Signal Processing Commons^™

Multilayer Perceptron With Auto Encoder Enabled Deep Learning Model For Recommender Systems, Subhashini Narayan

Future Computing and Informatics Journal

In this modern world of ever-increasing one-click purchases, movie bookings, music, health- care, fashion, the need for recommendations have increased the more. Google, Netflix, Spotify, Amazon and other tech giants use recommendations to customize and tailor their search engines to suit the user’s interests. Many of the existing systems are based on older algorithms which although have decent accuracies, require large training and testing datasets and with the emergence of deep learning, the accuracy of algorithms has further improved, and error rates have reduced due to the use of multiple layers. The need for large datasets has declined as well. …

Deep Feature Learning For Fog Episodes Prediction In Patients With Pd, Hadeer Elziaat, Nashwa El-Bendary, Ramdan Mowad

Future Computing and Informatics Journal

A common symptom of Parkinson's Disease is Freezing of Gait (FoG) that causes an interrupt of the forward progression of the patient’s feet while walking. Therefore, Freezing of Gait episodes is always engaged to the patient's falls. This paper proposes a model for Freezing of Gait episodes detection and prediction in patients with Parkinson's Disease. Predicting Freezing of Gait in this paper considers as a multi-class classification problem with 3 classes namely, FoG, pre-FoG, and walking episodes. In this paper, the extracted feature scheme applied for the detection and the prediction of FoG is Convolutional Neural Network (CNN) spectrogram time-frequency …

Data Forgery Detection In Automatic Generation Control: Exploration Of Automated Parameter Generation And Low-Rate Attacks, Yatish R. Dubasi

Computer Science and Computer Engineering Undergraduate Honors Theses

Automatic Generation Control (AGC) is a key control system utilized in electric power systems. AGC uses frequency and tie-line power flow measurements to determine the Area Control Error (ACE). ACE is then used by the AGC to adjust power generation and maintain an acceptable power system frequency. Attackers might inject false frequency and/or tie-line power flow measurements to mislead AGC into falsely adjusting power generation, which can harm power system operations. Various data forgery detection models are studied in this thesis. First, to make the use of predictive detection models easier for users, we propose a method for automated generation …

Distance-Based Formation Control Using Decentralized Sensing With Infrared Photodiodes, Steven Williams

LSU Master's Theses

This study presents an onboard sensor system for determining the relative positions of mobile robots, which is used in decentralized distance-based formation controllers for multi-agent systems. This sensor system uses infrared photodiodes and LEDs; its effective use requires coordination between the emitting and detecting robots. A technique is introduced for calculating the relative positions based on photodiode readings, and an automated calibration system is designed for future maintenance. By measuring the relative positions of their neighbors, each robot is capable of running an onboard formation controller, which is independent of both a centralized controller and a global positioning-like system (e.g., …

Simulating A Mobile Wireless Sensor Network Monitoring The Air Force Marathon, Matthew D. Eilertson

Theses and Dissertations

This thesis explores the feasibility of deploying a mobile Wireless Sensor Networks (WSN) to the Air Force (AF) Marathon in support of Air Force Research Laboratory (AFRL) research of sensor and networking infrastructure in denied or degraded environments. A simulation called MarathonSim is developed in the Objective Modular Network Testbed in C++ (OMNeT++) Discrete Event Simulator to test the performance of a mobile WSN. A full factorial design using numbers of runners, transmission powers, and routing protocols is executed to measure Packet Delivery Ratio (PDR) to a central database, average end-to-end delay of application packets, and average power consumed per …

Time Series Data Analysis Using Machine Learning-(Ml) Approach, Mvv Prasad Kantipudi Dr., Pradeep Kumar N.S Dr., S.Sreenath Kashyap Dr., Ss Anusha Vemuri Ms

Library Philosophy and Practice (e-journal)

Healthcare benefits related to continuous monitoring of human movement and physical activity can potentially reduce the risk of accidents associated with elderly living alone at home. Based on the literature review, it is found that many studies focus on human activity recognition and are still active towards achieving practical solutions to support the elderly care system. The proposed system has introduced a joint approach of machine learning and signal processing technology for the recognition of human's physical movements using signal data generated by accelerometer sensors. The framework adopts the concept of DSP to select very descriptive feature sets and uses …

Artificial Intelligence Aided Receiver Design For Wireless Communication Systems, Wenjie Xu

Theses, Dissertations and Capstones

Physical layer (PHY) design in the wireless communication field realizes gratifying achievements in the past few decades, especially in the emerging cellular communication systems starting from the first generation to the fifth generation (5G). With the gradual increase in technical requirements of large data processing and end-to-end system optimization, introducing artificial intelligence (AI) in PHY design has cautiously become a trend. A deep neural network (DNN), one of the population techniques of AI, enables the utilization of its ‘learnable’ feature to handle big data and establish a global system model. In this thesis, we exploited this characteristic of DNN as …

