Production Rule

Abstract: This chapter investigates the issue of the role of the computer,in musical analysis. Starting with a survey of the main approaches in computer analysis, we focus on the particular problem of Jazz chord sequences harmonic analysis. We propose a theory of chord sequence analysis, based on an explicit conceptual hierarchy of analysis objects. We discuss the implementation,of the theory

... This paper presents DUMBO (Qescobrindo sol&o'es Manipulando uma Base de Qcorrincias) [9], a system that incorporates Case-Based Reasoning (CBR) [5] paradigm in a traditional existing TTS architecture (CINEMA TTS [ 12]), aiming to use the knowledge stored in the TTS ...

This paper presents a novel approach to the task of automatic music genre classification which is based on multiple feature vectors and ensemble of classifiers. Multiple feature vectors are extracted from a single music piece. First, three 30-second music segments, one from the beginning, one from the middle and one from end part of a music piece are selected and feature vectors are extracted from each segment. Individual classifiers are trained to account for each feature vector extracted from each music segment. At the classification, the outputs provided by each individual classifier are combined through simple combination rules such as majority vote, max, sum and product rules, with the aim of improving music genre classification accuracy. Experiments carried out on a large dataset containing more than 3,000 music samples from ten different Latin music genres have shown that for the task of automatic music genre classification, the features extracted from the middle part of the music provide better results than using the segments from the beginning or end part of the music. Furthermore, the proposed ensemble approach, which combines the multiple feature vectors, provides better accuracy than using single classifiers and any individual music segment.

Liquid retaining structures, which are mainly used to retain domestic water, sewage, or industrial waste, are usually constructed with reinforced concrete in Hong Kong. During the design, novice engineers often encounter problems including decision-making based on rules of thumb, judgment, previous experience, heuristics, and code of practice. A computer-aided tool that incorporates engineering judgment along with algorithmic tools is highly desirable. This paper presents an intelligent tutoring system, with hybrid knowledge representation techniques including production rule system and object-oriented approach, which provides expert advice on design of liquid retaining structures. Intelligent tutoring system is a type of knowledge-based expert system with the particular purpose of teaching. It can serve the purpose for one-to-one tutoring, which is generally acknowledged to be the most effective teaching method, yet requiring high ratio of resources. This system is based on British Standards Code of Practice BS8007: 1987: Design of concrete structures for retaining aqueous liquids. Training exercises, learner model as well as tailored explanations on real design practice are furnished to help inexperienced designers or civil engineering students to learn how to design liquid retaining structures. Nowadays, with the popularity of personal computer, civil engineering students as well as novice engineers can glean hand-on knowledge on design of liquid retaining structures more effectively through this system. An evaluation of the developed system and investigation of the effectiveness to learn the domain design knowledge are undertaken.

Machine learning is an emerging field of computer science concerned with the learning of knowledge from exploration of already stored data. However, effective utilization of extracted knowledge is an important issue. Extracted knowledge may be best utilized via feeding to knowledge based system. To this end, the work reported in this paper is based on a novel idea to enhance the productivity of the previously developed systems. This paper presents the proposed architecture of a Learning Apprentice System in Medical Billing system being developed for medical claim processing. A new dimension is added whereby, the process of extracting and utilization of knowledge are implemented in relational database environment for improved performance. It opens enormous application areas as most business data is in relational format managed by some relational database management server. The major components of the proposed system include knowledge base, rule engine, knowledge editor, and data mini...

Abstract - It is showed the results achieved using neural networks to represent anesthesiological knowledge specially to the treatnrcnt of paticnts considered critical in anestlicsiological point of vicv. l'liis was accomplished in a hybrid expert system appficd to anestliesiology, called ...

The ever increasing demand of security has resulted in wide use of Biometric systems. Despite overcoming the traditional verification problems, the unimodal systems suffer from various challenges like intra class variation, noise in the sensor data etc, affecting the system performance. These problems are effectively handled by multimodal systems. In this paper, we present multimodal approach for palm- and fingerprints by feature level and score level fusions (sum and product rules). The proposed multi-modal systems are tested on a developed database consisting of 440 palm- and fingerprints each of 55 individuals. In feature level fusion, directional energy-based feature vectors of palm- and fingerprint identifiers are combined to form joint feature vector that is subsequently used to identify the individual using a distance classifier. In score level fusion, the matching scores of individual classifiers are fused by sum and product rules. Receiver operating characteristics curves are formed for unimodal and multimodal systems. Equal Error Rate (EER) of 0.538% for feature level fusion shows best performance compared to score level fusion of 0.6141 and 0.5482% of sum and product rules, respectively. Multimodal systems, however, significantly outperform unimodal palm- and fingerprints identifiers with EER of 2.822 and 2.553%, respectively.

Cultural landscapes in Europe provide a wide range of food products and fulfil social and environmental functions. In order to maintain agricultural practices that contribute to maintaining the biological and cultural value of semi-natural landscapes, agri-environmental schemes are being implemented in many western European countries. In the mountains of southern Europe a major issue is the encroachment of shrubs and trees through natural forest succession following agro-pastoral extensification.In this paper we analyse trends in land use strategies of sheep breeders in response to milk pricing and in relation to various within-farm mechanisms. We show that changes in production rules within the Roquefort cheese protected geographical indication have caused farmers to develop an alternative land use strategy. In this alternative model, farmers now consider rangelands as a valuable resource. By increasing the use of rangelands for sheep grazing and alimentation, this new strategy provides a more effective control of shrub and tree encroachment.We suggest that this involuntary consequence of production and market decisions has been at least as important as agri-environmental schemes in leading ewes’ milk producers to make changes in their land use strategy.

Producing off-line captions for the deaf and hearing impaired people is a labor-intensive task that can require up to 18 hours of production per hour of film. Captions are placed manually close to the region of interest but it must avoid masking human faces, texts or any moving objects that might be relevant to the story flow. Our goal is to use image processing techniques to reduce the off-line caption production process by automatically placing the captions on the proper consecutive frames. We implemented a computer-assisted captioning software tool which integrates detection of faces, texts and visual motion regions. The near frontal faces are detected using a cascade of weak classifier and tracked through a particle filter. Then, frames are scanned to perform text spotting and build a region map suitable for text recognition. Finally, motion mapping is based on the Lukas-Kanade optical flow algorithm and provides MPEG-7 motion descriptors. The combined detected items are then fed to a rule-based algorithm to determine the best captions localization for the related sequences of frames. This paper focuses on the defined rules to assist the human captioners and the results of a user evaluation for this approach.

PRODUCT DESIGN FOR MA"ACTURING : TEE USE OF KNOWLEDGE BASED SYS"EKj IN CONCURRENT ENGINEERING B. Gopalakrishnan, V. Pandiarajan Department of Industrial Engineering, West Virginia University Morgantown, WV 26506 ABSTRACT This paper aims to describe ...

The scope of this paper is the introduction of PTM E (Power Transformer Maintenance Expert), a new expert system application, which can be used as an efficient decision making tool in a sophisticat ed problem as the optimization of maintenance procedures (preventive, predictive and corrective) of Power Transformers. The expert system comprises a knowledge base and a set of production