Digital Commons Network^™

A Broad Spectrum Defense Against Adversarial Examples, Sean Mcguire

Theses and Dissertations

Machine learning models are increasingly employed in making critical decisions across a wide array of applications. As our dependence on these models increases, it is vital to recognize their vulnerability to malicious attacks from determined adversaries. In response to these adversarial attacks, new defensive mechanisms have been developed to ensure the security of machine learning models and the accuracy of the decisions they make. However, many of these mechanisms are reactionary, designed to defend specific models against a known specific attack or family of attacks. This reactionary approach does not generalize to future "yet to be developed" attacks. In this …

Towards Efficient Scoring Of Student-Generated Long-Form Analogies In Stem, Thilini Wijesiriwardene, Ruwan Wickramarachchi, Valerie L. Shalin, Amit P. Sheth

Publications

Switching from an analogy pedagogy based on comprehension to analogy pedagogy based on production raises an impractical manual analogy scoring problem. Conventional symbol-matching approaches to computational analogy evaluation focus on positive cases, and challenge computational feasibility. This work presents the Discriminative Analogy Features (DAF) pipeline to identify the discriminative features of strong and weak long-form text analogies. We introduce four feature categories (semantic, syntactic, sentiment, and statistical) used with supervised vector-based learning methods to discriminate between strong and weak analogies. Using a modestly sized vector of engineered features with SVM attains a 0.67 macro F1 score. While a semantic feature …

Height Information Aided 3d Real-Time Large-Scale Underground User Positioning, Houbing Song, Chengkai Tang, Cunle Zhang, Lingling Zhang, Yi Zhang

Publications

Due to the cost of inertial navigation and visual navigation equipment and lake of satellite navigation signals, they cannot be used in large‐scale underground mining environment. To solve this problem, this study proposes large‐scale underground 3D real‐time positioning method with seam height assistance. This method uses the ultrawide band positioning base station as the core and is combined with seam height information to build a factor graph confidence transfer model to realise3D positioning. The simulation results show that the proposed real‐time method is superior to the existing algorithms in positioning accuracy and can meet the needs of large‐scale underground users.

Parasol: Efficient Parallel Synthesis Of Large Model Spaces, Clay Stevens, Hamid Bagheri

School of Computing: Conference and Workshop Papers

Formal analysis is an invaluable tool for software engineers, yet state-of-the-art formal analysis techniques suffer from well-known limitations in terms of scalability. In particular, some software design domains—such as tradeoff analysis and security analysis—require systematic exploration of potentially huge model spaces, which further exacerbates the problem. Despite this present and urgent challenge, few techniques exist to support the systematic exploration of large model spaces. This paper introduces Parasol, an approach and accompanying tool suite, to improve the scalability of large-scale formal model space exploration. Parasol presents a novel parallel model space synthesis approach, backed with unsupervised learning to automatically derive …

An Empirical Comparison Of The Security And Performance Characteristics Of Topology Formation Algorithms For Bitcoin Networks, Muntadher Sallal, Ruairí De Fréin, Ali Malik, Benjamin Aziz

Articles

There is an increasing demand for digital crypto-currencies to be more secure and robust to meet the following business requirements: (1) low transaction fees and (2) the privacy of users. Nowadays, Bitcoin is gaining traction and wide adoption. Many well-known businesses have begun accepting bitcoins as a means of making financial payments. However, the susceptibility of Bitcoin networks to information propagation delay, increases the vulnerability to attack of the Bitcoin network, and decreases its throughput performance. This paper introduces and critically analyses new network clustering methods, named Locality Based Clustering (LBC), Ping Time Based Approach (PTBC), Super Node Based Clustering …

Studying Routing Issues In Vanets Using Ns-3 And Sumo, Mohammad Mahmoud Abdellatif, Omar E. Aly

Electrical Engineering

ehicular Ad-hoc Networks VANETs are normally sparse, highly dense, and highly mobile with many different and ever-changing topologies. These characteristics impose a challenge on finding a routing algorithm that fits the requirements of such network. The aim of this work is to study the performance issues of VANETs under different scenarios using realistic mobility models. In this paper, a comparative study is done among Ad-hoc On- Demand Distance Vector (AODV), Optimized Link State Routing (OLSR) and position-based routing protocols, namely Greedy Perimeter stateless routing (GPSR), and Max duration Min angle GPSR (MMGPSR). The comparison is done using key quality of …

An Inexpensive Maximum Power Point Tracking System For An Insulated Solar Electric Cooker Using An Off-The-Shelf Buck Converter, Andrew A. Perez

Physics

A specialized control circuit using an off-the-shelf buck converter is built for an Insulated Solar Electric Cooker (ISEC). Cost and efficient power delivery are the focus. An ISEC is synonymous to a direct load heat resistor, allowing a specific maximum power point tracking (MPPT) algorithm and fewer components. Only a microcontroller, voltage sensor, and digital-to-analog converter are used with the buck converter to maximize the power delivered by a 100W solar panel for the 3.3Ω load.

