Engineering Commons^™

Growing Reservoir Networks Using The Genetic Algorithm Deep Hyperneat, Nancy L. Mackenzie

Student Research Symposium

Typical Artificial Neural Networks (ANNs) have static architectures. The number of nodes and their organization must be chosen and tuned for each task. Choosing these values, or hyperparameters, is a bit of a guessing game, and optimizing must be repeated for each task. If the model is larger than necessary, this leads to more training time and computational cost. The goal of this project is to evolve networks that grow according to the task at hand. By gradually increasing the size and complexity of the network to the extent that the task requires, we will build networks that are more …

Memristors, Memcapacitors And Their Application In Neuromorphic Computing, Nithyakalyani Sampath

Student Research Symposium

Data-intensive computing operations, such as training neural networks, are essential but energy-intensive. Memcapacitance and memristance,which can be described as capacitance and resistance, with “memory”, are properties of semiconductor devices that are observed on the nano-scale. These properties allow for data storage without a constant source of power, leading to hardware which is more energy efficient.

We intend to demonstrate that we can build specialized hardware onto which a neural network can be directly mapped using memristors and memcapacitors, improving the energy efficiency of the network. We will use Simulation Program with Integrated Circuit Emphasis (SPICE) to model our memcapacitor and …

Development Of A Design Guideline For Pile Foundations Subjected To Liquefaction-Induced Lateral Spreading, Milad Souri, Arash Khosravifar

Student Research Symposium

Past earthquakes confirmed that seismically induced kinematic loads from soil lateral spreading and inertial loads from structure can cause severe damages to pile foundations. The research questions are:

• How to combine inertial and kinematic loads in design of pile foundations in liquefied soil?
• How the combination of inertia and kinematics changes with depth?
• How this combination is affected by long-duration earthquakes?
• How this combination affects inelastic demands in piles?

An Assessment Of The Decision Making Units’ Efficiency In Service Systems (The Case Of Cellular Telecom), Maoloud Dabab, Timothy R. Anderson

Student Research Symposium

Most tools and models on performance and quality of service management are generic and do not solve the complex technical systems, which the most critical component on the network and where these tools should be applied. The objective of this research is to assess the cellular performance and Base Transceiver Station (BTS) efficiency by proposing a robust model that is derived from multiple Key Performance Indicators (KPIs) based on technical and financial aspects. The novelty of this research provides a comprehensive multidimensional model for tuning the BTS parameters, which can lead to developing a standard global mobile network KPI. The …

Explanation Methods For Neural Networks, Jack H. Chen, Christof Teuscher

Student Research Symposium

Neural Networks (NNs) have become a basis of almost all state-of-the-art machine learning algorithms and classifiers. While NNs have been shown to generalize well to real-world examples, researchers have struggled to show why they work on an intuitive level. We designed several methods to explain the decisions of two state-of-the-art NN classifiers, ResNet and an All-CNN, in the context of the Japanese Society of Radiological Technology (JSRT) lung nodule dataset and the CIFAR-10 image dataset. Leading explanation methods LIME and Grad-CAM generate variations of heat maps which represent the regions of the input determined salient by the NN. We analyze …

Exploring And Expanding The One-Pixel Attack, Umairullah Khan, Walt Woods, Christof Teuscher

Student Research Symposium

In machine learning research, adversarial examples are normal inputs to a classifier that have been specifically perturbed to cause the model to misclassify the input. These perturbations rarely affect the human readability of an input, even though the model’s output is drastically different. Recent work has demonstrated that image-classifying deep neural networks (DNNs) can be reliably fooled with the modification of a single pixel in the input image, without knowledge of a DNN’s internal parameters. This “one-pixel attack” utilizes an iterative evolutionary optimizer known as differential evolution (DE) to find the most effective pixel to perturb, via the evaluation of …

Diagnostic Imaging Of Structural Concrete Using Ground Penetrating Radar And Ultrasonic Array, Sina Mehdinia, Thomas Schumacher, Eric Wan, Xubo Song

