Digital Commons Network^™

Artificial Superintelligence: Extinction Or Nirvana?, Jens Pohl

Architecture

The purpose of this paper is to explore the subject of Artificial General Intelligence (AGI) and Artificial Superintelligence (ASI) and identify in summary form the principal drivers and current status of Artificial Narrow Intelligence (ANI), the impact that intelligent software in combination with the Internet serving as a Global Knowledgebase is already having on human capabilities, the likely path to ASI, the possible threats posed by ASI and proposed measures to curtail those threats, and finally the potential benefits to the human species if AGI and ASI remain under human control.

On Supervised And Unsupervised Methodologies For Mining Of Text Data., Tanmay Basu Dr.

Doctoral Theses

The supervised and unsupervised methodologies of text mining using the plain text data of English language have been discussed. Some new supervised and unsupervised methodologies have been developed for effective mining of the text data after successfully overcoming some limitations of the existing techniques.The problems of unsupervised techniques of text mining, i.e., document clustering methods are addressed. A new similarity measure between documents has been designed to improve the accuracy of measuring the content similarity between documents. Further, a hierarchical document clustering technique is designed using this similarity measure. The main significance of the clustering algorithm is that the number …

Novelty Wins, “Straight Toward Objective” Loses! Or Book Review: Why Greatness Cannot Be Planned: The Myth Of The Objective, By Kenneth O. Stanley And Joel Lehman, Reuben Hersh

Journal of Humanistic Mathematics

Experiments in evolutionary artificial intelligence demonstrate that progress toward an important, difficult goal is not best achieved by attempting to go directly toward that goal, but rather, by rewarding novelty.

Message Passing For Collective Graphical Models, Tao Sun, Daniel Sheldon, Akshat Kumar

Research Collection School Of Computing and Information Systems

Collective graphical models (CGMs) are a formalism for inference and learning about a population of independent and identically distributed individuals when only noisy aggregate data are available. We highlight a close connection between approximate MAP inference in CGMs and marginal inference in standard graphical models. The connection leads us to derive a novel Belief Propagation (BP) style algorithm for collective graphical models. Mathematically, the algorithm is a strict generalization of BP—it can be viewed as an extension to minimize the Bethe free energy plus additional energy terms that are non-linear functions of the marginals. For CGMs, the algorithm is much …

Probabilistic Inference Based Message-Passing For Resource Constrained Dcops, Supriyo Ghosh, Akshat Kumar, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Distributed constraint optimization (DCOP) is an important framework for coordinated multiagent decision making. We address a practically useful variant of DCOP, called resource-constrained DCOP (RC-DCOP), which takes into account agents’ consumption of shared limited resources. We present a promising new class of algorithm for RC-DCOPs by translating the underlying co- ordination problem to probabilistic inference. Using inference techniques such as expectation- maximization and convex optimization machinery, we develop a novel convergent message-passing algorithm for RC-DCOPs. Experiments on standard benchmarks show that our approach provides better quality than previous best DCOP algorithms and has much lower failure rate. Comparisons against an …

Continuous Monitoring Of Enterprise Risks: A Delphi Feasibility Study, Robert Baksa

Dissertations

A constantly evolving regulatory environment, increasing market pressure to improve operations, and rapidly changing business conditions are creating the need for ongoing assurance that organizational risks are continually and adequately mitigated. Enterprises are perpetually exposed to fraud, poor decision making and/or other inefficiencies that can lead to significant financial loss and/or increased levels of operating risk. Increasingly, Information Systems are being harnessed to reinvent the risk management process. One promising technology is Continuous Auditing, which seeks to transform the audit process from periodic reviews of a few transactions to a continuous review of all transactions. However, the highly integrated, rapidly …

Estimating The Accuracy Of Automated Classification Systems Using Only Expert Ratings That Are Less Accurate Than The System, Paul E. Lehner

