Expert System Method Research Articles

Perancangan Program Sistem Pakar Berbasiskan Web untuk Rehabilitasi Medik Penderita Skoliosis

The application program created in this research is a web-based expert system program for medical rehabilitation of patients with scoliosis. The program aims to make consultation between users and the experts. With the expert system method based on components of medical science this application can help achieve thegoal, that is to make easier for people to recognize and prevent the occurrence of scoliosis, as well as to make easier for doctors making conclusions. Bu using this expert system, students can make decisions quickly when there are problems with Scoliosis disease.

Automation of operative control of the state of chart of contact network of hauling elektrosnabzheniya of railway on basis of methods of consulting models

It is considered the methods of expert systems for automation of the operative control of a condition of the scheme of a contact network of traction electrosupply of the railway. It is designated the directions of researches on formation of structure of the knowledge base.

Modeling and Planning on Urban Logistics Park Location Selection Based on the Artificial Neural Network

Nowadays China has been soaked in the craze of planning and construct u rban l ogistics p ark, and almost all developed countries all regard the urban logistics park’s construction as a major motivation to the national economic. It is vital that the scientific planning of urban logistics park will ensure China’s rapid development. However, too many inappropriate or unscientific planning and construction under the guidance of Government have brought giant economic loss to China. How to plan and design the urban logistics park scientifically, It is a hot topic of research being widely discussed not only by Government s but also enterprisers and scholars home and abroad. This paper begins with exploratory research for modeling and planning on the urban logistics park location selection based on the BP Artificial Neural Network (BP ANN). This paper divides into 3 sections: the first to mainly introduce the history of urban logistics park development and the significance of modelling and planning urban logistics park ,the second to analyze basic principle of the BP ANN, the third to simulate and plan the location selection of urban logistics park based on the BP ANN model. The urban logistics park’s location selection planning is a complicated and dynamical system engineering with a lot of black box problems, which can’t be resloved by System Dynamics, Expert System and traditional mathematical methods (e.g. Operations Research, Statistics), and BP ANN model has seldom been applied to plan urban logistics park in China. So, the research in this paper is an innovation.

Landslide Risk Assessment Expert System Along the Oil and Gas Pipeline Routes

The West-East gas pipeline project in Western China was as an example in the research work. Expert system platform was used as a basic tool. The typical model database systems of West-East gas pipeline project was built. On the base of collection, collation, comprehensive analysis of existing data, through a case study of a large number of landslides, the induced landslides and stability control factor were becoming clear. A landslide risk assessment criteria and evaluation index system was established. On this basis, through application of expert system method, a Expert system platform based landslide risk evaluation expert system about long-distance pipeline routes was developed.It also give a application example of this expert system.

Computational toxicology: a tool for all industries

AbstractStatistical, expert system, and machine learning methods among others have been used to develop in silico tools for the prediction of toxicological hazard from chemical structure. The models are being applied to the mammalian and environmental toxicological assessment of chemicals across a range of industries including cosmetics, foods, industrial chemicals, and pharmaceuticals. Their use within a regulatory environment has also been encouraged by recent legislation. Generally, the models address the potential toxicity of low to medium molecular weight organic chemicals but models for other chemical types such as proteins and nanoparticles have also received some attention. © 2011 John Wiley & Sons, Ltd.This article is categorized under: Computer and Information Science > Chemoinformatics

Research for CNC Machine Tool Servo System Fault Diagnosis Expert System

A new method of CNC machine tool servo system fault diagnosis expert system is proposed.We analyse and design the protype structure of CNC machine tool servo system fault diagnosis expert system base on the methods and theories of expert system. Feasible for the establishment of the expert system are described from knowledge base to reasoning model,and we also provide an important basis for the establishment and development of the expert system.

Research on Intelligence Analysis System for Karst Water Inrush Geological Risk Assessment during Tunnel Construction

With Yichang-Wanzhou Railway project being taken into account, this article systematically analyzes the control factors of geological hazard in tunnel construction including stratum, lithology, fold, rupture and groundwater seepage,etc, establishes hazard assessment index system, and induces the underlying principle and methods of index assignment. On the basis of the theory and technology of expert system, this article develops an intelligence analysis system for karst water inrush geological hazard risk assessment in tunnel construction, explores the construction method of karst water inrush geological hazard expert system and the implementation of software platform, and takes Qiyueshan Tunnel as an example to make the research of engineering application.

