Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Loren Wyard-Scott is active.

Publication


Featured researches published by Loren Wyard-Scott.


pacific rim conference on communications, computers and signal processing | 1995

A potential maze solving algorithm for a micromouse robot

Loren Wyard-Scott; Q.-H.M. Meng

Discretely assigned potential levels can be effectively used in making autonomous route decisions for a mobile robot to reach a goal. This paper demonstrates methods of assigning and manipulating these artificial potentials to provide locally optimized path choices while maintaining the integrity of the potentials. The basic algorithm is improved by retaining information of the number of decisions that have been made. Results from implementation and simulation of the algorithm for a micromouse maze-solving robot are presented. Consideration is given to implementation using a limited power microprocessor.


IEEE Annual Meeting of the Fuzzy Information, 2004. Processing NAFIPS '04. | 2004

Fuzzy logic in agent-based game design

Yifan Li; Petr Musilek; Loren Wyard-Scott

The underlying artificial intelligence of computer games is constantly in need of improvement to meet the ever-increasing demands of game players. This paper discusses how intelligent agents and fuzzy logic can help increase the quality and amount of a computer games most important element: interaction. The applications of fuzzy logic in behavior design are illustrated in detail through implementation of an arcade-style game.


intelligent robots and systems | 2005

Enhanced learning classifier system for robot navigation

Petr Musilek; Sa Li; Loren Wyard-Scott

This paper describes an enhanced learning classifier system used to evolve obstacle-avoidance rules used in mobile robot navigation. The robot learns these rules via feedback from the environment, available as sonar readings. Conventional classifiers, when used in this application, show evidence of shortcomings: becoming trapped in local minima, loss of (desirable) rules, and favouring of generalized rules. Enhancements to the classification system are described and tested using a simulated robot and environment. The enhancements prove to be worthwhile in that they overcome the limitations, and can generally handle more complex situations.


Journal of Artificial Intelligence Research | 2009

Identification of pleonastic it using the web

Yifan Li; Petr Musilek; Marek Reformat; Loren Wyard-Scott

In a significant minority of cases, certain pronouns, especially the pronoun it, can be used without referring to any specific entity. This phenomenon of pleonastic pronoun usage poses serious problems for systems aiming at even a shallow understanding of natural language texts. In this paper, a novel approach is proposed to identify such uses of it : the extrapositional cases are identified using a series of queries against the web, and the cleft cases are identified using a simple set of syntactic rules. The system is evaluated with four sets of news articles containing 679 extrapositional cases as well as 78 cleft constructs. The identification results are comparable to those obtained by human efforts.


canadian conference on electrical and computer engineering | 2014

Simulation of adaptive duty cycling in solar powered environmental monitoring systems

Michal Prauzek; Asher G. Watts; Petr Musilek; Loren Wyard-Scott; Jiri Koziorek

This paper discusses a simulator for energy management in wireless sensor platforms. The simulator presently focuses on environmentally powered monitoring systems and sensors described within this document. The Mathworks Simulink environment was used to construct the simulator and allows real meteorological data to be used for long term simulated operation under different energy management strategies. Three of these strategies are tested and presented here; one is dynamically controlled by a fuzzy rule based system which allows it to adapt to the environmental energy profile, while the other two are statically controlled for comparison. The static control strategies seek to minimize energy related failures or to maximize the number of stored measurements disregarding failures. Ultimately, the strategy which allows the simulated sensor platform to adapt its operational level to the energy available in the environment is superior. It produces a data set with the highest number of data points and a very low number of consecutive device failures. It performs better in both areas than either of the other static energy management strategies.


