Computer Engineering Commons^™

Controllable Language Generation Using Deep Learning, Rohola Zandie

Electronic Theses and Dissertations

The advent of deep neural networks has sparked a revolution in Artificial Intelligence (AI), notably with the creation of Transformer models like GPT-X and ChatGPT. These models have surpassed previous methods in various Natural Language Processing (NLP) tasks. As the NLP field evolves, there is a need to further understand and question the capabilities of these models. Text generation, a crucial part of NLP, remains an area where our comprehension is limited while being critical in research.

This dissertation focuses on the challenging problem of controlling the general behaviors of language models such as sentiment, topical focus, and logical reasoning. …

Reference Frames In Human Sensory, Motor, And Cognitive Processing, Dongcheng He

Electronic Theses and Dissertations

Reference-frames, or coordinate systems, are used to express properties and relationships of objects in the environment. While the use of reference-frames is well understood in physical sciences, how the brain uses reference-frames remains a fundamental question. The goal of this dissertation is to reach a better understanding of reference-frames in human perceptual, motor, and cognitive processing. In the first project, we study reference-frames in perception and develop a model to explain the transition from egocentric (based on the observer) to exocentric (based outside the observer) reference-frames to account for the perception of relative motion. In a second project, we focus …

Artificial Emotional Intelligence In Socially Assistive Robots, Hojjat Abdollahi

Electronic Theses and Dissertations

Artificial Emotional Intelligence (AEI) bridges the gap between humans and machines by demonstrating empathy and affection towards each other. This is achieved by evaluating the emotional state of human users, adapting the machine’s behavior to them, and hence giving an appropriate response to those emotions. AEI is part of a larger field of studies called Affective Computing. Affective computing is the integration of artificial intelligence, psychology, robotics, biometrics, and many more fields of study. The main component in AEI and affective computing is emotion, and how we can utilize emotion to create a more natural and productive relationship between humans …

A Music-Therapy Robotic Platform For Children With Autism: A Pilot Study, Huanghao Feng, Mohammad H. Mahoor, Francesca Dino

Electrical and Computer Engineering: Faculty Scholarship

Children with Autism Spectrum Disorder (ASD) experience deficits in verbal and nonverbal communication skills including motor control, turn-taking, and emotion recognition. Innovative technology, such as socially assistive robots, has shown to be a viable method for Autism therapy. This paper presents a novel robot-based music-therapy platform for modeling and improving the social responses and behaviors of children with ASD. Our autonomous social interactive system consists of three modules. Module one provides an autonomous initiative positioning system for the robot, NAO, to properly localize and play the instrument (Xylophone) using the robot’s arms. Module two allows NAO to play customized songs …

A Low-Cost, Long-Range, And Solar-Based Iot Soil Quality Monitor, Salvador Garcia, Trina Nguyen, Julian Wong

Interdisciplinary Design Senior Theses

The project objective is to create a low-cost, long-range, and solar-based IoT soil quality monitoring system. The system must transmit packages of data gathered from separate nodes, consisting of two dierent types of sensors, to a centralized gateway receiver to be displayed to the user in an elegant and readable manner. The end goal of the project is to supplement produce grown by large agricultural bodies around the United States without the misuse of water resources. This report presents the need for this system, details the components of the system, and the rationale behind design choices. It serves as a …

Classification Of Electropherograms Using Machine Learning For Parkinson’S Disease, Soroush Dehghan

Electronic Theses and Dissertations

Parkinson’s disease (PD) is a neurodegenerative movement disorder that progresses gradually over time. The onset of symptoms in people who are suffering from PD can vary from case to case, and it depends on the progression of the disease in each patient. The PD symptoms gradually develop and exacerbate the patient’s movements throughout time. An early diagnosis of PD could improve the outcomes of treatments and could potentially delay the progression of this disorder and that makes discovering a new diagnostic method valuable. In this study, I investigate the feasibility of using a machine learning (ML) approach to classify PD …

