Physics Commons^™

Intelligent Millimeter-Wave System For Human Activity Monitoring For Telemedicine, Abdullah K. Alhazmi, Mubarak A. Alanazi, Awwad H. Alshehry, Saleh M. Alshahry, Jennifer Jaszek, Cameron Djukic, Anna Brown, Kurt Jackson, Vamsy P. Chodavarapu

Electrical and Computer Engineering Faculty Publications

Telemedicine has the potential to improve access and delivery of healthcare to diverse and aging populations. Recent advances in technology allow for remote monitoring of physiological measures such as heart rate, oxygen saturation, blood glucose, and blood pressure. However, the ability to accurately detect falls and monitor physical activity remotely without invading privacy or remembering to wear a costly device remains an ongoing concern. Our proposed system utilizes a millimeter-wave (mmwave) radar sensor (IWR6843ISK-ODS) connected to an NVIDIA Jetson Nano board for continuous monitoring of human activity. We developed a PointNet neural network for real-time human activity monitoring that can …

Exponential Fusion Of Interpolated Frames Network (Efif-Net): Advancing Multi-Frame Image Super-Resolution With Convolutional Neural Networks, Hamed Elwarfalli, Dylan Flaute, Russell C. Hardie

Electrical and Computer Engineering Faculty Publications

Convolutional neural networks (CNNs) have become instrumental in advancing multi-frame image super-resolution (SR), a technique that merges multiple low-resolution images of the same scene into a high-resolution image. In this paper, a novel deep learning multi-frame SR algorithm is introduced. The proposed CNN model, named Exponential Fusion of Interpolated Frames Network (EFIF-Net), seamlessly integrates fusion and restoration within an end-to-end network. Key features of the new EFIF-Net include a custom exponentially weighted fusion (EWF) layer for image fusion and a modification of the Residual Channel Attention Network for restoration to deblur the fused image. Input frames are registered with subpixel …

A Patient-Specific Algorithm For Lung Segmentation In Chest Radiographs, Manawaduge Supun De Silva, Barath Narayanan Narayanan, Russell C. Hardie

Electrical and Computer Engineering Faculty Publications

Lung segmentation plays an important role in computer-aided detection and diagnosis using chest radiographs (CRs). Currently, the U-Net and DeepLabv3+ convolutional neural network architectures are widely used to perform CR lung segmentation. To boost performance, ensemble methods are often used, whereby probability map outputs from several networks operating on the same input image are averaged. However, not all networks perform adequately for any specific patient image, even if the average network performance is good. To address this, we present a novel multi-network ensemble method that employs a selector network. The selector network evaluates the segmentation outputs from several networks; on …

Electro-Optical Sensors For Atmospheric Turbulence Strength Characterization With Embedded Edge Ai Processing Of Scintillation Patterns, Ernst Polnau, Don L. N. Hettiarachchi, Mikhail A. Vorontsov

Electro-Optics and Photonics Faculty Publications

This study introduces electro-optical (EO) sensors (TurbNet sensors) that utilize a remote laser beacon (either coherent or incoherent) and an optical receiver with CCD camera and embedded edge AI computer (Jetson Xavier Nx) for in situ evaluation of the path-averaged atmospheric turbulence refractive index structure parameter C-n(2) at a high temporal rate. Evaluation of C-n(2) values was performed using deep neural network (DNN)-based real-time processing of short-exposure laser-beacon light intensity scintillation patterns (images) captured by a TurbNet sensor optical receiver. Several pre-trained DNN models were loaded onto the AI computer and used for TurbNet sensor performance evaluation in a set …

Towards A Low-Cost Solution For Gait Analysis Using Millimeter Wave Sensor And Machine Learning, Mubarak A. Alanazi, Abdullah K. Alhazmi, Osama Alsattam, Kara Gnau, Meghan Brown, Shannon Thiel, Kurt Jackson, Vamsy P. Chodavarapu

Electrical and Computer Engineering Faculty Publications

Human Activity Recognition (HAR) that includes gait analysis may be useful for various rehabilitation and telemonitoring applications. Current gait analysis methods, such as wearables or cameras, have privacy and operational constraints, especially when used with older adults. Millimeter-Wave (MMW) radar is a promising solution for gait applications because of its low-cost, better privacy, and resilience to ambient light and climate conditions. This paper presents a novel human gait analysis method that combines the micro-Doppler spectrogram and skeletal pose estimation using MMW radar for HAR. In our approach, we used the Texas Instruments IWR6843ISK-ODS MMW radar to obtain the micro-Doppler spectrogram …

Imnets: Deep Learning Using An Incremental Modular Network Synthesis Approach For Medical Imaging Applications, Redha A. Ali, Russell C. Hardie, Barath Narayanan Narayanan, Temesguen Messay

