Other Electrical and Computer Engineering Commons^™

Owsnet: Towards Real-Time Offensive Words Spotting Network For Consumer Iot Devices, Bharath Sudharsan, Sweta Malik, Peter Corcoran, Pankesh Patel, John G. Breslin, Muhammad Intizar Ali

Publications

Every modern household owns at least a dozen of IoT devices like smart speakers, video doorbells, smartwatches, where most of them are equipped with a Keyword spotting(KWS) system-based digital voice assistant like Alexa. The state-of-the-art KWS systems require a large number of operations, higher computation, memory resources to show top performance. In this paper, in contrast to existing resource-demanding KWS systems, we propose a light-weight temporal convolution based KWS system named OWSNet, that can comfortably execute on a variety of IoT devices around us and can accurately spot multiple keywords in real-time without disturbing the device's routine functionalities.

When OWSNet …

Cognitive Digital Twins For Smart Manufacturing, Muhammad Intizar Ali, Pankesh Patel, John G. Breslin, Ramy Harik, Amit Sheth

Publications

Smart manufacturing or Industry 4.0, a trend initiated a decade ago, aims to revolutionize traditional manufacturing using technology-driven approaches. Modern digital technologies such as the Industrial Internet of Things (IIoT), Big Data Analytics, Augmented/Virtual Reality, and Artificial Intelligence (AI) are the key enablers of new smart manufacturing approaches. The digital twin is an emerging concept whereby a digital replica can be built of any physical object. Digital twins are becoming mainstream; many organizations have started to rely on digital twins to monitor, analyze, and simulate physical assets and processes. The current use of digital twins for smart manufacturing is largely …

A Reconfigurable Stretchable Liquid Metal Antenna, Phase Shifter, And Array For Wideband Applications, David M. Hensley

Electrical and Computer Engineering ETDs

While liquid metals, such as mercury, have been used in electronics for quite some time, the non-toxic gallium based liquid metals have caused an increase in research for liquid metal applications. Some of the potential applications that have been previously presented range from reconfigurable antennas, strain and pressure sensors, and speakers and microphones to name a few. The focus of this work is to provide further research into the use of gallium based liquid metals as a reconfigurable antenna, a phase shifter, and an array. This is done by designing, constructing, and characterizing each of these reconfigurable liquid metal (LM) …

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 …

Classification Of Primary Versus Metastatic Pancreatic Tumor Cells Using Multiple Biomarkers And Whole Slide Imaging, Poupack Pooshang Baghery

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

Pancreatic cancer is a challenging cancer with a high mortality rate and a 5-year survival rate between 2% to 9%. The role of biomarkers is crucial in cancer prognosis, diagnosis, and predicting the possible responses to a specific therapy. The Discovery and development of various types of biomarkers have been studied intensively in the hope of determining the best treatment approaches, better management, and possibly cure of this deadly cancer. However, metastasis, responsible for about 90% of the deaths from cancer, is still poorly understood. A few research that have investigated the expression of a particular biomarker or a panel …

Learning Discriminative And Efficient Attention For Person Re-Identification Using Agglomerative Clustering Frameworks, Kshitij Nikhal

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

Recent advancements like multiple contextual analysis, attention mechanisms, distance-aware optimization, and multi-task guidance have been widely used for supervised person re-identification (ReID), but the implementation and effects of such methods in unsupervised person ReID frameworks are non-trivial and unclear, respectively. Moreover, with increasing size and complexity of image- and video-based ReID datasets, manual or semi-automated annotation procedures for supervised ReID are becoming labor intensive and cost prohibitive, which is undesirable especially considering the likelihood of annotation errors increase with scale/complexity of data collections. Therefore, this thesis proposes a new iterative clustering framework that incorporates (a) two attention architectures that learn …

Pneumonia Radiograph Diagnosis Utilizing Deep Learning Network, Wesley O'Quinn

Honors College Theses

Pneumonia is a life-threatening respiratory disease caused by bacterial infection. The goal of this study is to develop an algorithm using Convolutional Neural Networks (CNNs) to detect visual signals for pneumonia in medical images and make a diagnosis. Although Pneumonia is prevalent, detection and diagnosis are challenging. The deep learning network AlexNet was utilized through transfer learning. A dataset consisting of 11,318 images was used for training, and a preliminary diagnosis accuracy of 72% was achieved.