Journal of Modern Applied Statistical Methods

A method is presented to estimate the accuracy of an automated classification system based only on expert ratings on test cases, where the system may be substantially more accurate than the raters. In this method an estimate of overall rater accuracy is derived from the level of inter-rater agreement, Bayesian updating based on estimated rater accuracy is applied to estimate a ground truth probability for each classification on each test case, and then overall system accuracy is estimated by comparing the relative frequency that the system agrees with the most probable classification at different probability levels. A simulation analysis provides …

Unified Behavior Framework For Discrete Event Simulation Systems, Alexander J. Kamrud

Theses and Dissertations

Intelligent agents provide simulations a means to add lifelike behavior in place of manned entities. Generally when developed, a single intelligent agent model is chosen, such as rule based, behavior trees, etc. This choice introduces restrictions into what behaviors agents can manifest, and can require significant testing in edge cases. This thesis presents the use of the UBF in the AFSIM environment. The UBF provides the flexibility to implement any and all intelligent agent models, allowing the developer to choose the model he/she feels best fits the experiment at hand. Furthermore, the UBF demonstrates several key software engineering principles through …

The Application Of Biomedical Engineering Techniques To The Diagnosis And Management Of Tropical Diseases: A Review, Fatimah Ibrahim, Tzer Hwai Gilbert Thio, Tarig Faisal, Michael Neuman

Michigan Tech Publications, Part 1

This paper reviews a number of biomedical engineering approaches to help aid in the detection and treatment of tropical diseases such as dengue, malaria, cholera, schistosomiasis, lymphatic filariasis, ebola, leprosy, leishmaniasis, and American trypanosomiasis (Chagas). Many different forms of non-invasive approaches such as ultrasound, echocardiography and electrocardiography, bioelectrical impedance, optical detection, simplified and rapid serological tests such as lab-on-chip and micro-/nano-fluidic platforms and medical support systems such as artificial intelligence clinical support systems are discussed. The paper also reviewed the novel clinical diagnosis and management systems using artificial intelligence and bioelectrical impedance techniques for dengue clinical applications.

Fl-Lab V2: Design And Development Of An Easy-To-Use, Interactive Fuzzy Logic Control Software System, Utku Kose, Omer Deperlioglu

Applied Mathematics & Information Sciences

The Fuzzy Logic or the Fuzzy Logic Control is an Artificial Intelligence approach/technique, which is especially used for designing and developing intelligent controlling systems. It provides an effective and efficient method to simulate the human thinking and behaviors in order to ensure the related intelligent controlling structure. In this context, this paper introduces the FL-LAB v2: a software system, which can be used to design and develop different kinds of Fuzzy Logic inference and controlling systems, by using an easy-to-use, interactive and effective software environment. This software system is the second version of pre-introduced software system and it provides more …

The Application Of Biomedical Engineering Techniques To The Diagnosis And Management Of Tropical Diseases: A Review, F. Ibrahim, T.H.G. Thio, T. Faisal, M. Neuman

Research Publications (2011 to 2015)

This paper reviews a number of biomedical engineering approaches to help aid in the detection and treatment of tropical diseases such as dengue, malaria, cholera, schistosomiasis, lymphatic filariasis, ebola, leprosy, leishmaniasis, and American trypanosomiasis (Chagas). Many different forms of non-invasive approaches such as ultrasound, echocardiography and electrocardiography, bioelectrical impedance, optical detection, simplified and rapid serological tests such as lab-on-chip and micro-/nano-fluidic platforms and medical support systems such as artificial intelligence clinical support systems are discussed. The paper also reviewed the novel clinical diagnosis and management systems using artificial intelligence and bioelectrical impedance techniques for dengue clinical applications.

