Electrical & Computer Engineering Department Theses and Dissertations

Permanent URI for this collection

Information about the Purdue School of Engineering and Technology Graduate Degree Programs available at IUPUI can be found at: http://www.engr.iupui.edu/academics.shtml


Recent Submissions

Now showing 1 - 10 of 217
  • Item
    Integrating Data-driven Control Methods with Motion Planning: A Deep Reinforcement Learning-based Approach
    (2023-12) Prabu, Avinash; Li, Lingxi; Chen, Yaobin; King, Brian; Tian, Renran
    Path-tracking control is an integral part of motion planning in autonomous vehicles, in which the vehicle's lateral and longitudinal positions are controlled by a control system that will provide acceleration and steering angle commands to ensure accurate tracking of longitudinal and lateral movements in reference to a pre-defined trajectory. Extensive research has been conducted to address the growing need for efficient algorithms in this area. In this dissertation, a scenario and machine learning-based data-driven control approach is proposed for a path-tracking controller. Firstly, a Deep Reinforcement Learning model is developed to facilitate the control of longitudinal speed. A Deep Deterministic Policy Gradient algorithm is employed as the primary algorithm in training the reinforcement learning model. The main objective of this model is to maintain a safe distance from a lead vehicle (if present) or track a velocity set by the driver. Secondly, a lateral steering controller is developed using Neural Networks to control the steering angle of the vehicle with the main goal of following a reference trajectory. Then, a path-planning algorithm is developed using a hybrid A* planner. Finally, the longitudinal and lateral control models are coupled together to obtain a complete path-tracking controller that follows a path generated by the hybrid A* algorithm at a wide range of vehicle speeds. The state-of-the-art path-tracking controller is also built using Model Predictive Control and Stanley control to evaluate the performance of the proposed model. The results showed the effectiveness of both proposed models in the same scenario, in terms of velocity error, lateral yaw angle error, and lateral distance error. The results from the simulation show that the developed hybrid A* algorithm has good performance in comparison to the state-of-the-art path planning algorithms.
  • Item
    Wearable Big Data Harnessing with Deep Learning, Edge Computing and Efficiency Optimization
    (2023-12) Zou, Jiadao; Zhang, Qingxue; King, Brian; Christopher, Lauren; Chien, Stanley
    In this dissertation, efforts and innovations are made to advance subtle pattern mining, edge computing, and system efficiency optimization for biomedical applications, thereby advancing precision medicine big data. Brain visual dynamics encode rich functional and biological patterns of the neural system, promising for applications like intention decoding, cognitive load quantization and neural disorder measurement. We here focus on the understanding of the brain visual dynamics for the Amyotrophic lateral sclerosis (ALS) population. We leverage a deep learning framework for automatic feature learning and classification, which can translate the eye Electrooculography (EOG) signal to meaningful words. We then build an edge computing platform on the smart phone, for learning, visualization, and decoded word demonstration, all in real-time. In a further study, we have leveraged deep transfer learning to boost EOG decoding effectiveness. More specifically, the model trained on basic eye movements is leveraged and treated as an additional feature extractor when classifying the signal to the meaningful word, resulting in higher accuracy. Efforts are further made to decoding functional Near-Infrared Spectroscopy (fNIRS) signal, which encodes rich brain dynamics like the cognitive load. We have proposed a novel Multi-view Multi-channel Graph Neural Network (mmGNN). More specifically, we propose to mine the multi-channel fNIRS dynamics with a multi-stage GNN that can effectively extract the channel- specific patterns, propagate patterns among channels, and fuse patterns for high-level abstraction. Further, we boost the learning capability with multi-view learning to mine pertinent patterns in temporal, spectral, time-frequency, and statistical domains. Massive-device systems, like wearable massive-sensor computers and Internet of Things (IoTs), are promising in the era of big data. The crucial challenge is about how to maximize the efficiency under coupling constraints like energy budget, computing, and communication. We propose a deep reinforcement learning framework, with a pattern booster and a learning adaptor. This framework has demonstrated optimally maximizes the energy utilization and computing efficiency on the local massive devices under a one-center fifteen-device circumstance. Our research and findings are expected to greatly advance the intelligent, real-time, and efficient big data harnessing, leveraging deep learning, edge computing, and efficiency optimization.
  • Item
    Object Detection Using Vision Transformed EfficientDet
    (2023-08) Kar, Shreyanil; El-Sharkawy, Mohamed A.; King, Brian S.; Rizkalla, Maher E.
