This thesis presents a series of neural network classifiers for object detection in both optical and infrared images. The focus of this work is on efficient and accurate solutions. The thesis discusses the evolution of the highly efficient and tiny network Binary Classification Vision Transformer (BC-ViT) and how through thoughtful modifications and improvements, the BC-ViT can be utilized for tasks of increasing complexity. Chapter 2 discusses the creation of BC-ViT and its initial use case for underwater image classification of optical images. The BC-ViT is able to complete its task with an accuracy of 99.29\% while being comprised of a mere 15,981 total trainable parameters. Chapter 3, Waste Multi-Class Vision Transformer (WMC-ViT), introduces the usefulness of mindful algorithm design for the realm of multi-class classification on a mutually exclusive dataset. WMC-ViT shows that the task oriented design strategy allowed for a network to achieve an accuracy score of 94.27\% on a five class problem while still maintaining a tiny parameter count of 35,492. The final chapter demonstrates that by utilizing functional blocks of BC-ViT, a simple and effective target detection algorithm for infrared images can be created. The Edge Infrared Vision Transformer (EIR-ViT) showed admirable results with a high IoU …

Renewable power systems are becoming more affordable and provide better options than fossil-fuel generation, for not only the environment, but a benefit of a reduced cost of operation. Methods to optimize charging batteries from renewable technologies is an important subject for off-grid and micro-grids, and is becoming more relevant for larger installations. Overcharging or undercharging the battery can result in failure and reduction of battery life. The Arduino hybrid MPPT controller takes the advantage of solar and wind energy sources by controlling two systems simultaneously. The ability to manage two systems with one controller is better for an overall production of energy, cost, and manageability, at a minor expense of efficiency. The hybrid MPPT uses two synchronous buck DC-DC converters to control both wind and solar. The hybrid MPPT performed at a maximum of 93.6% efficiency, while the individual controller operated at a maximum 97.1% efficiency when working on the bench test. When designing the controller to manage power production from a larger generator, the inductor size was too large due to the frequency provided by the Arduino. A larger inductor means less allowable current to flow before the inductor becomes over saturated, reducing the efficiency of the controller. Utilizing …

Zero-knowledge proofs protocols are effective interactive methods to prove a node's identity without disclosing any additional information other than the veracity of the proof. They are implementable in several ways. In this thesis, I investigate the graph isomorphism based zero-knowledge proofs protocol. My experiments and analyses suggest that graph isomorphism can easily be solved for many types of graphs and hence is not an ideal solution for implementing ZKP.

In this work, we explored one material from the broad family of 2D semiconductors, namely WSe2 to serve as an enabler for advanced, low-power, high-performance nanoelectronics and optoelectronic devices. A 2D WSe2 based field-effect-transistor (FET) was designed and fabricated using electron-beam lithography, that revealed an ultra-high mobility of ~ 625 cm2/V-s, with tunable charge transport behavior in the WSe2 channel, making it a promising candidate for high speed Si-based complimentary-metal-oxide-semiconductor (CMOS) technology. Furthermore, optoelectronic properties in 2D WSe2 based photodetectors and 2D WSe2/2D MoS2 based p-n junction diodes were also analyzed, where the photoresponsivity R and external quantum efficiency were exceptional. The monolayer WSe2 based photodetector, fabricated with Al metal contacts, showed a high R ~502 AW-1 under white light illumination. The EQE was also found to vary from 2.74×101 % - 4.02×103 % within the 400 nm -1100 nm spectral range of the tunable laser source. The interfacial metal-2D WSe2 junction characteristics, which promotes the use of such devices for end-use optoelectronics and quantum scale systems, were also studied and the interfacial stated density Dit in Al/2D WSe2 junction was computed to be the lowest reported to date ~ 3.45×1012 cm-2 eV-1. We also examined the large exciton binding …

This thesis describes development of low cost indoor air quality (IAQ) monitoring system for research. It describes data collection of various parameters concentration present in indoor air and sends data back to host PC for further processing. Thesis gives detailed information about hardware and software implementation of IAQ monitoring system. Also discussed are building wireless ZigBee network, creating user friendly graphical user interface (GUI) and analysis of obtained results in comparison with professional benchmark system to check system reliability. Throughputs obtained are efficient enough to use system as a reliable IAQ monitor.