Student Research Symposium

Structural concrete is the most widely used construction material in the world. Many structures critical to a society such as bridges, hospitals, and airports are built with concrete. While this material is well understood from a mechanical design point of view, still no accurate quantitative tools exist to assess it for damage and deterioration. This is of particular concern for an urban area like Portland with a mega-thrust earthquake waiting to occur. Non-destructive evaluation tools that can quickly and accurately give a full picture of the integrity of structural concrete elements will be key to help plan effective and safe …

Reliable Explanations Via Adversarial Examples On Robust Networks, Walt Woods, Jack H. Chen, Christof Teuscher

Student Research Symposium

Neural Networks (NNs) are increasingly used as the basis of advanced machine learning techniques in sensitive fields such as autonomous vehicles and medical imaging. However, NNs have been found vulnerable to a class of imperceptible attacks, called adversarial examples, which arbitrarily alter the output of the network. To close the schism between needing reliability in real-world applications and the fragility of NNs, we propose a new method for stabilizing networks, and show that as an added bonus, our technique results in reliable, high-fidelity explanations for the NN's decision. Compared to the state-of-the-art, this technique increased the area under the curve …

Radiation Source Localization By Using Backpropagation Neural Network, Jian Meng, Christof Teuscher, Walt Woods

Student Research Symposium

The most difficult part of the radiation localization is that we cannot use the traditional acoustic localization method to determine where the radiation source is. It’s mainly because the electromagnetic waves are totally different with the sound wave. From the expression of the radioactive intensity, we can tell that the intensity of radiation not only depend on the distance from the radiation but also related to the type of the nuclide. In general, the relationship between the intensity and the distance satisfy the inverse-square law, which is a non-linear relationship. In other words, if we can use the measurement and …

Bond-Type Cfrp Anchorage System For Prestressed Concrete Applications, Yasir Saeed, Franz Rad, Salam Al-Obaidi

Student Research Symposium

High tensile strength, adjustable and high modulus of elasticity, high strength-to-weight ratio, and non-corrosiveness are great features which have made Fiber Reinforced Polymer (FRP) very attractive to engineers. Prestressed concrete applications require high strength prestressing material that could apply and maintain effective compressive force to concrete members. Although FRPs, especially Carbon FRP (CFRP), have the desired strength, no efficient system for its anchorage to concrete has been devised yet. This paper presents an experimental evaluation on new bond-type CFRP anchors. A total of eleven samples were prepared and tested. The CFRP rods were 0.375 in. and 0.50 in. diameter. The …

Biochemical Reservoir Computing, Hoang Nguyen, Christof Teuscher

Student Research Symposium

Reservoir computing is an emerging machine learning paradigm. Compared to traditional feedforward neural networks, the reservoir can be unstructured and recurrent and only the output layer is trained. Reservoirs can be built with various types of physical components, yet, biochemical building blocks have not been widely used. This project focuses on designing and testing a reservoir computer (RC) based on chemical reaction network (CRN). We simulated high-level CRNs in MATLAB and their complex chemical dynamics were observed over time. A CRN constructed by a network of coupled deoxyribozyme oscillators was chosen for the final RC model. The inputs of the …

Coastal Bridges Subjected To Waves: Analysis And Quantification Of Forces, Alaa Waleed Hameed, Thomas Schumacher

Student Research Symposium

Coastal bridges can be exposed to significant wave forces during hurricane events. This research is studying the parameters that govern the structural response through data analysis of a large experimental data set. This data set was generated by testing a heavily-instrumented 1:5-scale bridge superstructure model, which was modeled after the I-10 Bridge over the Escambia Bay, under various wave conditions and water levels in a large wave flume. A unique aspect of the model is that the flexibility of the substructure can be adjusted to represent different types of bridge support systems. This poster discusses the first part of the …