    This research presents a novel approach for object detection by integrating Vision Transformers (ViT) into the EfficientDet architecture. The field of computer vision, encompassing artificial intelligence, focuses on the interpretation and analysis of visual data. Recent advancements in deep learning, particularly convolutional neural networks (CNNs), have significantly improved the accuracy and efficiency of computer vision systems. Object detection, a widely studied application within computer vision, involves the identification and localization of objects in images. The ViT backbone, renowned for its success in image classification and natural language processing tasks, employs self-attention mechanisms to capture global dependencies in input images. However, ViT’s capability to capture fine-grained details and context information is limited. To address this limitation, the integration of ViT into the EfficientDet architecture is proposed. EfficientDet is recognized for its efficiency and accuracy in object detection. By combining the strengths of ViT and EfficientDet, the proposed integration enhances the network’s ability to capture fine-grained details and context information. It leverages ViT’s global dependency modeling alongside EfficientDet’s efficient object detection framework, resulting in highly accurate and efficient performance. Noteworthy object detection frameworks utilized in the industry, such as RetinaNet, EfficientNet, and EfficientDet, primarily employ convolution. Experimental evaluations were conducted using the PASCAL VOC 2007 and 2012 datasets, widely acknowledged benchmarks for object detection. The integrated ViT-EfficientDet model achieved an impressive mean Average Precision (mAP) score of 86.27% when tested on the PASCAL VOC 2007 dataset, demonstrating its superior accuracy. These results underscore the potential of the proposed integration for real-world applications. In conclusion, the research introduces a novel integration of Vision Transformers into the EfficientDet architecture, yielding significant improvements in object detection performance. By combining ViT’s ability to capture global dependencies with EfficientDet’s efficiency and accuracy, the proposed approach offers enhanced object detection capabilities. Future research directions may explore additional datasets and evaluate the performance of the proposed framework across various computer vision tasks.
  • Item
    User Leaving Detection Via MMwave Imaging
    (2023-08) Xu, Jiawei; King, Brian; Li, Tao; Zhang, Qingxue
    The use of smart devices such as smartphones, tablets, and laptops skyrocketed in the last decade. These devices enable ubiquitous applications for entertainment, communication, productivity, and healthcare but also introduce big concern about user privacy and data security. In addition to various authentication techniques, automatic and immediate device locking based on user leaving detection is an indispensable way to secure the devices. Current user leaving detection techniques mainly rely on acoustic ranging and do not work well in environments with multiple moving objects. In this paper, we present mmLock, a system that enables faster and more accurate user leaving detection in dynamic environments. mmLock uses a mmWave FMCW radar to capture the user’s 3D mesh and detects the leaving gesture from the 3D human mesh data with a hybrid PointNet-LSTM model. Based on explainable user point clouds, mmLock is more robust than existing gesture recognition systems which can only identify the raw signal patterns. We implement and evaluate mmLock with a commercial off-the-shelf (COTS) TI mmWave radar in multiple environments and scenarios. We train the PointNet-LSTM model out of over 1 TB mmWave signal data and achieve 100% true-positive rate in most scenarios.
  • Item
    Utilizing Transfer Learning and Multi-Task Learning for Evaluating the Prediction of Chromatin Accessibility in Cancer and Neuron Cell Lines Using Genomic Sequences
    (2023-08) Shorinwa, Toluwanimi; Salama, Paul; Rizkalla, Maher; El-Sharkawy, Mohamed
    The prediction of chromatin accessibility for cancer and neuron cell lines using genomic sequences is quite challenging. Advances in machine learning and deep learning techniques allow such challenges to be addressed. This thesis investigates the use of both the transfer learning and the multi-task learning techniques. In particular, this research demonstrates the potential of transfer learning and multi-task learning in improving the prediction accuracy for twenty-three cancer types in human and neuron cell lines. Three different network architectures are used: the Basset network, the network, and the DeepSEA network. In addition, two transfer learning techniques are also used. In the first technique data relevant to the desired prediction task is not used during the pre-training stage while the second technique includes limited data about the desired prediction task in the pre-training phase. The preferred performance evaluation metric used to evaluate the performance of the models was the AUPRC due to the numerous negative samples. Our results demonstrate an average improvement of 4% of the DeepSEA network in predicting all twenty-three cancer cell line types when using the first technique, a decrease of 0.42% when using the second technique, and an increase of 0.40% when using multi-task learning. Also, it had an average improvement of 3.09% when using the first technique, 1.16% when using the second technique and 4.60% for the multi-task learning when predicting chromatin accessibility for the 14 neuron cell line types. The DanQ network had an average improvement of 1.18% using the first transfer learning technique, the second transfer learning technique showed an average decrease of 1.93% and also, a decrease of 0.90% for the multi-task learning technique when predicting for the different cancer cell line types. When predicting for the different neuron cell line types the DanQ had an average improvement of 1.56% using the first technique, 3.21% when using the second technique, and 5.35% for the multi-task learning techniques. The Basset network showed an average improvement of 2.93% using the first transfer learning technique and an average decrease of 0.02%, and 0.63% when using the second technique and multi-task learning technique respectively. Using the Basset network for prediction of chromatin accessibility in the different neuron types showed an average increase of 2.47%, 3.80% and 5.50% for the first transfer learning technique, second transfer learning technique and the multi-task learning technique respectively. The results show that the best technique for the cancer cell lines prediction is the first transfer learning model as it showed an improvement for all three network types, while the best technique for predicting chromatin accessibility in the neuron cell lines is the multi-task learning technique which showed the highest average improvement among all networks. The DeepSEA network showed the greatest improvement in performance among all techniques when predicting the different cancer cell line types. Also, it showed the greatest improvement when using the first transfer learning technique for predicting chromatin accessibility for neuron cell lines in the brain. The basset network showed the greatest improvement for the multi-task learning technique and the second transfer learning technique when predicting the accessibility for neuron cell lines.
