Digital Commons Network^™

Planning And Learning For Non-Markovian Negative Side Effects Using Finite State Controllers, Aishwarya Srivastava, Sandhya Saisubramanian, Praveen Paruchuri, Akshat Kumar, Shlomo Zilberstein

Research Collection School Of Computing and Information Systems

Autonomous systems are often deployed in the open world where it is hard to obtain complete specifications of objectives and constraints. Operating based on an incomplete model can produce negative side effects (NSEs), which affect the safety and reliability of the system. We focus on mitigating NSEs in environments modeled as Markov decision processes (MDPs). First, we learn a model of NSEs using observed data that contains state-action trajectories and severity of associated NSEs. Unlike previous works that associate NSEs with state-action pairs, our framework associates NSEs with entire trajectories, which is more general and captures non-Markovian dependence on states …

Mitigating Popularity Bias For Users And Items With Fairness-Centric Adaptive Recommendation, Zhongzhou Liu, Yuan Fang, Min Wu

Research Collection School Of Computing and Information Systems

Recommendation systems are popular in many domains. Researchers usually focus on the effectiveness of recommendation (e.g., precision) but neglect the popularity bias that may affect the fairness of the recommendation, which is also an important consideration that could influence the benefits of users and item providers. A few studies have been proposed to deal with the popularity bias, but they often face two limitations. Firstly, most studies only consider fairness for one side - either users or items, without achieving fairness jointly for both. Secondly, existing methods are not sufficiently tailored to each individual user or item to cope with …

Learning To Count Isomorphisms With Graph Neural Networks, Xingtong Yu, Zemin Liu, Yuan Fang, Xinming Zhang

Research Collection School Of Computing and Information Systems

Subgraph isomorphism counting is an important problem on graphs, as many graph-based tasks exploit recurring subgraph patterns. Classical methods usually boil down to a backtracking framework that needs to navigate a huge search space with prohibitive computational costs. Some recent studies resort to graph neural networks (GNNs) to learn a low-dimensional representation for both the query and input graphs, in order to predict the number of subgraph isomorphisms on the input graph. However, typical GNNs employ a node-centric message passing scheme that receives and aggregates messages on nodes, which is inadequate in complex structure matching for isomorphism counting. Moreover, on …

On Generalized Degree Fairness In Graph Neural Networks, Zemin Liu, Trung Kien Nguyen, Yuan Fang

Research Collection School Of Computing and Information Systems

Conventional graph neural networks (GNNs) are often confronted with fairness issues that may stem from their input, including node attributes and neighbors surrounding a node. While several recent approaches have been proposed to eliminate the bias rooted in sensitive attributes, they ignore the other key input of GNNs, namely the neighbors of a node, which can introduce bias since GNNs hinge on neighborhood structures to generate node representations. In particular, the varying neighborhood structures across nodes, manifesting themselves in drastically different node degrees, give rise to the diverse behaviors of nodes and biased outcomes. In this paper, we first define …

Flexible Job-Shop Scheduling Via Graph Neural Network And Deep Reinforcement Learning, Wen Song, Xinyang Chen, Qiqiang Li, Zhiguang Cao

Research Collection School Of Computing and Information Systems

Recently, deep reinforcement learning (DRL) has been applied to learn priority dispatching rules (PDRs) for solving complex scheduling problems. However, the existing works face challenges in dealing with flexibility, which allows an operation to be scheduled on one out of multiple machines and is often required in practice. Such one-to-many relationship brings additional complexity in both decision making and state representation. This article considers the well-known flexible job-shop scheduling problem and addresses these issues by proposing a novel DRL method to learn high-quality PDRs end to end. The operation selection and the machine assignment are combined as a composite decision. …

Pose- And Attribute-Consistent Person Image Synthesis, Cheng Xu, Zejun Chen, Jiajie Mai, Xuemiao Xu, Shengfeng He