Virtual Network Function Embedding Under Nodal Outage Using Deep Q-Learning, Swarna Bindu Chetty, Hamed Ahmadi, Sachin Sharma, Avishek Nag

Articles

With the emergence of various types of applications such as delay-sensitive applications, future communication networks are expected to be increasingly complex and dynamic. Network Function Virtualization (NFV) provides the necessary support towards efficient management of such complex networks, by virtualizing network functions and placing them on shared commodity servers. However, one of the critical issues in NFV is the resource allocation for the highly complex services; moreover, this problem is classified as an NP-Hard problem. To solve this problem, our work investigates the potential of Deep Reinforcement Learning (DRL) as a swift yet accurate approach (as compared to integer linear …

Households Electricity Consumption Analysis: A Bibliometric Approach, Gaikwad Sachin Ramnath, Harikrishnan R

Library Philosophy and Practice (e-journal)

The household electricity consumption ranks in the second position after the industrial electricity consumption, across the globe. This is because of the factors, which include, higher consumer income, electrification, digitalization and advancement in technologies. Moreover, the electricity demand is also depending on household characteristics, non-household characteristics and occupant’s behavior. The aim behind this study is to provide insights to researchers on household electricity consumption areas with different aspects, which includes factors affecting them, need of data collection, its approaches and techniques. To know about the research dedicated to the above-mentioned aspects, it is crucial to explore the Scopus database, refer …

Implementing Inverse Design Tools For Plasmonic Digital Logic Devices, Krishna Narayan, Mark C. Harrison

Engineering Faculty Articles and Research

Despite the benefits that optics and photonics have brought to improving communications, there remains a lack of commercialized optical computing devices and systems, which reduces the benefits of using light as an information-carrying medium. We are developing architectures and designs of photonic logic gates for creating larger-scale functional photonic logic circuits. In contrast to other approaches, we are focusing on the development of logic devices which can be cascaded in arbitrary ways to allow for more complex photonic integrated circuit design. Additionally, optical computing often uses on-off keying, which fails to take advantage of denser encoding schemes often used to …

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 …

Deep Learning For Anisoplanatic Optical Turbulence Mitigation In Long-Range Imaging, Matthew A. Hoffmire, Russell C. Hardie, Michael A. Rucci, Richard Van Hook, Barry K. Karch

Electrical and Computer Engineering Faculty Publications

We present a deep learning approach for restoring images degraded by atmospheric optical turbulence. We consider the case of terrestrial imaging over long ranges with a wide field-of-view. This produces an anisoplanatic imaging scenario where turbulence warping and blurring vary spatially across the image. The proposed turbulence mitigation (TM) method assumes that a sequence of short-exposure images is acquired. A block matching (BM) registration algorithm is applied to the observed frames for dewarping, and the resulting images are averaged. A convolutional neural network (CNN) is then employed to perform spatially adaptive restoration. We refer to the proposed TM algorithm as …

Biological Semantic Segmentation On Ct Medical Images For Kidney Tumor Detection Using Nnu-Net Framework, Andres Bergsneider

Master's Theses

Healthcare systems are constantly challenged with bottlenecks due to human-reliant operations, such as analyzing medical images. High precision and repeatability is necessary when performing a diagnostics on patients with tumors. Throughout the years an increasing number of advancements have been made using various machine learning algorithms for the detection of tumors helping to fast track diagnosis and treatment decisions. “Black Box” systems such as the complex deep learning networks discussed in this paper rely heavily on hyperparameter optimization in order to obtain the most ideal performance. This requires a significant time investment in the tuning of such networks to acquire …

Mechanisms Of Sensory Adaptation In The Primate Visual System, Boris Isaac Peñaloza Rojas

Electronic Theses and Dissertations

Under ecological conditions, the luminance impinging on the retina varies within a dynamic range of 220 dB. Stimulus contrast can also vary drastically within a scene, and eye movements leave little time for sampling luminance. In addition, the amount of information reaching our visual system far exceeds the brain’s information processing capacity. Given the limited dynamic range of its neurons and its limited capacity in processing visual information in real-time, the brain deploys both structural and functional solutions that work in tandem to adapt to the surroundings. In this work, employing visual psychophysics and computational neuroscience, we study the mechanisms …

Experimental And Design Effort To Understand A Wider Sense Of Memory Application, Nicholas Zogbi

Discovery Undergraduate Interdisciplinary Research Internship

Magnetic Random-Access Memory (mRAM) is a more efficient, smaller, and less power-hungry memory device that can be implemented into computers. Using Magnetic Tunnel Junctions (MTJ) we store memory in devices that are far less complex than other types of memory with just the use of currents and magnetic fields changing the data.

