Computer Engineering Commons^™

Artificial Immune System Based Wastewater Parameter Estimation, Cengi̇z Sertkaya, Ni̇lüfer Yurtay

Turkish Journal of Electrical Engineering and Computer Sciences

The basis of a wastewater treatment system is to achieve the desired characteristics of the wastewater treatment process. An estimation of the obtained wastewater treatment characteristics provides the information needed to set up the current process steps, and it is important to have an optimum treatment. In this study, an artificial immune system (AIS) structure is developed to estimate important wastewater output parameters such as pH, DBO, DQO, and SS for the first time. The proposed AIS models are based on the clonal selection principle, and the dataset is provided from the University of California Irvine (UCI) Machine Learning Library. …

Rapid Translation Of Finite-Element Theory Into Computer Implementation Based On A Descriptive Object-Oriented Programming Approach, Murat Yilmaz

Turkish Journal of Electrical Engineering and Computer Sciences

In this study, we present a framework for rapid prototyping of finite element (FE) theory for computer implementations. For this purpose, we propose an object-oriented (OO) application programming interface in the form of a domain-specific modeling language (DSML). In contrast to the traditional OO approach, the proposed framework deliberately avoids the use of subclassing for concrete implementations of node and element classes; it uses external objects, namely descriptors, instead. The descriptive design of the DSML provides developers with generic programming support for the construction and solution of discretization schemes, in the context of partial differential equations, in a self-explanatory syntax. …

Influence Maximization In Social Networks: An Integer Programming Approach, Muhammed Emre Keski̇n, Mehmet Güray Güler

Turkish Journal of Electrical Engineering and Computer Sciences

The use of social networks has been spreading rapidly in recent years. There is a growing interest in influence maximization in social networks, especially after observing that the effects of social events of the Arab Spring, Gezi events of Turkey, uprising in Ukraine, etc. have been built by the help of social networks. Consequently, many institutions like political parties or commercial firms are willing to spread their messages throughout social networks. There are many studies that concentrate on finding the most influential initial nodes, called seeds, which maximize the spread of an intended message over the social network. However, most …

Horizontal Diversity In Test Generation For High Fault Coverage, Arbab Alamgir, Abu Khari Bin A'Ain, Norlina Paraman, Usman Ullah Sheikh, Ian Grout

Turkish Journal of Electrical Engineering and Computer Sciences

Determination of the most appropriate test set is critical for high fault coverage in testing of digital integrated circuits. Among black-box approaches, random testing is popular due to its simplicity and cost effectiveness. An extension to random testing is antirandom that improves fault detection by maximizing the distance of every subsequent test pattern from the set of previously applied test patterns. Antirandom testing uses total Hamming distance and total cartesian distance as distance metrics to maximize diversity in the testing sequence. However, the algorithm for the antirandom test set generation has two major issues. Firstly, there is no selection criteria …

Short-Term Load Forecasting Of Natural Gas With Deep Neural Network Regression, Gregory Merkel, Richard J. Povinelli, Ronald H. Brown

Electrical and Computer Engineering Faculty Research and Publications

Deep neural networks are proposed for short-term natural gas load forecasting. Deep learning has proven to be a powerful tool for many classification problems seeing significant use in machine learning fields such as image recognition and speech processing. We provide an overview of natural gas forecasting. Next, the deep learning method, contrastive divergence is explained. We compare our proposed deep neural network method to a linear regression model and a traditional artificial neural network on 62 operating areas, each of which has at least 10 years of data. The proposed deep network outperforms traditional artificial neural networks by 9.83% weighted …

Deep Convolutional Particle Filter With Adaptive Correlation Maps For Visual Tracking, Reza Jilil Mozhdehi, Yevgeniy Vladimirovich Reznichenko, Abubakar Siddique, Henry P. Medeiros

Electrical and Computer Engineering Faculty Research and Publications

The robustness of the visual trackers based on the correlation maps generated from convolutional neural networks can be substantially improved if these maps are used to employed in conjunction with a particle filter. In this article, we present a particle filter that estimates the target size as well as the target position and that utilizes a new adaptive correlation filter to account for potential errors in the model generation. Thus, instead of generating one model which is highly dependent on the estimated target position and size, we generate a variable number of target models based on high likelihood particles, which …

