Ahmed Zemirline, Laurent Lecornu, Basel Solaiman · HAL (Le Centre pour la Communication Scientifique Directe) · 2007
In this work, we present a new fusion method that uses fuzzy set theory. This method is applied to the diagnostic system rule bases. It aims at combining all the rule bases into only one rule base and then taking into consideration the characteristics of this base. The fusion method is characterized by a hybrid fusion which combines rule fusion approach with knowledge fusion approach. Knowledge fusion relies on the distortion measure of various bases. This distortion measure is integrated into the rule fusion process in order to generate one rule base for improving the diagnostic system performance. It is defined as the confidence degrees associated to each rule base parameter. The confidence degrees are then integrated into prediction procedure of the new diagnostic system.
Cited by 3Open access
Sujata Rani, Parteek Kumar · 2014
Cited by 4
WU Bao-min · 2005
This paper is intended to present a design and implementation for a rule-based English TTS system.Our system uses phonemes as the basic synthesis unit,establishes a phoneme dictionary,and transforms the input into its corresponding phonemic sequence through morphologic and simple syntactic text analysis.Synthetic speech is based on PSOLA algorithm.Experimental results indicate that our synthesized speech is clear and understandable,providing a prospective of further research.
Cited by 0
Riccardo Poli, Mike Brayshaw, Aaron Sloman · 1995
In this paper we present HTR, a hybrid trainable rule-based system. The key features of the system include: the heterogeneous integration of multiple control regimes, rule induction and refinement mechanisms, easy and concise specification of knowledge, treatment and support for uncertainty. All these features are obtained thanks to the introduction of a new formalism for rule specification that extends the behaviour of a traditional rule based system. The formalism utilises predicates as an intermediate layer between the conditions and the actions of rules. Different kinds of predicates support various sorts of control, distributed conflict resolution, and learning from examples. In particular we describe the characteristics of truth-table-based, collection-based and artificial-neural-net based predicates which are pre-defined in HTR. We also report on a method for automatic rule induction using genetic algorithms. Experimental results exploiting the afore-mentioned feat...
Cited by 0
Selman, Bart, Hirst, Graeme · eScholarship (California Digital Library) · 1985
We describe a connectionist parsing scheme based on context-free grammar rules. In this scheme we use an updating rule similar to the one used in the Boltzmann machine (Fahlman, Hinton and Sejnowski 1983) and apply simulated annealing. We show that at low temperatures the time average of the visited states at thermal equilibrium represents thte correct parse of the input sentence. In contrast with previously proposed connectionist schemes for natural alnguage processing, this scheme handles the traditionally sequential rule-based parsing in a general manner in the network. Another difference is the use of the computational scheme of the Boltzmann machine. This allows us to formulate general rules for the setting of weights and thresholds in our system. The parsing scheme is built from a small set of connectionist primitives that represent the grammar rules. These primitives are linked together using pairs of computing units that behave like discrete switches. These units are used as binders between concepts represented in collection of rules, and are very useful in the construction of connectionist schemes for any form of rule-based processing.
Cited by 11
Riccardo Poli, Mike Brayshaw · 1995
In this paper we introduce a new formalism for rule specification that extends the behaviour of a traditional rule based system and allows the natural development of hybrid trainable systems. The formalism in itself allows a simple and concise specification of rules and lends itself to the introduction of symbolic rule induction mechanisms (example-based knowledge acquisition) as well as artificial neural networks. In the paper we describe such a formalism and four increasingly powerful mechanisms for rule induction. The first one is based on a truth-table representation; the second is based on a form of example based learning; the third on feed-forward artificial neural nets; the fourth on genetic algorithms. Examples of systems based on these hybrid paradigms are presented and their advantages with respect to traditional approaches are discussed. 1 Introduction Since the re-emergence of neural networks in the early 1980's there has been a great debate about neural versus symbolic ap...
Cited by 0
Heider, Michael, Wurth, Jonathan, Sraj, Roman · Zenodo (CERN European Organization for Nuclear Research) · 2022
This repo contains the first public version of the Supervised Rule-based Learning System (SupRB). At the time of publication we referred to the system as SupRB2 which is still reflected in the code files. A comprehensive description of the current system can be found at doi.org/10.1145/3520304.3529014 Newer versions will be found under: https://github.com/heidmic/suprb
Cited by 0Open access
Elbrus Imanov, Hamit Altıparmak, Gunay E. Imanova · Advances in intelligent systems and computing · 2018
Cited by 10
Soumya Priyadarsini Panda, Varun Nagesh Jolly Behera, Alloran Pradhan et al. · International Journal of Innovative Technology and Exploring Engineering · 2019
Designing intelligent expert systems capable of answering different human queries is a challenging and emerging area of research. A huge amount of web data is available online and majority of which are in the form of unstructured documents covering articles, online news, corporate reports, medical records, social media communication data, etc. A user in need of certain information has to assess all the relevant documents to obtain the exact answer of their queries which is a time consuming and tedious work. Also, sometimes it becomes quite difficult to obtain the exact information from a list of documents quickly as and when required unless the whole document is read. This paper presents a rule-based information extraction system for unstructured web data that access the document contents quickly and provides the relevant answers to the user queries in a structured format. A number of tests were conducted to determine the overall performance of the proposed model and the results obtained in all the experiments performed shows the effectiveness of the model in providing required answers to different user queries quickly.