Analog & Digital Remote Synthesizer, Adam Brunner, Andrew Cihon-Scott, Scott Grisso, Linus Wright

Williams Honors College, Honors Research Projects

The purpose of this project is to develop and design an analog synthesizer musical instrument that integrates embedded digital hardware into the design to enable control from a remote source. The use of digital hardware enables the potential for a wide range of convenient features such as sound profile saving and loading, output recording functionality, and the ability to accept digital input from another musical instrument utilizing the Musical Instrument Digital Interface (MIDI). In addition to the synthesizer itself, this project also includes the design of a companion application that can be hosted on a wide variety of consumer computing …

Deep Learning Assisted Intelligent Visual And Vehicle Tracking Systems, Liang Xu

Theses and Dissertations

Sensor fusion and tracking is the ability to bring together measurements from multiple sensors of the current and past time to estimate the current state of a system. The resulting state estimate is more accurate compared with the direct sensor measurement because it balances between the state prediction based on the assumed motion model and the noisy sensor measurement. Systems can then use the information provided by the sensor fusion and tracking process to support more-intelligent actions and achieve autonomy in a system like an autonomous vehicle. In the past, widely used sensor data are structured, which can be directly …

Light Loaded Automated Guided Vehicle, Marcus Radtka, Nazar Paramashchuk, Lawrence Shevock

Williams Honors College, Honors Research Projects

The objective of the locomotion system was to design and implement the mechanical, electrical, and software related functions to ensure the LLAGV had the capability of maneuvering its surroundings. The LLAGV’s motors were represented in an open loop transfer function to utilize RPM feedback and a compensator when needed. The modeled compensator helped control the LLAGV’s speed and acceleration, enabling further control of the LLAGV. The internal circuitry has the means to properly distributed power to all components and allowed the user to control the LLAGV to their desire. The application software within the LLAGV locomotion system (LLAGV-LS) had consideration …

Energy Considerations In Blockchain-Enabled Applications, Cesar Enrique Castellon Escobar

UNF Graduate Theses and Dissertations

Blockchain-powered smart systems deployed in different industrial applications promise operational efficiencies and improved yields, while mitigating significant cybersecurity risks pertaining to the main application. Associated tradeoffs between availability and security arise at implementation, however, triggered by the additional resources (e.g., memory, computation) required by each blockchain-enabled host. This thesis applies an energy-reducing algorithmic engineering technique for Merkle Tree root and Proof of Work calculations, two principal elements of blockchain computations, as a means to preserve the promised security benefits but with less compromise to system availability. Using pyRAPL, a python library to measure computational energy, we experiment with both the …

Improve The Prototype Of Low-Cost Near-Infrared Diffuse Optical Imaging System, Chen Xu, Mohammed Z. Shakil

Publications and Research

Diffuse Optical Tomography (DOT) and Optical Spectroscopy using near-infrared (NIR) diffused light has demonstrated great potential for the initial diagnosis of tumors and in the assessment of tumor vasculature response to neoadjuvant chemotherapy. The aims of this project are 1) to test the different types of LEDs in the near-infrared range, and design the driving circuit, and test the modulation of LEDs at different frequencies; 2) to test the APDs as a detector, and build the receiver system and compare efficiency with pre-built systems. In this project, we are focusing on creating a low-cost infrared transmission system for tumor and …

The Role Of Network Components In Improving The Reliability And Survivability Of Mobile Communication Networks, Dilmurod Davronbekov, Utkir Karimovich Matyokubov

Acta of Turin Polytechnic University in Tashkent

This article compares the different architectures of mobile communication networks (MCN) and examines the survivability of the network. Typical survival strategies for improving MCN survivability, failure mitigation strategies for network elements, wireless network survival rates, failure scenarios at MCN levels, and survival indicators are presented. The importance of fiber-optic communication in the construction of communication lines between MCN components has been studied. The issue of designing MCNs in a cost-effective and highly viable way is considered, and the necessary expressions of the design process are given.

