Guidedby the personalized learning theory, artificial intelligence and data mining technology, this essay has put forward an E-learning system that supports personalized study. Firstly, Use the decision tree algorithm...
详细信息
ISBN:
(纸本)9781538635735
Guidedby the personalized learning theory, artificial intelligence and data mining technology, this essay has put forward an E-learning system that supports personalized study. Firstly, Use the decision tree algorithm to study the classification of learners, and then send the classified learner model to the reasoning network. Lastly, in order to meet the decision support demands of personalized learning environment, this paper has carried out deep research into rete algorithm, and describes its use method in personalized learning environment. The system can intelligently provide the corresponding decision support according to the classified learner model.
Environment state estimation and control action determination is the key step in industrial environment control. In some complex environments, decisive factors may be various, and each has multiple thresholds, a large...
详细信息
Environment state estimation and control action determination is the key step in industrial environment control. In some complex environments, decisive factors may be various, and each has multiple thresholds, a large number of matching operations have to be done by the controller, and it is a problem to do all rule judgments quickly and precisely. First, the problem is analyzed and main steps and characteristics of rete network for estimation of multiple factors are given. Second, the improvement of conventional rete algorithm, beforehand matching, is analyzed, and then, according to the properties of industrial environments, branch filtration, is introduced based on beforehand matching as a new improvement of rete algorithm. Finally some tests are carried out, and by comparing with conventional rete algorithm and the algorithm with beforehand matching, it can be seen that the improved rete algorithm with branch filtration is effective in reducing unnecessary matching operations. (C) 2017 The Authors. Published by Elsevier Ltd.
Environment state estimation and control action determination is the key step in industrial environment control. In some complex environments, decisive factors may be various, and each has multiple thresholds, a large...
详细信息
Environment state estimation and control action determination is the key step in industrial environment control. In some complex environments, decisive factors may be various, and each has multiple thresholds, a large number of matching operations have to be done by the controller, and it is a problem to do all rule judgments quickly and precisely. First, the problem is analyzed and main steps and characteristics of rete network for estimation of multiple factors are given. Second, the improvement of conventional rete algorithm, beforehand matching, is analyzed, and then, according to the properties of industrial environments, branch filtration, is introduced based on beforehand matching as a new improvement of rete algorithm. Finally some tests are carried out, and by comparing with conventional rete algorithm and the algorithm with beforehand matching, it can be seen that the improved rete algorithm with branch filtration is effective in reducing unnecessary matching operations.
Usually, most of execution time of match-resolve-act reasoning cycle is spent in the matching phase. This issue has prevented the applicability of rule base systems. In this paper, the parallelism of alpha- and beta-n...
详细信息
ISBN:
(纸本)9781509030712
Usually, most of execution time of match-resolve-act reasoning cycle is spent in the matching phase. This issue has prevented the applicability of rule base systems. In this paper, the parallelism of alpha- and beta-networks constructions in rete algorithm have been realized on Graphics Processing Unit (GPU). It is possible to speed up the reasoning time 20 times faster than the current high performance multi-core processors. Furthermore, the parallel realization of rete algorithm with GPU should be helpful on developing intelligent agents or data mining, using rule base systems.
The rete algorithm is an efficiently organized pattern matching algorithm for implementing production rule systems, used to determine which of the production rules should fire based on its data store. This paper prese...
详细信息
ISBN:
(纸本)9781467385947
The rete algorithm is an efficiently organized pattern matching algorithm for implementing production rule systems, used to determine which of the production rules should fire based on its data store. This paper presents how rete algorithm can be used to improve the efficiency of expert system recommendation. The 'COURSE FINDER' is an expert undergraduate course recommendation system. This system aims to assist undergraduate students who wish to join Amrita School of Arts and Sciences, Mysore. This expert system enables students to select suitable courses based on their skill sets without needing to consult an advisor. This system works on Rule based mechanism and rete algorithm. The result was expected, where most of the undergraduate students who tested the system, were satisfied.
Usually, most of execution time of match-resolve-act reasoning cycle is spent in the matching phase. This issue has prevented the applicability of rule base systems. In this paper, the parallelism of α- and β-networ...