Cited by 6Open access
D. Filipović, Anđela Trajković, Siniša Nikolić · Lecture notes in networks and systems · 2024
Cited by 0
Sim, Jasmine. · DR-NTU (Nanyang Technological University) · 2011
This final year project is the extension of existing project with code name FAME. FAME is a C# language game engine software application to study and simulate steering behaviours of multi autonomous agents. \n \nBefore this FYP, several steering behaviours has been studied and implemented. One of the most interesting behaviour is flocking. It also includes behaviours like arrival, goal seeking, and wandering. Flocking algorithm is developed to attempt simulating the beautiful natural phenomenon of a collective motion of a large number of entities. Examples like flocks of thousand birds, schools of countless fish or great herds of animals (In computer science, ―this gathering of mass individuals are commonly termed flocking). The task is to design and implement various behaviour rules for the autonomous agents. The rules will define how the agent will react/move in different scenarios. For example, take the fishes in an aquarium. If food was dropped into the tank, the fishes will cluster around to eat the food. \n \nInstead of confining FAME to provide some pre-defined set of states and rules, we would like game developers whom are using FAME to be able to design, customize and implement their own set of FSM easily to meet their game/application requirement.
Cited by 0
Bryan S. Todd, R. Stamper, Paul Macpherson · International Journal of Bio-Medical Computing · 1993
Cited by 11
Michael E. Arbilo, J. Felix, Jaime G. Miguel et al. · 1987
Cited by 0
Kunihiko Higa, V. Owei · 2002
Although user-friendly and rule-based expert system shells ease the implementation of expert systems and allow for quick prototyping, their use could easily lead to ill-structured knowledge-bases. They provide no methodical way to design and maintain rule-bases (RBs). Thus, the use of these shells does not reduce the complexity of the RB design/maintenance methodology is given. The focus is on the implementation aspect of the methodology, and the RB size reduction methodology is formalized. The result is an integrated rule reduction system (IRRS) that checks for and detects incompleteness and inconsistencies in RBs and performs RB size reduction.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Cited by 0
Kristijan Cincar, Todor Ivaşcu · 2021 International Conference on e-Health and Bioengineering (EHB) · 2021
In this paper we present a rule-based generic model for health status evaluation. Considering that the physiological measurements are related to the physical activity that the monitored patient performs, the normal threshold ranges can be used for health status evaluation only when the patient is sitting quietly. For the activities with different intensities, different threshold ranges must be considered as normal ranges. Using the MET (Metabolic Equivalent of Tasks) score of each physical activity, proposed system automatically extracts the threshold ranges in the form of rules for each monitored vital sign for each physical activity known by the system. The system performance was evaluated using PAMAP2 dataset and showing the promising results.
Cited by 0
Chakkrit Snae, Michael Brückner · Informing Science and IT Education Conference · 2006
Names are important in many societies, even in technologically oriented ones which use e.g. ID systems to identify individual people. There are many elements of personal names which vary in different cultures. Names such as surnames are the most important as they are used in many processes, such as identifying of people and genealogical research. On the other hand variation of names can be a major problem for the identification and search for people, e.g. web search or security reasons. We show name variations for different cultures to guide the implementation of a rule based naming system, currently worked out for Thai names. We characterize the LIG (Levenshtein, Index of Similarity Group (called ISG), and Guth) algorithms which help to find reasonable variants of names and use an ontology of names to capture the meaning of the variants which are based on Thai naming methodologies and rules. A further benefit of this process is an optimized name searching.
Cited by 7
Borgues Da Silva, L. E., Lambert-Torres, G., April, Georges-Émile et al. · PolyPublie (École Polytechnique de Montréal) · 1994
Cited by 0
P. A. Bonatti, J. L. De Coi, D. Olmedilla et al. · 2015
Abstract—Open distributed environments such as the World Wide Web facilitate information sharing but provide limited support to the protection of sensitive information and resources. Trust negotiation (TN) frameworks have been proposed as a better solution for open environments, in which parties may get in touch and interact without being previously known to each other. In this paper we illustrate PROTUNE, a rule-based TN system. By describing PROTUNE, we will illustrate the advantages that arise from an advanced rule-based approach in terms of deployment efforts, user friendliness, communication efficiency, and interoperability. The generality and technological feasibility of PROTUNE’s approach are assessed through an extensive analysis and experimental evaluations.
Cited by 0
Michael G. Walker, Robert L. Blum, Lawrence M. Fagan · M.D. computing : benchmark papers · 1988
Cited by 4
Spark Tsai · Zenodo (CERN European Organization for Nuclear Research) · 2026
The rapid adoption of AI coding assistants has introduced unprecedented challenges in controlling generated behavior. Current approaches—including prompt engineering, custom instructions, and repository-level rules files—rely on natural language that lacks semantic precision and enforcement capability. These methods conflate intent optimization with behavior enforcement, leading to semantic drift, context overload, and rule conflicts without systematic governance mechanisms. This paper introduces Behavior Rule Architecture (BRA), a structured framework for defining and managing AI execution behavior through normative rules. BRA establishes a clear separation between Normative Natural Language (NNL) for intent expression and Rule Normative Language (RNL) for behavior enforcement using MUST/MUST NOT semantics. The architecture comprises three layers: (1) Rule Language Layer for semantic transformation from intent to enforceable rules, (2) Rule Architecture Layer for atomic rule definition with Policy (MUST) and Constraint (MUST NOT) classifications based on observability differences, and (3) Governance Asset Layer for organizing reusable rule libraries through Decision Behavior Normative Categories and composable Application Rulesets. BRA addresses three fundamental challenges in AI behavior governance: formalization of behavioral constraints, auditability through structured metadata, and reusability via shared rule libraries. The framework enables the transition from ad-hoc prompt engineering to systematic behavior rule management, establishing the engineering foundation for controllable, auditable, and governable AI systems.
Cited by 0Open access