A Study Of Static And Dynamic Characteristics Of Multifunctional Signal Converters, Akmal Abdumalikov

Chemical Technology, Control and Management

The issues of continuity, accuracy, speed and reliability of signal conversion, which are the main problems of quality control and management of production processes, remain relevant. Research shows that in practice there are different signal variables, the study of which is highly formalized in a number of modeling tasks and basic classification studies, in particular transients in converters, its sources and elements requires a unified mathematical approach, that is, visual, highly formalized modeling and research based on it. The paper presents a graph model of multifunctional signal converters that provide microprocessor and electronic devices with signals in the form of …

Signals In The Soil: An Introduction To Wireless Underground Communications, Abdul Salam, Usman Raza

Faculty Publications

In this chapter, wireless underground (UG) communications are introduced. A detailed overview of WUC is given. A comprehensive review of research challenges in WUC is presented. The evolution of underground wireless is also discussed. Moreover, different component of UG communications is wireless. The WUC system architecture is explained with a detailed discussion of the anatomy of an underground mote. The examples of UG wireless communication systems are explored. Furthermore, the differences of UG wireless and over-the-air wireless are debated. Different types of wireless underground channel (e.g., In-Soil, Soil-to-Air, and Air-to-Soil) are reported as well.

Underground Phased Arrays And Beamforming Applications, Abdul Salam, Usman Raza

Faculty Publications

This chapter presents a framework for adaptive beamforming in underground communication. The wireless propagation is thoroughly analyzed to develop a model using the soil moisture as an input parameter to provide feedback mechanism while enhancing the system performance. The working of array element in the soil is analyzed. Moreover, the effect of soil texture and soil moisture on the resonant frequency and return loss is studied in detail. The wave refraction from the soil–air interface highly degrades the performance of the system. Furthermore, to beam steering is done to achieve high gain for lateral component improving the UG communication. The …

Current Advances In Internet Of Underground Things, Abdul Salam, Usman Raza

Faculty Publications

The latest developments in Internet of Underground Things are covered in this chapter. First, the IOUT Architecture is discussed followed by the explanation of the challenges being faced in this paradigm. Moreover, a comprehensive coverage of the different IOUT components is presented that includes communications, sensing, and system integration with the cloud. An in-depth coverage of the applications of the IOUT in various disciplines is also surveyed. These applications include areas such as decision agriculture, pipeline monitoring, border control, and oil wells.

How Can 5g Make Our Lives Better?, Firas Slewa Dawod

International Programs

Our lives will be significantly improved with the advent of the new cellular wireless technology due to all its new features and applications. This Poster discusses the main features and application of 5G technology and its positive impact on society, in particular facilitating interactive and smart communities.

Learning Deep Architectures For Power Systems Operation And Analysis, Mahdi Khodayar

Electrical Engineering Theses and Dissertations

With the rapid increase in size and computational complexities of power systems, the need for powerful computational models to capture strong patterns from energy datasets is emerged. In this thesis, we provide a comprehensive review on recent advances in deep neural architectures that lead to significant improvements in classification and regression problems in the area of power engineering. Furthermore, we introduce our novel deep learning methodologies proposed for a large variety of applications in this area. First, we present the interval deep probabilistic modeling for wind speed forecasting. Incorporating the Rough Set Theory into deep neural networks, we create an …

Three-Dimensional (3d) Reconstruction Of Computed Tomography (Ct) Abdominal Images Using Visualization Toolkit (Vtk), Mat Saad Afifah Husna

Student Works (2020-2029)

A computerized tomography (CT) or computerized axial tomography (CAT) scan combines data from several X-raysito produce a detailed image of structures inside the body. CT scans produce 2D of a “slice” or section of the abdomen but the data can also be used to construct 3-dimensional images. However, CT scan unable to accurately represent the internal structure of soft tissues and soft-tissue lesions. Therefore, using the program in Visualization Tool Kit (VTK) is needed to construct a much more clearer 3D image. To reconstruct 3D images from 2D images of a “slice” or section of abdomen which will be resulting …

Cup-Net: Compressed Ultrafast Photography Using Convolutional Neural Networks, Matthew Parker

ENGS 88 Honors Thesis (AB Students)

Compressed ultrafast photography (CUP) is a cutting-edge imaging technique that uses a variation of the traditional streak camera to obtain video at 100 billion frames per second with a single exposure. In order to achieve this level of temporal detail, CUP leverages compressed sensing (CS). Compressed sensing theory states that a compressed representation of an image can be directly acquired using a non-adaptive measurement matrix so long as the encoding matrix follows certain properties such as restrictive isometry and incoherence. This compressed representation of the original scene can later be reconstructed back into the original form. CUP applies CS by …

Biometric Identification With Ecg Signals, Connor Lindstrom, Jonathan Wood, Jacob Torchia, Jonathan Lee

Electrical Engineering

This project introduces a new form of biometric identification with an ECG signal with the use of machine learning concepts. The ECG signal makes a good candidate for identification because of its unique characteristics that make it easy to distinguish individuals from one another. A patient who has previously had ECG scans stored in a database before, can be verified using this program. This project has the capability of identifying a person or verifying a person solely using their ECG signal. Utilizing this biometric identification, hospitals would be able to add to the reliability of their identification process. Additionally, companies …