详细信息
ISBN:
(纸本)9781509030729
Usually, most of execution time of match-resolve-act reasoning cycle is spent in the matching phase. This issue has prevented the applicability of rule base systems. In this paper, the parallelism of α- and β-networks constructions in rete algorithm have been realized on Graphics Processing Unit (GPU). It is possible to speed up the reasoning time 20 times faster than the current high performance multi-core processors. Furthermore, the parallel realization of rete algorithm with GPU should be helpful on developing intelligent agents or data mining, using rule base systems.
Additive manufacturing (AM) has the capability of producing parts with more complicated shapes and functions compared with subtractive manufacturing. Design for additive manufacturing (DfAM) aims at producing design s...
详细信息
Additive manufacturing (AM) has the capability of producing parts with more complicated shapes and functions compared with subtractive manufacturing. Design for additive manufacturing (DfAM) aims at producing design solutions that can be additively manufactured. During DfAM, analysing the printability and integratbility of a target assembly are important tasks. However, the tasks require systematic analysis of the structural/functional/material characteristics, working conditions, and interaction relations among the parts in the target assembly, fully understanding of the capability and limitation of the applied AM equipment, and comprehensive design decision-making considering the characteristics of AM processing, etc. This makes it challenging to conduct printability and integratbility analysis tasks. In this regard, an expert system is established which is realised with Function-Behaviour-Structure oriented assembly structure characteristic analysing, ontology instance-based assembly structure characteristic modelling, and modified rete algorithm-based design decision-making. The system is capable of providing decision guidance on which parts in a target assembly can be printed and which among these printable parts can be printed integratedly. In this way, it can support DfAM implementation in a computer-aided manner. A WebApp that encapsulates the system is developed, and a robot arm DfAM redesign project is used as a case study.
In this paper, we propose a control method of ubiquitous computers using the rete algorithm in grid topology network. The proposed method distributes and reduces the loads for processing rules and collecting data base...
详细信息
ISBN:
(纸本)9781479951468
In this paper, we propose a control method of ubiquitous computers using the rete algorithm in grid topology network. The proposed method distributes and reduces the loads for processing rules and collecting data based on the rete algorithm. We evaluated the proposed method and confirmed that the proposed method reduces the network traffic as loads.
The application of semantic web technologies such as semantic inference to the field of the internet of things (IoT) can realize data semantic information enhancement and semantic knowledge discovery, which plays a ke...
详细信息
The application of semantic web technologies such as semantic inference to the field of the internet of things (IoT) can realize data semantic information enhancement and semantic knowledge discovery, which plays a key role in enhancing data value and application intelligence. However, mainstream semantic inference engines cannot be applied to IoT computing devices with limited storage resources and weak computing power and cannot reason about uncertain knowledge. To solve this problem, the authors propose a lightweight semantic inference engine, Tiny-UKSIE, based on the rete algorithm. The genetic algorithm (GA) is adopted to optimize the Alpha network sequence, and the inference time can be reduced by 8.73% before and after optimization. Moreover, a four-tuple knowledge representation method with probability factors is proposed, and probabilistic inference rules are constructed to enable the inference engine to infer uncertain knowledge. Compared with mainstream inference engines, storage resource usage is reduced by up to 97.37%, and inference time is reduced by up to 24.55%.
At present, most small and medium-sized enterprises still adopt the "hard coding" method to develop system, in this way, it lack of flexibility and reusability, and disable to respond users' need with co...
详细信息
At present, most small and medium-sized enterprises still adopt the "hard coding" method to develop system, in this way, it lack of flexibility and reusability, and disable to respond users' need with continuous updating quickly. To address this problem, we design a rule engine-based system generator that uses the improved rete algorithm to match data objects with user-defined rules (production) and then implement specific functions through the system generator. Compared with the traditional development mode, this method is more concise and fast, has better reusability, and can effectively solve some problems of the traditional development methods. The user only need to configure the fact data according to the existing rules, and the system autonomously processes according to the configuration instance to generate various functions. The paper mainly introduces the implementation of the rule engine and the system generator. (C) 2020 The Authors. Published by Elsevier B.V.
暂无评论