electrical power and energy conference | 2013

Managing the energy-for-data exchange in remote monitoring systems

Asher G. Watts; Petr Musilek; Loren Wyard-Scott

Remote monitoring in the arctic is necessary to understand the effects of climate change on the cryosphere. The harsh climate makes this difficult by limiting access, interfering with equipment, and providing minimal environmental energy. Energy harvesting allows some independence of remote monitors but requires an energy management strategy to be effective. This strategy must regulate the remote monitors exchange of energy for data and be able to balance data requirements with the environments limited energy profile. A simulation is used to compare two strategies: the first attempts to maximize data quality at the expense of energy security, while the second limits its energy usage to selectively improve certain data properties at the expense of others. The second strategy is able to collect more data using less energy because of its flexibility. In the future, this simulation will be experimentally validated and used to explore control strategies for various remote monitoring applications.


joint ifsa world congress and nafips annual meeting | 2013

Optimizing fuzzy control of energy harvesting remote monitoring systems

Asher G. Watts; Petr Musilek; Loren Wyard-Scott

The operational lifetime of remote monitoring systems can be extended using energy harvesting techniques. Environmental energy is limited and intermittent so energy management is necessary for effective implementation and optimal performance. The objective of remote monitoring is to acquire the highest quality data possible within this energy-constrained environment. A simulator is used to facilitate the exploration and optimization of energy management strategies for environmental monitoring stations in the Canadian Arctic. The original simulator was designed to facilitate testing and demonstrate proof of concept; now that the original simulator has proven effective, the fuzzy control system used for energy management within the simulator can be improved with data quality in mind. By shifting the focus of the controller from the time domain to the state domain, improving the detail of the load model, increasing the flexibility of the control scheme, and implementing a data-centric approach to the optimization, the simulator and its controller can be significantly improved. Future work will restructure the fuzzy controller to address these improvements and work towards implementing the controller in a practical setting.


frontiers in education conference | 2010

Mini workshop — Real World Engineering Projects: Discovery-based curriculum modules for first-year students

Joan Carletta; Pamela T. Bhatti; Tom T. Hartley; Yanfei Liu; Andrea Mitofsky; James Andrew Smith; Loren Wyard-Scott; Alfred C. H. Yu

This mini workshop is organized to provide an interactive forum for the introduction a set of six new curriculum modules developed under IEEEs Real World Engineering Projects (RWEP) program. The modules, which are representative of a larger collection of curriculum modules available to the public via an open-access RWEP web portal, are designed for use in the first-year engineering and computer science classroom, and are hands-on, team-based projects that emphasize the societal impact of the work that engineers do. After a brief introduction to the RWEP program and the six showcased curriculum modules, the authors of the modules will present their ideas and demonstrate the laboratory activities associated with their modules in interactive, informal simultaneous sessions.


frontiers in education conference | 2009

Special session: IEEE Real World Engineering Projects: Discovery-based curriculum modules for first-year students

Joan Carletta; Taryn Bayles; Karl Kalveram; Sami Khorbotly; C. J. B. Macnab; Leyla Nazhandali; Jonathan Rice; James Andrew Smith; Laurence E. Turner; Stephen Williams; Loren Wyard-Scott

This special session is organized to provide an interactive forum for the introduction of a set of new curriculum modules developed under IEEEs Real World Engineering Projects (RWEP) program. The modules, which are representative of a larger collection of curriculum modules available to the public via an open-access RWEP web portal, are designed for use in the first-year engineering and computer science classroom, and are hands-on, team-based projects that emphasize the societal impact of the work that engineers do. After a brief introduction to the RWEP program and the showcased curriculum modules, the authors of the modules will work one-on-one with the audience providing tutorials on the laboratory activities associated with their modules in a highly interactive, simultaneous mode. Audience members can learn in-depth about the modules that interest them most. Each project will have its own demonstration table, with posters of information and hands-on demonstrations and/or videos. This will allow for audience members to interact directly with the authors, and to try out the same sorts of activities that are proposed for the students.


Information Sciences | 2006

Immune programming

Petr Musilek; Adriel Lau; Marek Reformat; Loren Wyard-Scott

Collaboration


Dive into the Loren Wyard-Scott's collaboration.

Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Yifan Li

University of Alberta

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Pamela T. Bhatti

Georgia Institute of Technology

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Researchain Logo
Decentralizing Knowledge