Artificial Intelligence and Robotics Commons^™

Relationship Preserving Auction For Repeated E-Procurement, Park J., Lee J., Lau H.

Research Collection School Of Computing and Information Systems

While e-procurement auction has helped firms to achieve lower procurement costs, auction mechanisms that prevail at present in procurement markets need to address an important issue that concerns the ability to maintain long term relationships with the partners, especially in repeated e-procurement settings. In this paper, we propose a Relationship Preserving Auction (RPA) mechanism that augments the conventional auction mechanism with a bidder relationship scoring model. Our proposed mechanism gives increased chances of winning to the bidders who have bidden at relatively competitive price but had comparatively less wins so far. Keeping these bidders in the auction over time will …

Scaling Ant Colony Optimization With Hierarchical Reinforcement Learning Partitioning, Erik J. Dries, Gilbert L. Peterson

Faculty Publications

This paper merges hierarchical reinforcement learning (HRL) with ant colony optimization (ACO) to produce a HRL ACO algorithm capable of generating solutions for large domains. This paper describes two specific implementations of the new algorithm: the first a modification to Dietterich’s MAXQ-Q HRL algorithm, the second a hierarchical ant colony system algorithm. These implementations generate faster results, with little to no significant change in the quality of solutions for the tested problem domains. The application of ACO to the MAXQ-Q algorithm replaces the reinforcement learning, Q-learning, with the modified ant colony optimization method, Ant-Q. This algorithm, MAXQ-AntQ, converges to solutions …

A Simplex Model For Layered Niche Networks, Philip Fraundorf

Physics Faculty Works

No abstract provided.

H-Dpop: Using Hard Constraints For Search Space Pruning In Dcop, Akshat Kumar, Adrian Petcu, Boi Faltings

Research Collection School Of Computing and Information Systems

In distributed constraint optimization problems, dynamic programming methods have been recently proposed (e.g. DPOP). In dynamic programming many valuations are grouped together in fewer messages, which produce much less networking overhead than search. Nevertheless, these messages are exponential in size. The basic DPOP always communicates all possible assignments, even when some of them may be inconsistent due to hard constraints. Many real problems contain hard constraints that significantly reduce the space of feasible assignments. This paper introduces H-DPOP, a hybrid algorithm that is based on DPOP, which uses Constraint Decision Diagrams (CDD) to rule out infeasible assignments, and thus compactly …

Linear Relaxation Techniques For Task Management In Uncertain Settings, Pradeep Varakantham, Stephen F. Smith

Research Collection School Of Computing and Information Systems

In this paper, we consider the problem of assisting a busy user in managing her workload of pending tasks. We assume that our user is typically oversubscribed, and is invariably juggling multiple concurrent streams of tasks (or work flows) of varying importance and urgency. There is uncertainty with respect to the duration of a pending task as well as the amount of follow-on work that may be generated as a result of executing the task. The user’s goal is to be as productive as possible; i.e., to execute tasks that realize the maximum cumulative payoff. This is achieved by enabling …

Multi-View Ear Recognition Based On B-Spline Pose Manifold Construction, Zhiyuan Zhang, Heng Liu

Research Collection School Of Computing and Information Systems

In this work, multi-view ear recognition problems are examined in detail. A new multi-view ear recognition approach based on B-Spline pose manifold construction in discriminative projection space which is formed by null kernel discriminant analysis (NKDA) feature extraction is presented. Many experiments and comparisons are provided to show the effectiveness of our multi-view ear recognition approach.

Electric Elves: What Went Wrong And Why, Milind Tambe, Emma Bowring, Jonathan Pearce, Pradeep Reddy Varakantham, Paul Scerri, David V. Pynadath

Research Collection School Of Computing and Information Systems

Software personal assistants continue to be a topic of significant research interest. This article outlines some of the important lessons learned from a successfully-deployed team of personal assistant agents (Electric Elves) in an office environment. In the Electric Elves project, a team of almost a dozen personal assistant agents were continually active for seven months. Each elf (agent) represented one person and assisted in daily activities in an actual office environment. This project led to several important observations about privacy, adjustable autonomy, and social norms in office environments. In addition to outlining some of the key lessons learned we outline …

Characterizing Effective Auction Mechanisms: Insights From The 2007 Tac Mechanism Design Competition, Jinzhong Niu, Kai Cai, Simon Parsons, Enrico Gerding, Peter Mcburney

Publications and Research

This paper analyzes the entrants to the 2007 TAC Market Design competition. It presents a classification of the entries to the competition, and uses this classification to compare these entries. The paper also attempts to relate market dynamics to the auction rules adopted by these entries and their adaptive strategies via a set of post-tournament experiments. Based on this analysis, the paper speculates about the design of effective auction mechanisms, both in the setting of this competition and in the more general case.