Crossroad - Avoid Crowd Intelligence, Xukun Zhang, Yuzheng Wu, Haochen Zhang

Interdisciplinary Design Senior Theses

Nowadays, waiting takes big chunks of daily-life activity. People may always find themselves facing long queues, waiting in a crowded facility, even when they have tried to avoid peak hours. Heading to a highly populated public area may have felt like heading to a battlefield. Without access to the real-time information of the facility, people start to discover that waiting starts to become an unpredictable event that can sometimes delay their schedule or even worse. This project serves as a solution to tackle this lack of transparency. Crossroad aims to combine facilities’ cameras with micro-controller to see the engagement of …

Jamming Attack Workaround Study, Soren Madsen, Jack Schoen

Interdisciplinary Design Senior Theses

The Internet of Things (IoT) is a fast growing industry with strong footholds in the smart home market featuring devices such as the Amazon Echo, Ring security cameras, smart TVs, and much more. However, it doesn’t stop there; the industrial sector has begun using smart devices for measurement, automated tasks, and time sensitive communication. Many of these devices have become reliant on WiFi technology and are vulnerable to attacks on the security of the protocols involved.

In this paper, we discuss the details of the deauthentication attack on WPA and WPA2 systems and propose a solution for detection and recovery …

Deep Learning Methods For Fingerprint-Based Indoor And Outdoor Positioning, Fahad Alhomayani

Electronic Theses and Dissertations

Outdoor positioning systems based on the Global Navigation Satellite System have several shortcomings that have deemed their use for indoor positioning impractical. Location fingerprinting, which utilizes machine learning, has emerged as a viable method and solution for indoor positioning due to its simple concept and accurate performance. In the past, shallow learning algorithms were traditionally used in location fingerprinting. Recently, the research community started utilizing deep learning methods for fingerprinting after witnessing the great success and superiority these methods have over traditional/shallow machine learning algorithms. The contribution of this dissertation is fourfold:

First, a Convolutional Neural Network (CNN)-based method for …

Design, Manufacture, And Test Of A Hybrid Aerial-Ground Robotic Platform, William Garrett Willmon

Electronic Theses and Dissertations

A hybrid aerial-ground robotic platform allows for enhanced functionality combining most of the operational profiles of an aerial and ground vehicle with applications to intelligence, surveillance, reconnaissance (ISR), infrastructure inspection, emergency response, photography, etc. Motivated by this challenge, we designed, developed, and tested a prototype hybrid aerial-ground robotic vehicle capable of guidance, navigation, and control in the air and on the ground. The thesis focus is on the system design. As such, at first, we designed and analyzed the mechanical component to ensure durability. We then designed the electrical component to reduce overall weight and maximize battery life. We developed …

Xylo-Bot: A Therapeutic Robot-Based Music Platform For Children With Autism, Huanghao Feng

Electronic Theses and Dissertations

Children with Autism Spectrum Disorder (ASD) experience deficits in verbal and nonverbal communication skills, including motor control, emotional facial expressions, and eye gaze / joint attention. This Ph.D. dissertation focuses on studying the feasibility and effectiveness of using a social robot, called NAO, and a toy music instrument, xylophone, at modeling and improving the social responses and behaviors of children with ASD. In our investigation, we designed an autonomous social interactive music teaching system to fulfill this mission.

