Digital Commons Network^™

Applying Deep Learning For Cell Detection In Time-Lapse Microscopic Images, Jay Patel

Honors Theses

The budding yeast Saccharomyces cerevisiae is an effective model for studying cellular aging. We can measure the lifespan of yeast cells in two ways: replicative and chronological lifespans. Chronological focuses on the time that a cell can survive. The replicative lifespan (RLS) is the number of cell divisions that a single mother cell can go through before ceases to be dividing. RLS is a measurement of individual cells and is more informative on the aging process than in chronological lifespan. Many genes that influence yeast RLS have been shown to be highly conserved and have a similar effect on aging …

Antipodal Robotic Grasping Using Deep Learning, Shirin Joshi

Theses

In this work, we discuss two implementations that predict antipodal grasps for novel objects: A deep Q-learning approach and a Generative Residual Convolutional Neural Network approach. We present a deep reinforcement learning based method to solve the problem of robotic grasping using visio-motor feedback. The use of a deep learning based approach reduces the complexity caused by the use of hand-designed features. Our method uses an off-policy reinforcement learning framework to learn the grasping policy. We use the double deep Q-learning framework along with a novel Grasp-Q-Network to output grasp probabilities used to learn grasps that maximize the pick success. …

Behavioral Model Based Trust Management Design For Iot At Scale, Brennan Huber

Masters Theses and Doctoral Dissertations

With the rise in the number of devices in the Internet of Things (IoT), the number of malicious devices will also drastically increase. Smart cities' decisions are based on data being collected by IoT devices in real-time, of which a connected-vehicle system is included. Behaviors such as malicious data injection can significantly impact connected vehicles. To aid in combating this threat, monitoring smart city and connected vehicle's sensor data will allow for construction of a behavioral model. Implementing machine learning will aid in constructing a standard behavior such that any device that begins to malfunction or behave maliciously can be …

Archaeology Or Crime Scene? Teeth Micro And Macro Structure Analysis As Dating Variable, Jessica A. Vincenty

Student Theses

Simple methods to aid in the determination of forensic or archaeologic relevancy of skeletonized remains have been researched since the 1950s. With advances in microscopic imaging techniques and machine learning computer data analysis methods the relevancy of decontextualized, comingled remains has room for improvement. This thesis is a study done to pioneer a new approach to analyzing dental skeletal remains to determine forensic relevancy.

Archaeological dental samples collected from the ancient city of Ur in modern day southern Iraq in addition to modern dental extractions were processed for scanning electron microscopy imaging. Archaeological and modern samples displayed different surface and …

Signal Processing Combined With Machine Learning For Biomedical Applications, Md Shakhawat Hossain

Theses and Dissertations

The Master’s thesis is comprised of four projects in the realm of machine learning and signal processing. The abstract of the thesis is divided into four parts and presented as follows,

Abstract 1: A Kullback-Leibler Divergence-Based Predictor for Inter-Subject Associative BCI.

Inherent inter-subject variability in sensorimotor brain dynamics hinders the transferability of brain-computer interface (BCI) model parameters across subjects. An individual training session is essential for effective BCI control to compensate for variability. We report a Kullback-Leibler Divergence (KLD)-based predictor for inter-subject associative BCI. An online dataset comprising left/right hand, both feet, and tongue motor imagery tasks was used to …

Learning Dynamics From Large Biological Data Sets: Machine Learning Meets Systems Biology, William Gilpin, Yitong Huang, Daniel B. Forger

Mathematics Sciences: Faculty Publications

In the past few decades, mathematical models based on dynamical systems theory have provided new insight into diverse biological systems. In this review, we ask whether the recent success of machine learning techniques for large-scale biological data analysis provides a complementary or competing approach to more traditional modeling approaches. Recent applications of machine learning to the problem of learning biological dynamics in diverse systems range from neuroscience to animal behavior. We compare the underlying mechanisms and limitations of traditional dynamical models with those of machine learning models. We highlight the unique role that traditional modeling has played in providing predictive …

Novel Deep Learning Methods Combined With Static Analysis For Source Code Processing, Duy Quoc Nghi Bui

Dissertations and Theses Collection (Open Access)