Research Collection School Of Computing and Information Systems

PersonImageSynthesisaimsattransferringtheappearanceofthesourcepersonimageintoatargetpose. Existingmethods cannot handle largeposevariations and therefore suffer fromtwocritical problems: (1)synthesisdistortionduetotheentanglementofposeandappearanceinformationamongdifferentbody componentsand(2)failureinpreservingoriginalsemantics(e.g.,thesameoutfit).Inthisarticle,weexplicitly addressthesetwoproblemsbyproposingaPose-andAttribute-consistentPersonImageSynthesisNetwork (PAC-GAN).Toreduceposeandappearancematchingambiguity,weproposeacomponent-wisetransferring modelconsistingoftwostages.Theformerstagefocusesonlyonsynthesizingtargetposes,whilethelatter renderstargetappearancesbyexplicitlytransferringtheappearanceinformationfromthesourceimageto thetargetimageinacomponent-wisemanner. Inthisway,source-targetmatchingambiguityiseliminated duetothecomponent-wisedisentanglementofposeandappearancesynthesis.Second,tomaintainattribute consistency,werepresenttheinputimageasanattributevectorandimposeahigh-levelsemanticconstraint usingthisvectortoregularizethetargetsynthesis.ExtensiveexperimentalresultsontheDeepFashiondataset demonstratethesuperiorityofourmethodoverthestateoftheart,especiallyformaintainingposeandattributeconsistenciesunderlargeposevariations.

Scalable And Globally Optimal Generalized L1 K-Center Clustering Via Constraint Generation In Mixed Integer Linear Programming, Aravinth Chembu, Scott Sanner, Hassan Khurram, Akshat Kumar

Research Collection School Of Computing and Information Systems

The k-center clustering algorithm, introduced over 35 years ago, is known to be robust to class imbalance prevalent in many clustering problems and has various applications such as data summarization, document clustering, and facility location determination. Unfortunately, existing k-center algorithms provide highly suboptimal solutions that can limit their practical application, reproducibility, and clustering quality. In this paper, we provide a novel scalable and globally optimal solution to a popular variant of the k-center problem known as generalized L1 k-center clustering that uses L1 distance and allows the selection of arbitrary vectors as cluster centers. We show that this clustering objective …

Constrained Reinforcement Learning In Hard Exploration Problems, Pankayaraj Pathmanathan, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

One approach to guaranteeing safety in Reinforcement Learning is through cost constraints that are imposed on trajectories. Recent works in constrained RL have developed methods that ensure constraints can be enforced even at learning time while maximizing the overall value of the policy. Unfortunately, as demonstrated in our experimental results, such approaches do not perform well on complex multi-level tasks, with longer episode lengths or sparse rewards. To that end, wepropose a scalable hierarchical approach for constrained RL problems that employs backward cost value functions in the context of task hierarchy and a novel intrinsic reward function in lower levels …

Future Aware Pricing And Matching For Sustainable On-Demand Ride Pooling, Xianjie Zhang, Pradeep Varakantham, Hao Jiang

Research Collection School Of Computing and Information Systems

The popularity of on-demand ride pooling is owing to the benefits offered to customers (lower prices), taxi drivers (higher revenue), environment (lower carbon footprint due to fewer vehicles) and aggregation companies like Uber (higher revenue). To achieve these benefits, two key interlinked challenges have to be solved effectively: (a) pricing – setting prices to customer requests for taxis; and (b) matching – assignment of customers (that accepted the prices) to taxis/cars. Traditionally, both these challenges have been studied individually and using myopic approaches (considering only current requests), without considering the impact of current matching on addressing future requests. In this …

An Empirical Study Of Package Management Issues Via Stack Overflow, Syful Islam, Raula Kula, Christoph Treude, Bodin Chinthanet, Takashi Ishio, Kenichi Matsumoto

Research Collection School Of Computing and Information Systems

The package manager (PM) is crucial to most technology stacks, acting as a broker to ensure that a verified dependency package is correctly installed, configured, or removed from an application. Diversity in technology stacks has led to dozens of PMs with various features. While our recent study indicates that package management features of PM are related to end-user experiences, it is unclear what those issues are and what information is required to resolve them. In this paper, we have investigated PM issues faced by end-users through an empirical study of content on Stack Overflow (SO). We carried out a qualitative …

Bidding Graph Games With Partially-Observable Budgets, Guy Avni, Ismael Jecker, Dorde Zikelic

