Artificial Intelligence and Robotics Commons^™

Rnn-Based Generation Of Polyphonic Music And Jazz Improvisation, Andrew Hannum

Electronic Theses and Dissertations

This paper presents techniques developed for algorithmic composition of both polyphonic music, and of simulated jazz improvisation, using multiple novel data sources and the character-based recurrent neural network architecture char-rnn. In addition, techniques and tooling are presented aimed at using the results of the algorithmic composition to create exercises for musical pedagogy.

Towards Using A Physio-Cognitive Model In Tutoring For Psychomotor Tasks., Jong W. Kim, Chris Dancy, Robert A. Sottilare

Faculty Conference Papers and Presentations

We report our exploratory research of psychomotor task training in intelligent tutoring systems (ITSs) that are generally limited to tutoring in the desktop learning environment where the learner acquires cognitively oriented knowledge and skills. It is necessary to support computer-guided training in a psychomotor task domain that is beyond the desktop environment. In this study, we seek to extend the current capability of GIFT (Generalized Intelligent Frame-work for Tutoring) to address these psychomotor task training needs. Our ap-proach is to utilize heterogeneous sensor data to identify physical motions through acceleration data from a smartphone and to monitor respiratory activity through …

Recurrent Neural Networks And Their Applications To Rna Secondary Structure Inference, Devin Willmott

Theses and Dissertations--Mathematics

Recurrent neural networks (RNNs) are state of the art sequential machine learning tools, but have difficulty learning sequences with long-range dependencies due to the exponential growth or decay of gradients backpropagated through the RNN. Some methods overcome this problem by modifying the standard RNN architecure to force the recurrent weight matrix W to remain orthogonal throughout training. The first half of this thesis presents a novel orthogonal RNN architecture that enforces orthogonality of W by parametrizing with a skew-symmetric matrix via the Cayley transform. We present rules for backpropagation through the Cayley transform, show how to deal with the Cayley …

Towards A Physio-Cognitive Model Of Slow-Breathing, Chris Dancy

Faculty Conference Papers and Presentations

How may controlled breathing be beneficial, or detrimental to behavior? Computational process models are useful to specify the potential mechanisms that lead to behavioral adaptation during different breathing exercises. We present a physio-cognitive model of slow breathing implemented within a hybrid cognitive architecture, ACT-R/Φ. Comparisons to data from an experiment indicate that the physiological mechanisms are operating in a manner that is consistent with actual human function. The presented computational model provides predictions of ways that controlled breathing interacts with mechanisms of arousal to mediate cognitive behavior. The increasing use of breathing techniques to counteract effects of stressors makes it …

Towards A Physio-Cognitive Model Of The Exploration Exploitation Trade-Off., David M. Schwartz, Christopher L. Dancy

Faculty Conference Papers and Presentations

Managing the exploration vs exploitation trade-off is an important part of our everyday lives. It occurs in minor decisions such as choosing what music to listen to as well as major decisions, such as picking a research direction to pursue. The dilemma is the same despite the context: does one exploit the environment, using current knowledge to acquire a satisfactory solution, or explore other options and potentially find a better answer. An accurate cognitive model must be able to handle this trade-off because of the importance it plays in our lives. We are developing physio-cognitive models to better understand how …

Simulating Human-Ai Collaboration With Act-R And Project Malmo, Zachary M. Brill, Christopher L. Dancy

Faculty Conference Papers and Presentations

We use the ACT-R cognitive architecture (Anderson, 2007) to explore human-AI collaboration. Computational models of human and AI behavior, and their interaction, allow for more effective development of collaborative artificial intelligent agents. With these computational models and simulations, one may be better equipped to predict the situations in which certain classes of intelligent agents may be more suited to collaborate with people. One can more tractably understand and predict how different AI agents affect task behavior in these situations. To simulate human-AI collaboration, we are developing ACT-R models that work with more traditional AI agents to solve a task in …

Model Ai Assignments 2018, Todd W. Neller, Zack Butler, Nate Derbinsky, Heidi Furey, Fred Martin, Michael Guerzhoy, Ariel Anders, Joshua Eckroth

Computer Science Faculty Publications

The Model AI Assignments session seeks to gather and disseminate the best assignment designs of the Artificial Intelligence (AI) Education community. Recognizing that assignments form the core of student learning experience, we here present abstracts of seven AI assignments from the 2018 session that are easily adoptable, playfully engaging, and flexible for a variety of instructor needs. Assignment specifications and supporting resources may be found at http://modelai.gettysburg.edu.

