Computer Engineering Commons^™

Drone Path Scheduling For Data Gathering In Disaster Effected Environments, James Bologna

Theses and Dissertations

Creative networks in a disaster effected area have been a concern for a long time. With the innovation of flying ad hoc networks the problem can be tackled from a more practical standpoint. The use of low altitude drones equipped with wireless transmission and receiving capability can be used under the circumstances to enable ad-hoc communication. Drone coordination and route planning is a critical consideration when determining how to gather data from ground nodes, since the drones are constrained by limited battery capacity. In this research, we set out to explore a wide range of policies for determining the trajectories …

Wavelet–Based Functional Data Analysis For Classification And Change Point Detection, Nenad Mijatovic

Theses and Dissertations

Data collection and analysis, performed close to the source and transferred to other devices for different analysis, are the major paradigms of the Internet of Things (IoT). Usually, the raw data comes in the form of a time-series sequence that can be considered as functions, and as such can be examined by the functional analysis apparatus. Among others, the two major tasks in data analysis are (1) categorical signal classification and (2) change detection in signal statistical parameters. Here, we study both problems: featureless signal classification using discriminative interpolation regularized with the ℓ1 norm is performed using Classification by Discriminative …

Characterization Of Rf Signal Propagation For Wireless Sensor Network Deployed In Mountainous Environment, Bandar Mohammad Alshawi

Theses and Dissertations

Wireless sensor network (WSN) nodes, in mountainous forests, report real-time data to base stations concerning events, in which researchers and decision makers are interested in. A thorough research reveals the deficiency of any study modeling radio frequency (RF) in that environment. The lack of accurately modeling RF signal propagation in any environment can have a great impact on the network life, connectivity, and coverage. This dissertation models the loss of RF signal in the mountainous environment and demonstrates the inconsistency of theoretical models, compared to actual measurements. The models proposed in this research yield satisfactory results, and the theoretical models …

Human-Centered Enterprise Resource Maintenance Management, Sharon Sue Chinoy

Theses and Dissertations

In complex domains, maintenance personnel may be required to use multiple software tools for receiving status information and controlling resources across the enterprise. These tools have evolved to be effective for collecting status, but often lack integrated contextual information for personnel to understand failure event impact to the enterprise and operational mission. Through a human-centered design approach, salient concepts and semantically relevant maintenance information can be captured within a domain. This research will show that an ontology can be a useful method to establish a common frame of reference to promote better situation awareness and more effective decision-making and collaboration …

Mindful: A Novel Virtual System Migration Decision-Making Framework For Automated Cyber-Resiliency, Nicholas James Lowing

Theses and Dissertations

Virtual system migration has revolutionized modern computing. As an advantageous byproduct of virtualization, virtual system migration has allowed for cheaper, more robust cloud management. The selection of a destination host during migration is a key component of migration management. However, there is currently no state-of-the-art, standardized framework for making this decision. Previous work related to automated load balancing is plentiful, but when load balancing is not the primary focus of the cloud management strategy there is a lack of research. We focus on this case, where virtual systems are no longer moved based on some predefined optimization pattern, but rather …

Mitigating Loss Of Control In General Aviation: A Human-Systems Integrated Flight Test Method For Mapping Pilot Cognition And Aircraft Dynamics, Tiziano Bernard

Theses and Dissertations

General aviation (GA) loss of control accidents, in the United States, have continued to occur despite efforts by government and non-government research agencies. The lack of data during loss of control events (due to the absence of data recorders in small aircraft) does not allow for an accurate reconstruction of the accidents, causing accident investigators to focus on generic causes like pilot error. Flight test research has shown that there are various systems induced causal factors that can potentially set up an aircraft to depart controlled flight and do not aid pilot efforts. An example of these causal factors is …

A Framework For Characterizing The Security Posture Of Cyber Systems, Matthew Ridley

Theses and Dissertations

Modern day applications can be spread across multiple virtual or physical systems, and be accessed or attacked by pretty much any one any where. Cybersecurity is used to mitigate these cyber threats but there are limited resources that can be dedicated to security. As result, trade-offs and decisions must be made around what is prioritized and what isn’t. Cyber risk management provides methodologies for identifying threats, evaluating risks and making decisions, however, it can be difficult to determine whether the system is actually secure enough and the risk is actually within an acceptable parameters. This thesis provides a framework for …

Holistic Approach For Characterizing The Performance Of Wireless Sensor Networks, Amar Yusof Jaffar