This thesis creates a new method for the ethical splitting of data as well as improvements to neural network architectures to increase performance. Ethical dataset splitting should be based on statistics from the data, this prevents artificial manipulation of the data that helps or hurts the performance of a network. This bias introduced to the dataset can also be present by using the popular method of randomly splitting data into datasets. To remove bias from dataset splitting, the splits of a dataset must be based on statistics from the data. Improving neural network architectures to increase performance is very important for a wide range of applications, especially for classification of heartbeats. Every improvement matters, especially when the application means that any errors could put the life of a person in danger. These advancements being applied to heartbeat classification have exciting implications for saving thousands of lives and billions of dollars. The presented methods can also be expanded to a wide variety of applications and adapted to different types of data as increasing performance and splitting up datasets is important in all fields of machine learning.

GNU Radio and OSSIE (Open-Source SCA (Software communication architecture) Implementation-Embedded) are two open source software toolkits for SDR (Software Defined Radio) developments, both of them can be supported by USRP (Universal Software Radio Peripheral). In order to compare the performance of these two toolkits, an FM receiver over GNU Radio and OSSIE are tested in my thesis, test results are showed in Chapter 4 and Chapter 5. Results showed that the FM receiver over GNU Radio has better performance, due to the OSSIE is lack of synchronization between USRP interface and the modulation /demodulation components. Based on this, the SISO (Single Input Single Output) communication system over GNU Radio is designed to transmit and receive sound or image files between two USRP equipped with RFX2400 transceiver at 2.45G frequency. Now, GNU Radio and OSSIE are widely used for academic research, but the future work based on GNU Radio and OSSIE can be designed to support MIMO, sensor network, and real time users etc.

Low Earth orbit (LEO) satellite systems have been proposed as a resource for combating the challenges in 5G network coverage and expanding connectivity to a global realm. This research focuses on the current architecture of LEO satellite constellations, with an emphasis on satellite coverage, visibility patterns and coordination schemes. Key-elements of integrating LEO satellites into the eMBB component of 5G are presented and a breakdown of potential link channel characteristics and physical layer performance metrics are described. The produced information allows for a justified analysis on the conceptualized integration.

This thesis covers applications of machine learning to the fields of remote sensing and environmental monitoring. First, a generalized background on the concepts, tools, and methods used throughout the remainder of the research project are introduced. Chapter 3 covers the implementation of artificial neural networks to improve low-cost particulate matter sensing networks using collocated high-quality sensors with varying dataset parameters. In Chapter 4, an attention-enhanced LSTM-Convolutional neural network is presented to reconstruct satellite-based aerosol optical depth data lost to atmospheric interference. Chapter 5 applies attention mechanisms and convolutional neural networks to the reconstruction and upsampling of satellite-based land surface temperature maps. Chapter 6 presents a model employing geospatial techniques and machine learning methods with a combination of ground-based and remote sensing data to produce a daily ultra-high resolution 30 meter mapping of the PM2.5 concentration across Denton County, Texas.

Modern power generation aims to utilize renewable energy sources such as solar power and wind to supply customers with power. This approach avoids exhaustion of fossil fuels as well as provides clean energy. Microgrids have become popular over the years, as they contain multiple renewable power sources and battery storage systems to supply power to the entities within the network. These microgrids can share power with the main grid or operate islanded from the grid. During an islanded scenario, self-sustainability is crucial to ensure balance between supply and demand within the microgrid. This can be accomplished by a smart microgrid that can monitor system conditions and respond to power imbalance by shedding loads based on priority. Such a method ensures security of the most important loads in the system and manages energy by automatically disconnecting lower priority loads until system conditions have improved. This thesis introduces a prioritized load shedding algorithm for the microgrid at the University of North Texas Discovery Park and highlight how such an energy management algorithm can add reliability to an islanded microgrid.