Electrical and Computer Engineering Faculty Publications

Deep learning approaches play a crucial role in computer-aided diagnosis systems to support clinical decision-making. However, developing such automated solutions is challenging due to the limited availability of annotated medical data. In this study, we proposed a novel and computationally efficient deep learning approach to leverage small data for learning generalizable and domain invariant representations in different medical imaging applications such as malaria, diabetic retinopathy, and tuberculosis. We refer to our approach as Incremental Modular Network Synthesis (IMNS), and the resulting CNNs as Incremental Modular Networks (IMNets). Our IMNS approach is to use small network modules that we call SubNets …

Microscopic Nuclei Classification, Segmentation, And Detection With Improved Deep Convolutional Neural Networks (Dcnn), Md Zahangir Alom, Vijayan K. Asari, Anil Parwani, Tarek M. Taha

Electrical and Computer Engineering Faculty Publications

Background Nuclei classification, segmentation, and detection from pathological images are challenging tasks due to cellular heterogeneity in the Whole Slide Images (WSI). Methods In this work, we propose advanced DCNN models for nuclei classification, segmentation, and detection tasks. The Densely Connected Neural Network (DCNN) and Densely Connected Recurrent Convolutional Network (DCRN) models are applied for the nuclei classification tasks. The Recurrent Residual U-Net (R2U-Net) and the R2UNet-based regression model named the University of Dayton Net (UD-Net) are applied for nuclei segmentation and detection tasks respectively. The experiments are conducted on publicly available datasets, including Routine Colon Cancer (RCC) classification and …

Towards Improved Inertial Navigation By Reducing Errors Using Deep Learning Methodology, Hua Chen, Tarek M. Taha, Vamsy P. Chodavarapu

Electrical and Computer Engineering Faculty Publications

Autonomous vehicles make use of an Inertial Navigation System (INS) as part of vehicular sensor fusion in many situations including GPS-denied environments such as dense urban places, multi-level parking structures, and areas with thick tree-coverage. The INS unit incorporates an Inertial Measurement Unit (IMU) to process the linear acceleration and angular velocity data to obtain orientation, position, and velocity information using mechanization equations. In this work, we describe a novel deep-learning-based methodology, using Convolutional Neural Networks (CNN), to reduce errors from MEMS IMU sensors. We develop a CNN-based approach that can learn from the responses of a particular inertial sensor …

Evaluating Deep-Learning Models For Debris-Covered Glacier Mapping, Zhiyuan Xie, Vijayan K. Asari, Umesh K. Haritashya

Electrical and Computer Engineering Faculty Publications

In recent decades, mountain glaciers have experienced the impact of climate change in the form of accelerated glacier retreat and other glacier-related hazards such as mass wasting and glacier lake outburst floods. Since there are wide-ranging societal consequences of glacier retreat and hazards, monitoring these glaciers as accurately and repeatedly as possible is important. However, the accurate glacier boundary, especially the debriscovered glacier (DCG) boundary, which is one of the primary inputs in many glacier analyses, remains a challenge even after many years of research using conventional remote sensing methods or machine-learning methods. The GlacierNet, a deep-learning-based approach, utilized the …

Resampling And Super-Resolution Of Hexagonally Sampled Images Using Deep Learning, Dylan Flaute, Russell C. Hardie, Hamed Elwarfalli

Electrical and Computer Engineering Faculty Publications

Super-resolution (SR) aims to increase the resolution of imagery. Applications include security, medical imaging, and object recognition. We propose a deep learning-based SR system that takes a hexagonally sampled low-resolution image as an input and generates a rectangularly sampled SR image as an output. For training and testing, we use a realistic observation model that includes optical degradation from diffraction and sensor degradation from detector integration. Our SR approach first uses non-uniform interpolation to partially upsample the observed hexagonal imagery and convert it to a rectangular grid. We then leverage a state-of-the-art convolutional neural network (CNN) architecture designed for SR …

Wavelength And Power Dependence On Multilevel Behavior Of Phase Change Materials, Gary A. Sevison, Joshua A. Burrow, Haiyun Guo, Andrew M. Sarangan, Joshua R. Hendrickson, Imad Agha

Electro-Optics and Photonics Faculty Publications

We experimentally probe the multilevel response of GeTe, Ge2Sb2Te5 (GST), and 4% tungsten-doped GST (W-GST) phase change materials (PCMs) using two wavelengths of light: 1550 nm, which is useful for telecom-applications, and near-infrared 780 nm, which is a standard wavelength for many experiments in atomic and molecular physics. We find that the materials behave differently with the excitation at the different wavelengths and identify useful applications for each material and wavelength. We discuss thickness variation in the thin films used as well and comment on the interaction of the interface between the material and the substrate with regard to the …

Optical Switching Performance Of Thermally Oxidized Vanadium Dioxide With An Integrated Thin Film Heater, Andrew M. Sarangan, Gamini Ariyawansa, Ilya Vitebskiy, Igor Anisimov