  • Item
    Deep Brain Dynamics and Images Mining for Tumor Detection and Precision Medicine
    (2023-08) Ramesh, Lakshmi; Zhang, Qingxue; King, Brian; Chen, Yaobin
    Automatic brain tumor segmentation in Magnetic Resonance Imaging scans is essential for the diagnosis, treatment, and surgery of cancerous tumors. However, identifying the hardly detectable tumors poses a considerable challenge, which are usually of different sizes, irregular shapes, and vague invasion areas. Current advancements have not yet fully leveraged the dynamics in the multiple modalities of MRI, since they usually treat multi-modality as multi-channel, and the early channel merging may not fully reveal inter-modal couplings and complementary patterns. In this thesis, we propose a novel deep cross-attention learning algorithm that maximizes the subtle dynamics mining from each of the input modalities and then boosts feature fusion capability. More specifically, we have designed a Multimodal Cross-Attention Module (MM-CAM), equipped with a 3D Multimodal Feature Rectification and Feature Fusion Module. Extensive experiments have shown that the proposed novel deep learning architecture, empowered by the innovative MM-CAM, produces higher-quality segmentation masks of the tumor subregions. Further, we have enhanced the algorithm with image matting refinement techniques. We propose to integrate a Progressive Refinement Module (PRM) and perform Cross-Subregion Refinement (CSR) for the precise identification of tumor boundaries. A Multiscale Dice Loss was also successfully employed to enforce additional supervision for the auxiliary segmentation outputs. This enhancement will facilitate effectively matting-based refinement for medical image segmentation applications. Overall, this thesis, with deep learning, transformer-empowered pattern mining, and sophisticated architecture designs, will greatly advance deep brain dynamics and images mining for tumor detection and precision medicine.
  • Item
    VR-Based Testing Bed for Pedestrian Behavior Prediction Algorithms
    (2023-08) Armin, Faria; Tian, Renran; Chen, Yaobin; Li, Lingxi
    Upon introducing semi- and fully automated vehicles on the road, drivers will be reluctant to focus on the traffic interaction and rely on the vehicles' decision-making. However, encountering pedestrians still poses a significant difficulty for modern automated driving technologies. Considering the high-level complexity in human behavior modeling to solve a real-world problem, deep-learning algorithms trained from naturalistic data have become promising solutions. Nevertheless, although developing such algorithms is achievable based on scene data collection and driver knowledge extraction, evaluation remains challenging due to the potential crash risks and limitations in acquiring ground-truth intention changes. This study proposes a VR-based testing bed to evaluate real-time pedestrian intention algorithms as VR simulators are recognized for their affordability and adaptability in producing a variety of traffic situations, and it is more reliable to conduct human-factor research in autonomous cars. The pedestrian wears the head-mounted headset or uses the keyboard input and makes decisions in accordance with the circumstances. The simulator has added a credible and robust experience, essential for exhibiting the real-time behavior of the pedestrian. While crossing the road, there exists uncertainty associated with pedestrian intention. Our simulator will anticipate the crossing intention with consideration of the ambiguity of the pedestrian behavior. The case study has been performed over multiple subjects in several crossing conditions based on day-to-day life activities. It can be inferred from the study outcomes that the pedestrian intention can be precisely inferred using this VR-based simulator. However, depending on the speed of the car and the distance between the vehicle and the pedestrian, the accuracy of the prediction can differ considerably in some cases.