A Conical-Beam Dual-Band Double Aperture-Coupled Stacked Elliptical Patch Antenna Design For 5g, Feza Turgay Çeli̇k, Kami̇l Karaçuha

Turkish Journal of Electrical Engineering and Computer Sciences

This study investigates a dual-band, aperture coupled and stacked elliptical patch antenna with conical radiation. To obtain such characteristics, the TM21 mode of the radiating elliptical patches is excited by utilizing two special apertures and shorting planes. The proposed antenna operates both at 2.45 GHz and 3.5 GHz. The design aims to be used indoor applications of 5G operating in both free and planned 5G bands, respectively. Therefore, the low-profile antenna element that has a monopole-like radiation pattern is a good candidate for two-dimensional arraying. The design steps and the evolution of the proposed antenna are presented in detail. The …

Segmentation Of Diatoms Using Edge Detection And Deep Learning, Hüseyi̇n Gündüz, Cüneyd Nadi̇r Solak, Serkan Günal

Turkish Journal of Electrical Engineering and Computer Sciences

Diatoms are photosynthesizing algae found in almost every aquatic environment. Detecting the number and diversity of diatoms is very important to analyze water quality appropriately. Accurate segmentation of diatoms is therefore crucial for this detection process. In this study, a new and effective model for the automatic segmentation of diatoms based on image processing and deep learning algorithms is proposed. In the proposed model, edge segments of a given image containing diatoms and nondiatom particles are first obtained. These edge segments are then combined, resulting in closed contours representing diatom candidates. In the final step, the diatom candidates are classified …

Comparison Of Ml Algorithms To Distinguish Between Human Or Human-Like Targets Using The Hog Features Of Range-Time And Range-Doppler Images In Through-The-Wall Applications, Yunus Emre Acar, İsmai̇l Saritaş, Ercan Yaldiz

Turkish Journal of Electrical Engineering and Computer Sciences

When detecting the human targets behind walls, false detections occur for many systematic and environmental reasons. Identifying and eliminating these false detections is of great importance for many applications. This study investigates the potential of machine learning (ML) algorithms to distinguish between the human and human-like targets behind walls. For this purpose, a stepped-frequency continuous-wave (SFCW) radar has been set up. Experiments have been carried out with real human targets and moving plates imitating a regular breath of a healthy human. Unlike conventional methods, human and human-like returns are classified using range-Doppler images containing range and Doppler information. Then, the …

A New Approach For Congestive Heart Failure And Arrhythmia Classification Using Downsampling Local Binary Patterns With Lstm, Süleyman Akdağ, Fatma Kuncan, Yilmaz Kaya

Turkish Journal of Electrical Engineering and Computer Sciences

Electrocardiogram (ECG) is a vital diagnosis approach for the rapid explication and detection of various heart diseases, especially cardiac arrest, sinus rhythms, and heart failure. For this purpose, in this study, a different perspective based on downsampling one-dimensional-local binary pattern (1D-DS-LBP) and long short-term memory (LSTM) is presented for the categorization of Electrocardiogram (ECG) signals. A transformation method named 1DDS-LBP has been presented for Electrocardiogram signals. The 1D-DS-LBP method processes the bigness smallness relationship between neighbors. According to the proposed method, by downsampling the signal, the histograms of 1D local binary patterns (1D-LBP) calculated from the obtained signal groups are …

A Quantitative Evaluation Of Explainable Ai Methods Using The Depth Of Decision Tree, Nizar Abdulaziz Mahyoub Ahmed, Adi̇l Alpkoçak