Electro-Optics and Photonics Faculty Publications

Optical switching performance of vanadium dioxide produced by thermal oxidation of vanadium is presented in this paper. A 100nm thick vanadium was oxidized under controlled conditions in a quartz tube furnace to produce approximately 200nm thick VO2. The substrate was appropriately coated on the front and back side to reduce reflection in the cold state, and an integrated thin film heater was fabricated to allow in-situ thermal cycling. Electrical measurements show a greater than three orders of magnitude change in resistivity during the phase transition. Optical measurements exhibit 70% transparency at 1500nm and about 15dB extinction across a wide spectral …

Guest Editorial: Edge Intelligence For Beyond 5g Networks, Yan Zhang, Zhiyong Feng, Hassnaa Moustafa, Feng Ye, Usman Javaid, Chunfen Cui

Electrical and Computer Engineering Faculty Publications

Beyond fifth-generation (B5G) networks, or so-called "6G", is the next-generation wireless communications systems that will radically change how Society evolves. Edge intelligence is emerging as a new concept and has extremely high potential in addressing the new challenges in B5G networks by providing mobile edge computing and edge caching capabilities together with Artificial Intelligence (AI) to the proximity of end users. In edge intelligence empowered B5G networks, edge resources are managed by AI systems for offering powerful computational processing and massive data acquisition locally at edge networks. AI helps to obtain efficient resource scheduling strategies in a complex environment with …

Color-Compressive Bilateral Filter And Nonlocal Means For High-Dimensional Images, Christina Karam, Kenjiro Sugimoto, Keigo Hirakawa

Electrical and Computer Engineering Faculty Publications

We propose accelerated implementations of bilateral filter (BF) and nonlocal means (NLM) called color-compressive bilateral filter (CCBF) and color-compressive nonlocal means (CCNLM). CCBF and CCNLM are random filters, whose Monte-Carlo averaged output images are identical to the output images of conventional BF and NLM, respectively. However, CCBF and CCNLM are considerably faster because the spatial processing of multiple color channels are combined into a single random filtering process. This implies that the complexity of CCBF and CCNLM is less sensitive to color dimension (e.g., hyperspectral images) relatively to other BF and NLM methods. We experimentally verified that the execution time …

Plasmon-Driven Nanowire Actuators For On-Chip Manipulation, Shuangyi Linghu, Zhaoqi Gu, Jinsheng Lu, Wei Fang, Zongyin Yang, Huakang Yu, Zhiyuan Li, Runlin Zhu, Jian Peng, Qiwen Zhan, Songlin Zhuang1, Min Gu, Fuxing Gu

Electro-Optics and Photonics Faculty Publications

Chemically synthesized metal nanowires are promising building blocks for next-generation photonic integrated circuits, but technological implementation in monolithic integration will be severely hampered by the lack of controllable and precise manipulation approaches, due to the strong adhesion of nanowires to substrates in non-liquid environments. Here, we demonstrate this obstacle can be removed by our proposed earthworm-like peristaltic crawling motion mechanism, based on the synergistic expansion, friction, and contraction in plasmon-driven metal nanowires in non-liquid environments. The evanescently excited sur- face plasmon greatly enhances the heating effect in metal nanowires, thereby generating surface acoustic waves to drive the nanowires crawling along …

Tunable Optical Filter Using Phase Change Materials For Smart Ir Night Vision Applications, Remona Heenkenda, Keigo Hirakawa, Andrew Sarangan

Electro-Optics and Photonics Faculty Publications

In this paper we present a tunable filter using Ge2Sb2Se4Te1 (GSST) phase change material. The design principle of the filter is based on a metal-insulator-metal (MIM) cavity operating in the reflection mode. This is intended for night vision applications that utilize 850nm as the illumination source. The filter allows us to selectively reject the 850nm band in one state. This is illustrated through several daytime and nighttime imaging applications.

Polarization-Selective Modulation Of Supercavity Resonances Originating From Bound States In The Continuum, Chan Kyaw, Riad Yahiaoui, Joshua A. Burrow, Viet Tran, Kyron Keelen, Wesley Sims, Eddie C. Red, Willie S. Rockward, Mikkel A. Thomas, Andrew M. Sarangan, Imad Agha, Thomas A. Searles

Electro-Optics and Photonics Faculty Publications

Bound states in the continuum (BICs) are widely studied for their ability to confine light, produce sharp resonances for sensing applications and serve as avenues for lasing action with topological characteristics. Primarily, the formation of BICs in periodic photonic band gap structures are driven by symmetry incompatibility; structural manipulation or variation of incidence angle from incoming light. In this work, we report two modalities for driving the formation of BICs in terahertz metasurfaces. At normal incidence, we experimentally confirm polarization driven symmetry-protected BICs by the variation of the linear polarization state of light. In addition, we demonstrate through strong coupling …