Sensor network plays a significant role in determining the performance of network inference tasks. A wireless sensor network with a large number of sensor nodes can be used as an effective tool for gathering data in various situations. One of the major issues in WSN is developing an efficient protocol which has a significant impact on the convergence of the network. Parameter estimation is one of the most important applications of sensor network. In order to model such large and complex networks for estimation, efficient strategies and algorithms which take less time to converge are being developed. To deal with this challenge, an approach of having multilayer network structure to estimate parameter and reach convergence in less time is estimated by comparing it with known gossip distributed algorithm. Approached Multicast multilayer algorithm on a network structure of Gaussian mixture model with two components to estimate parameters were compared and simulated with gossip algorithm. Both the algorithms were compared based on the number of iterations the algorithms took to reach convergence by using Expectation Maximization Algorithm.Finally a series of theoretical and practical results that explicitly showed that Multicast works better than gossip in large and complex networks for estimation in consensus …

Crystalline indium oxide nanowires were synthesized following optimization of growth parameters. Oxygen vacancies were found to impact the optical and electronic properties of the as-grown nanowires. Photoluminescence measurements showed a strong U.V emission peak at 3.18 eV and defect peaks in the visible region at 2.85 eV, 2.66 eV and 2.5 eV. The defect peaks are attributed to neutral and charged states of oxygen vacancies. Post-growth annealing in oxygen environment and passivation with sulphur are shown to be effective in reducing the intensity of the defect induced emission. The as-grown nanowires connected in an FET type of configuration shows n-type conductivity. A single indium oxide nanowire with ohmic contacts was found to be sensitive to gas molecules adsorbed on its surface.

The syndrome source coding for lossless data compression with side information based on fixed-length linear block codes is the main emphasis of this work. We demonstrate that the source entropy rate can be achieved for syndrome source coding with side information when the sources are correlated. Next, we examine employing LDPC codes to apply the channel and syndrome concepts in order to satisfy the Slepian Wolf limit. Our findings indicate that irregular codes perform significantly better when the compression ratio is larger. Additionally, we looked at how well different applications performed when running on two different mobile networks. We have tested those applications which are used in our day-to-day life. Our main focus is to make wireless communication much easier. We know that nowadays data is increasing which led to increase in the transfer of data. There are a lot of errors while doing so like channel error, bit error rate, jitter, etc. To overcome such kind of problems compression and decompression should be done effectively without any complexity to achieve a high performance ratio.

Consumer drones have used both standards such as Wi-Fi as well as proprietary communication protocols, such as DJI's OcuSync. While these methods are well suited to certain flying scenarios, they are limited in range to around 4.3 miles. Government and military unmanned aerial vehicles (UAVs) controlled through satellites allow for a global reach in a low-latency environment. To address the range issue of commercial UAVs, this thesis investigates using standardized cellular technologies for command and control of UAV systems. The thesis is divided into five chapters: Chapter 1 is the introduction to the thesis. Chapter 2 describes the equipment used as well as the test setup. This includes the drone used, the cellular module used, the microcontroller used, and a description of the software written to collect the data. Chapter 3 describes the data collection goals, as well as locations in the sky that were flown in order to gather experimental data. Finally, the results are presented in Chapter 4, which draws limited correlation between the collected data and flight readiness Chapter 5 wraps up the thesis with a conclusion and future areas for research are also presented.

Broadly defined, group testing is the study of finding defective items in a large set. In the medical infection setting, that implies classifying each member of a population as infected or uninfected, while minimizing the total number of tests.

Cognitive Radio (CR) technology creates the opportunity for unlicensed users to make use of the spectral band provided it does not interfere with any licensed user. It is a prominent tool with spectrum sensing functionality to identify idle channels and let the unlicensed users avail them. Thus, the CR technology provides the consumers access to a very large spectrum, quality spectral utilization, and energy efficiency due to spectral load balancing. However, the full potential of the CR technology can be realized only with CRs equipped with accurate mechanisms to predict/sense the spectral holes and vacant spectral bands without any prior knowledge about the characteristics of traffic in a real-time environment. Multi-layered perception (MLP), the popular neural network trained with the back-propagation (BP) learning algorithm, is a keen tool for classification of the spectral bands into "busy" or "idle" states without any a priori knowledge about the user system features. In this dissertation, we proposed the use of an evolutionary algorithm, Bacterial Foraging Optimization Algorithm (BFOA), for the training of the MLP NN. We have compared the performance of the proposed system with the traditional algorithm and with the Hybrid GA-PSO method. With the results of a simulation experiment that this …

This thesis deals with the decentralized autonomous system, in which individual nodes acting like peers, communicate and participate in collaborative tasks and decision making processes. An experimental test-bed is created using four Garcia robots. The robots act like peers and interact with each other using user datagram protocol (UDP) messages. Each robot continuously monitors for messages coming from other robots and respond accordingly. Each robot broadcasts its location to all the other robots within its vicinity. Robots do not have built-in global positioning system (GPS). So, an indoor localization method based on signal strength is developed to estimate robot's position. The signal strength that the robot gets from the nearby wireless access points is used to calculate the robot's position. Trilateration and fingerprint are some of the indoor localization methods used for this purpose. The communication functionality of the decentralized system has been tested and verified in the autonomous systems laboratory.

