http://hdl.handle.net/123456789/10343 Sat, 17 Oct 2026 02:50:47 GMT 2026-10-17T02:50:47Z http://hdl.handle.net/123456789/21856 Cryptography on Risc-V Systems: Ascon Algorithm on Cv32e40x Core Cv-X-If Based ISE using Pynq-Z1 Soc Fpga Ali Raza, 09-242242-001 In 2023 the National Institute of Standards and Technology (NIST) selected Ascon as the standard for lightweight cryptography (LWC), formalized as NIST SP 800-232. As Ascon becomes the basis for confdentiality, integrity and authentication on constrained devices, the cost of accelerating it on RISC-V is a pressing engineering question. RISC-V instruction set extension work has characterized Ascon authenticated encryption and hashing in detail, but three gaps remain: Ascon-MAC, Ascon-PRF and Ascon-PRFShort are largely unaddressed. Every comparable RISC-V work measures the CAESAR-era v1.2 specifcation rather than the standardized algorithms and none reports a single shared hardware permutation core measured on real silicon across the complete seven member family. This thesis therefore establishes what such an accelerator costs in performance, area and power on real hardware, and how its beneft is distributed across the seven members. A CV-X-IF tightly coupled Ascon-p accelerator was designed for a CV32E40X Embedded RISC-V core, synthesized and deployed on a Xilinx Zynq-7000 PYNQ-Z1 FPGA board. It occupies 597 LUTs and 368 flip-flops with no DSP or block RAM, and closes timing at 60 MHz with positive margin. The software baseline and the accelerated run execute on the same bitstream, differing only in one control register bit, and that baseline is hand-written RV32I assembly rather than the compiled C used in the comparable literature, making the ratios conservative. All 28 measurement points, spanning 0 to 1024 bytes and covering AsconAEAD128 under both associated-data conventions, passed NIST Known Answer Test verifcation in both modes. Speedups measured on hardware, not in simulation, range from 2.98x on the single call Ascon-PRFShort to 21.37x on Ascon-Hash256 at 1024 bytes. The area and timing are tool reports, power is a vectorless estimate, and no energy result is claimed. The beneft is not uniform. At a common 16 byte length the seven members span 3.41x to 11.12x from identical hardware, bounded not by the permutation they share but by the non-permutation work accompanying each call. To the author’s knowledge, this is the frst silicon measured characterization of a single shared Ascon accelerator serving the complete seven member SP 800-232 era family on a RISC-V core. Supervised by Dr. Syed Khawar Hussain Shah Thu, 01 Jan 2026 00:00:00 GMT http://hdl.handle.net/123456789/21856 2026-01-01T00:00:00Z http://hdl.handle.net/123456789/21857 Enhanced FGPA Implementations of Communication Protocol Receivers with Early Anomaly Detection Capabilities Naveed Iqbal, 09-242242-007 Communication protocols such as UART, and SPI remain widely used across embedded systems, avionics, automotive electronics, and industrial equipment. While these protocols are mature and reliable, their conventional receiver implementations generally report only basic errors (e.g., parity, framing, or synchronization faults). Such mechanisms are insuffcient for detecting subtle or intermittent anomalies caused by transmitterside inconsistencies, hardware degradations, signal integrity variations, or protocol-timing deviations. These irregularities often remain hidden in the testing phase. With advancements in Field-Programmable Gate Arrays (FPGAs), there is increasing potential to embed intelligent diagnostic capabilities directly within communication protocol receivers. This thesis proposes an enhanced approach of implementation and with integrated SelfMonitoring Receiver Implementation (SMRI) framework, a novel FPGA based approach that improves the existing receivers and integrates practical anomaly detection mechanisms into the receiver architecture itself. The SMRI framework is designed to identify issues that may not yet result in incorrect data reception but indicate an increased probability of failure under specifc conditions. The proposed research evaluates this framework using commonly used communication standard UART, and also give a brief touch to its use in SPI Protocol, demonstrating how builtin anomaly detection can enhance system validation, reliability, and predictive fault monitoring during early testing phases Supervised by Dr. Syed Khawar Hussain Shah Thu, 01 Jan 2026 00:00:00 GMT http://hdl.handle.net/123456789/21857 2026-01-01T00:00:00Z http://hdl.handle.net/123456789/14465 Classification of EEG Signals for Neuromarketing applications Syed Mohsin Ali Shah, 01-242192-008 Every year, more than 400 billion dollars is spent on marketing campaigns. It is a common practice to promote diverse customer goods through advertising campaigns in order to boost revenues and consumer awareness. The effectiveness of business investments in marketing campaigns is entirely dependent on consumers’ willingness and ability to describe how they feel after watching an advertisement. Conventional marketing techniques (e.g., television commercials and newspaper ads) are unaware of human emotions/response while watching the advertisements. Traditional advertising techniques seek to govern the consumer’s opinion toward a product, which may not reflect their actual behavior at the time of purchase. It is probable that advertisers misjudge consumer behavior because predicted opinions do not always correspond to consumers’ actual