Ai Education Matters: Teaching Hidden Markov Models, Todd W. Neller

Computer Science Faculty Publications

In this column, we share resources for learning about and teaching Hidden Markov Models (HMMs). HMMs find many important applications in temporal pattern recognition tasks such as speech/handwriting/gesture recognition and robot localization. In such domains, we may have a finite state machine model with known state transition probabilities, state output probabilities, and state outputs, but lack knowledge of the states generating such outputs. HMMs are useful in framing problems where external sequential evidence is used to derive underlying state information (e.g. intended words and gestures). [excerpt]

Ai Education Matters: Lessons From A Kaggle Click-Through Rate Prediction Competition, Todd W. Neller

Computer Science Faculty Publications

In this column, we will look at a particular Kaggle.com click-through rate (CTR) prediction competition, observe what the winning entries teach about this part of the machine learning landscape, and then discuss the valuable opportunities and resources this commends to AI educators and their students. [excerpt]

Energy Slices: Benchmarking With Time Slicing, Katarina Grolinger, Hany F. Elyamany, Wilson Higashino, Miriam Am Capretz, Luke Seewald

Electrical and Computer Engineering Publications

Benchmarking makes it possible to identify low-performing buildings, establishes a baseline for measuring performance improvements, enables setting of energy conservation targets, and encourages energy savings by creating a competitive environment. Statistical approaches evaluate building energy efficiency by comparing measured energy consumption to other similar buildings typically using annual measurements. However, it is important to consider different time periods in benchmarking because of differences in their consumption patterns. For example, an office can be efficient during the night, but inefficient during operating hours due to occupants’ wasteful behavior. Moreover, benchmarking studies often use a single regression model for different building categories. …

Evaluating Flexibility Metrics On Simple Temporal Networks With Reinforcement Learning, Hamzah I. Khan

HMC Senior Theses

Simple Temporal Networks (STNs) were introduced by Tsamardinos (2002) as a means of describing graphically the temporal constraints for scheduling problems. Since then, many variations on the concept have been used to develop and analyze algorithms for multi-agent robotic scheduling problems. Many of these algorithms for STNs utilize a flexibility metric, which measures the slack remaining in an STN under execution. Various metrics have been proposed by Hunsberger (2002); Wilson et al. (2014); Lloyd et al. (2018). This thesis explores how adequately these metrics convey the desired information by using them to build a reward function in a reinforcement learning …

Deep Convolutional Neural Networks Enable Discrimination Of Heterogeneous Digital Pathology Images, Pegah Khosravi, Ehsan Kazemi, Marcin Imielinski, Olivier Elemento, Iman Hajirasouliha

Publications and Research

Pathological evaluation of tumor tissue is pivotal for diagnosis in cancer patients and automated image analysis approaches have great potential to increase precision of diagnosis and help reduce human error.

In this study, we utilize several computational methods based on convolutional neural networks (CNN) and build a stand-alone pipeline to effectively classify different histopathology images across different types of cancer.

In particular, we demonstrate the utility of our pipeline to discriminate between two subtypes of lung cancer, four biomarkers of bladder cancer, and five biomarkers of breast cancer. In addition, we apply our pipeline to discriminate among four immunohistochemistry …

C++ Risk Simulation To Generate Ai, David Sky Nunez

A with Honors Projects

For this A with Honors project, the student set out to create a way to run thousands of simulations for the board game, RISK, supplying information for the game player to be able to make more strategic decisions when playing the game.

Exploring Natural User Abstractions For Shared Perceptual Manipulator Task Modeling & Recovery, Senglee Koh

Electronic Theses and Dissertations

State-of-the-art domestic robot assistants are essentially autonomous mobile manipulators capable of exerting human-scale precision grasps. To maximize utility and economy, non-technical end-users would need to be nearly as efficient as trained roboticists in control and collaboration of manipulation task behaviors. However, it remains a significant challenge given that many WIMP-style tools require superficial proficiency in robotics, 3D graphics, and computer science for rapid task modeling and recovery. But research on robot-centric collaboration has garnered momentum in recent years; robots are now planning in partially observable environments that maintain geometries and semantic maps, presenting opportunities for non-experts to cooperatively control task …

Predictive Analytics In The Criminal Justice System: Media Depictions And Framing, Kar Mun Cheng

Honors Program Theses

Artificial intelligence and algorithms are increasingly becoming commonplace in crime-fighting efforts. For instance, predictive policing uses software to predetermine criminals and areas where crime is most likely to happen. Risk assessment software are employed in sentence determination and other courtroom decisions, and they are also being applied towards prison overpopulation by assessing which inmates can be released. Public opinion on the use of predictive software is divided: many police and state officials support it, crediting it with lowering crime rates and improving public safety. Others, however, have questioned its effectiveness, citing civil liberties concerns as well as the possibility of …

