On Some Inferences Based on Stratified Forward Chaining: An Application to E-Government

In this paper, it is explained that the forward and backward chaining can be naturally integrated on an extended Rete network via the generation of hypotheses from forward chaining inference. We introduce the concept of the hypothesis objects and augment the production rule format by adding the hypothesis condition elements in the LHS part of a rule, which control the forward and backward chaining invocation of rules. A rule can be used in forward directions, backward directions, or mixed directions. To be applied to the backward chaining, a modified version of Rete has been formulated by adding the hypothesis-and-nodes and backward direction edges to the node network. We then develop a backward chaining algorithm which takes advantage of already existing partial match results obtained by the previous forward chaining in the ERMI. The whole mixed inference process has the potential advantages over purely forward and backward chaining strategy.

Whole task training, forward chaining, and backward chaining techniques were compared in teaching two different 120-step sequences of behavior to college students. In Exp. 1 participants learned a sequence that began with easy movements, progressed through more difficult movements, and ended with easy movements. Whole task training resulted in more errors than either forward or backward chaining. Differences were found in the location of errors. Both whole task training and forward chaining resulted in fewer errors at the beginning of the sequence and backward chaining resulted in fewer errors at the end of the sequence. Because the results of Exp. 1 may have been affected by the increased difficulty of the middle of the sequence, Exp. 2 was undertaken using a sequence of behavior where all segments were of equal difficulty. Whole task training and forward chaining resulted in fewer errors than backward chaining. The location of errors was similar to that found in Exp. 1.

The popularity of Olympic-style weightlifting in fitness routines is growing, but participating in these exercises with improper technique places lifters at increased risk for injury. Fitness training professionals have developed multiple teaching strategies, but have not subjected these strategies to systematic evaluation, particularly with novice lifters. Two strategies recommended by professional training organizations are akin to forward and backward chaining, which have been shown effective at teaching other novel, complex behaviors. The present study compared these forward- and backward-chaining-like strategies to teach novice lifters "the clean" and "the snatch," two Olympic weightlifting movements frequently incorporated into high-intensity training programs. Participants performed lifts taught with forward chaining more accurately than lifts taught with backward chaining.

Price, consumption, and production influence global food estimation. Food consumption and food production needs improving affordability, government policy and expert proposition in decision making. Expert have developed a scenario combining direct weather impact on key grain producing regions, indirect impact through crop pathogens, consequences for markets, and stock of global food. Global food production tended to increase, meanwhile consumption under production. In Indonesia, production is under consumption. It is anomaly by global situation and world condition. Government policy is tariff, export, and import. Export food influenced by price food commodity is not stable, meanwhile food import tended to increase because by national food consumption increasing demand. Government policy and expert proposition to modern society, need Expert System is increasing rapidly. In Artificial Intelligence, Expert System is a computer system that emulates the decision making ability of a human expert. There are two reasoning strategies in Expert System: Forward Chaining and Backward Chaining. The aim of this paper is to identify which reasoning strategy system (Forward Chaining). This paper focus on the concept of knowledge representation in Artificial Intelligence and implementing of Forward Chaining on Food Affordability. Food Affordability used to planning of food in the future. Finally, Inference using Forward Chaining on Food Affordability, the result it is good and can be used to planning and policy on national food.

A doctor or medical scholar needs a reference book to learn how to diagnose tropical diseases. This reference book is sometimes a hassle if you have to carry it everywhere. This reference book is also impractical if you have to search it first to find the symptoms and diseases you want to study. So that we need a system to make it easier for doctors and medical scholars to study the science of diagnosis and look for symptoms and diseases. Expert systems are knowledge-based programs that provide expert quality solutions to problems in a specific domain. This expert system is used in the fields of medicine, agriculture, business, and others. Expert systems in the field of medicine make it easy to identify diseases suffered by patients through the symptoms present in the patient. This expert system helps doctors make diagnoses to convince doctors about the results of the diagnosis. The expert system in this study uses a combined method. The combined method is forward chaining and backward chaining. The forward chaining method is used to determine specific symptoms that appear, while the backward chaining method is used to trace general symptoms that arise from specific symptoms that have been previously selected. The result of combining these methods provides a diagnostic percentage of 100%. Meanwhile, the user's assessment of the system gives a good response.