Jcat: A Platform For The Tac Market Design Competition, Jinzhong Niu, Kai Cai, Simon Parsons, Enrico Gerding, Peter Mcburney, Thierry Moyaux, Steve Phelps, David Shield

Publications and Research

No abstract provided.

Wireless Sensor Network Modeling Using Modified Recurrent Neural Network: Application To Fault Detection, Azzam Issam Moustapha

Doctoral Dissertations

Wireless Sensor Networks (WSNs) consist of a large number of sensors, which in turn have their own dynamics. They interact with each other and the base station, which controls the network. In multi-hop wireless sensor networks, information hops from one node to another and finally to the network gateway or base station. Dynamic Recurrent Neural Networks (RNNs) consist of a set of dynamic nodes that provide internal feedback to their own inputs. They can be used to simulate and model dynamic systems such as a network of sensors.

In this dissertation, a dynamic model of wireless sensor networks and its …

K-Means+Id3 And Dependence Tree Methods For Supervised Anomaly Detection, Kiran S. Balagani

Doctoral Dissertations

In this dissertation, we present two novel methods for supervised anomaly detection. The first method "K-Means+ID3" performs supervised anomaly detection by partitioning the training data instances into k clusters using Euclidean distance similarity. Then, on each cluster representing a density region of normal or anomaly instances, an ID3 decision tree is built. The ID3 decision tree on each cluster refines the decision boundaries by learning the subgroups within a cluster. To obtain a final decision on detection, the k-Means and ID3 decision trees are combined using two rules: (1) the nearest neighbor rule; and (2) the nearest consensus rule. The …

Behavior-Based Power Management In Autonomous Mobile Robots, Charles A. Fetzek

Theses and Dissertations

Current attempts to prolong the life of a robot on a single battery charge focus on lowering the operating frequency of the onboard hardware, or allowing devices to go to sleep during idle states. These techniques have much overhead and do not come built in to the underlying robotic architecture. In this thesis, battery life is greatly extended through development of a behavior-based power management system, including a Markov decision process power planner, thereby allowing future robots increased time to operate and loiter in their required domain. Behavior-based power management examines sensors needed by the currently active behavior set and …

Exploitation Of Self Organization In Uav Swarms For Optimization In Combat Environments, Dustin J. Nowak

Theses and Dissertations

This investigation focuses primarily on the development of effective target engagement for unmanned aerial vehicle (UAV) swarms using autonomous self-organized cooperative control. This development required the design of a new abstract UAV swarm control model which flows from an abstract Markov structure, a Partially Observable Markov Decision Process. Self-organization features, bio-inspired attack concepts, evolutionary computation (multi-objective genetic algorithms, differential evolution), and feedback from environmental awareness are instantiated within this model. The associated decomposition technique focuses on the iterative deconstruction of the problem domain state and dynamically building-up of self organizational rules as related to the problem domain environment. Resulting emergent …

Dynamic Behavior Sequencing In A Hybrid Robot Architecture, Jeffrey P. Duffy

Theses and Dissertations

Hybrid robot control architectures separate plans, coordination, and actions into separate processing layers to provide deliberative and reactive functionality. This approach promotes more complex systems that perform well in goal-oriented and dynamic environments. In various architectures, the connections and contents of the functional layers are tightly coupled so system updates and changes require major changes throughout the system. This work proposes an abstract behavior representation, a dynamic behavior hierarchy generation algorithm, and an architecture design to reduce this major change incorporation process. The behavior representation provides an abstract interface for loose coupling of behavior planning and execution components. The hierarchy …

A Secure Group Communication Architecture For A Swarm Of Autonomous Unmanned Aerial Vehicles, Adrian N. Phillips

Theses and Dissertations

This thesis investigates the application of a secure group communication architecture to a swarm of autonomous unmanned aerial vehicles (UAVs). A multicast secure group communication architecture for the low earth orbit (LEO) satellite environment is evaluated to determine if it can be effectively adapted to a swarm of UAVs and provide secure, scalable, and efficient communications. The performance of the proposed security architecture is evaluated with two other commonly used architectures using a discrete event computer simulation developed using MatLab. Performance is evaluated in terms of the scalability and efficiency of the group key distribution and management scheme when the …