An Fpga-Based Hardware Accelerator For The Digital Image Correlation Engine, Keaten Stokke

Graduate Theses and Dissertations

The work presented in this thesis was aimed at the development of a hardware accelerator for the Digital Image Correlation engine (DICe) and compare two methods of data access, USB and Ethernet. The original DICe software package was created by Sandia National Laboratories and is written in C++. The software runs on any typical workstation PC and performs image correlation on available frame data produced by a camera. When DICe is introduced to a high volume of frames, the correlation time is on the order of days. The time to process and analyze data with DICe becomes a concern when …

Reinforcement Learning In Self Organizing Cellular Networks, Roohollah Amiri

Boise State University Theses and Dissertations

Self-organization is a key feature as cellular networks densify and become more heterogeneous, through the additional small cells such as pico and femtocells. Self- organizing networks (SONs) can perform self-configuration, self-optimization, and self-healing. These operations can cover basic tasks such as the configuration of a newly installed base station, resource management, and fault management in the network. In other words, SONs attempt to minimize human intervention where they use measurements from the network to minimize the cost of installation, configuration, and maintenance of the network. In fact, SONs aim to bring two main factors in play: intelligence and autonomous adaptability. …

Virtual Satcom, Long Range Broadband Digital Communications, Dennis George Watson

Electrical & Computer Engineering Theses & Dissertations

The current naval strategy is based on a distributed force, networked together with high-speed communications that enable operations as an intelligent, fast maneuvering force. Satellites, the existing network connector, are weak and vulnerable to attack. HF is an alternative, but it does not have the information throughput to meet the distributed warfighting need. The US Navy does not have a solution to reduce dependency on space-based communication systems while providing the warfighter with the required information speed.

Virtual SATCOM is a solution that can match satellite communications (SATCOM) data speed without the vulnerable satellite. It is wireless communication on a …

Deep Cellular Recurrent Neural Architecture For Efficient Multidimensional Time-Series Data Processing, Lasitha S. Vidyaratne

Electrical & Computer Engineering Theses & Dissertations

Efficient processing of time series data is a fundamental yet challenging problem in pattern recognition. Though recent developments in machine learning and deep learning have enabled remarkable improvements in processing large scale datasets in many application domains, most are designed and regulated to handle inputs that are static in time. Many real-world data, such as in biomedical, surveillance and security, financial, manufacturing and engineering applications, are rarely static in time, and demand models able to recognize patterns in both space and time. Current machine learning (ML) and deep learning (DL) models adapted for time series processing tend to grow in …

A Comparative Evaluation Of The Detection And Tracking Capability Between Novel Event-Based And Conventional Frame-Based Sensors, James P. Boettiger

Theses and Dissertations

Traditional frame-based technology continues to suffer from motion blur, low dynamic range, speed limitations and high data storage requirements. Event-based sensors offer a potential solution to these challenges. This research centers around a comparative assessment of frame and event-based object detection and tracking. A basic frame-based algorithm is used to compare against two different event-based algorithms. First event-based pseudo-frames were parsed through standard frame-based algorithms and secondly, target tracks were constructed directly from filtered events. The findings show there is significant value in pursuing the technology further.

Handheld Data Analyzer, Nicholas Shade, Jake Herman, Doug Kern, Graham Hazlett, Anita Richardson

ENGS 89/90 Reports

The goal of this project is to design and build a handheld data analyzer prototype paired with an iPad app that our sponsor can further develop into a marketable product. The system should allow technicians to easily collect vibration data from IEPE accelerometers, inspect the data, and upload the reading to our sponsor’s database system for further analysis.

Coverage Guided Differential Adversarial Testing Of Deep Learning Systems, Jianmin Guo, Houbing Song, Yue Zhao, Yu Jiang

Publications

Deep learning is increasingly applied to safety-critical application domains such as autonomous cars and medical devices. It is of significant importance to ensure their reliability and robustness. In this paper, we propose DLFuzz, the coverage guided differential adversarial testing framework to guide deep learing systems exposing incorrect behaviors. DLFuzz keeps minutely mutating the input to maximize the neuron coverage and the prediction difference between the original input and the mutated input, without manual labeling effort or cross-referencing oracles from other systems with the same functionality. We also design multiple novel strategies for neuron selection to improve the neuron coverage. The …

Visual Music Assistant, David Klett

Williams Honors College, Honors Research Projects

The Visual Music Assistant system provides an augmented reality experience via Microsoft's HoloLens device. The application we will develop will provide an intuitive user interface to learn how to play on a keyboard (88-key piano).