Research Collection School Of Computing and Information Systems

Two-player zero-sum graph games are a central model, which proceeds as follows. A token is placed on a vertex of a graph, and the two players move it to produce an infinite play, which determines the winner or payoff of the game. Traditionally, the players alternate turns in moving the token. In bidding games, however, the players have budgets and in each turn, an auction (bidding) determines which player moves the token. So far, bidding games have only been studied as fullinformation games. In this work we initiate the study of partial-information bidding games: we study bidding games in which …

Learning Control Policies For Stochastic Systems With Reach-Avoid Guarantees, Dorde Zikelic, Mathias Lechner, A. Thomas Henzinger, Krishnendu Chatterjee

Research Collection School Of Computing and Information Systems

We study the problem of learning controllers for discrete-time non-linear stochastic dynamical systems with formal reach-avoid guarantees. This work presents the first method for providing formal reach-avoid guarantees, which combine and generalize stability and safety guarantees, with a tolerable probability threshold p ∈ [0,1] over the infinite time horizon in general Lipschitz continuous systems. Our method leverages advances in machine learning literature and it represents formal certificates as neural networks. In particular, we learn a certificate in the form of a reach-avoid supermartingale (RASM), a novel notion that we introduce in this work. Our RASMs provide reachability and avoidance guarantees …

Safe Delivery Of Critical Services In Areas With Volatile Security Situation Via A Stackelberg Game Approach, Tien Mai, Arunesh Sinha

Research Collection School Of Computing and Information Systems

Vaccine delivery in under-resourced locations with security risks is not just challenging but also life threatening. The COVID pandemic and the need to vaccinate added even more urgency to this issue. Motivated by this problem, we propose a general framework to set-up limited temporary (vaccination) centers that balance physical security and desired (vaccine) service coverage with limited resources. We set-up the problem as a Stackelberg game between the centers operator (defender) and an adversary, where the set of centers is not fixed a priori but is part of the decision output. This results in a mixed combinatorial and continuous optimization …

An Enhanced Cloud-Native Deep Learning Pipeline For The Classification Of Network Traffic, Ahmed Sobhy Elkenawy

Theses and Dissertations

In a rapidly changing world, the way of solving real-world problems has changed to leverage the power of the advancements in multiple fields. Cloud-native computing approaches can be utilized with deep learning techniques to provide solutions in several important areas. For instance, with the emergence of the pandemic, much dependence on modern technologies came out as a replacement for face-to-face interaction. Deep learning can reach a high level of accuracy, which makes it very effective in the support of modern services and technologies. However, there are some challenging issues because deep learning requires many large-scale experiments, which demand a lot …

Synthesis, Theoretical Study, And Biological Evaluation Of Some Metal Ions With Ligand "Methyl -6-[2-(4-Hydroxyphenyl) -2-((1-Phenylethylidene) Amino) Acetamido] -2,2-Dimethyl-5—Oxo-1-Thia-4-Azabicyclo [3.2.0] Heptane-3-Carboxyylate, Sahar S. Hassan, Nafeesa J. Kadhim, Zahraa. A. Jaber

Baghdad Science Journal

Schiff base (methyl 6-(2- (4-hydroxyphenyl) -2- (1-phenyl ethyl ideneamino) acetamido) -3, 3-dimethyl-7-oxo-4-thia-1-azabicyclo[3.2.0] heptane-2-carboxylate)Co(II), Ni(II), Cu (II), Zn (II), and Hg(II)] ions were employed to make certain complexes. Metal analysis M percent, elemental chemical analysis (C.H.N.S), and other standard physico-chemical methods were used. Magnetic susceptibility, conductometric measurements, FT-IR and UV-visible Spectra were used to identified. Theoretical treatment of the generated complexes in the gas phase was performed using the (hyperchem-8.07) program for molecular mechanics and semi-empirical computations. The (PM3) approach was used to determine the heat of formation (ΔH˚f), binding energy (ΔEb), and total energy (ET) for ligands and metal complexes …

Utilizing Design Thinking To Enhance Wellbeing In Interdisciplinary Courses: A Positive Social Psychology Approach, Areej Elsayary