It is desirable to combine machine learning and program analysis so that one can leverage the best of both to increase the performance of software analytics. On one side, machine learning can analyze the source code of thousands of well-written software projects that can uncover patterns that partially characterize software that is reliable, easy to read, and easy to maintain. On the other side, the program analysis can be used to define rigorous and unique rules that are only available in programming languages, which enrich the representation of source code and help the machine learning to capture the patterns better. …

Data-Driven Control With Learned Dynamics, Wenjian Hao

All Theses

This research focuses on studying data-driven control with dynamics that are actively learned from machine learning algorithms. With system dynamics being identified using neural networks either explicitly or implicitly, we can apply control following either a model-based approach or a model-free approach. In this thesis, the two different methods are explained in detail and finally compared to shed light on the emerging data-driven control research field.

In the first part of the thesis, we first introduce state-of-art Reinforcement Learning (RL) algorithm representing data-driven control using a model-free learning approach. We discuss the advantages and shortcomings of the current RL algorithms …

Water Quality Prediction Based On Machine Learning Techniques, Zhao Fu

UNLV Theses, Dissertations, Professional Papers, and Capstones

Water is one of the most important natural resources for all living organisms on earth. The monitoring of treated wastewater discharge quality is vitally important for the stability and protection of the ecosystem. Collecting and analyzing water samples in the laboratory consumes much time and resources. In the last decade, many machine learning techniques, like multivariate linear regression (MLR) and artificial neural network (ANN) model, have been proposed to address the problem. However, simple linear regression analysis cannot accurately forecast water quality because of complicated linear and nonlinear relationships in the water quality dataset. The ANN model also has shortcomings …

Age-Suitability Prediction For Literature Using Deep Neural Networks, Eric Robert Brewer

Theses and Dissertations

Digital media holds a strong presence in society today. Providers of digital media may choose to obtain a content rating for a given media item by submitting that item to a content rating authority. That authority will then issue a content rating that denotes to which age groups that media item is appropriate. Content rating authorities serve publishers in many countries for different forms of media such as television, music, video games, and mobile applications. Content ratings allow consumers to quickly determine whether or not a given media item is suitable to their age or preference. Literature, on the other …

Critical Media, Information, And Digital Literacy: Increasing Understanding Of Machine Learning Through An Interdisciplinary Undergraduate Course, Barbara R. Burke, Elena Machkasova

Irish Communication Review

Widespread use of Artificial Intelligence in all areas of today’s society creates a unique problem: algorithms used in decision-making are generally not understandable to those without a background in data science. Thus, those who use out-of-the-box Machine Learning (ML) approaches in their work and those affected by these approaches are often not in a position to analyze their outcomes and applicability.

Our paper describes and evaluates our undergraduate course at the University of Minnesota Morris, which fosters understanding of the main ideas behind ML. With Communication, Media & Rhetoric and Computer Science faculty expertise, students from a variety of majors, …

A Machine Learning Approach To Delineating Neighborhoods From Geocoded Appraisal Data, Rao Hamza Ali, Josh Graves, Stanley Wu, Jenny Lee, Erik Linstead

Engineering Faculty Articles and Research

Identification of neighborhoods is an important, financially-driven topic in real estate. It is known that the real estate industry uses ZIP (postal) codes and Census tracts as a source of land demarcation to categorize properties with respect to their price. These demarcated boundaries are static and are inflexible to the shift in the real estate market and fail to represent its dynamics, such as in the case of an up-and-coming residential project. Delineated neighborhoods are also used in socioeconomic and demographic analyses where statistics are computed at a neighborhood level. Current practices of delineating neighborhoods have mostly ignored the information …

Predicting The Long-Term Stability Of Compact Multiplanet Systems, Daniel Tamayo, Miles Cranmer, Samuel Hadden, Hanno Rein, Peter Battaglia, Alysa Obertas, Philip J. Armitage, Shirley Ho, David N. Spergel, Christian Gilbertson, Naireen Hussain, Ari Silburt, Daniel Jontof-Hutter, Kristen Menou

Pacific Faculty Work

We combine analytical understanding of resonant dynamics in two-planet systems with machine-learning techniques to train a model capable of robustly classifying stability in compact multiplanet systems over long timescales of 109 orbits. Our Stability of Planetary Orbital Configurations Klassifier (SPOCK) predicts stability using physically motivated summary statistics measured in integrations of the first 104 orbits, thus achieving speed-ups of up to 105 over full simulations. This computationally opens up the stability-constrained characterization of multiplanet systems. Our model, trained on_100,000 three-planet systems sampled at discrete resonances, generalizes both to a sample spanning a continuous period-ratio range, as well as to a …