  • Item
    Improving Object Detection using Enhanced EfficientNet Architecture
    (2023-08) Kamel Ibrahim, Michael; El-Sharkawy, Mohamed; King, Brian; Rizkalla, Maher
    EfficientNet is designed to achieve top accuracy while utilizing fewer parameters, in addition to less computational resources compared to previous models. In this paper, we are presenting compound scaling method that re-weight the network’s width (w), depth(d), and resolution (r), which leads to better performance than traditional methods that scale only one or two of these dimensions by adjusting the hyperparameters of the model. Additionally, we are presenting an enhanced EfficientNet Backbone architecture. We show that EfficientNet achieves top accuracy on the ImageNet dataset, while being up to 8.4x smaller and up to 6.1x faster than previous top performing models. The effec- tiveness demonstrated in EfficientNet on transfer learning and object detection tasks, where it achieves higher accuracy with fewer parameters and less computation. Henceforward, the proposed enhanced architecture will be discussed in detail and compared to the original architecture. Our approach provides a scalable and efficient solution for both academic research and practical applications, where resource constraints are often a limiting factor.
  • Item
    Non-intrusive Wireless Sensing with Machine Learning
    (2023-08) Xie, Yucheng; Li, Lingxi; Li, Feng; Guo, Xiaonan; King, Brian
    This dissertation explores the world of non-intrusive wireless sensing for diet and fitness activity monitoring, in addition to assessing security risks in human activity recognition (HAR). It delves into the use of WiFi and millimeter wave (mmWave) signals for monitoring eating behaviors, discerning intricate eating activities, and observing fitness movements. The proposed systems harness variations in wireless signal propagation to record human behavior while providing exhaustive details on dietary and exercise habits. Significant contributions encompass unsupervised learning methodologies for detecting dietary and fitness activities, implementing soft-decision and deep neural networks for assorted activity recognition, constructing tiny motion mechanisms for subtle mouth muscle movement recovery, employing space-time-velocity features for multi-person tracking, as well as utilizing generative adversarial networks and domain adaptation structures to enable less cumbersome training efforts and cross-domain deployments. A series of comprehensive tests validate the efficacy and precision of the proposed non-intrusive wireless sensing systems. Additionally, the dissertation probes the security vulnerabilities in mmWave-based HAR systems and puts forth various sophisticated adversarial attacks - targeted, untargeted, universal, and black-box. It designs adversarial perturbations aiming to deceive the HAR models whilst striving to minimize detectability. The research offers powerful insights into issues and efficient solutions relative to non-intrusive sensing tasks and security challenges linked with wireless sensing technologies.
  • Item
    Deep Reinforcement Learning of IoT System Dynamics for Optimal Orchestration and Boosted Efficiency
    (2023-08) Shi, Haowei; Zhang, Qingxue; King, Brian; Fang, Shiaofen
    This thesis targets the orchestration challenge of the Wearable Internet of Things (IoT) systems, for optimal configurations of the system in terms of energy efficiency, computing, and data transmission activities. We have firstly investigated the reinforcement learning on the simulated IoT environments to demonstrate its effectiveness, and afterwards studied the algorithm on the real-world wearable motion data to show the practical promise. More specifically, firstly, challenge arises in the complex massive-device orchestration, meaning that it is essential to configure and manage the massive devices and the gateway/server. The complexity on the massive wearable IoT devices, lies in the diverse energy budget, computing efficiency, etc. On the phone or server side, it lies in how global diversity can be analyzed and how the system configuration can be optimized. We therefore propose a new reinforcement learning architecture, called boosted deep deterministic policy gradient, with enhanced actor-critic co-learning and multi-view state transformation. The proposed actor-critic co-learning allows for enhanced dynamics abstraction through the shared neural network component. Evaluated on a simulated massive-device task, the proposed deep reinforcement learning framework has achieved much more efficient system configurations with enhanced computing capabilities and improved energy efficiency. Secondly, we have leveraged the real-world motion data to demonstrate the potential of leveraging reinforcement learning to optimally configure the motion sensors. We used paradigms in sequential data estimation to obtain estimated data for some sensors, allowing energy savings since these sensors no longer need to be activated to collect data for estimation intervals. We then introduced the Deep Deterministic Policy Gradient algorithm to learn to control the estimation timing. This study will provide a real-world demonstration of maximizing energy efficiency wearable IoT applications while maintaining data accuracy. Overall, this thesis will greatly advance the wearable IoT system orchestration for optimal system configurations.