Conceptual Study Of Rotary-Wing Microrobotics, Kelson D. Chabak

Theses and Dissertations

This thesis presents a novel rotary-wing micro-electro-mechanical systems (MEMS) robot design. Two MEMS wing designs were designed, fabricated and tested including one that possesses features conducive to insect level aerodynamics. Two methods for fabricating an angled wing were also attempted with photoresist and CrystalBond™ to create an angle of attack. One particular design consisted of the wing designs mounted on a gear which are driven by MEMS actuators. MEMS comb drive actuators were analyzed, simulated and tested as a feasible drive system. The comb drive resonators were also designed orthogonally which successfully rotated a gear without wings. With wings attached …

Ant Clustering With Locally Weighting Ant Perception And Diversified Memory, Gilbert L. Peterson, Christopher B. Mayer, Thomas L. Kubler

Faculty Publications

Ant clustering algorithms are a robust and flexible tool for clustering data that have produced some promising results. This paper introduces two improvements that can be incorporated into any ant clustering algorithm: kernel function similarity weights and a similarity memory model replacement scheme. A kernel function weights objects within an ant’s neighborhood according to the object distance and provides an alternate interpretation of the similarity of objects in an ant’s neighborhood. Ants can hill-climb the kernel gradients as they look for a suitable place to drop a carried object. The similarity memory model equips ants with a small memory consisting …

Thermal Roots Of Correlation-Based Complexity, Philip Fraundorf

Physics Faculty Works

Bayesian maxent lets one integrate thermal physics and information theory points of view in the quantitative study of complex systems. Since net surprisal (a free energy analog for measuring “departures from expected”) allows one to place second law constraints on mutual information (a multimoment measure of correlations), it makes a quantitative case for the role of reversible thermalization in the natural history of invention, and suggests multiscale strategies to monitor standing crop as well. It prompts one to track evolved complexity starting from live astrophysically observed processes, rather than only from evidence of past events. Various gradients and boundaries that …

Lightweight Objective Quality Of Voice Estimation Through Machine Learning, Daniel Riordan

Theses

Communication systems are undergoing constant and rapid innovation, both at the design stage and in the field. This in turn has led to an inereasing need for fast, efficient, portable and economic methods for the testing of these systems. For voice carrying communication systems the quality of the transmitted voice that the system produces is a large factor in the overall performance rating of the system. This measure is known as the ‘Quality of Voice’ (QoV) and can be evaluated either subjectively or objectively.

Speech quality is a complex subjective phenomenon that can be best quantified by subjective testing. A …

Object Detection And Classification With Applications To Skin Cancer Screening, Jonathan Blackledge, Dmitryi Dubovitskiy

Articles

This paper discusses a new approach to the processes of object detection, recognition and classification in a digital image. The classification method is based on the application of a set of features which include fractal parameters such as the Lacunarity and Fractal Dimension. Thus, the approach used, incorporates the characterisation of an object in terms of its texture.

The principal issues associated with object recognition are presented which includes two novel fast segmentation algorithms for which C++ code is provided. The self-learning procedure for designing a decision making engine using fuzzy logic and membership function theory is also presented and …

A Practical Approach To Robotic Design For The Darpa Urban Challenge, Benjamin J. Patz, Yiannis Papelis, Remo Pillat, Gary Stein, Don Harper

VMASC Publications

This article presents a practical approach to engineering a robot to effectively navigate in an urban environment. Inherent in this approach is the use of relatively simple sensors, actuators, and processors to generate robot vision, intelligence, and planning. Sensor data are fused from multiple low-cost, two-dimensional laser scanners With an innovative rotational mount to provide three-dimensional coverage with image processing using both range and intensity data. Information is combined With Doppler radar returns to yield a world view processed by a context-based reasoning control system to yield tactical mission commands forwarded to traditional proportional-integral-derivative (PID) control loops. As an example …

Robot Controller Architecture: Layered Mode Selection Logic With Fuzzy Sensor Fusion Network, Traig E.B. Born

Theses and Dissertations

A behavior based robot controller was implemented using Layered Mode Selection Logic as a behavior coordination mechanism and a Fuzzy Sensor Fusion Network to provide perception. A series of collision experiments were conducted to create a Fuzzy Sensor Fusion Network capable of detecting collisions using acceleration readings from wheel encoders. An obstacle avoidance behavior was created, and it was demonstrated that the robot could be constrained by movable obstacles. The avoidance behavior was modified to create an obstacle manipulation behavior. This behavior allowed the robot to escape when enclosed by movable obstacles. The fuzzy sensor fusion network was enhanced to …

Enhancing Recursive Supervised Learning Using Clustering And Combinatorial Optimization (Rsl-Cc), Kiruthika Ramanathan, Sheng Uei Guan