Apprehensive Drought Characteristics Over Iraq: Results Of A Multidecadal Spatiotemporal Assessment, Maysoun Ayad Hameed, Ali Ahmadalipour, Hamid Moradkhani

Student Research Symposium

Drought is an extreme climate phenomenon that happens slowly and periodically threatens the environmental and socio-economic sectors. Iraq is one of the countries in the Middle East that has been dealing with serious drought-related issues in the 21st century. Here, we investigate meteorological drought across Iraq from 1948 to 2009 at 0.25◦ spatial resolution. The Standardized Precipitation Evapotranspiration Index (SPEI) has been utilized as a multi-scalar drought index accounting for the effects of temperature variability on drought. Four of the main characteristics of drought including extent, intensity, frequency and duration are studied and the associated spatiotemporal patterns are investigated for …

Using Reservoir Computing To Build A Robust Interface With Dna Circuits In Determining Genetic Similarities Between Pathogens, Christopher Neighbor, Christof Teuscher

Student Research Symposium

As computational power increases, the field of neural networks has advanced exponentially. In particular recurrent neural networks (RNNs) are being utilized to simulate dynamic systems and to learn to predict time series data. Reservoir computing is an architecture which has the potential to increase training speed while reducing computational costs. Reservoir computing consists of a RNN with a fixed connections “reservoir” while only the output layer is trained. The purpose of this research is to explore the effective use of reservoir computing networks with the eventual application towards use in a DNA based molecular computing reservoir for use in pathogen …

Concrete Beams With Fully Corroded Steel Repaired With Cfrp Laminates, Needa M. Lingga, Yasir Saeed, Franz Rad, Anas Yosefani

Student Research Symposium

This research focused on concrete beams with voids simulating beams with fully corroded steel that were repaired with CFRP laminates. The experimental program included testing five, approximately one- third-scaled simply supported rectangular concrete beams. The aim was to investigate the extent of improvement by CFRP to flexural and shear capacity of beams that contain fully corroded steel bars, simulated by voids. Load carrying capacity, deflection, and ductility were measured and compared. Test results showed that one layer of CFRP increased the load capacity to slightly higher than the typical code-designed RC beam, and two layers of CFRP increased it by …

Wideband Absorber Characterization Using Coaxial Airline And Electromagnetic Simulation, Ha Tran, Thanh Le, Branimir Pejcinovic

Student Research Symposium

With the increase in popularity of electronic devices especially the wireless devices, microwave absorber becomes more essential to reduce electromagnetic interference. A deep understanding of electromagnetic properties namely electric permittivity and magnetic permeability is required in order to fabricate, test and use microwave absorber. In this study, we focused on developing a procedure to parameterize material electromagnetic properties. We first extract material properties by placing samples inside an airline and taking measurements of scattering parameters matrix with a vector network analyzer. Air-line is the preferred transmission line medium since the traveling wave inside the airline is both TEM and confined. …

Business Model Innovation: Review Of The Concept, Importance, Classifications, And Elements, Ahmed Alibage, Mark Ahn

Student Research Symposium

The research trend on business models continues to surge, foreseeing them as the future blueprint to create and sustain competitive advantages, as well as the major driver that guides the strategic renovation efforts of businesses all over the world. In this research, we intensively review the literature on the business model regarding the concept emergence, theoretical background, definitions, importance, classifications, and the structure of the elements. Our interest is in gaining a better understanding of how to innovate a business model that can lead to create and sustaincompetitive advantages. Based on our findings, the literature to date lacks the systematic …

Toward Understanding Pu And Peou Of Technology Acceptance Model, Nayem Rahman

Student Research Symposium

Technology Acceptance Model (TAM) is considered one of the most popular models used in Information System (IS) research. Fred Davis developed this model as part of his doctoral research at MIT in 1986. Since then this model has been widely used in IS research and other disciplines. Two main components of TAM are Perceived Usefulness (PU) and Perceived Ease of Use (PEOU). This model allowed researchers to plug-in external factors to these two components. Researchers have used a variety of external factors to draw relationships between these two internal factors of TAM model. However, most of the research used these …