Deep Learning-Based Framework For Autism Functional Mri Image Classification, Xin Yang, Saman Sarraf, Ning Zhang

Journal of the Arkansas Academy of Science

The purpose of this paper is to introduce deep learning-based framework LeNet-5 architecture and implement the experiments for functional MRI image classification of Autism spectrum disorder. We implement our experiments under the NVIDIA deep learning GPU Training Systems (DIGITS). By using the Convolutional Neural Network (CNN) LeNet-5 architecture, we successfully classified functional MRI image of Autism spectrum disorder from normal controls. The results show that we obtained satisfactory results for both sensitivity and specificity.

Decreasing Occlusion And Increasing Explanation In Interactive Visual Knowledge Discovery, Abdulrahman Ahmed Gharawi

All Master's Theses

Lack of explanation and occlusion are the major problems for interactive visual knowledge discovery, machine learning and data mining in multidimensional data. This thesis proposes a hybrid method that combines visual and analytical means to deal with these problems. This method, denoted as FSP, uses visualization of n-D data in 2-D in a set of Shifted Paired Coordinates (SPC). SPC for n-D data consists of n/2 pairs of Cartesian coordinates that are shifted relative to each other to avoid their overlap. Each n-D point is represented as a directed graph in SPC. It is shown that the FSP method simplifies …

Exploring The Functional And Geometric Bias Of Spatial Relations Using Neural Language Models, Simon Dobnik, Mehdi Ghanimifard, John D. Kelleher

Conference papers

The challenge for computational models of spatial descriptions for situated dialogue systems is the integration of information from different modalities. The semantics of spatial descriptions are grounded in at least two sources of information: (i) a geometric representation of space and (ii) the functional interaction of related objects that. We train several neural language models on descriptions of scenes from a dataset of image captions and examine whether the functional or geometric bias of spatial descriptions reported in the literature is reflected in the estimated perplexity of these models. The results of these experiments have implications for the creation of …

Ai For Ground Robots For Autonomous Coverage Of Designated Areas, Danxue Huang

Summer Community of Scholars Posters (RCEU and HCR Combined Programs)

No abstract provided.

The Impact Of Cost On Feature Selection For Classifiers, Richard Clyde Mccrae

CCAC Theses and Dissertations

Supervised machine learning models are increasingly being used for medical diagnosis. The diagnostic problem is formulated as a binary classification task in which trained classifiers make predictions based on a set of input features. In diagnosis, these features are typically procedures or tests with associated costs. The cost of applying a trained classifier for diagnosis may be estimated as the total cost of obtaining values for the features that serve as inputs for the classifier. Obtaining classifiers based on a low cost set of input features with acceptable classification accuracy is of interest to practitioners and researchers. What makes this …

Expanding The Artificial Intelligence-Data Protection Debate, Fred H. Cate, Christopher Kuner, Orla Lynskey, Christopher Millard, Nora Ni Loideain, Dan Jerker B. Svantesson

Articles by Maurer Faculty

No abstract provided.

The Stance On Artificial Intelligence, Edward Gonzalez-Olmedo

Nebraska College Preparatory Academy: Senior Capstone Projects

Mary Shelley’s novel Frankenstein brings up the question: When do we draw the line on technological Artificial Intelligence (AI) advancement? The importance of this is that we need to be able to control the technology that we produce. Humans always strive for an advancement in technology, and AI is one of the more advanced concepts. Mary Shelley introduces this problem with Frankenstein when he creates a creature which cannot be controlled by its creator. Humans have begun to tinker with this new technology, yet mankind does not fully understand AI.

● Human desire is inevitable. ● The creation of AI …

Mitigation Of Environmental Hazards Of Sulfide Mineral Flotation With An Insight Into Froth Stability And Flotation Performance, Muhammad Badar Hayat

Doctoral Dissertations

"Today's major challenges facing the flotation of sulfide minerals involve constant variability in the ore composition; environmental concerns; water scarcity and inefficient plant performance. The present work addresses these challenges faced by the flotation process of complex sulfide ore of Mississippi Valley type with an insight into the froth stability and the flotation performance. The first project in this study was aimed at finding the optimum conditions for the bulk flotation of galena (PbS) and chalcopyrite (CuFeS₂) through Response Surface Methodology (RSM). In the second project, an attempt was made to replace toxic sodium cyanide (NaCN) with the biodegradable chitosan …