Turkish Journal of Electrical Engineering and Computer Sciences

It is necessary to develop an explainable model to clarify how and why a medical model makes a particular decision. Local posthoc explainable AI (XAI) techniques, such as SHAP and LIME, interpret classification system predictions by displaying the most important features and rules underlying any prediction locally. Therefore, in order to compare two or more XAI methods, they must first be evaluated qualitatively or quantitatively. This paper proposes quantitative XAI evaluation metrics that are not based on biased and subjective human judgment. On the other hand, it is dependent on the depth of the decision tree (DT) to automatically and …

A New Network-Based Community Detection Algorithm For Disjoint Communities, Peli̇n Çeti̇n, Şahi̇n Emrah Amrahov

Turkish Journal of Electrical Engineering and Computer Sciences

A community is a group of people that shares something in common. The definition of the community can be generalized as things that have common properties. By using this definition, community detection can be used to solve different problems in various areas. In this study, we propose a new network-based community detection algorithm that can work on different types of datasets. The proposed algorithm works on unweighted graphs and determines the weight by using cosine similarity. We apply a bottom-up approach and find the disjoint communities. First, we accept each node as an independent community. Then, the merging process is …

On Approximate Nash Equilibria Of The Two-Source Connection Game, Buğra Çaşkurlu, Utku Umur Açikalin, Fati̇h Erdem Kizilkaya, Özgün Eki̇ci̇

Turkish Journal of Electrical Engineering and Computer Sciences

The arbitrary-sharing connection game is prominent in the network formation game literature [1]. An undirected graph with positive edge weights is given, where the weight of an edge is the cost of building it. An edge is built if agents contribute a sufficient amount for its construction. For agent i, the goal is to contribute the least possible amount while assuring that the source node si is connected to the terminal node ti . In this paper, we study the special case of this game in which there are only two source nodes. In this setting, we prove that there …

Chemical Disease Relation Extraction Through The Combination Of Multiple Mention Levels: Relscan+, Stanley Chika Onye, Nazi̇fe Di̇mi̇li̇ler, Ari̇f Akkeleş

Turkish Journal of Electrical Engineering and Computer Sciences

Chemical-induced disease (CID) relation extraction has been pivotal in the understanding of biological processes. A CID relation between a chemical and disease entity may be extracted either from a single sentence or from two or more adjacent sentences. We use `intrasentence level' to refer to the mention of the desired entities in the same sentence and `intersentence level? to refer to the mention of these entities in two or more adjacent sentences. This study proposes a three-phase architecture for extracting CID relations from biomedical literature by considering both sentence levels and additionally the combination of these two sentence levels which …

Learning To Play An Imperfect Information Card Game Using Reinforcement Learning, Buğra Kaan Demi̇rdöver, Ömer Baykal, Ferdanur Alpaslan

Turkish Journal of Electrical Engineering and Computer Sciences

Artificial intelligence and machine learning are widely popular in many areas. One of the most popular ones is gaming. Games are perfect testbeds for machine learning and artificial intelligence with various scenarios and types. This study aims to develop a self-learning intelligent agent to play the Hearts game. Hearts is one of the most popular trick-taking card games around the world. It is an imperfect information card game. In addition to having a huge state space, Hearts offers many extra challenges due to its nature. In order to ease the development process, the agent developed in the scope of this …

Presenting A Method To Detect Intrusion In Iot Through Private Blockchain, Rezvan Mahmoudie, Saeed Parsa, Amir Masoud Rahmani

Turkish Journal of Electrical Engineering and Computer Sciences

Blockchain (BC) has been used as a new solution to overcome security and privacy challenges in the Internet of Things (IoT). However, recent studies have indicated that the BC has a limited scalability and is computationally costly. Also, it has significant overhead and delay in the network, which is not suitable to the nature of IoT. This article aims at implementing BC in the IoT context for smart home management, as the integration of these two technologies ensures the IoT's security and privacy. Therefore, we proposed an overlay network in private BC to optimize its compatibility with IoT by increasing …

Design And Implementation Of A Low Cost And Portable Tactile Stimulator, Coşkun Kazma, Vecdi̇ Emre Levent, Merve Çardak, Ni̇zametti̇n Aydin

Turkish Journal of Electrical Engineering and Computer Sciences

When central nervous system has a problem, somatic area I and II respond to stimulation differently. Therefore, it is possible to identify some of the central nervous diseases when somatosensory on the fingertip is stimulated and responses are recorded and analyzed. We designed a system to stimulate the mechanoreceptors on fingertips. It is composed of a mechanical system for fingertip stimulation, an embedded controller, a control computer, and a software to control overall operation. During test, mechanoreceptors are stimulated according to the test protocols. Individuals' answers are recorded to be evaluated by the developed software. In this study, several design …