Atmospheric Turbulence Study With Deep Machine Learning Of Intensity Scintillation Patternsartem, Artem V. Vorontsov, Mikhail A. Vorontsov, Grigorii A. Fillimonov, Ernst Polnau

Electro-Optics and Photonics Faculty Publications

A new paradigm for machine learning-inspired atmospheric turbulence sensing is developed and applied to predict the atmospheric turbulence refractive index structure parameter using deep neural network (DNN)-based processing of short-exposure laser beam intensity scintillation patterns obtained with both: experimental measurement trials conducted over a 7 km propagation path, and imitation of these trials using wave-optics numerical simulations. The developed DNN model was optimized and evaluated in a set of machine learning experiments. The results obtained demonstrate both good accuracy and high temporal resolution in sensing. The machine learning approach was also employed to challenge the validity of several eminent atmospheric …

Artificial Neural Network Discovery Of A Switchable Metasurface Reflector, J. R. Thompson, J. A. Burrow, P. J. Shah, J. Slagle, E. S. Harper, A. Van Rynbach, I. Agha, M. S. Mills

Electro-Optics and Photonics Faculty Publications

Optical materials engineered to dynamically and selectively manipulate electromag- netic waves are essential to the future of modern optical systems. In this paper, we simulate various metasurface configurations consisting of periodic 1D bars or 2D pillars made of the ternary phase change material Ge2Sb2Te5 (GST). Dynamic switching behavior in reflectance is exploited due to a drastic refractive index change between the crystalline and amorphous states of GST. Selectivity in the reflection and transmission spectra is manipulated by tailoring the geometrical parameters of the metasurface. Due to the immense number of possible metasurface configurations, we train deep neural networks capable of …

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 …

Ensemble Lung Segmentation System Using Deep Neural Networks, Redha A. Ali, Russell C. Hardie, Hussin K. Ragb

Electrical and Computer Engineering Faculty Publications

Lung segmentation is a significant step in developing computer-aided diagnosis (CAD) using Chest Radiographs (CRs). CRs are used for diagnosis of the 2019 novel coronavirus disease (COVID-19), lung cancer, tuberculosis, and pneumonia. Hence, developing a Computer-Aided Detection (CAD) system would provide a second opinion to help radiologists in the reading process, increase objectivity, and reduce the workload. In this paper, we present the implementation of our ensemble deep learning model for lung segmentation. This model is based on the original DeepLabV3+, which is the extended model of DeepLabV3. Our model utilizes various architectures as a backbone of DeepLabV3+, such as …

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 …

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 …

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 …

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 …

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 …

Recursive Non-Local Means Filter For Video Denoising, Redha A. Ali, Russell C. Hardie

Electrical and Computer Engineering Faculty Publications

In this paper, we propose a computationally efficient algorithm for video denoising that exploits temporal and spatial redundancy. The proposed method is based on non-local means (NLM). NLM methods have been applied successfully in various image denoising applications. In the single-frame NLM method, each output pixel is formed as a weighted sum of the center pixels of neighboring patches, within a given search window.

The weights are based on the patch intensity vector distances. The process requires computing vector distances for all of the patches in the search window. Direct extension of this method from 2D to 3D, for video …

Speckle Effects In Target-In-The-Loop Laser Beam Projection Systems, Mikhail Vorontsov

Electro-Optics and Photonics Faculty Publications

In target-in-the-loop laser beam projection scenarios typical of remote sensing, directed energy, and adaptive optics applications, a transmitted laser beam propagates through an optically inhomogeneous medium toward a target, scatters off the target’s rough surface, and returns back to the transceiver plane. Coherent beam scattering off the randomly rough surface results in strong speckle modulation in the transceiver plane. This speckle modulation has been a long-standing challenge that limits performance of remote sensing, active imaging, and adaptive optics techniques. Using physics-based models of laser beam scattering off a randomly rough surface, we show that received speckle-field spatial and temporal characteristics …

Analysis Of The Joint Impact Of Atmospheric Turbulence And Refractivity On Laser Beam Propagation, Victor A. Kulikov, Mikhail Vorontsov

Electro-Optics and Photonics Faculty Publications

A laser beam propagation model that accounts for the joint effect of atmospheric turbulence and refractivity is introduced and evaluated through numerical simulations. In the numerical analysis of laser beam propagation, refractive index inhomogeneities along the atmospheric propagation path were represented by a combination of the turbulence-induced random fluctuations described in the framework of classical Kolmogorov turbulence theory and large-scale refractive index variations caused by the presence of an inverse temperature layer. The results demonstrate that an inverse temperature layer located in the vicinity of a laser beam’s propagation path may strongly impact the laser beam statistical characteristics including the …

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 …