A novel modular robot-music teaching system consisting of three modules is presented. Module 1 provides an autonomous self-awareness positioning system for the …

Deep Siamese Neural Networks For Facial Expression Recognition In The Wild, Wassan Hayale

Electronic Theses and Dissertations

The variation of facial images in the wild conditions due to head pose, face illumination, and occlusion can significantly affect the Facial Expression Recognition (FER) performance. Moreover, between subject variation introduced by age, gender, ethnic backgrounds, and identity can also influence the FER performance. This Ph.D. dissertation presents a novel algorithm for end-to-end facial expression recognition, valence and arousal estimation, and visual object matching based on deep Siamese Neural Networks to handle the extreme variation that exists in a facial dataset. In our main Siamese Neural Networks for facial expression recognition, the first network represents the classification framework, where we …

Microgrid-Enabled Reactive Power Support To Enhance Grid Economics, Sarhan Hasan

Electronic Theses and Dissertations

Reactive power plays an essential role in voltage control and stability in electric power systems. Various Volt/VAR techniques are utilized in electric power systems to maintain the voltage profile within defined acceptable limits and accordingly provide reliability and stability. Reactive power has been commonly generated through large-scale synchronous generators or distributed capacitor banks to provide proper transmission and distribution level system management, however, reactive power can be further used as an effective means to reduce total system operation cost. In this dissertation, an optimal reactive power model is proposed to determine the optimal nodal reactive powers that result in the …

Automated Recognition Of Facial Affect Using Deep Neural Networks, Behzad Hasani

Electronic Theses and Dissertations

Automated Facial Expression Recognition (FER) has been a topic of study in the field of computer vision and machine learning for decades. In spite of efforts made to improve the accuracy of FER systems, existing methods still are not generalizable and accurate enough for use in real-world applications. Many of the traditional methods use hand-crafted (a.k.a. engineered) features for representation of facial images. However, these methods often require rigorous hyper-parameter tuning to achieve favorable results.

Recently, Deep Neural Networks (DNNs) have shown to outperform traditional methods in visual object recognition. DNNs require huge data as well as powerful computing units …

Facial Action Unit Detection With Deep Convolutional Neural Networks, Siddhesh Padwal

Electronic Theses and Dissertations

The facial features are the most important tool to understand an individual's state of mind. Automated recognition of facial expressions and particularly Facial Action Units defined by Facial Action Coding System (FACS) is challenging research problem in the field of computer vision and machine learning. Researchers are working on deep learning algorithms to improve state of the art in the area. Automated recognition of facial action units has man applications ranging from developmental psychology to human robot interface design where companies are using this technology to improve their consumer devices (like unlocking phone) and for entertainment like FaceApp. Recent studies …

Lactic Acid Threshold Stimulator, Justin Brackett, Karen Carreon, Fernando Guerra, Malyna Sanchez

Interdisciplinary Design Senior Theses

As a person works out, the threshold of lactic acid will build causing anywhere from discomfort to pain. Reducing the discomfort caused by lactic acid could greatly improve an individual’s performance while working out. Reducing this discomfort may be done through Electrical Muscle Stimulation (EMS), which is the procedure of contracting muscles through sending electrical signals. Our team’s goal is to create LATS, a wearable and mobile application that alleviates discomfort and aids muscle recovery during the intense parts of a workout. The system consists of a heart rate monitor to measure lactic acid levels, a garment that is worn …

3d Formation Control In Multi-Robot Teams Using Artificial Potential Fields, Sanjana Reddy Mohan

Electronic Theses and Dissertations

Multi-robot teams find applications in emergency response, search and rescue operations, convoy support and many more. Teams of autonomous aerial vehicles can also be used to protect a cargo of airplanes by surrounding them in some geometric shape. This research develops a control algorithm to attract UAVs to one or a set of bounded geometric shapes while avoiding collisions, re-configuring in the event of departure or addition of UAVs and maneuvering in mission space while retaining the configuration. Using potential field theory, weighted vector fields are described to attract UAVs to a desired formation. In order to achieve this, three …

Development Of A Locomotion And Balancing Strategy For Humanoid Robots, Emile Bahdi

