No description available.

The purpose of this work is to develop a web based decision support system, based onfuzzy logic, to assess the motor state of Parkinson patients on their performance in onscreenmotor tests in a test battery on a hand computer. A set of well defined rules, basedon an expert’s knowledge, were made to diagnose the current state of the patient. At theend of a period, an overall score is calculated which represents the overall state of thepatient during the period. Acceptability of the rules is based on the absolute differencebetween patient’s own assessment of his condition and the diagnosed state. Anyinconsistency can be tracked by highlighted as an alert in the system. Graphicalpresentation of data aims at enhanced analysis of patient’s state and performancemonitoring by the clinic staff. In general, the system is beneficial for the clinic staff,patients, project managers and researchers.

Route specification can be a time consuming process in flight planning, and at the same time, it should be done very diligently for the sake of a safe flight and to reach the target on time. An autonomous decision support system can save time spent on finding the most accurate and shortest route from departure to destination. Different kinds of external sources are used as input for making intelligent decisions by taking advantage of a rule based reasoning approach. In this regard, a rule based decision support concept based on Drools rule engine is proposed in order to ease the workload of pilots during route specification. / Flygruttsplanering är en tidskrävande process vid uppdragsplanering. Den bör göras med stor omsorg för att garantera en säker flygning som når målet på utsatt tid. Ett autonomt beslutstödssystem kan spara tid genom att hitta den säkraste och kortaste rutten mellan avgång och destination. I detta sammanhang används olika externa källor som indata och de ligger till grund för att fatta intelligenta beslut med hjälp av regelbaserat resonerande. Konceptet regelbaserat beslutsstöd är baserat på Drools regelmotor för att minska arbetsbördan för piloter under ruttplanering.

With the recent discoveries of phenomena such as plateau potentials, bistability, and synaptic amplification the focus of motoneuron research has been directed to the dendritic processes giving rise to these latent behaviors. The common consensus is that the mechanism behind bistability (an L-type calcium channel generating a persistent inward current, PIC; Schwindt and Crill 1980, Hounsgaard and Kiehn 1985, 1989) is also responsible for the amplification of synaptic input in motoneurons. However, modeling studies utilizing only calcium-based PICs (Powers 1993, Booth et al. 1997, Elbasinouy et al. 2005) have been unable to reproduce the high degree of synaptic amplification observed in experimental preparations (Prather et al. 2001, Lee et al. 2003, Hultborn et al. 2003). The present work examines a theoretical amplification mechanism (electrotonic compression), based on a sodium PIC of dendritic origin, which acts to supplement the synaptic amplification due to the calcium PIC. The current goal is to test the "goodness-of-fit" of electrotonic compression with established mechanisms and behaviors. The findings of this modeling study support the concept of a dendritic sodium PIC which acts to reduce the attenuation of synaptic currents enroute to the motoneuron soma. Furthermore, it is suggested that the ratiometric expression of ion channels giving rise to this mechanism takes the form of a distribution "rule" applied ubiquitously across the dendritic tree, while the plateau-producing L-type calcium channels undergo a more discretized or regional distribution. This study demonstrates the power inherent to the controlled expansion of morphological complexity in an already complex model. While modeling studies are suitable testbeds for the evaluation of theoretical and/or experimentally intractable facets of physiology, great care and consideration should be given to the specification of models with high dimensionality. With the continual progression of our knowledge-base and computational capabilities, we can expect that more and more empirical observations will find their way into models of increasing complexity wherein the layers of embedded hypotheses are frequently implicit. It is therefore imperative that the neural modeling discipline adopt more rigorous methodologies to both accommodate and rein-in this growing complexity.