A Theory Of Name Resolution, Pierre Néron, Andrew Tolmach, Eelco Visser, Guido Wachsmuth

Computer Science Faculty Publications and Presentations

We describe a language-independent theory for name binding and resolution, suitable for programming languages with complex scoping rules including both lexical scoping and modules. We formulate name resolution as a two-stage problem. First a language-independent scope graph is constructed using language-specific rules from an abstract syntax tree. Then references in the scope graph are resolved to corresponding declarations using a language-independent resolution process. We introduce a resolution calculus as a concise, declarative, and language- independent specification of name resolution. We develop a resolution algorithm that is sound and complete with respect to the calculus. Based on the resolution calculus we …

Sparse Coding Based Dense Feature Representation Model For Hyperspectral Image Classification, Ender Oguslu, Guoqing Zhou, Zezhong Zheng, Khan Iftekharuddin, Jiang Li

Electrical & Computer Engineering Faculty Publications

We present a sparse coding based dense feature representation model (a preliminary version of the paper was presented at the SPIE Remote Sensing Conference, Dresden, Germany, 2013) for hyperspectral image (HSI) classification. The proposed method learns a new representation for each pixel in HSI through the following four steps: sub-band construction, dictionary learning, encoding, and feature selection. The new representation usually has a very high dimensionality requiring a large amount of computational resources. We applied the l₁/l_q regularized multiclass logistic regression technique to reduce the size of the new representation. We integrated the method with a linear …

A Study On Solution Of Matrix Riccati Differential Equations Using Ant Colony Programming And Simulink / Mohd Zahurin Mohamed Kamali, Mohd Zahurin Mohamed Kamali

Student Works (2010-2019)

Swarm intelligence is a modern artificial intelligence discipline that is concerned with the design and optimization of multiagent systems with applications in robotics. This non-traditional approach is fundamentally different from the traditional approaches. In- stead of a sophisticated controller that governs the global behavior of the system, the swarm intelligence principle is based on many unsophisticated entities (for example such as ants, termites, bees etc.) that cooperate and interact in order to exhibit a desired behav- ior. In this thesis, we implement the modified ant colony programming (ACP) algorithm for solving the matrix Riccati differential equation (MRDE). Solving MRDE, especially …

Overview Of Global Supercomputing, Richard S. Segall, Neha Gupta

Faculty Publications

In this chapter, a discussion is presented of what a supercomputer really is, as well as of both the top few of the world's fastest supercomputers and the overall top 500 in the world. Discussions are also of cognitive science research using supercomputers for artificial intelligence, architectural classes of supercomputers, and discussion and visualization using tables and graphs of global supercomputing comparisons across different countries. Discussion of supercomputing applications and overview of other book chapters of the entire book are all presented. This chapter serves as an introduction to the entire book and concludes with a summary of the topics …

Autonomous Quadcopter Videographer, Quiquia Rey Coaguila

Electronic Theses and Dissertations

In recent years, the interest in quadcopters as a robotics platform for autonomous photography has increased. This is due to their small size and mobility, which allow them to reach places that are difficult or even impossible for humans. This thesis focuses on the design of an autonomous quadcopter videographer, i.e. a quadcopter capable of capturing good footage of a specific subject. In order to obtain this footage, the system needs to choose appropriate vantage points and control the quadcopter. Skilled human videographers can easily spot good filming locations where the subject and its actions can be seen clearly in …

Modeling User Transportation Patterns Using Mobile Devices, Erfan Davami

Electronic Theses and Dissertations

Participatory sensing frameworks use humans and their computing devices as a large mobile sensing network. Dramatic accessibility and affordability have turned mobile devices (smartphone and tablet computers) into the most popular computational machines in the world, exceeding laptops. By the end of 2013, more than 1.5 billion people on earth will have a smartphone. Increased coverage and higher speeds of cellular networks have given these devices the power to constantly stream large amounts of data. Most mobile devices are equipped with advanced sensors such as GPS, cameras, and microphones. This expansion of smartphone numbers and power has created a sensing …

Semi-Universal Portfolios With Transaction Costs, Dingjiang Huang, Yan Zhu, Bin Li, Shuigeng Zhou, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Online portfolio selection (PS) has been extensively studied in artificial intelligence and machine learning communities in recent years. An important practical issue of online PS is transaction cost, which is unavoidable and nontrivial in real financial trading markets. Most existing strategies, such as universal portfolio (UP) based strategies, often rebalance their target portfolio vectors at every investment period, and thus the total transaction cost increases rapidly and the final cumulative wealth degrades severely. To overcome the limitation, in this paper we investigate new investment strategies that rebalances its portfolio only at some selected instants. Specifically, we design a novel on-line …