There are two trends in the software initiatives of the U. S. Department of Defense which will have direct impact on future software development and which suggest a focus for current basic research in software. These trends are 1) the move toward smart weapons, suggesting the use of Expert Systems to control these weapons, and 2) the directive that all software for embedded computer systems be written in Ada. The research focus suggested by these developments is an analysis of the Ada programming language and its associated programming support environment (APSE) to determine how to design and construct an Expert System for natural implementation in Ada.It is well known that Ada can be used as a language for Expert Systems. There now exist several Expert System Shells written in Ada and more are being developed every day. The issue still open to research is how to do this optimally, making the best use of the expressive power of the language. An absurd example will make this clearer. It is also known that it is possible to write an Expert System in COBOL. Doing such would be a very tedious and error prone task, because the expressive power of the COBOL language is focused on commercial applications.Another possibility for writing an Expert System in Ada would be to take an existing Expert System in LISP and translate the code, line for line into Ada. Admittedly this is a plausible task; this author has done some preliminary investigation in this area. However, it is arguable that such an approach will not result in efficient Ada code, for constructs which are natural to LISP might not translate into constructs natural to Ada.While it is difficult to give a precise definition of an Expert System, it is easy to list characteristics which are usually associated with such a system. This paper presents the results of some preliminary research on the implementation of these features by means of some of the structures in Ada, such as Generic Program Units, Packages and Data Encapsulation, which are typical of the language's rich expressive power and which must form the basis of any natural implementation in Ada of an Expert System.One of the features expected in an Expert System is forward and backward chaining, probably implemented with a version of the Rete algorithm. For this reason, this research included writing several small symbolic pattern matching procedures and testing their performance.This research also investigated the use of Ada packages with encapsulated data types to implement a blackboard structure. It was found that a global data structure and appropriate operators could be implemented. As a side result of this work, the frame construct with attached operators and inheritance mechanisms was implemented.The research reported here also addressed the issue of Object Oriented Programming which has become quite popular in LISP programming. Here the match to Ada is quite natural for the latter language itself is also designed to support the Object Oriented Approach. Several LISP textbook examples were translated to the corresponding Ada structure and manipulated with some test programs.Several directions for future research have been generated as a result of this preliminary work. One open question is how to implement concepts originally developed for a language with late binding, such as LISP, in a language with strong typing such as Ada. Another issue concerns the translation of LISP code into Ada code. Early work suggests that it will be more profitable to view the LISP as a high level specification language for an Ada system rather than a program to be translated with literal fidelity. These and several other projects are being pursued and will be reported out in future papers.

Expert-system technology has emerged from beneath the umbrella of Artificial Intelligence and into the mainstream of engineering problem solving. There already are several notable examples of the application of this state-of-the-art technology in the petroleum industry. Clearly, expert systems that run efficiently on standard personal computers are particularly of value. A new expert-system generator that overcomes the speed, memory and mass-storage limitations of XT/AT-class personal computers is presented in this paper. The shell is optimized for the specific characteristics of the target user, knowledge expert and computer. Expert systems developed using this shell currently are being used by our technical personnel for drilling fluid and related applications.

Agent systems are designed to work in complex dynamic environments, which requires an agent to repeatedly deliberate over its choice of actions. A common way to achieve this is to use agent architectures based on the Belief-Desire-Intention (BDI) model, in which an agent continuously deliberates over the best way to achieve its goals in the current environment. In this paper we explore how a BDI approach can be implemented in Lygon, a logic programming language based on linear logic. In particular, we show how backward and forward chaining techniques can be used to provide proactive and reactive agent behaviours. We discuss some extensions to Lygon which allow us to use abduction techniques to generate plans to achieve a given goal, as well as an addition to the syntax of Lygon which greatly simplifies the specification of a sequence of goals to be achieved. We also show how a simple addition to the backward chaining process allows us to specify proactive checking of maintenance goals.

Three studies are presented comparing forward and backward chaining techniques. In the Experiment 1, an 8-step Lego® play construct was taught. In one condition, a construct was taught using forward chaining techniques and in the other condition a construct was taught using backward chaining techniques in an alternating treatments design. In the Experiment 2, a 12-step Lego® construct was taught using the same procedures outlined above. Finally, in Experiment 3, a pre-vocational task, building chess pieces, was taught. Efficiency of both chaining procedures was measured by number of trials to acquisition and number of error rates across conditions and participants. Results show that both chaining procedures were equally effective, all participants acquired the behavior chains with both chaining procedures and there was little difference in acquisition time and error rate between the two procedures.