Global Atmospheric Budget Of Acetone: Air-Sea Exchange And The Contribution To Hydroxyl Radicals, Siyuan Wang, Eric C. Apel, Rebecca H. Schwantes, Kelvin H. Bates, Daniel J. Jacob, Emily V. Fischer, Rebecca S. Hornbrook, Alan J. Hills, Louisa K. Emmons, Laura L. Pan, Shawn Honomichl, Simone Tilmes, Jean‐François Lamarque, Mingxi Yang, Christa A. Marandino, E. S. Saltzman, Warren J. De Bruyn, Sohiko Kameyama, Hiroshi Tanimoto, Yuko Omori, Samuel R. Hall, Kirk Ullmann, Thomas B. Ryerson, Chelsea R. Thompson, Jeff Peischl, Bruce C. Daube, Róisín Commane, Kathryn Mckain, Colm Sweeney, Alexander B. Thames, David O. Miller, William H. Brune, Glenn S. Diskin, Joshua P. Digangi, Steven C. Wofsy

Biology, Chemistry, and Environmental Sciences Faculty Articles and Research

Acetone is one of the most abundant oxygenated volatile organic compounds (VOCs) in the atmosphere. The oceans impose a strong control on atmospheric acetone, yet the oceanic fluxes of acetone remain poorly constrained. In this work, the global budget of acetone is evaluated using two global models: CAM‐chem and GEOS‐Chem. CAM‐chem uses an online air‐sea exchange framework to calculate the bidirectional oceanic acetone fluxes, which is coupled to a data‐oriented machine‐learning approach. The machine‐learning algorithm is trained using a global suite of seawater acetone measurements. GEOS‐Chem uses a fixed surface seawater concentration of acetone to calculate the oceanic fluxes. Both …

Southwest Pacific Tropical Cyclone Frequency And Intensity Related To Observed And Modeled Geophysical And Aerosol Variables, Rupsa Bhowmick

LSU Doctoral Dissertations

The dissertation focuses on western region of Southwest Pacific Ocean (SWPO)

basin (135E - 180, and 5S - 35S) tropical cyclone (TC) climatology using observed

and modeled data. The classification-based machine learning approach

identifies the synoptic geophysical and aerosol environment favorable or unfavorable

for TC intensification and intensity change prior to landfall incorporating

observational and satellite data. A multiple poisson regression model with varying

temporal monthly lags was used to build a relationship between the number of

monthly TC days with basin wide average dust aerosol optical depth (AOD), sea

surface temperature (SST), and upper ocean temperature (UOT). This idea …

Atmospheric Contrail Detection With A Deep Learning Algorithm, Nasir Siddiqui

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

Aircraft contrail emission is widely believed to be a contributing factor to global climate change. We have used machine learning techniques on images containing contrails in hopes of being able to identify those which contain contrails and those that do not. The developed algorithm processes data on contrail characteristics as captured by long-term image records. Images collected by the United States Department of Energy’s Atmospheric Radiation Management user facility(ARM) were used to train a deep convolutional neural network for the purpose of this contrail classification. The neural network model was trained with 1600 images taken by the Total Sky Imager(TSI) …

Gep Automatic Clustering Algorithm With Dynamic Penalty Factors, Chen Yan, Kangshun Li, Yang Lei

Journal of System Simulation

Abstract: Various problems such as sensitive selection of initial clustering center, easily falling into local optimal solution, and determining numbers of clusters, still exist in the traditional clustering algorithm. A GEP automatic clustering algorithm with dynamic penalty factors was proposed. This algorithm combines penalty factors and GEP clustering algorithm, and doesn't rely on any priori knowledge of the data set. And a dynamic algorithm was proposed to generate the penalty factors according to the distribution characteristics of different data sets, which is a better solution for the impact of isolated points and noise points. According to four dataset, penalty factors' …

Learning To Learn Kernels With Variational Random Features, Xiantong Zhen, Haoliang Sun, Yingjun Du, Jun Xu, Yilong Yin, Ling Shao, Cees Snoek