Designing A Portfolio Of Parameter Configurations For Online Algorithm Selection, Aldy Gunawan, Hoong Chuin Lau, Mustafa Misir

Research Collection School Of Computing and Information Systems

Algorithm portfolios seek to determine an effective set of algorithms that can be used within an algorithm selection framework to solve problems. A limited number of these portfolio studies focus on generating different versions of a target algorithm using different parameter configurations. In this paper, we employ a Design of Experiments (DOE) approach to determine a promising range of values for each parameter of an algorithm. These ranges are further processed to determine a portfolio of parameter configurations, which would be used within two online Algorithm Selection approaches for solving different instances of a given combinatorial optimization problem effectively. We …

Language Processing And The Artificial Mind: Teaching Code Literacy In The Humanities, Jerry Scott Weltman

LSU Master's Theses

Humanities majors often find themselves in jobs where they either manage programmers or work with them in close collaboration. These interactions often pose difficulties because specialists in literature, history, philosophy, and so on are not usually "code literate." They do not understand what tasks computers are best suited to, or how programmers solve problems. Learning code literacy would be a great benefit to humanities majors, but the traditional computer science curriculum is heavily math oriented, and students outside of science and technology majors are often math averse. Yet they are often interested in language, linguistics, and science fiction. This thesis …

A Neuro-Genetic Hybrid Approach To Automatic Identification Of Plant Leaves, Oluleye Hezekiah Babatunde

Theses: Doctorates and Masters

Plants are essential for the existence of most living things on this planet. Plants are used for providing food, shelter, and medicine. The ability to identify plants is very important for several applications, including conservation of endangered plant species, rehabilitation of lands after mining activities and differentiating crop plants from weeds.

In recent times, many researchers have made attempts to develop automated plant species recognition systems. However, the current computer-based plants recognition systems have limitations as some plants are naturally complex, thus it is difficult to extract and represent their features. Further, natural differences of features within the same plant …

An Automatic Dialog System For Student Advising, Brian Mcmahan

Journal of Undergraduate Research at Minnesota State University, Mankato

Automatic dialog systems are an implementation of natural language processing theory with the goal of allowing the use of natural sentences to communicate with a computer system. The general purpose of this project was to design and implement an automatic dialog system for augmenting university student advising. Student advising is a relatively narrow domain of possible questions and responses. The automatic dialog system focused on prescriptive advising rather than developmental advising to further narrow the domain to scheduling and registration matters. A student advisor was interviewed and recorded during a mock advising session in order to model the interaction between …

Evolutionary Search Techniques With Strong Heuristics For Multi-Objective Feature Selection In Software Product Lines, Abdel Salam Sayyad

Graduate Theses, Dissertations, and Problem Reports (ETD)

Software design is a process of trading off competing objectives. If the user objective space is rich, then we should use optimizers that can fully exploit that richness. For example, this study configures software product lines (expressed as feature models) using various search-based software engineering methods. Our main result is that as we increase the number of optimization objectives, the methods in widespread use (e.g. NSGA-II, SPEA2) perform much worse than IBEA (Indicator-Based Evolutionary Algorithm). IBEA works best since it makes most use of user preference knowledge. Hence it does better on the standard measures (hypervolume and spread) but it …

Assisted History Matching Using Pattern Recognition Technology, Alireza Shahkarami

Graduate Theses, Dissertations, and Problem Reports (ETD)

Reservoir simulation and modeling is utilized throughout field development in different capacities. Sensitivity analysis, history matching, operations optimization and uncertainty assessment are the conventional analyses in full field model studies. Realistic modeling of the complexities of a reservoir requires a large number of grid blocks. As the complexity of a reservoir increases and consequently the number of grid blocks, so does the time required to accomplish the abovementioned tasks.;This study aims to examine the application of pattern recognition technologies to improve the time and efforts required for completing successful history matching projects. The pattern recognition capabilities of Artificial Intelligence and …