Research Collection School Of Computing and Information Systems

The use of a team of weak learners to learn a dataset has been shown better than the use of one single strong learner. In fact, the idea is so successful that boosting, an algorithm combining several weak learners for supervised learning, has been considered to be one of the best off-the-shelf classifiers. However, some problems still remain, including determining the optimal number of weak learners and the overfitting of data. In an earlier work, we developed the RPHP algorithm which solves both these problems by using a combination of genetic algorithm, weak learner and pattern distributor. In this paper, …

New Method For Approximating Vague Sets To Fuzzy Sets Based On Voting Model, Jian Liu, Zhizhan Liu, Shunxiang Wu, Yongjian Zhang

Electrical and Computer Engineering Faculty Research & Creative Works

By analyzing Vague Sets voting model, we bring forth a new method for approximating Vague Sets to Fuzzy Sets, and its general process is presented in the article. In a voting model, firstly, we suppose that the abstainers must vote for once more, and the results are close studied. Then the randomicity, uncertainty, and conformity of voting are found. As we know, an abstainer may favor somebody, oppose somebody, or just abstain. In this article, we suppose the distribution of results is consistent with a normal distribution. So, we advance the new approximation method based on Gauss Distribution. © 2008 …

Medical Language Processing For Patient Diagnosis Using Text Classification And Negation Labelling, Brian Mac Namee, John D. Kelleher, Sarah Jane Delany

Conference papers

This paper describes the approach of the DIT AIGroup to the i2b2 Obesity Challenge to build a system to diagnose obesity and related co-morbidities from narrative, unstructured patient records. Based on experimental results a system was developed which used knowledge-light text classification using decision trees, and negation labelling.

Referring Expression Generation Challenge 2008 Dit System Descriptions (Dit-Fbi, Dit-Tvas, Dit-Cbsr, Dit-Rbr, Dit-Fbi-Cbsr, Dit-Tvas-Rbr), John D. Kelleher, Brian Mac Namee

Conference papers

This papers desibes a set of systems developed at DIT for the Referring Expression Generation challenage at INLG 2008.In Proceedings of the 5th International Natural Language Generation Conference (INLG-08)

A Translation Mechanism For Recommendations, Pierpaolo Dondio, Luca Longo, Stephen Barrett

Conference papers

An important class of distributed Trust-based solutions is based on the information sharing. A basic requirement of such systems is the ability of participating agents to effectively communicate, receiving and sending messages that can be interpreted correctly. Unfortunately, in open systems it is not possible to postulate a common agreement about the representation of a rating, its semantic meaning and cognitive and computational mechanisms behind a trust-rating formation. Social scientists agree to consider unqualified trust values not transferable, but a more pragmatic approach would conclude that qualified trust judgments are worth being transferred as far as decisions taken considering others’ …

The Oil Drilling Model And Iterative Deepening Genetic Annealing Algorithm For The Traveling Salesman Problem, Hoong Chuin Lau, Fei Xiao

Research Collection School Of Computing and Information Systems

In this work, we liken the solving of combinatorial optimization problems under a prescribed computational budget as hunting for oil in an unexplored ground. Using this generic model, we instantiate an iterative deepening genetic annealing (IDGA) algorithm, which is a variant of memetic algorithms. Computational results on the traveling salesman problem show that IDGA is more effective than standard genetic algorithms or simulated annealing algorithms or a straightforward hybrid of them. Our model is readily applicable to solve other combinatorial optimization problems.

A Unified Framework For Solving Multiagent Task Assignment Problems, Kevin Cousin

Theses and Dissertations

Multiagent task assignment problem descriptors do not fully represent the complex interactions in a multiagent domain, and algorithmic solutions vary widely depending on how the domain is represented. This issue is compounded as related research fields contain descriptors that similarly describe multiagent task assignment problems, including complex domain interactions, but generally do not provide the mechanisms needed to solve the multiagent aspect of task assignment. This research presents a unified approach to representing and solving the multiagent task assignment problem for complex problem domains. Ideas central to multiagent task allocation, project scheduling, constraint satisfaction, and coalition formation are combined to …

A Hybrid Multi-Robot Control Architecture, Daylond J. Hooper

Theses and Dissertations

Multi-robot systems provide system redundancy and enhanced capability versus single robot systems. Implementations of these systems are varied, each with specific design approaches geared towards an application domain. Some traditional single robot control architectures have been expanded for multi-robot systems, but these expansions predominantly focus on the addition of communication capabilities. Both design approaches are application specific and limit the generalizability of the system. This work presents a redesign of a common single robot architecture in order to provide a more sophisticated multi-robot system. The single robot architecture chosen for application is the Three Layer Architecture (TLA). The primary strength …