Machine Learning Faculty Publications

We introduce kernels with random Fourier features in the meta-learning framework for few-shot learning. We propose meta variational random features (MetaVRF) to learn adaptive kernels for the base-learner, which is developed in a latent variable model by treating the random feature basis as the latent variable. We formulate the optimization of MetaVRF as a variational inference problem by deriving an evidence lower bound under the meta-learning framework. To incorporate shared knowledge from related tasks, we propose a context inference of the posterior, which is established by an LSTM architecture. The LSTMbased inference network effectively integrates the context information of previous …

Objsim: Efficient Testing Of Cyber-Physical Systems, Jun Sun, Zijiang Yang

Research Collection School Of Computing and Information Systems

Cyber-physical systems (CPSs) play a critical role in automating public infrastructure and thus attract wide range of attacks. Assessing the effectiveness of defense mechanisms is challenging as realistic sets of attacks to test them against are not always available. In this short paper, we briefly describe smart fuzzing, an automated, machine learning guided technique for systematically producing test suites of CPS network attacks. Our approach uses predictive ma- chine learning models and meta-heuristic search algorithms to guide the fuzzing of actuators so as to drive the CPS into different unsafe physical states. The approach has been proven effective on two …

A Nonlinear Distortion Removal Based On Deep Neural Network For Underwater Acoustic Ofdm Communication With The Mitigation Of Peak To Average Power Ratio, Xuefei Ma, Waleed Raza, Zhiqiang Wu, Muhammad Bilal, Ziqi Zhou, Amir Ali

Electrical Engineering Faculty Publications

Machine learning and deep learning algorithms have proved to be a powerful tool for developing data-driven signal processing algorithms for challenging engineering problems. This paper studies the modern machine learning algorithm for modeling nonlinear devices like power amplifiers (PAs) for underwater acoustic (UWA) orthogonal frequency divisional multiplexing (OFDM) communication. The OFDM system has a high peak to average power ratio (PAPR) in the time domain because the subcarriers are added coherently via inverse fast Fourier transform (IFFT). This causes a higher bit error rate (BER) and degrades the performance of the PAs; hence, it reduces the power efficiency. For long-range …

Rethinking The Weakness Of Stream Ciphers And Its Application To Encrypted Malware Detection, William T. Stone, Junggab Son

Master of Science in Computer Science Theses

Encryption key use is a critical component to the security of a stream cipher: because many implementations simply consist of a key scheduling algorithm and logical exclusive or (XOR), an attacker can completely break the cipher by XORing two ciphertexts encrypted under the same key, revealing the original plaintexts and the key itself. The research presented in this paper reinterprets this phenomenon, using repeated-key cryptanalysis for stream cipher identification. It has been found that a stream cipher executed under a fixed key generates patterns in each character of the ciphertexts it produces and that these patterns can be used to …

Identification Of Microscopy Cell Images By Using Convolutional Neural Network Application, Ajis Norfatin Farisya

Student Works (2020-2029)

Breast cancer has been the major factor of cancer death and the second main cause of women’s deaths in the world. The false positive results of this cancer cell detection during the screening test leads to false treatment and emotional disturbance of the patients. Thus, breast cancer cell lines (MCF7) is used as the microscopy image samples together with the Human Bone Osteosarcoma Epithelial Cells (U2OS), and Human Hepatocyte as control to study the effectiveness of convolutional neural network (CNN) as a method of image recognition. The objectives of this study are to determine the ability of convolutional neural network …

A Study Of The Thermodynamics Of Small Systems And Phase Transition In Bulk Square Well-Hard Disk Binary Mixture, Gulce Kalyoncu

Graduate Theses and Dissertations

Under the umbrella of statistical mechanics and particle-based simulations, two distinct problems have been discussed in this study. The first part included systems of finite clusters of three and 13 particles, where the particles are interacting via Lennard Jones potential. A machine learning technique, Diffusion Maps (DMap), has been employed to the large datasets of thermodynamically small systems from Monte Carlo simulations in order to identify the structural and energetic changes in these systems. DMap suggests at most three dimensions are required to describe and identify the systems with 9 (N = 3) and 39 (N = 13) dimensions. At …

Prediction Of Feed Utilization Performance In Clarias Gariepinus Using Multiple Linear Regression In Machine Learning, Adekunle Oluwatosin Familusi