Efficient Interconnectivity Among Networks Under Security Constraint, Pankaz Das, Rezoan A. Shuvro, Mahshid Rahnamay-Naeini, Nasir Ghani, Majeed M. Hayat

Electrical and Computer Engineering Faculty Research and Publications

Interconnectivity among networks is essential for enhancing communication capabilities of networks such as the expansion of geographical range, higher data rate, etc. However, interconnections may initiate vulnerability (e.g., cyber attacks) to a secure network due to introducing gateways and opportunities for security attacks such as malware, which may propagate from the less secure network. In this paper, the interconnectivity among subnetworks is maximized under the constraint of security risk. The dynamics of propagation of security risk is modeled by the evil-rain influence model and the SIR (Susceptible-Infected-Recovered) epidemic model. Through extensive numerical simulations using different network topologies and interconnection patterns, …

Efficiency Improvement Of Fault-Tolerant Three-Level Power Converters, Ramin Katebi, Jiangbiao He, Waqar A. Khan, Nathan Weise

Electrical and Computer Engineering Faculty Research and Publications

Fault-tolerant power converters play a critical role in the transportation electrification. However, fault-tolerant operation, high efficiency, and low cost usually result in design criteria that have conflicting constraints and goals. The majority of the fault-tolerant power converter topologies presented in the literature confirm these conflicts. In this paper, three types of fault-tolerant neutral-point clamped (NPC) converters are investigated. Various modulation strategies are explored to reduce the losses of the redundant phase leg. The simulation and experimental results show that the Switching Frequency Optimal Phase opposition Disposition modulation strategy is the most effective approach in minimizing the losses in the redundant …

Detection And Quantification Of Multi-Analyte Mixtures Using A Single Sensor And Multi-Stage Data-Weighted Rlse, Karthick Sothivelr, Florian Bender, Fabien Josse, Edwin E. Yaz, Antonio J. Ricco

Electrical and Computer Engineering Faculty Research and Publications

This work reports the development and experimental verification of a sensor signal processing technique for online identification and quantification of aqueous mixtures of benzene, toluene, ethylbenzene, xylenes (BTEX) and 1, 2, 4-trimethylbenzene (TMB) at ppb concentrations using time-dependent frequency responses from a single polymer-coated shear-horizontal surface acoustic wave sensor. Signal processing based on multi-stage exponentially weighted recursive leastsquares estimation (EW-RLSE) is utilized for estimating the concentrations of the analytes in the mixture that are most likely to have produced a given sensor response. The initial stages of EW-RLSE are used to eliminate analyte(s) that are erroneously identified as present in …

Stochastic Search Methods For Mobile Manipulators, Amoako-Frimpong Samuel Yaw, Matthew Messina, Henry P. Medeiros, Jeremy Marvel, Roger Bostelman

Electrical and Computer Engineering Faculty Research and Publications

Mobile manipulators are a potential solution to the increasing need for additional flexibility and mobility in industrial applications. However, they tend to lack the accuracy and precision achieved by fixed manipulators, especially in scenarios where both the manipulator and the autonomous vehicle move simultaneously. This paper analyzes the problem of dynamically evaluating the positioning error of mobile manipulators. In particular, it investigates the use of Bayesian methods to predict the position of the end-effector in the presence of uncertainty propagated from the mobile platform. The precision of the mobile manipulator is evaluated through its ability to intercept retroreflective markers using …

Assessing Ratio-Based Fatigue Indexes Using A Single Channel Eeg, Lucas B. Coffey

UNF Graduate Theses and Dissertations

Driver fatigue is a state of reduced mental alertness which impairs the performance of a range of cognitive and psychomotor tasks, including driving. According to the National Highway Traffic Safety Administration, driver fatigue was responsible for 72,000 accidents that lead to more than 800 deaths in 2015. A reliable method of driver fatigue detection is needed to prevent such accidents. There has been a great deal of research into studying driver fatigue via electroencephalography (EEG) to analyze brain wave data. These research works have produced three competing EEG data-based ratios that have the potential to detect driver fatigue.