A New Classification Network For Diagnosing Alzheimer’S Disease In Class-Imbalance Mri Datasets, Ziyang Chen, Zhuowei Wang, Meng Zhao, Qin Zhao, Xuehu Liang, Jiajian Li, Xiaoyu Song

Electrical and Computer Engineering Faculty Publications and Presentations

Automatic identification of Alzheimer’s Disease (AD) through magnetic resonance imaging (MRI) data can eectively assist to doctors diagnose and treat Alzheimer’s. Current methods improve the accuracy of AD recognition, but they are insufficient to address the challenge of small interclass and large intraclass dierences. Some studies attempt to embed patch-level structure in neural networks which enhance pathologic details, but the enormous size and time complexity render these methods unfavorable. Furthermore, several self-attention mechanisms fail to provide contextual information to represent discriminative regions, which limits the performance of these classifiers. In addition, the current loss function is adversely aected by outliers …

Natural Language Processing For Novel Writing, Leqing Qu, Okan Ersoy

Department of Electrical and Computer Engineering Technical Reports

No abstract provided.

Synthetic Aperture Radar Imaging, Srivatsan Ravichandran, Okan Ersoy

Department of Electrical and Computer Engineering Technical Reports

Simulation programs are used to locate the positions of the input target points and generate a 2D SAR image with the Range Migration Algorithm. Using the same methodology, we can create a scene geometry using the concept of Point cloud and run the simulation program to generate raw SAR data.

Low-Cost Compact Optical Spectroscopy And Novel Spectroscopic Algorithm For Point-Of-Care Real-Time Monitoring Of Nanoparticle Delivery In Biological Tissue Models, Zahid Hasan, Jing Yan, Zhongchao Yi, Madison O. Korfhage, Sheng Tong, Caigang Zhu

Markey Cancer Center Faculty Publications

Objective: Real-time monitoring of nanoparticle delivery in biological models is essential to optimize nanoparticle- mediated therapies. However, few techniques are available for convenient real-time monitoring of nanoparticle concentrations in tissue samples. This work reported novel optical spectroscopic approaches for low-cost point-of-care real-time quantification of nanoparticle concentrations in biological tissue samples.

Methods: Fiber probe measured diffuse reflectance can be described with a simple analytical model by introducing an explicit dependence on the reduced scattering coefficient. Relying on this, the changes on the inverse of diffuse reflectance are proportional to absorption change when the scattering perturbation is negligible. We developed this model …

Analysis Of Patch And Sample Size Effects For 2d-3d Cnn Models Using Multiplatform Dataset: Hyperspectral Image Classification Of Rosis And Jilin-1 Gp01 Imagery, Taşkin Kavzoğlu, Eli̇f Özlem Yilmaz

Turkish Journal of Electrical Engineering and Computer Sciences

Modern hyperspectral sensors provide a huge volume of data at spectral and spatial domains with high redundancy, which requires robust methods for analysis. In this study, 2D and 3D CNN models were applied to hyperspectral image datasets (ROSIS and Jilin-1 GP01) using varying patch and sample sizes to determine their combined impacts on the performance of deep learning models. Differences in classification performances in relation to particle and sample sizes were statistically analysed using McNemar?s test. According to the findings, raising the patch and sample size enhances the performance of the 2D/3D CNN model and produces more accurate results in …

Noncontact Machinery Operation Status Monitoring System With Gated Recurrent Unit Model, Jason Jing Wei Lim, Boon Yaik Ooi, Wai Kong Lee, Teik Boon Tan, Soung Yue Liew

Turkish Journal of Electrical Engineering and Computer Sciences

In manufacturing industry, assembly line monitoring provides statistical information about overall performance and reliability of the legacy machines, ensuring that the machines give maximum yield output. However, most legacy machines lack internet connectivity and advanced functionality, increasing the difficulty for tracking task. Therefore, this work seeks to introduce a noncontact acoustic method to track machines rather than the mainstream vibrational approach. In order to provide accurate tracking of the daily machine operation for our machine tracking system, we consider scenario of background noises such as environmental sounds from multiple sources as well as neighbouring machine?s sound. Thus, several neural networks …

Diacritics Correction In Turkish With Context-Aware Sequence To Sequence Modeling, Asi̇ye Tuba Özge, Özge Bozal, Umut Özge