Theses and Dissertations

Researchers are actively investigating wireless sensor networks (WSNs) with respect to node design, architecture, networking protocols, and processing algorithms. However, few researchers consider the impact of deployments on the performance of a system. As a result, an appropriate deployment simulator that estimates the performance of WSNs concerning several deployment variables is needed. This research presents a holistic deployment framework that assists decision makers in making optimum WSN deployment choices by considering the terrain of their region of interest and type of deployment. This framework employs empirical propagation models to predict the performance of the deployment in terms of connectivity, coverage, …

Real-Time Facial Expression And Speech Emotion Recognition App Development On Mobile Phones Using Cloud Computing, Humaid Saif Saeed Alasli Alshamsi

Theses and Dissertations

Emotion plays a vital role in humans’ daily lives. Understanding emotions and recognizing how to react to others’ feelings are fundamental to engaging in successful social interactions. Emotion recognition through facial expression and speech play a significant role in human communication. This subject is becoming important in academic research as new techniques such as emotion recognition from speech context inspire us to recognize how emotions are related to the content we are uttering. The demand and importance of emotion recognition have highly increased in many applications in recent years, such as video games, human-computer interactions, cognitive computing, and affective computing. …

Vanishing Connections: Application Resiliency Through Cross-Network Tcp Migration, David Elliott

Theses and Dissertations

Computer applications are subject to a plethora of security challenges, ranging from concerns over network monitoring to avoiding expensive and damaging intrusion and compromise. A vast number of techniques exist to mitigate applications’ vulnerability to these threats: network policies can be adjusted, traffic can be rerouted, firewalls can be installed, hosts can be hardened, applications can be patched. A large body of research exists to improve the security of hosts in this context. However, for applications that have already been the subject of damaging attacks, we no longer focus primarily on security, but shift to resiliency, or the capacity of …

Design And Simulation Of An Intelligent Self-Adaptive System For A Smart Home, Basman M. Hasan Alhafidh

Theses and Dissertations

Home automation and control systems as basic elements of smart cities have played a key role in the development of our homes environments . They have a wide range of applications in many fields at home such as security and monitoring, healthcare, energy, and entertainment applications. The improvement of humans’ living standards make people keep trying to delegate many of their needs to a home automation system. Such a system has been built with capabilities of predicting what the user intends to do in smart home environment. However, there are many issues that need more investigation and solutions, such as: …

Human-Centered Design Of A 3d-Augmented Strategic Weather Management System For The Aviation Community, Sébastien Léonce Paul Boulnois

Theses and Dissertations

Convective weather is one of the main causes of accidents in the National Airspace System according to the Federal Aviation Administration. The purpose of this research, aligned with current NextGen research efforts, was to determine how weather information, presented in 2D and/or 3D, and associated with interaction features, could impact airline pilots’ weather-related situation awareness and decision-making capabilities. Human-Centered Design principles, along with Design Thinking, were used and led to the design of a 3D-Augmented Strategic Weather Management System aiming to satisfy this research question. The system is called “Onboard Weather Situation Awareness System” (OWSAS) in the scope of this …

Improving Stb Devices’ Parental Control, Mahmood Fawzi Alfathe

Theses and Dissertations

In this dissertation, an IPTV system was designed with new viewer parental control authentication method. People deal with traditional IPTV systems that use simple authentication numeric passcodes, and this topic did not receive the attention to overcome its security problems. In this dissertation two contributions were introduced, the first one is to design and implement an IPTV system that uses humans’ Biometrics authentication instead of numeric passwords; the second contribution was presented by integrating and testing the efficiency of the suggested solution as an authentication key against traditional numerical passcodes. Also, the characteristics of this new method were tested. In …

Automatic Speech Recognition Adaptation For Various Noise Levels, Azhar Sabah Abdulaziz

Theses and Dissertations

The automatic speech recognition (ASR) is a set of complicated algorithms that convert the intended spoken utterance into a textual form. Acoustic features, which are extracted from the speech signal, are matched against a trained network of linguistic and acoustic models. The ASR performance is degraded significantly when the ambient noise is different than that of the training data. Many approaches have been introduced to address this problem with various degrees of complexity and improvement rates. The general pattern of solving this issue lies in three categories: empowering features, train a general acoustic model and transform models to match noisy …

Digital Automatic Speech Recognition Using Kaldi, Sarah Habeeb Alyousefi

Theses and Dissertations

The Automatic speech recognition (ASR) system is one of most important technologies that used for human-machine interaction. The main goal of the ASR system is to recognize different natural languages that are spoken by humans. The difficulties of these recognition systems depend on many factors, such as noises, variability of the speakers, and problems of continuous speech. For that reason, many researchers and foundations have designed different kinds of licensed toolkits and software that are specialized in building speech recognition systems, including , Julius, Sphinx-4, RWTH ASR, and HTK toolkits. In this thesis, Kaldi toolkit, which is one of the …