This thesis describes environmental data collection and transmission from the field to a server using Wi-Fi. Also discussed are components, radio wave propagation, received power calculations, and throughput tests. Measured receive power resulted close to calculated and simulated values. Throughput tests resulted satisfactory. The thesis provides detailed systematic procedures for Wi-Fi radio link setup and techniques to optimize the quality of a radio link.

One statement that we can make with absolute certainty in our current time is that wireless communication is now the standard and the de-facto type of communication. Cognitive radios are able to interpret the frequency spectrum and adapt. The aim of this work is to be able to predict whether a frequency channel is going to be busy or free in a specific time located in the future. To do this, the problem is modeled as a time series problem where each usage of a channel is treated as a sequence of busy and free slots in a fixed time frame. For this time series problem, the method being implemented is one of the latest, state-of-the-art, technique in machine learning for time series and sequence prediction: long short-term memory neural networks, or LSTMs.

This thesis aims to increase photovoltaic (PV) panel power efficiency by employing a cooling system based on water circulation, which represents an improved version of water flow based active cooling systems. Theoretical calculations involved finding the heat produced by the PV panel and the circulation water flow required to remove this heat. A data logger and a cooling system for a test panel of 20W was designed and employed to study the relationship between the PV panel surface temperature and its output power. This logging and cooling system includes an Arduino microcontroller extended with a data logging shield, temperature sensing probes, current sensors, and a DC water pump. Real-time measurements were logged every minute for one or two day periods under various irradiance and air temperature conditions. For these experiments, a load resistance was chosen to operate the test panel at its maximum power point. Results indicate that the cooling system can yield an improvement of 10% in power production. Based on the observations from the test panel experiments, a cooling system was devised for a PV panel array of 640 W equipped with a commercial charge controller. The test data logger was repurposed for this larger system. An identical …

My thesis is to understand the concept of compressive sensing algorithms. Compressive sensing will be a future alternate technique for the Nyquist rate, specific to some applications where sparsity property plays a major role. Software implementation of compressive sensing (CS) takes more time to reconstruct a signal from CS measurements, so we use the orthogonal matching pursuit and basis pursuit algorithms. We have used an image size of 256x256 is used for reconstruction and also implemented a field-programmable gate array (FPGA) of the orthogonal matching pursuit using an image.

This thesis presents the rate distortion analysis of conditional motion estimation, a process in which motion computation is restricted to only active pixels in the video. We model active pixels as independent and identically distributed Gaussian process and inactive pixels as Gaussian-Markov process and derive the rate distortion function based on conditional motion estimation. Rate-Distortion curves for the conditional motion estimation scheme are also presented. In addition this thesis also presents the hardware implementation of a block based motion estimation algorithm. Block matching algorithms are difficult to implement on FPGA chip due to its complexity. We implement 2D-Logarithmic search algorithm to estimate the motion vectors for the image. The matching criterion used in the algorithm is Sum of Absolute Differences (SAD). VHDL code for the motion estimation algorithm is verified using ISim and is implemented using Xilinx ISE Design tool. Synthesis results for the algorithm are also presented.

Electrocardiography (ECG) signal transmitter is the device used to transmit the electrical signals of the heart to the remote machine. These electrical signals are ECG signals caused due to electrical activities in the heart. ECG signals have very low amplitude and frequency; hence amplification of the signals is needed to strengthen the signal. Conversion of the amplified signal into digital information and transmitting that information without losing any data is the key. This information is further used in monitoring the heart.

Multimedia environmental monitoring involves capturing valuable visual and audio information from the field station. This will permit the environmentalists and researchers to analyze the habitat and vegetation of a region with respect to other environmental specifics like temperature, soil moisture, etc. This thesis deals with the development of a test bed for multimedia monitoring by capturing image information and making it available for the public. A USB camera and a Single board computer are used to capture images at a specified frequency. A web-client is designed to display the image data and establish a secured remote access to reconfigure the field station. The development includes two modes of image acquisition including a basic activity recognition algorithm. Good quality images are captured with the cost for development of the system being less than 2 hundred dollars.