Find, Build, And Export Information For 3d Printing Of Your Favorite Molecules And Crystal Structures At Two Dedicated Websites, Paul R. Destefano, Peter Moeck

Student Research Symposium

As 3D printers require instructions, the Nano-Crystallography Group at Portland State University is creating two websites (http://nanocrystallography.org/3dconvert/ and http://nanocrystallography.research.pdx.edu/3d-print-files/convert/) where such instructions are created, interactively, for the atomic arrangements of virtually all known molecules and crystals.

We will prepare a "pipeline" into which crystallographic information enters from two curated open access crystallographic databases, is manipulated to create the desired 3D models, and then is exported in either STL format (the standard for monochrome 3D printing) or VRML/X3D (the ISO successor to STL). The two aforementioned databases are the North-American mirror of the Crystallography Open Database (http://nanocrystallography.org) …

Monitoring Of Applied Stress In Concrete Using Ultrasonic Full-Waveform Comparison Techniques, Ali Hafiz

Student Research Symposium

Ultrasonic testing is a non-destructive approach commonly used to evaluate concrete structures. A challenge with concrete is that it is heterogeneous, which causes multiple wave scattering resulting in longer and more complex wave paths. The recorded ultrasonic waveform can be divided into two portions: the coherent (or early) and the diffuse (or Coda) portion. While conventional methods only use the coherent portion, e.g. the first wave arrival to determine the wave velocity, we are interested in the entire waveform, i.e. until the wave amplitude is completely dampened out. The objective of this study was to determine what portion of the …

Understanding Photovoltaic Properties Of Pbs Quantum Dot Solids Via Solution Contacting, Vitalii Dereviankin, Erik Johansson

Student Research Symposium

Photovoltaic (PV) devices based on PbS quantum dot (QD) solids demonstrate high photontoelectron conversion yields. However, record power conversion efficiency remain low, in part due to small photovoltages, which in turn are affected by both bulk and interfacial defects. Their relative impacts on limiting the photovoltaic performance of QD solids are not known. Interfacial defects can be formed when contacting a semiconductor and may dominate the semiconductor/metal or metaloxide junction properties. The objective of this study is to explore whether electrochemical contacting using liquid electrolytes provides means of contacting QD solids without introducing interfacial defects. We have initially focused on …

Fe Analysis Of Alternative Thermal Breaks For Steel Buildings, Salih Q. Mahmood

Student Research Symposium

“Thermal bridge” is a term used for structural or non-structural elements that have higher heat transfer than any other elements or spots in the building envelope, reducing the efficiency of the building thermal insulation. About 20% of the heat occurs via such thermal bridges. Thermal insulations (thermal breaks) are used within a steel connection to mitigate the effect of thermal bridges. In this research, connections with steel fillers studied by Dusicka (2007) were simulated using the finite element (FE) program ABAQUS. The results from the FE model were validated with those from the experimental work done by Dusicka (2007) and …

Extended Saleh Model For Behavioral Modeling Of Envelope Tracking Power Amplifiers, Haider Al Kanan, Fu Li, Felice Francesco Tafuri

Student Research Symposium

Envelope Tracking (ET) is one of the most deployed efficiency enhancement techniques to improve efficiency of RF Power Amplifiers (PAs) in wireless communication. ET PA behavioral models are important to predict the impact of the nonlinear distortion, and memory effect of ET PA on the spectrum in wireless communication. ET PA linearization techniques can be designed based on the behavioral modeling.