All Works

Design thinking is considered to be a positive social psychology intervention. Students who practice using the design thinking process during their coursework will most likely solve personal problems that improve their well-being. This study investigates the impact of using the design thinking process in interdisciplinary courses to enhance students' well-being through developing mindsets that enable them to solve their problems and set personal goals unconsciously. A modified PERMA-PH model is used to guide this study. The PERMA included Positive Emotions, Negative Emotions, Engagement, Relationship, Meaning and Purpose, and Accomplishments, the "PH" (future plans and health) was added to the PE …

Engineering A Microbiosphere To Clean Up The Ocean – Inspiration From The Plastisphere, Khulood A. Alnahdi, Laila W. Alali, Mezna K. Suwaidan, M. Kalim Akhtar

All Works

Plastic is a ubiquitous material that has become an essential part of our lives. More than one hundred million tons of plastic has accumulated in the world’s oceans as a result of poor waste management. This plastic waste gradually fragments into smaller pieces known as microplastics and nanoplastics. These small plastic particles can cause significant damage to marine ecosystems, and negatively impact human health. According to a recent review of international patents, the majority of ocean-cleaning inventions are limited to microplastics larger than 20 μm. Furthermore, such technologies are ineffective for nanoplastics, which measure less than 1000 nm, or even …

Carla+: An Evolution Of The Carla Simulator For Complex Environment Using A Probabilistic Graphical Model, Sumbal Malik, Manzoor Ahmed Khan, Aadam, Hesham El-Sayed, Farkhund Iqbal, Jalal Khan, Obaid Ullah

All Works

In an urban and uncontrolled environment, the presence of mixed traffic of autonomous vehicles, classical vehicles, vulnerable road users, e.g., pedestrians, and unprecedented dynamic events makes it challenging for the classical autonomous vehicle to navigate the traffic safely. Therefore, the realization of collaborative autonomous driving has the potential to improve road safety and traffic efficiency. However, an obvious challenge in this regard is how to define, model, and simulate the environment that captures the dynamics of a complex and urban environment. Therefore, in this research, we first define the dynamics of the envisioned environment, where we capture the dynamics relevant …

Independent Analysis And Interpretation Of The New Mexico Constitution: If Not Now, When?, The Honorable Linda M. Vanzi, Mark T. Baker

New Mexico Law Review

This article posits that the mode of analysis of state constitutional issues adopted by the New Mexico Supreme Court in State v. Gomez, as it has been applied in the civil context, has neither “promote[d] the development of a sound body of state constitutional jurisprudence” nor led to “consistent, predictable, and reasonable state court decision-making,” as some envisioned in 1998. Instead, it has often led to essentially automatic deference to federal precedent interpreting comparable provisions of the Federal Constitution and very limited, if any, consideration of protections afforded under our state constitution. In addition, the inconsistent application of the Gomez …

Negligent Commercial Transactions: Does New Mexico Face A Slippery Slope After Morris?, Annika Cleveland

New Mexico Law Review

In its July 2021 decision, Morris v. Giant Four Corners, the New Mexico Supreme Court held that the doctrine of negligent entrustment includes liability for someone who supplies gasoline to a person they knew or should have known was intoxicated. While the Morris court’s decision is novel in New Mexico, courts will likely interpret the inclusion narrowly, restricting the duty to circumstances where a commercial transaction enabled a DWI. By reviewing the decisions of other jurisdictions to include certain commercial transactions under negligent entrustment claims and the impact those decisions had on subsequent litigation, this article argues that Morris will …

Randomized Controlled Trial Of The Behavioral Intervention For Increasing Physical Activity In Multiple Sclerosis Project: Secondary, Patient-Reported Outcomes, Robert W. Motl, Brian M. Sandroff, Lara A. Pilutti, Gary R. Cutter, Roberto Aldunate, Ariel Kidwell, Rachel E. Bollaert

Exercise Science Faculty Research and Publications

Background

We undertook a randomized controlled trial (RCT) that investigated the effectiveness of a theory-based, Internet-delivered, behavioral intervention focusing on physical activity promotion for immediate and sustained improvements in secondary, patient-reported outcomes (PROs) of function, symptoms, and quality of life (QOL) in multiple sclerosis (MS).

