic electrolyte [lithium aluminum germanium phosphate (LAGP)] over both sides of polyethylene (PE) polymer membrane using electron beam physical vapor deposition (EB-PVD) technique. Ionic conductivities of membranes were evaluated after soaking PE and LAGP/PE/LAGP membranes in a 1 Molar (1M) lithium hexafluroarsenate (LiAsF₆) electrolyte in ethylene carbonate (EC), dimethyl carbonate (DMC) and ethylmethyl carbonate (EMC) in volume ratio (1:1:1). Scanning electron microscopy (SEM) and X-ray diffraction (XRD) techniques were employed to evaluate morphology and structure of the separators before and after cycling performance tests to better understand structure-property correlation. …

Industry-University Collaboration: A University Of Dayton Model, Guru Subramanyam

Electrical and Computer Engineering Faculty Publications

This paper introduces industry-university collaboration activities currently in place at the University of Dayton's School of Engineering. These collaborations are important to prepare industry-ready graduates who excel in technical, entrepreneurial, and leadership skills. One of the key curricular components is the industry-sponsored multidisciplinary projects. Industry involvement in advisory committee, strategic research partnerships, and other forms are discussed.

Negative Index In A Lossy Chiral Metamaterial Under First-Order Material Dispersion Using A Drude Model, Tarig A. Algadey, Monish Ranjan Chatterjee

Electrical and Computer Engineering Faculty Publications

Using the Drude model for complex conductivity,phase and group velocities, and indices are calculated under first-order dispersion in chiral metamaterials. Conditions are derived for negative index, and the results compared with parametric analyses.