Journal of Bioresource Management

Machine learning models can be used to make predictions about nutrient utilization performance index using available proximate analysis data on feed composition. Data from similar experiments on nutrient utilization performance was used to fit a multiple linear regression model for the prediction of four performance indexes. The Specific Growth Rate and percentage inclusion with strength of 0.57 was noted along with a negative relationship between protein efficiency and protein content. A negative relationship between Nitrogen Free Extract (NFE) and Protein Efficiency Ratio (PER) at NFE content ≥25 % was observed. PER was predicted with 85 % accuracy, while Weight Gain …

Data-Driven And Model-Based Methods With Physics-Guided Machine Learning For Damage Identification, Zhiming Zhang

LSU Doctoral Dissertations

Structural health monitoring (SHM) has been widely used for structural damage diagnosis and prognosis of a wide range of civil, mechanical, and aerospace structures. SHM methods are generally divided into two categories: (1) model-based methods; (2) data-driven methods. Compared with data-driven SHM, model-based methods provide an updated physics-based numerical model that can be used for damage prognosis when long-term data is available. However, the performance of model-based methods is susceptible to modeling error in establishing the numerical model, which is usually unavoidable due to model simplification and omission. The major challenge of data-driven SHM methods lies in data insufficiency, e.g., …

In Search Of Trustworthy And Transparent Intelligent Systems With Human-Like Cognitive And Reasoning Capabilities, Nikhil R. Pal

Journal Articles

At present we are witnessing a tremendous interest in Artificial Intelligence (AI), particularly in Deep Learning (DL)/Deep Neural Networks (DNNs). One of the reasons appears to be the unmatched performance achieved by such systems. This has resulted in an enormous hope on such techniques and often these are viewed as all—cure solutions. But most of these systems cannot explain why a particular decision is made (black box) and sometimes miserably fail in cases where other systems would not. Consequently, in critical applications such as healthcare and defense practitioners do not like to trust such systems. Although an AI system is …

Literature Review: How U.S. Government Documents Are Addressing The Increasing National Security Implications Of Artificial Intelligence, Bert Chapman

Libraries Faculty and Staff Scholarship and Research

This article emphasizes the increasing importance of artificial intelligence (AI) in military and national security policy making. It seeks to inform interested individuals about the proliferation of publicly accessible U.S. government and military literature on this multifaceted topic. An additional objective of this endeavor is encouraging greater public awareness of and participation in emerging public policy debate on AI's moral and national security implications..

Towards Cooperating In Repeated Interactions Without Repeating Structure, Huy Pham

Theses and Dissertations

A big challenge in artificial intelligence (AI) is creating autonomous agents that can interact well with other agents over extended periods of time. Most previously developed algorithms have been designed in the context of Repeated Games, environments in which the agents interact in the same scenario repeatedly. However, in most real-world interactions, relationships between people and autonomous agents consist of sequences of distinct encounters with different incentives and payoff structures. Therefore, in this thesis, we consider Interaction Games, which model interactions in which the scenario changes from encounter to encounter, often in ways that are unanticipated by the players. For …

Optimized 3d Reconstruction For Infrastructure Inspection With Automated Structure From Motion And Machine Learning Methods, Samuel Arce Munoz

Theses and Dissertations

Infrastructure monitoring is being transformed by the advancements on remote sensing, unmanned vehicles and information technology. The wide interaction among these fields and the availability of reliable commercial technology are helping pioneer intelligent inspection methods based on digital 3D models. Commercially available Unmanned Aerial Vehicles (UAVs) have been used to create 3D photogrammetric models of industrial equipment. However, the level of automation of these missions remains low. Limited flight time, wireless transfer of large files and the lack of algorithms to guide a UAV through unknown environments are some of the factors that constraint fully automated UAV inspections. This work …

Pathways To The Native Storyteller: A Method To Enable Computational Story Understanding, Aramide O. Kehinde

College of Computing and Digital Media Dissertations

The primary objective of this thesis is to develop a method that uses machine learning algorithms to enable computational story understanding. This research is conducted with the aim of establishing a system called the Native Storyteller that plans and creates storytelling experiences for human users. The paper first establishes the desired capabilities of the system and then deep dives into how to enable story understanding, which is the core ability the system needs to function. As such, the research places emphasis on natural language processing and its application to solving key problems in this context. Namely, machine representation of story …