Speech Emotion Recognition Using Connectionist Models In A Tandem System, Mary Najafi

Theses and Dissertations

This article presents a tandem Speech Emotion Recognition (SER) system by which 8 archetypal emotions can be differentiated based upon two different types of acoustic features as inputs to Artificial Neural Network (ANN) models. The two types of features that are fed into the classifiers reveal the degree of excitement and pleasentness of speech. The author has implied the time-based characteristics of speech in the feature extraction method by monitoring the trend of local features through time. Thus, two global features are proposed that are derived from Teager Energy Operator (TEO)-based (T EOg) and spectral features, Mel-Frequency Cepstral Coeffcients (MF …

Pollen Grains Recognition Based On Computer Vision Methods, Amar Idrees Daood

Theses and Dissertations

The classification of pollen grains is a main task in many disciplines including ecology, forensic sciences, allergy control, and oil exploration. In these application areas, visual inspection is the common method used for classifying pollen. However, recognition by visual inspection consumes much time and effort. Even though some level of automation exists, the automatic recognition of pollen grains remains an open problem. Current pollen-classification solutions rely on measurements of visual cues such as contour or texture. However, these features do not capture the visual complexity of information needed for discriminating among various species of pollen, especially when both a large-scale …

Managed Containers For Increased Cyber-Resilience, Xavier J. Merino Aguilera

Theses and Dissertations

Traditional defense mechanisms are no longer adequate in protecting critical infrastructure and mission critical systems. These systems require to be always-on-always-connected. High availability and data integrity become crucial to deliver their mission. Unable to guarantee uncompromisable security and given that systems will inevitably be attacked, we must change our goals to guarantee mission survivability, the ability of the system to fight through the attack. Previous work has been done to increase availability and integrity using virtual machines. We move away from virtual machines towards Linux containers and implement resiliency strategies to guarantee stateful system recovery after an attack. The goal …

The Impact Of Different Propagation Environments On The Performance Of Wireless Sensor Networks, Abdallah Mubark Aldosary

Theses and Dissertations

This dissertation presents a methodology for evaluating the performance of wireless sensor network (WSN) protocols in different propagation environments. To create this methodology, practical RF propagation models that include many of the substantial features of different propagation environments are utilized, and radio energy models for different propagation environments are developed. Accurate environment-specific radio frequency (RF) propagation models should be utilized in order to improve the overall process of decision-making during pre-deployment of WSNs, to facilitate the deployment of the WSN, and to enhance the battery efficiency of sensing nodes so that the network lifetime can be prolonged. The investigating of …

Repeatability Of Reference Signal Received Power Measurements In Lte Networks, Hayder A Abdulrasool Khzaali

Theses and Dissertations

No abstract provided.

Optimization Framework For Deployment Of Wireless Sensor Networks, Tajudeen Olawale Olasupo

Theses and Dissertations

In order to tackle the problem of network connectivity and sensing coverage in random placement of sensor nodes over an area of interest, this research presents an optimization and visualization framework for characterization and prediction of optimal deployments of large-scale wireless sensor networks (WSNs). This study presents efficient image processing algorithms for classification of deployment terrain in order to optimize deployment and connectivity coverage with required minimum number of nodes and transmission power. It reports formation of efficient models for WSN signal propagation under different terrain conditions. The study describes the developmental approach of the WSN optimization framework and visualization …

Feature Based Object Tracking: A Probabilistic Approach, Kaleb Smith

Theses and Dissertations

Video analysis is a rich research topic, due to the wide spectrum of applications such as surveillance, activity recognition, security, and event detection. One of the important challenges in video analysis is object tracking, which provides the ability to determine the exact location of an object of interest within each frame. Many challenges affect the efficiency of a tracking algorithm such as scene illumination change, occlusion, scaling change and determining a search window from which to track object(s). We present an integrated probabilistic model for object track- ing, that combines implicit dynamic shape representations and probabilistic object modeling. We demonstrate …

Evaluation Of User Perceived Qoe In Mobile Systems Using Social Media Analytics, Ahmed Yaseen Mjhool

Theses and Dissertations

In mobile system environments, the quality perceived by users is inconstant and reliant on many factors such as cellular network, data connection, cost, coverage area, etc. Even though Quality of Service (QoS) management is enabled in most modern telecommunication systems, it does not guarantee the actual user’s perceived Quality of Experience (QoE) level. Many cellular networks rely on engineering test research, such as drive testing or smart mobile applications, to collect the required parameters in order to provide better service quality to users. However, this approach does not always yield customer satisfaction. Hence, user opinions should be considered. These opinions …