Electronic Theses and Dissertations

The locomotion ability and high mobility are the most distinguished features of humanoid robots. Due to the non-linear dynamics of walking, developing and controlling the locomotion of humanoid robots is a challenging task. In this thesis, we study and develop a walking engine for the humanoid robot, NAO, which is the official robotic platform used in the RoboCup Spl. Aldebaran Robotics, the manufacturing company of NAO provides a walking module that has disadvantages, such as being a black box that does not provide control of the gait as well as the robot walk with a bent knee. The latter disadvantage, …

Large-Scale Flexible Membrane For Automatic Strain Monitoring Of Transportation Infrastructure, Simon Laflamme, Venkata D. Kolipara, Hussam S. Saleem, Randall L. Geiger

Randall Geiger

Structural Health Monitoring (SHM) of transportation infrastructures is a complex task, typically conducted by visual inspection due to the technical and economical constrains of existing health monitoring technologies. It results that health monitoring is highly dependent on scheduling and on the judgment of the inspectors, which can be costly and ineffective. Thus, it is fundamental to automate the SHM process to allow timely inspection, maintenance, and management of transportation infrastructure. The authors propose a flexible membrane that can be deployed over large surfaces, at low cost, for automatic and continuous monitoring of strains. The membrane, termed sensing skin, is constituted …

Network Connection Blocker, Method, And Computer Readable Memory For Monitoring Connections In A Computer Network And Blocking The Unwanted Connections, Douglas W. Jacobson, James A. Davis

Douglas Jacobson

A network connection blocker for monitoring connections between host computers in a network and blocking the unwanted connections. The host computers transmit connection packets between each other in accordance with a network protocol suite when seeking to establish, providing network services with, and close the connections. The network protocol suite includes a connection oriented transport layer protocol. The network connection blocker comprises a network interface that receives the connection packets transmitted between the host computers. It also comprises a blocking module that processes the received connection packets to detect the unwanted connections. The blocking module then generates connection packets in …

Optimized Trajectory Generation For Car-Like Robots On A Closed Loop Track, Tyler Friedl

Electronic Theses and Dissertations

This thesis presents a method for generating an optimized path through a given track. The path is generated by choosing waypoints throughout the track then iteratively optimizing the position of these waypoints. The waypoints are then connected by optimized paths represented by curvature polynomials. The end result is a path through the track represented as a spline of curvature polynomials. This method is applied to multiple simulated tracks and the results are presented. By generating and representing the paths in the continuous domain, the method has improved computational efficiency from many of the discrete methods used to generate an optimal …

System Identification Of A Circulation Control Unmanned Aerial Vehicle, Mohammed Agha

Electronic Theses and Dissertations

The advancement in automation and sensory systems in recent years has led to an increase the demand of UAV missions. Due to this increase in demand, the research community has gained interest in investigating UAV performance enhancing systems. Circulation Control (CC), which is an active control flow method used to enhance UAV lift, is a performance enhancing system currently studied. In prior research, experimental studies have shown that Circulation Control wings (CCW) implemented on class-I UAVs can reduce take-off distance by 54%. Wind tunnel tests reveal that CC improves aircraft payload capabilities through lift enhancement. Increasing aircraft payload capabilities causes …

Design And Development Of The Ebear: A Socially Assistive Robot For Elderly People With Depression, Amirhossein Kargarbideh

Electronic Theses and Dissertations

There has been tremendous progress in the field of robotics in the past decade and especially developing humanoid robots with social abilities that can assist human at a socio-emotional level. The objective of this thesis is to develop and study a perceptive and expressive animal-like robot equipped with artificial intelligence in assisting the elderly people with depression. We investigated how social robots can become companions of elderly individuals with depression and improve their mood and increase their happiness and well-being. The robotic platform built in this thesis is a bear-like robot called the eBear. The eBear can show facial expression …

Towards Closed-Loop Deep Brain Stimulation: Behavior Recognition From Human Stn, Soroush Niketeghad