Method

Persons with MS (N = 318) were recruited from throughout the United States and randomized into behavioral intervention (n = 159) or attention/social contact control (n = 159) conditions. The conditions were administered over a 6-month period by persons who were uninvolved in screening, recruitment, random assignment, and outcome assessment. There …

Steering Particles Via Micro-Actuation Of Chemical Gradients Using Model Predictive Control, Mark N. Mcdonald, Cameron K. Peterson, Douglas R. Tree

Faculty Publications

Biological systems rely on chemical gradients to direct motion through both chemotaxis and signaling, but synthetic approaches for doing the same are still relatively naïve. Consequently, we present a novel method for using chemical gradients to manipulate the position and velocity of colloidal particles in a microfluidic device. Specifically, we show that a set of spatially localized chemical reactions that are sufficiently controllable can be used to steer colloidal particles via diffusiophoresis along an arbitrary trajectory. To accomplish this, we develop a control method for steering colloidal particles with chemical gradients using nonlinear model predictive control with a model based …

Ash Aerosol Particle Size Distribution, Composition, And Deposition Behavior While Co-Firing Coal And Steam-Exploded Biomass In A 1.5 Mwth Combustor, Rajarshi Roy, Brian Schooff, Xiaolong Li, Scott Montgomery, Jacob Tuttle, Jost O.L. Wendt, Kingsley Dickson, Brian Iverson, Andrew R. Fry

Faculty Publications

Five different blends of Utah bituminous coal and steam-exploded pine (100/0, 75/25, 50/50, 25/75, 0/100 by mass) were fired in a 1.5 MWth combustor. Primary objectives were to understand mineral matter behavior by analyzing aerosol size distribution, aerosol size-segregated composition, ash deposition mass, and ash composition. For particle size < 0.1 μm, pure coal had the lowest aerosol concentration and pure biomass showed the highest (higher nucleation of potassium salts), a trend which reversed for particles >0.1 μm. During pure biomass combustion, aerosol particles >15 μm contained higher mass fractions of potassium (+126%), calcium (+132%), and iron (+115%) and lower fractions of aluminum (−49%) and silicon (−29%) than pure coal. Ash deposition mass decreased with increasing biomass blends. …

A Theoretical Framework For The Ecological Role Of Three-Dimensional Structural Diversity, Elizabeth A. Larue, Robert T. Fahey, Brandon C. Alveshere, Jeff W. Atkins, Parth Bhatt, Brian Buma, Anping Chen, Stella Cousins, Jessica M. Elliott, Andrew J. Elmore, Christopher R. Hakkenberg, Brady S. Hardiman, Jeremy S. Johnson, Daniel M. Kashian, Anil Koirala, Monica Papeş, Jamille B. St Hilaire, Thilina D. Surasinghe, Jenny Zambrano, Lu Zhai, Songlin Fei

Michigan Tech Publications, Part 1

The three-dimensional (3D) physical aspects of ecosystems are intrinsically linked to ecological processes. Here, we describe structural diversity as the volumetric capacity, physical arrangement, and identity/traits of biotic components in an ecosystem. Despite being recognized in earlier ecological studies, structural diversity has been largely overlooked due to an absence of not only a theoretical foundation but also effective measurement tools. We present a framework for conceptualizing structural diversity and suggest how to facilitate its broader incorporation into ecological theory and practice. We also discuss how the interplay of genetic and environmental factors underpin structural diversity, allowing for a potentially unique …

A Catalog Of The Highest-Energy Cosmic Rays Recorded During Phase I Of Operation Of The Pierre Auger Observatory, A. Abdul Halim, P. Abreu, M. Aglietta, I. Allekotte, P. Allison, K. Almeida Cheminant, J. Chirinos, B. Fick, D. Nitz, I. Norwood, A. Puyleart, Et Al.