The Hopping Rotochute is a promising micro vehicle with the capability of exploring rough and complex terrains with minimum energy consumption. While it is able to fly over obstacles via thrust produced by its coaxial rotor, its physical architecture, inspired from a "Weebles Wooble," provides re-orientation wherever it hits the ground. Therefore, this aerial and ground vehicle represents a potential hybrid vehicle capable of reconnaissance and surveillance missions in complex environments. The most recent version of the Hopping Rotochute is manually controlled to follow a trajectory. The control commands, listed in a file prior to the particular mission, are executed exactly as defined, like a "batch job," regardless of the uncertain external events. This control scheme is likely to cause great deviations from the route. Consequently, the vehicle may finish the mission very far away from the desired end point. However, if a vehicle is capable of receiving the control commands during a mission, "interactive processing" can be realized and efficient path tracking would be achieved. Hence, the development of the Hopping Rotochute that follows a trajectory autonomously reveals the foundation of this thesis. Two control approaches inspired the proposed methodology for developing an autonomous trajectory-following algorithm. The first approach is rule-based control that enables decision making through conditional statements. In this thesis, rule-based control is used to select a target point for a particular hop based on the existence of an obstacle and/or wind in the environment. The second approach is model predictive control employed to predict future outputs from hop performance models. In other words, this technique approaches the problem by providing intelligence pertaining to how a particular hop will end up before being attempted. Hence, the optimum control commands are selected based on the predicted performance of a particular hop. This research demonstrates that the autonomous Hopping Rotochute can be realized by rule-based control embedded with some performance models. In the assumption of known boundaries such as wall and ceiling information, this study has two aims: (1) to avoid obstacles by creating a smaller operational volume inside the real boundaries so that the vehicle is restricted from exiting the operational volume and no violation occurs within the real boundaries; (2) to estimate the wind by previous hops to select the next hopping point with respect to the estimated wind information. Based on the developed methodology, simulations are conducted for four different scenarios in the existence of obstacles and/or wind, and the results of the simulations are analyzed. Finally, based on the statistics of simulation results, the effectiveness of the proposed methodology is discussed.

Title from PDF of title page. / Document formatted into pages; contains 57 pages. / Thesis (M.S.C.S.)--University of South Florida, 2003. / Includes bibliographical references. / Text (Electronic thesis) in PDF format. / ABSTRACT: A clinical trial is defined as a study conducted on a group of patients to determine the effect of a treatment. Assignment of patients to clinical trials is a data and labor intensive task. Usually, medical personnel manually check the eligibility of a patient for a clinical trial based on the patient's medical history and current medical condition. According to studies, most clinical trials are under-enrolled which negatively affects their effectiveness. We have developed web-based agents that can test the eligibility of patients for many clinical trials at once. We have tested various heuristics for optimizing cost and data entry needed in assigning patients to clinical trials. Testing eligibility of a patient for many clinical trials is only feasible if it is cost and data entry efficient. Agents with different heuristics were then tested on data from current breast cancer patients at the Moffitt Cancer Center. / ABSTRACT: Results with different heuristics are compared with each other and with that of the clinicians. It is shown that cost savings are possible in clinical trial assignment. Also, less data entry is needed when probabilistic agents are used to reorder questions. / System requirements: World Wide Web browser and PDF reader. / Mode of access: World Wide Web.

Thesis (M. Sc.(Computer Science))--University of Pretoria, 2003. / Includes bibliographical references.

Thesis (M.S.)--Mississippi State University. Department of Computer Science and Engineering. / Title from title screen. Includes bibliographical references.

Lithuanian language is quite in an early stage of language processing. And therefore has a high demand on automated tools like taggers, parsers, word sense disambiguators etc. During the last 10 years only a few researchers were attempting to create a parser for Lithuanian language. However none of them are used in practices nowadays. The process of designing and implementing rule based parser for Lithuanian language is presented in this paper. Rules and constraints of the formal grammar follow the principles of Dependency Grammar. Necessary language recourses were made up at the Computational Centre of Linguistics. Research area analysis and overview of the most popular methodologies is presented here as well. Syntax parser of the Lithuanian language was evaluated against the Gold Standard and gave 80,2 % of accuracy of in recognizing parts of the sentence.

Expert system techniques are now being incorporated successfully in commercial computer software packages. This thesis introduces the techniques of developing a rule-based expert system in a general-purpose programming language -- C. The topics of this thesis include significance of expert system shells and approaches used, structure of the knowledge base, loading of the knowledge base, manipulation of the probabilities of rule attributes, and implementation of the inference engine. The inference engine uses the information that users supply to find an object that matches. Today C language is one of the most popular programming languages in use and C compilers consistently produce extremely fast and efficient executable programs. Thisthesisdemonstrates that C language is an appropriate computer language for a rule-based expert system. / Department of Computer Science