Aes Encryption Algorithm Using Arm Trustzone Technology, Chia-Che Lee

Theses and Dissertations

With the huge impact of IoT devices, the security needs are becoming more important than what it had before. Since embedded systems have limited resources, the traditional security solutions are not quite fitting to IoTs because the huge power consumption and resource. ARM TrustZone Technology is a hardware based security feature using in ARM-based devices with minimum resource taken. TrustZone provides a critical environment to isolate security and non-security tasks within Normal and Security World. Both worlds can be a General Purpose Operating System (GPOS) or a Real-Time Operating System (RTOS) depending on designer has needs, and running simultaneously on …

Real-Time Monitoring Of Sand And Dust Storm Winds Using Wireless Sensor Technology, Hana Mohammed Mujlid

Theses and Dissertations

This dissertation proposes an empirical model for prediction of the radio path loss in Wireless Sensor Networks (WSNs). The model applies to WSNs that are deployed in environments with dust and sand storms. It is developed as a result of statistical analysis of the measured data collected during dust and sand storms. The measured data were obtained at 2.4GHz and for different levels of the storm severity. For the purpose of data collection a custom measurement system based on Xbee air interface was developed. The proposed model shows a very good agreement with the measured data. It is also demonstrated …

Google Speech Recognition Using Embedded System, Anita Devi

Theses and Dissertations

This thesis will describe the theoretical background and implementation details of Google Speech Recognition using embedded system. AM37x Evaluation Board developed by Texas Instrument is used as a test bed. All major applications of Google Speech Recognition are covered in this thesis. Also, Evaluation of Google Speech API based on standard dataset is also part of the thesis.

Each implementation details are included with the theoretical background and pre-requisite details:

• Overview of the background of Automatic Speech Recognition Technology.
• Overview of Google Speech Recognition.
• Overview of AM37x Evaluation Module.
• Drivers and Android OS upgradation details.
• Installation of Google pre-requisite Apps …

Comparing The Effect Of Smoothing And N-Gram Order : Finding The Best Way To Combine The Smoothing And Order Of N-Gram, Wenyang Zhang

Theses and Dissertations

The SRILM is a toolkit for building and applying statistical language models (LMs), designed and developed primarily for use in speech recognition, statistical tagging and segmentation, and machine translation. It has been under development in the SRI Speech Technology and Research Laboratory since 1995. The toolkit has also greatly benefited from its use and enhancements during the Johns Hopkins University/CLSP summer workshops in 1995, 1996, 1997, and 2002. In this thesis, the effect of smoothing and order of N-gram for language model we build by srilm toolkit is studied. My primary method is to use comparison. Firstly, training corpus and …

Gammatone And Mfcc Features In Speaker Recognition, Wison Burgos

Theses and Dissertations

The feature analysis component of an Automated Speaker Recognition (ASR) system plays a crucial role in the overall performance of the system. There are many feature extraction techniques available, but ultimately we want to maximize the performance of these systems. From this point of view, the algorithms developed to compute feature components are analyzed. Current state-of-the-art ASR systems perform quite well in a controlled environment where the speech signal is noise free. The objective of this thesis investigates the results that can be obtained when you combine Mel-Frequency Cepstral Coefficients (MFCC) and Gammatone Frequency Cepstral Coefficients (GFCC) as feature components …

Evaluating And Training Intraoperative Analysis Of The Mitral Valve, Neil A. Tenenholtz

Link Foundation Modeling, Simulation and Training Fellowship Reports

Mitral valve repair is the recommended method of treating valve incompetency. However, the procedure is quite difficult and, as a result, underperformed due to surgeon’s need to predict the closed valve shape of the patient’s arrested heart. While the interactive process of predicting closed valve shape is achieved by physically manipulating valve tissue (known as valve analysis), surgical training consists of traditional, non-interactive pedagogy (e.g., book-based learning and lectures) followed by an apprenticeship model where the trainee is gradually given hands-on experience, resulting in post-medical school training that is often 10 years or greater. The continuing education of practicing cardiac …

A Physics-Based Modeling And Real-Time Simulation Of Biomechanical Diffusion Process Through Optical Imaged Alveolar Tissues On Graphical Processing Units, Ilhan Kaya

Link Foundation Modeling, Simulation and Training Fellowship Reports

Tissue engineering has broad applications fro1n creating the much needed engineered tissue and organ structures for regenerative medicine to providing in vitro testbeds for drug testing. In the later, application domain, creating alveolar lung tissue and simulating the diffusion process of oxygen and other possible agents front the air into the blood stream as well as modeling the removal of carbon dioxide and other possible entities-from the blood stream are of critical importance to simulating lung functions in various environments. In this paper, we propose a physics-based model to simulate the alveolar gas exchange and the alveolar diffusion process. Tissue …