Convergence Of A Reinforcement Learning Algorithm In Continuous Domains, Stephen Carden

All Dissertations

In the field of Reinforcement Learning, Markov Decision Processes with a finite number of states and actions have been well studied, and there exist algorithms capable of producing a sequence of policies which converge to an optimal policy with probability one. Convergence guarantees for problems with continuous states also exist. Until recently, no online algorithm for continuous states and continuous actions has been proven to produce optimal policies. This Dissertation contains the results of research into reinforcement learning algorithms for problems in which both the state and action spaces are continuous. The problems to be solved are introduced formally as …

Collaborative Online Multitask Learning, Guangxia Li, Steven C. H. Hoi, Kuiyu Chang, Wenting Liu, Ramesh Jain

Research Collection School Of Computing and Information Systems

We study the problem of online multitask learning for solving multiple related classification tasks in parallel, aiming at classifying every sequence of data received by each task accurately and efficiently. One practical example of online multitask learning is the micro-blog sentiment detection on a group of users, which classifies micro-blog posts generated by each user into emotional or non-emotional categories. This particular online learning task is challenging for a number of reasons. First of all, to meet the critical requirements of online applications, a highly efficient and scalable classification solution that can make immediate predictions with low learning cost is …

A Continuous Learning Strategy For Self-Organizing Maps Based On Convergence Windows, Gregory T. Breard

Senior Honors Projects

A self-organizing map (SOM) is a type of artificial neural network that has applications in a variety of fields and disciplines. The SOM algorithm uses unsupervised learning to produce a low-dimensional representation of high- dimensional data. This is done by 'fitting' a grid of nodes to a data set over a fixed number of iterations. With each iteration, the nodes of the map are adjusted so that they appear more like the data points. The low-dimensionality of the resulting map means that it can be presented graphically and be more intuitively interpreted by humans. However, it is still essential to …

Meta Concepts: A Knowledge-Based Code Generation System, Nicholas Moss

Computer Science ETDs

People have an amazing ability to solve complex problems by performing a sequence of simpler operations (i.e: functions/procedures which take input variables and produce output variables). We are able to do so even when there exists a large number of possible choices for such operations and when the number of combinatoric ways that these operations can be chained together is astronomical. On the other hand, computers typically do not solve problems this way and have to be programmed with a precise set of instructions. What is it that allows us to perform such a feat while computers cannot? One of …

Bio-Inspired Optimization Of Ultra-Wideband Patch Antennas Using Graphics Processing Unit Acceleration, Brian Vyhnalek

ETD Archive

Ultra-wideband (UWB) wireless systems have recently gained considerable attention as effective communications platforms with the properties of low power and high data rates. Applications of UWB such as wireless USB put size constraints on the antenna, however, which can be very dicult to meet using typical narrow band antenna designs. The aim of this thesis is to show how bio-inspired evolutionary optimization algorithms, in particular genetic algorithm (GA), particle swarm optimization (PSO) and biogeography-based optimization (BBO) can produce novel UWB planar patch antenna designs that meet a size constraint of a 10 mm 10 mm patch. Each potential antenna design …

Evolutionary Algorithm Based Approach For Modeling Autonomously Trading Agents, Anil Yaman, Stephen Lucci, Izidor Gertner

Publications and Research

The autonomously trading agents described in this paper produce a decision to act such as: buy, sell or hold, based on the input data. In this work, we have simulated autonomously trading agents using the Echo State Network (ESNs) model. We generate a collection of trading agents that use different trading strategies using Evolutionary Programming (EP). The agents are tested on EUR/ USD real market data. The main goal of this study is to test the overall performance of this collection of agents when they are active simultaneously. Simulation results show that using different agents concurrently outperform a single agent …