Germanium stone and bioglass are useful for alleviating some common daily ailments, but they are not well recognized by the general public. Through addressing these limitations, the development of this expert system aims to provide information on the use of products or devices containing germanium stone and bioglass to address a specific health complaint and its symptoms. The expert system uses the backward chaining method to facilitate understanding of how to use therapeutic devices containing germanium stone and bioglass for a defined health complaint within the system. This involves selecting symptoms that match the experienced facts, followed by displaying the method of using the therapeutic device. The results from the expert system are presented in the form of a website for easier use by the general public, accessible from anywhere. Based on blackbox testing, the system functionality reached 100%. Highlights: Therapeutic Benefits: The system simplifies therapy selection using germanium stone and bioglass based on symptoms. Backward Chaining: This AI-based expert system utilizes backward chaining for precise recommendations. Web Accessibility: Designed as a user-friendly website for public access anytime and anywhere. Keywords: Expert System, Backward Chaining, Bioglass, Germanium Stone, Website

An expert system is a system that adopts the expertise of an expert in a particular field into the system. Rabbits are one of the animals that are close to humans and have high body adaptability. However, rabbits are not free from the threat of disease. Treatment requires more costs so we need a way to find out the disease and the solution so that we can take the necessary actions. To overcome this, an expertise media was created that can be accessed by rabbit owners online using the Forward Chaining and Certainty Factor methods. The expert system must be able to work under uncertainty, so the Forward Chaining (FC) and Certainty Factor (CF) methods were added to overcome this problem. Forward Chaining is a decision making method that is commonly used in expert systems and the Certainty factor method is a method to prove the uncertainty of an expert's thinking. The system diagnosis results display possible diseases suffered by rabbits and provide treatment solutions for diseases with the largest CF values. With the calculation results, the level of confidence information based on the table is Definitely Yes. The accuracy of the system output is proven from the results of system validity with experts.

Expert system is made to transfer the expert knowledge into the system, so it hopefully can give solution to problem.“Expert system for diagnosis of infection TBC lung disease” is an alternative for the various expert system that can be used to overcome the problem. The aim of designing expert system is for diagnosis of infection TBC lung disease, should that users can diagnose towards this illnes based on symptoms put into this system. Development of expert system uses knowledge base stored in database using Paradox, rule based with forward chaining method.The result of consultation with the system indicate that this system can determine disease and suggestion based on symptoms inputed by user. Keyword : Expert System, Forward Chaining, Knowledge Base

Hydroponics systems require tremendous attention both in nutrition, plant growth, the risk of pest and disease attacks. Thus, this hydroponic farming system requires high experience and expertise that is the main obstacle for business actors who want to start a vegetable cultivation business with a hydroponic system, especially for business actors who do not have a background in agriculture. The hydroponic cultivation expert system in this study aims to detect plant diseases and pests and provide solutions to these diseases. In addition, this expert system application also aims to monitor plant needs, so this application can help farmers grow up hydroponic vegetable cultivation businesses. The combination of the forward and backward chaining methods is applied to detect plant diseases and pests. Whereas the forward chaining method use to monitor plant needs. The combination of the forward and backward chaining methods in identifying plant diseases and pests can make it easier for users to determine the suffered by plants and provide information about these diseases. The application of the forward chaining method in monitoring plant needs can identify the level of fulfilment of entails of each component of plant needs according to the type of plant and the day after planting. The application of this hydroponic expert system can overcome the limited number of hydroponic experts in helping farmers identify plant diseases and pests and monitor plant needs.

The improving performance of inference engine in expert system has become an important research in recent years; as it is not realistic to search through all production rules during each cycle using an exhaustive search. Expert systems with a large set of rules can be slow, and maybe not suitable for real-time application. In this paper, new algorithm for forward chaining and backward chaining in inference engine is proposed. This algorithm accommodates balanced binary searched tree and binary tree sort that have good performance in large database. Moreover, this new inference engine is more certain as well. Displaying image and other supporting materials as the answer is facilitated.

The purpose of this research is to create and develop learning media in the form of applications used for plant identification in The Division of Pinophyta. The approach used is conventional approach with Expert System Development Life Cycle (ESDLC) method from Durkin, the inference mechanism used is Forward Chaining, while the software, used for Data Base Management System (DBMS) is MySQL, Unified Modeling Language (UML), Personal Home Page (PHP). Based on the results of the application assessment test in general obtained results that this expert system application deserves to be used as a learning media with criteria for Quality of end-user interface design (55.5%), Engagement (52.3%), Interactivity (64.3 %) and Tailorability (52.4%). Conclusion, application made by Expert System Development Life Cycle (ESDLC) method, with Forward Chaining inference mechanism worthy to be used as a learning medium of plant identification in Divisio Pinophyta.
 
 Keywords: Application, Plant Identification, Learning Media, Expert System, Forward Chaining