In collaboration with the System-on-Chip Extension Technologies (SoCET) and Computing Advances by Probabilistic Spin Logic (CAPSL) groups, we have been working on using the characteristics of MTJs to characterize available commercial mRAM devices so we can have a better understanding of the thresholds of the MTJs. The SoCET …

Dales Objects: A Large Scale Benchmark Dataset For Instance Segmentation In Aerial Lidar, Nina M. Singer, Vijayan K. Asari

Electrical and Computer Engineering Faculty Publications

We present DALES Objects, a large-scale instance segmentation benchmark dataset for aerial lidar. DALES Objects contains close to half a billion hand-labeled points, including semantic and instance segmentation labels. DALES Objects is an extension of the DALES (Varney et al., 2020) dataset, adding additional intensity and instance segmentation annotation. This paper provides an overview of the data collection, preprocessing, hand-labeling strategy, and final data format. We propose relevant evaluation metrics and provide insights into potential challenges when evaluating this benchmark dataset. Finally, we provide information about how researchers can access the dataset for their use at go.udayton.edu/dales3d.

Integration Of Robotic And Electro-Pneumatic Systems Using Advanced Control And Communication Schemes, Chinmay Kondekar

Dissertations, Master's Theses and Master's Reports

Modern industrial automation systems are designed by interconnecting various subsystems which work together to perform a process. The thesis project aims to integrate fragmented subsystems into a flexible and reconfigurable system through advanced communication protocols and perform a process to demonstrate the effectiveness of interconnected systems.

The system consists of three six-axis robots, one electro-pneumatic robot, and two conveyors connected using EthernetIP communication and hardwired connections. The interconnected system works together to perform machining of a workpiece using advanced control methods of CAD to robot path generation, central control through a PLC, and process control through HMI.

Standardized programming blocks …

Ieee Access Special Section Editorial: Trends And Advances In Bio-Inspired Image-Based Deep Learning Methodologies And Applications, Peter Peer, Carlos M. Travieso-Gonzalez, Vijayan K. Asari, Malay Kishore Dutta

Electrical and Computer Engineering Faculty Publications

Many of the technological advances we enjoy today have been inspired by biological systems due to their ease of operation and outstanding efficiency. Designing technological solutions based on biological inspiration has become a cornerstone of research in a variety of areas ranging from control theory and optimization to computer vision, machine learning, and artificial intelligence. Especially in the latter few areas, biologically relevant solutions are becoming increasingly important as we look for new ways to make artificial systems more efficient, intelligent, and overall effective.

Weed Recognition In Agriculture: A Mask R-Cnn Approach, Sruthi Keerthi Valicharla

Graduate Theses, Dissertations, and Problem Reports (ETD)

Recent interdisciplinary collaboration on deep learning has led to a growing interest in its application in the agriculture domain. Weed control and management are some of the crucial tasks in agriculture to maintain high crop productivity. The inception phase of weed control and management is to successfully recognize the weed plants, followed by providing a suitable management plan. Due to the complexities in agriculture images, such as similar colour and texture, we need to incorporate a deep neural network that uses pixel-wise grouping for identifying the plant species. In this thesis, we analysed the performance of one of the most …

Concusion Detection Headband Design, John Durkin, Noah Lewis, John Michel

Williams Honors College, Honors Research Projects

Concussion in sports is a prevalent medical issue. It can be difficult for medical professionals to diagnose concussions. With the fast pace nature of many sports, and the damaging effects of concussions, it is important that any concussion risks are assessed immediately. There is a growing trend of wearable technology that collects data such as steps, and provides the wearer with in-depth information regarding their performance. The Smart Headband project created a wearable that can record impact data and provide the wearer with a detailed analysis on their risk of sustaining a concussion. The Smart Headband uses accelerometers and gyroscopes …