Comparing Mode Shares For Non-Residential Destinations In Urban And Suburban Environments, Tasnia Subrin

Student Research Symposium

To ensure facility for multimodal transportation is one of the most important concerns in today’s transportation sector, with initiatives being taken to make multimodal transportation popular. The built environment variables have a strong relationship with transportation mode choice, but whether that relationship holds true in urban and suburban neighborhoods in the same manner has not been considered. Using data for three non-residential land uses, this research explores whether the built environment variables in suburban areas influences mode share like it does in urban areas. We used survey data conducted at the establishments regarding respondents’ travel characteristics from a previous study, …

Factors Affecting Big Data Technology Adoption, Nayem Rahman

Student Research Symposium

With the advancement of computer science, hardware and software engineering, and computing power, and later with the advent of the internet, social networking tools and other sources such as sensors data growth has increased significantly. These data are called big data which are mostly unstructured, generated in large volumes, data need to be captured in near real-time. To handle big data a completely new set of tools and technologies are being emerged. I have studied big data literature to identify the factors that might influence big data adoption. I was able to list quite a few factors or attributes that …

Design, Construction, And Utilization Of Physical Vapor Deposition Systems For Medical Sensor Fabrication, Nicholas Sayre, Erik J. Sánchez, Joe Kowalski

Student Research Symposium

The development of a novel blood glucose sensor is realized through construction of a homemade plasma coating system and utilization of semiconductor manufacturing processes in a small scale cleanroom environment. Photolithography, plasma sputtering, chemical etching and thin film measurement technologies are used in the medical sensor fabrication process. General process flow will be discussed, and system design and the plasma sputtering process will be presented as it is achieved by the system currently under development.

Agent-Based Control Of A Flapping Wing Micro Aerial Vehicle, Michal Podhradský

Student Research Symposium

Flapping wing micro aerial vehicles (FWMAVs) are biomimetic vehicles, because they imitate insects in the way they fly. FWMAVs are very small and highly manoeuvrable and can be used in reconnaissance, environmental monitoring, search & rescue, and other applications. The goal of the project is to develop & verify an agent based flight controller for FWMAV that can adapt to different flight conditions, actuator failures, and different vehicles while delivering constant performance. Agent based control was successfully applied in industry and distributed applications, but to our best knowledge never in an actual flying vehicle. Agent based control utilizes machine learning, …

Detecting Rule Of Balance In Photography, Uyen T. Mai, Feng Liu

Student Research Symposium

Rule of Balance is one of the most important composition rules in photography, which can be used as a standard for photo quality assessment. The rule of balance states that images with evenly distributed visual elements are visually pleasing and thus are highly aesthetic. This work presents a method to automatically classify balanced and unbalanced images. Detecting the rule of balance requires a robust technique to locate and analyze important objects and visual elements, which involves understanding of the image content. Since semantic understanding is currently beyond the state of the art in computer vision, we employ the saliency maps …

Computational Capabilities Of Leaky Integrate-And-Fire Neural Networks For Liquid State Machines, Amin Almassian, Christof Teuscher

Student Research Symposium

We analyze the computational capability of Leaky Integrate-and-Fire (LIF) Neural Networks used as a reservoir (liquid) in the framework of Liquid State Machines (LSM). Maass et. al. investigated LIF neurons in LSM and their results showed that they are capable of noise-robust, parallel, and real-time computation. However, it still remains an open question how the network topology affects the computational capability of a reservoir. To address that question, we investigate the performance of the reservoir as a function of the average reservoir connectivity. We also show that the dynamics of the LIF reservoir is sensitive to changes in the average …

Designing A Low Cost Prosthetic Arm Device, Samira Rezaei, Frank Fields, Tamara J. Depue

Student Research Symposium

The goal of the project is to build a functional low-cost prosthetic arm that is easily maintained. The focus is on prostheses that attach to the forearm. This design must perform daily life tasks such as picking up, holding and carrying objects while playing and working. To begin the design, a mechanical finger was built with wooden tongue depressors as bone material; rubber bands, string, and drinking straws as muscle material; and masking tape as ligament and tendon material. The length of each joint was set to the golden ratio. Using this method, a basic "hand" was created that could …