Michigan Tech Publications, Part 1

A catalog containing details of the highest-energy cosmic rays recorded through the detection of extensive air showers at the Pierre Auger Observatory is presented with the aim of opening the data to detailed examination. Descriptions of the 100 showers created by the highest-energy particles recorded between 2004 January 1 and 2020 December 31 are given for cosmic rays that have energies in the range 78-166 EeV. Details are also given on a further nine very energetic events that have been used in the calibration procedure adopted to determine the energy of each primary. A sky plot of the arrival directions …

Utilization Of Mechanically Recycled Carbon Fibers In Vinyl Ester Composites, Khaled Alharmoodi, Amir Hussain Idrisi, Abdel Hamid Ismail Mourad, Basim Abu-Jdayil

Michigan Tech Publications, Part 1

As we enter the twenty-first century, the aviation sector is expected to thrive as flying becomes the primary mode of transportation between states or nations. With such a demand, there is a corresponding need to manufacture aircraft components. The study focused on recycling carbon fiber composites received from the STRATA company, which were cut-off/waste material generated during the manufacture of airplane components. The cut-offs were then reduced to powder form using a standard face milling machine in three sizes (90, 150, and 250 µm). After, the powder was utilized to fabricate vinyl ester composites with four weight percentages (10%, 20%, …

An Assessment Of Blood Vessel Remodeling Of Nanofibrous Poly(Ε-Caprolactone) Vascular Grafts In A Rat Animal Model, Jana Horakova, Tereza Blassova, Zbynek Tonar, Connor Mccarthy, Katerina Strnadova, David Lukas, Petr Mikes, Patrick Bowen, Roger J. Guillory Ii, Megan C. Frost, Jeremy Goldman

Michigan Tech Publications, Part 1

The development of an ideal vascular prosthesis represents an important challenge in terms of the treatment of cardiovascular diseases with respect to which new materials are being considered that have produced promising results following testing in animal models. This study focuses on nanofibrous polycaprolactone-based grafts assessed by means of histological techniques 10 days and 6 months following suturing as a replacement for the rat aorta. A novel stereological approach for the assessment of cellular distribution within the graft thickness was developed. The cellularization of the thickness of the graft was found to be homogeneous after 10 days and to have …

Comparison Of High-Resolution Naip And Unmanned Aerial Vehicle (Uav) Imagery For Natural Vegetation Communities Classification Using Machine Learning Approaches, Parth Bhatt, Ann Maclean

Michigan Tech Publications, Part 1

To map and manage forest vegetation including wetland communities, remote sensing technology has been shown to be a valid and widely employed technology. In this paper, two ecologically different study areas were evaluated using free and widely available high-resolution multispectral National Agriculture Imagery Program (NAIP) and ultra-high-resolution multispectral unmanned aerial vehicle (UAV) imagery located in the Upper Great Lakes Laurentian Mixed Forest. Three different machine learning algorithms, random forest (RF), support vector machine (SVM), and averaged neural network (avNNet), were evaluated to classify complex natural habitat communities as defined by the Michigan Natural Features Inventory. Accurate training sets were developed …

The Effects Of Robot Voices And Appearances On Users' Emotion Recognition And Subjective Perception, Sangjin Ko, Jaclyn A. Barnes, Jiayuan Dong, Chung Hyuk Park, Ayanna Howard, Myounghoon Jeon

Michigan Tech Publications, Part 1

As the influence of social robots in people's daily lives grows, research on understanding people's perception of robots including sociability, trust, acceptance, and preference becomes more pervasive. Research has considered visual, vocal, or tactile cues to express robots' emotions, whereas little research has provided a holistic view in examining the interactions among different factors influencing emotion perception. We investigated multiple facets of user perception on robots during a conversational task by varying the robots' voice types, appearances, and emotions. In our experiment, 20 participants interacted with two robots having four different voice types. While participants were reading fairy tales to …

Effortful Control Moderates The Relation Between Negative Emotionality And Child Anxiety And Depressive Symptom Severity In Children With Anxiety Disorders, Elizabeth M Raines, Andres G Viana, Erika S Trent, Haley E Conroy, Karina Silva, Michael J Zvolensky, Eric A Storch

Center for Medical Ethics and Health Policy Staff Publications

The present study investigated the interactive effect of reactive (negative emotionality) and regulatory (effortful control) aspects of temperament in the prediction of child anxiety and depressive symptoms. Clinically anxious children and their mothers completed a battery of questionnaires that included self- and mother-ratings of child effortful control, negative emotionality, anxiety, and depressive symptoms. Multiple regression analyses were conducted to examine the moderating effect of effortful control on the relation between negative emotionality and child anxiety and depressive symptom severity. The interaction between negative emotionality and effortful control was statistically significant and simple slopes revealed that as effortful control increased, the …