Electronic Theses and Dissertations

Deep brain stimulation (DBS) provides significant therapeutic benefit for movement disorders such as Parkinson’s disease (PD). Current DBS devices lack real-time feedback (thus are open loop) and stimulation parameters are adjusted during scheduled visits with a clinician. A closed-loop DBS system may reduce power consumption and side effects by adjusting stimulation parameters based on patient’s behavior. Thus behavior detection is a major step in designing such systems. Various physiological signals can be used to recognize the behaviors. Subthalamic Nucleus (STN) Local field Potential (LFP) is a great candidate signal for the neural feedback, because it can be recorded from the …

Path Loss In An Urban Peer-To-Peer Channel For Six Public-Safety Frequency Bands, David W. Matolak, Qian Zhang, Qiong Wu

Faculty Publications

We provide path loss data and models for a peer-to-peer wireless channel for an urban environment in six public safety bands, for simultaneous transmission to five spatially separated receiving sites. Results are from measurements in Denver, Colorado. The six frequencies at which we measured are (in MHz) 430, 750, 905, 1834, 2400, and 4860. Both line-of-sight and non-line-of-sight conditions were covered, and we quantify path loss exponents and linear-fit standard deviations as functions of frequency and location. Line-of-sight results agree with prior work, but non-line-of-sight exponents, from 3.6-7.3, are generally larger than in most other references.

Wireless Networks-On-Chips: Architecture, Wireless Channel, And Devices, David W. Matolak, Avinash Kodi, Savas Kaya, Dominic Ditomaso, Soumyasanta Laha, William Rayess

Faculty Publications

Wireless networks-on-chips (WINoCs) hold substantial promise for enhancing multicore integrated circuit performance, by augmenting conventional wired interconnects. As the number of cores per IC grows, intercore communication requirements will also grow, and WINoCs can be used to both save power and reduce latency. In this article, we briefly describe some of the key challenges with WINoC implementation, and also describe our example design, iWISE, which is a scalable wireless interconnect design. We show that the integration of wireless interconnects with wired interconnects in NoCs can reduce overall network power by 34 percent while achieving a speedup of 2.54 on real …

Worse-Than-Rayleigh Fading: Experimental Results And Theoretical Models, David W. Matolak, Jeff Frolik

Faculty Publications

This article is motivated by the recent recognition that channel fading for new wireless applications is not always well described by traditional models used for mobile communication systems. In particular, fading data collected for vehicleto- vehicle and wireless sensor network applications has motivated new models for conditions in which channel fading statistics can be worse than Rayleigh. We review the use of statistical channel models, describe our example applications, and provide both measured and modeling results for these severe fading conditions.

5 Ghz Band Vehicle-To-Vehicle Channels: Models For Multiple Values Of Channel Bandwidth, Qiong Wu, David W. Matolak, Indranil Sen

Faculty Publications

In Sen and Matolak's earlier paper, 5-GHz-band vehicle-to-vehicle (V2V) channel models were presented for channel bandwidths of 5 and 10 MHz. In this paper, we provide additional tapped delay line models for bandwidths of 1, 20, 33.33, and 50 MHz based upon the data used in Sen and Matolak's paper. We provide tables of channel parameters for five types of V2V channel classes and also include example tap correlation coefficients. Root-mean-square delay spread values are summarized, as are values of bandwidth for which the channel frequency correlation takes values of 0.7 and 0.5. As with the results from Sen and …

3d Outside Cell Interference Factor For An Air-Ground Cdma ‘Cellular’ System, David W. Matolak

Faculty Publications

We compute the outside-cell interference factor of a code-division multiple-access (CDMA) system for a three-dimensional (3-D) air-to-ground (AG) "cellular-like" network consisting of a set of uniformly distributed ground base stations and airborne mobile users. The CDMA capacity is roughly inversely proportional to the outside-cell interference factor. It is shown that for the nearly free-space propagation environment of these systems, the outside-cell interference factor can be larger than that for terrestrial propagation models (as expected) and depends approximately logarithmically upon both the cell height and cell radius.