Research has …

Deep Recurrent Learning For Efficient Image Recognition Using Small Data, Mahbubul Alam

Electrical & Computer Engineering Theses & Dissertations

Recognition is fundamental yet open and challenging problem in computer vision. Recognition involves the detection and interpretation of complex shapes of objects or persons from previous encounters or knowledge. Biological systems are considered as the most powerful, robust and generalized recognition models. The recent success of learning based mathematical models known as artificial neural networks, especially deep neural networks, have propelled researchers to utilize such architectures for developing bio-inspired computational recognition models. However, the computational complexity of these models increases proportionally to the challenges posed by the recognition problem, and more importantly, these models require a large amount of data …

Characterization Of Language Cortex Activity During Speech Production And Perception, Hassan Baker

Electrical & Computer Engineering Theses & Dissertations

Millions of people around the world suffer from severe neuromuscular disorders such as spinal cord injury, cerebral palsy, amyotrophic lateral sclerosis (ALS), and others. Many of these individuals cannot perform daily tasks without assistance and depend on caregivers, which adversely impacts their quality of life. A Brain-Computer Interface (BCI) is technology that aims to give these people the ability to interact with their environment and communicate with the outside world. Many recent studies have attempted to decode spoken and imagined speech directly from brain signals toward the development of a natural-speech BCI. However, the current progress has not reached practical …

Coexistence And Secure Communication In Wireless Networks, Saygin Bakşi

Electrical & Computer Engineering Theses & Dissertations

In a wireless system, transmitted electromagnetic waves can propagate in all directions and can be received by other users in the system. The signals received by unintended receivers pose two problems; increased interference causing lower system throughput or successful decoding of the information which removes secrecy of the communication. Radio frequency spectrum is a scarce resource and it is allocated by technologies already in use. As a result, many communication systems use the spectrum opportunistically whenever it is available in cognitive radio setting or use unlicensed bands. Hence, efficient use of spectrum by sharing users is crucial to increase maximize …

Applying Machine Learning To Advance Cyber Security: Network Based Intrusion Detection Systems, Hassan Hadi Latheeth Al-Maksousy

Computer Science Theses & Dissertations

Many new devices, such as phones and tablets as well as traditional computer systems, rely on wireless connections to the Internet and are susceptible to attacks. Two important types of attacks are the use of malware and exploiting Internet protocol vulnerabilities in devices and network systems. These attacks form a threat on many levels and therefore any approach to dealing with these nefarious attacks will take several methods to counter. In this research, we utilize machine learning to detect and classify malware, visualize, detect and classify worms, as well as detect deauthentication attacks, a form of Denial of Service (DoS). …

Resource Optimization In Wireless Sensor Networks For An Improved Field Coverage And Cooperative Target Tracking, Husam Sweidan

Dissertations, Master's Theses and Master's Reports

There are various challenges that face a wireless sensor network (WSN) that mainly originate from the limited resources a sensor node usually has. A sensor node often relies on a battery as a power supply which, due to its limited capacity, tends to shorten the life-time of the node and the network as a whole. Other challenges arise from the limited capabilities of the sensors/actuators a node is equipped with, leading to complication like a poor coverage of the event, or limited mobility in the environment. This dissertation deals with the coverage problem as well as the limited power and …

Implementing Write Compression In Flash Memory Using Zeckendorf Two-Round Rewriting Codes, Vincent T. Druschke

Dissertations, Master's Theses and Master's Reports

Flash memory has become increasingly popular as the underlying storage technology for high-performance nonvolatile storage devices. However, while flash offers several benefits over alternative storage media, a number of limitations still exist within the current technology. One such limitation is that programming (altering a bit from its default value) and erasing (returning a bit to its default value) are asymmetric operations in flash memory devices: a flash memory can be programmed arbitrarily, but can only be erased in relatively large batches of storage bits called blocks, with block sizes ranging from 512K up to several megabytes. This creates a situation …