Machine Learning Techniques Implementation In Power Optimization, Data Processing, And Bio-Medical Applications, Khalid Khairullah Mezied Al-Jabery

Doctoral Dissertations

"The rapid progress and development in machine-learning algorithms becomes a key factor in determining the future of humanity. These algorithms and techniques were utilized to solve a wide spectrum of problems extended from data mining and knowledge discovery to unsupervised learning and optimization. This dissertation consists of two study areas. The first area investigates the use of reinforcement learning and adaptive critic design algorithms in the field of power grid control. The second area in this dissertation, consisting of three papers, focuses on developing and applying clustering algorithms on biomedical data. The first paper presents a novel modelling approach for …

Human-Intelligence And Machine-Intelligence Decision Governance Formal Ontology, Faisal Mahmud

Engineering Management & Systems Engineering Theses & Dissertations

Since the beginning of the human race, decision making and rational thinking played a pivotal role for mankind to either exist and succeed or fail and become extinct. Self-awareness, cognitive thinking, creativity, and emotional magnitude allowed us to advance civilization and to take further steps toward achieving previously unreachable goals. From the invention of wheels to rockets and telegraph to satellite, all technological ventures went through many upgrades and updates. Recently, increasing computer CPU power and memory capacity contributed to smarter and faster computing appliances that, in turn, have accelerated the integration into and use of artificial intelligence (AI) in …

Automated Tree-Level Forest Quantification Using Airborne Lidar, Hamid Hamraz

Theses and Dissertations--Computer Science

Traditional forest management relies on a small field sample and interpretation of aerial photography that not only are costly to execute but also yield inaccurate estimates of the entire forest in question. Airborne light detection and ranging (LiDAR) is a remote sensing technology that records point clouds representing the 3D structure of a forest canopy and the terrain underneath. We present a method for segmenting individual trees from the LiDAR point clouds without making prior assumptions about tree crown shapes and sizes. We then present a method that vertically stratifies the point cloud to an overstory and multiple understory tree …

Modeling And Mapping Location-Dependent Human Appearance, Zachary Bessinger

Theses and Dissertations--Computer Science

Human appearance is highly variable and depends on individual preferences, such as fashion, facial expression, and makeup. These preferences depend on many factors including a person's sense of style, what they are doing, and the weather. These factors, in turn, are dependent upon geographic location and time. In our work, we build computational models to learn the relationship between human appearance, geographic location, and time. The primary contributions are a framework for collecting and processing geotagged imagery of people, a large dataset collected by our framework, and several generative and discriminative models that use our dataset to learn the relationship …

Using The Qbest Equation To Evaluate Ellagic Acid Safety Data: Generating A Qnoael With Confidence Levels From Disparate Literature, Cynthia Rose Dickerson

Theses and Dissertations--Pharmacy

QBEST, a novel statistical method, can be applied to the problem of estimating the No Observed Adverse Effect Level (NOAEL or QNOAEL) of a New Molecular Entity (NME) in order to anticipate a safe starting dose for beginning clinical trials. The NOAEL from QBEST (called the QNOAEL) can be calculated using multiple disparate studies in the literature and/or from the lab. The QNOAEL is similar in some ways to the Benchmark Dose Method (BMD) used widely in toxicological research, but is superior to the BMD in some ways. The QNOAEL simulation generates an intuitive curve that is comparable to the …

Environmental Physical-Virtual Interaction To Improve Social Presence With A Virtual Human In Mixed Reality, Kangsoo Kim

Electronic Theses and Dissertations

Interactive Virtual Humans (VHs) are increasingly used to replace or assist real humans in various applications, e.g., military and medical training, education, or entertainment. In most VH research, the perceived social presence with a VH, which denotes the user's sense of being socially connected or co-located with the VH, is the decisive factor in evaluating the social influence of the VH—a phenomenon where human users' emotions, opinions, or behaviors are affected by the VH. The purpose of this dissertation is to develop new knowledge about how characteristics and behaviors of a VH in a Mixed Reality (MR) environment can affect …

A Recurrent Neural Network Architecture For Biomedical Event Trigger Classification, Jeevith Bopaiah

Theses and Dissertations--Computer Science

A “biomedical event” is a broad term used to describe the roles and interactions between entities (such as proteins, genes and cells) in a biological system. The task of biomedical event extraction aims at identifying and extracting these events from unstructured texts. An important component in the early stage of the task is biomedical trigger classification which involves identifying and classifying words/phrases that indicate an event. In this thesis, we present our work on biomedical trigger classification developed using the multi-level event extraction dataset. We restrict the scope of our classification to 19 biomedical event types grouped under four broad …