purchase behaviors. Neuromarketing is the new paradigm of understanding customer buyer behaviour, decision making as well as the prediction of their gestures for product utilization through an unconscious process. The field of neuromarketing has gained traction as means of bridging the gap between traditional advertising methods that focus on explicit consumer responses, and neuromarketing methodologies that focus on implicit consumer responses. Choice prediction allows it to figure out what buyers really desire about the product. Neuroscience information can be used in neuromarketing to know the behavior of a consumer with the help of brain activity using EEG signals. EEG-based preference recognition systems focus on three key phases. In previous studies, researchers did not focus on effective preprocessing and classification techniques of EEG signals, so in this study, an effective method for preprocessing and classification of EEG signals is proposed, using deep learning to determine the choices of consumers for various products by measuring their “liking” and “disliking” as neuromarketing applications. The proposed method involves effective preprocessing of EEG signals by removing noise and a synthetic minority oversampling technique (SMOTE) to deal with the class imbalance problem. The dataset employed in this study is a publicly available neuromarketing dataset. The dataset consists of EEG data recordings taken from 25 participants, shown different sorts of products. The responses of customers were recorded in terms of likes and dislikes. Automated features were extracted using a long-short term memory network (LSTM) and then concatenated with handcrafted features like power spectral density (PSD) and discrete wavelet transform (DWT) to create a complete feature set. The classification was done using the proposed hybrid classifier that optimizes the weights of two machine learning classifiers and one deep learning classifier and classifies the data between like and dislike. The machine learning classifiers include the Support Vector Machine (SVM), Random Forest (RF), and Deep Learning Classifier (DNN). The proposed hybrid model outperforms and achieves an accuracy of 96.89% among other different classifiers like RF, SVM, and DNN. In the proposed method, accuracy, sensitivity, and specificity were computed to evaluate and compare the proposed method with recent state-of-the-art methods. Supervised by Dr. Shehzad Khalid Sat, 01 Jan 2022 00:00:00 GMT http://hdl.handle.net/123456789/14465 2022-01-01T00:00:00Z http://hdl.handle.net/123456789/14467 Aerial Imagery Pile Burn Detection using Deep Learning Hoor Ul Ain Tahir, 01-242202-003 Wildfires are one of the costliest and deadliest natural disasters around the globe, affecting millions of acres of forest resources and threatening the lives of human and animals. Thousands of forest fires across the globe results in serious damage to the environment. Further, industrial explosions, domestic fires, farm fires, and wildfires are huge problem that causes negative effects on the environment contributing significantly towards the issue of climate change. Damage caused by such incidents are time-sensitive and can be fatal resulting in a huge loss to life and property if not timely dealt with. Recent advances in aerial images show that they can be beneficial in wildfire studies. Among different technologies and methods for collecting aerial images, drones have been used recently for manual/automatic monitoring of potential risk areas. Images received from the drones can be processed using vision and machine learning techniques for automated and timely detection of fires thus shortening the response time and reducing the damage caused by the fire whilst minimizing the cost of firefighting. Automated vision-based fire detection has therefore become an important research topic in recent years. Desired properties of good vision-based fire detection are low false alarm rate, fast response time, and high accuracy. This thesis presents a comprehensive literature review of recent vision-based approaches for the automated detection of fire from images and videos. It also includes computing the area under the fire and planning to mitigate the fire. The literature has broadly been categorized into classic vision/machine learning-based approaches and deep learning-based approaches. Based on the comparison of these approaches using a variety of datasets and performance metrics, it has been observed that deep learning-based approaches generally yield better performance as compared to classic vision/machine learning-based techniques. In this research, we further explored various deep learning alternatives for accurate fire detection. A Yolov5-based deep learning model has been proposed in this research for efficient region-based detection and segmentation of fire. Pixel level segmentation is also performed using Mask RCNN to estimate the area under the fire so that planning can be done to mitigate with the fire. The problem of availability of limited labeled training data as compared to the training samples required for deep learning-based model training is mitigated through variety of preprocessing and augmentation techniques. Comparison with existing vision-based fire segmentation approaches on publicly available datasets show the improved performance of proposed approach as compared to the competitors. Supervised by Dr. Shehzad Khalid Sat, 01 Jan 2022 00:00:00 GMT http://hdl.handle.net/123456789/14467 2022-01-01T00:00:00Z