Turkish Journal of Electrical Engineering and Computer Sciences

Digital texts in many languages have examples of missing or misused diacritics which makes it hard for natural language processing applications to disambiguate the meaning of words. Therefore, diacritics restoration is a crucial step in natural language processing applications for many languages. In this study we approach this problem as bidirectional transformation of diacritical letters and their ASCII counterparts, rather than unidirectional diacritic restoration. We propose a context-aware character-level sequence to sequence model for this transformation. The model is language independent in the sense that no language-specific feature extraction is necessary other than the utilization of word embeddings and is …

Mitigating Cascading Failures In Power Grids Via Markov Decision-Based Load-Shedding With Dc Power Flow Model, Pankaz Das, Rezoan Ahmed Shuvro, Kassie Povinelli, Francesco Sorrentino, Majeed M. Hayat

Electrical and Computer Engineering Faculty Research and Publications

Despite the reliability of modern power systems, large blackouts due to cascading failures (CFs) do occur in power grids with enormous economic and societal costs. In this article, CFs in power grids are theoretically modeled proposing a Markov decision process (MDP) framework with the aim of developing optimal load-shedding (LS) policies to mitigate CFs. The embedded Markov chain of the MDP, established earlier to capture the dynamics of CFs, features a reduced state-space and state-dependent transition probabilities. We introduce appropriate actions affecting the dynamics of CFs and associated costs. Optimal LS policies are computed that minimize the expected cumulative cost …

Multichannel Blind Deconvolution Of Circularly Polarized Imagery, Patrick B. Cunningham

Theses and Dissertations

Current methods can be used to recreate an expected Stokes polarization vector from measured light for characterization purposes. However, this only applies to three of the Stokes parameters, that is, the linear polarization components. Circular polarization is not currently being utilized for object characterization because the mathematical complexity is greater than for that of linear polarization. This research will analyze a way to expand existing algorithms to include circular polarization and enable the complete reconstruction of the Stokes vector from the measured light into a blind deconvolution algorithm for Stokes estimation and image reconstruction.

Development Of A Security-Focused Multi-Channel Communication Protocol And Associated Quality Of Secure Service (Qoss) Metrics, Paul M. Simon

Theses and Dissertations

The threat of eavesdropping, and the challenge of recognizing and correcting for corrupted or suppressed information in communication systems is a consistent challenge. Effectively managing protection mechanisms requires an ability to accurately gauge the likelihood or severity of a threat, and adapt the security features available in a system to mitigate the threat. This research focuses on the design and development of a security-focused communication protocol at the session-layer based on a re-prioritized communication architecture model and associated metrics. From a probabilistic model that considers data leakage and data corruption as surrogates for breaches of confidentiality and integrity, a set …

Accelerated Bs/Ms Program In Electrical And Computer Engineering, Robert S. Woodley, Steve Eugene Watkins

Electrical and Computer Engineering Faculty Research & Creative Works

The Electrical and Computer Engineering Department at Missouri University of Science and Technology implemented an Accelerated BS/MS Program in 2019. This program is designed to encourage and facilitate undergraduate majors in electrical and computer engineering to pursue a masters program. It is similar to engineering programs at other institutions that are identified with titles such as accelerated masters, combined BS/MS, and 4+1 options. It reduces the time needed for undergraduates to earn a graduate degree and exposes these students to research work. It provides a route for faculty to obtain quality graduate students and it builds enrollment for the department. …

Falcon Neuro: An Event-Based Sensor On The International Space Station, Matthew G. Mcharg, Richard L. Balthazor, Matthew P. Borg, Brian J. Mcreynolds, David H. Howe, Colin J. Maloney, Daniel O'Keefe, Rayomand Bam, Gabriel Wilson, Paras Karki, Alexandre Marcireau, Gregory Cohen

Student Publications

We report on the Falcon neuro event-based sensor (EBS) instrument that is designed to acquire data from lightning and sprite phenomena and is currently operating on the International Space Station. The instrument consists of two independent, identical EBS cameras pointing in two fixed directions, toward the nominal forward direction of flight and toward the nominal Nadir direction. The payload employs stock DAVIS 240C focal plane arrays along with custom-built control and readout electronics to remotely interface with the cameras. To predict the sensor’s ability to effectively record sprites and lightning, we explore temporal response characteristics of the DAVIS 240C and …