Automating land cover mapping of Scotland using expert system and knowledge integration methods

Effective land cover mapping often requires the use of multiple data sources and data interpretation methods, particularly when no one data source or interpretation method provides sufficiently good results. Method-oriented approaches are often only effective for specific land cover class/data source combinations, and cannot be applied when different classification systems or data sources are required or available. Here we present a method, based on Endorsement Theory, of pooling evidence from multiple expert systems and spatial datasets to produce land cover maps. Individual ‘experts’ are trained to produce evidence for or against a class, with this evidence being categorised according to strength. An evidence integration rule set is applied to evidence lists to produce conclusions of different strength regarding individual classes, and the most likely class identified. The only expert system design implemented currently within the methodology is a neural network model, although the system has been designed to accept information from decision trees, fuzzy k-means and Bayesian statistics as well. We have used the technique to produce land cover maps of Scotland using three classification systems of varying complexity. Mapping accuracy varied between 52.6% for a map with 96 classes to 88.8% for a map with eight classes. The accuracy of the maps generated is higher than when individual datasets are used, showing that the evidence integration method applied is suitable for improving land cover mapping accuracy. We showed that imagery was not necessarily the most important data source for mapping where a large number of classes are used, and also showed that even data sources that produce low accuracy scores when used for mapping by themselves do improve the accuracy of maps produced using this integrative approach. Future work in developing the method is identified, including the inclusion of additional expert systems and improvement of the evidence integration, and evaluation carried out of the overall effectiveness of the approach.

Safety Assessment of Transmission Grid Based on Fuzzy Comprehensive Evaluation and BP Neural Network

In the practice of safety assessment on transmission grid, there is the variation degree of many indexes which can not be accurately described, and fuzzy comprehensive evaluation method can reflect the safety degree of every element. In addition, the combination use of BP neural network and expert system method can determine impact extent of assessment factors on safety of transmission grid and the weight of each factor relative to safety of transmission grid. Therefore, the paper proposes the safety assessment of transmission grid based on BP neural network and fuzzy comprehensive evaluation. Finally, an example is used to prove the method is high precision and practical.

Continuous and Reinforcement Learning Methods for First-Person Shooter Games

Machine learning is now widely studied as the basis for artificial intelligence systems within computer games. Most existing work focuses on methods for learning static expert systems, typically emphasizing candidate selection. This paper extends this work by exploring the use of continuous and reinforcement learning techniques to develop fully-adaptive game AI for first-person shooter bots. We begin by outlining a framework for learning static control models for tanks within the game BZFlag, then extend that framework using continuous learning techniques that allow computer controlled tanks to adapt to the game style of other players, extending overall playability by thwarting attempts to infer the underlying AI. We further show how reinforcement learning can be used to create bots that learn how to play based solely through trial and error, providing game engineers with a practical means to produce large numbers of bots, each with individual intelligences and unique behaviours; all from a single initial AI model.

Automatic EEG Spike Detection

Since the 1970s advances in science and technology during each succeeding decade have renewed the expectation of efficient, reliable automatic epileptiform spike detection (AESD). But even when reinforced with better, faster tools, clinically reliable unsupervised spike detection remains beyond our reach. Expert-selected spike parameters were the first and still most widely used for AESD. Thresholds for amplitude, duration, sharpness, rise-time, fall-time, after-coming slow waves, background frequency, and more have been used. It is still unclear which of these wave parameters are essential, beyond peak-peak amplitude and duration. Wavelet parameters are very appropriate to AESD but need to be combined with other parameters to achieve desired levels of spike detection efficiency. Artificial Neural Network (ANN) and expert-system methods may have reached peak efficiency. Support Vector Machine (SVM) technology focuses on outliers rather than centroids of spike and nonspike data clusters and should improve AESD efficiency. An exemplary spike/nonspike database is suggested as a tool for assessing parameters and methods for AESD and is available in CSV or Matlab formats from the author at brainvue@gmail.com. Exploratory Data Analysis (EDA) is presented as a graphic method for finding better spike parameters and for the step-wise evaluation of the spike detection process.

A parallelized DPPQN based Expert System method and implementation

In this paper, we propose a parallelized Dual Projected Pseudo Quasi-Newton (parallelized DPPQN) based Expert System method to solve a kind of distributed constrained optimization problem. The proposed parallelized DPPQN based Expert System method differs from the conventional Lagrange method by treating the inequality constraints as the domain of the original variable in the dual function and uses projection theory to process the inequality constraints. The proposed algorithm was implemented in a n + 1 processors network. We also demonstrated the efficiency in solving a typical constrained weighted least squares problem in power system. The parallelized DPPQN based Expert System method associated with a projected Jacobi method can be applied to general large scale nonlinear network optimization problems in large distributed interconnected systems.

Нові підходи до формування соціально-психологічної моделі фасилітативної компетентності майбутніх фахівців гуманітарної сфери

The authors consider a model of the mastering of psychological-pedagogical technologies of formation of a group experience which was developed with the help of the method of expert systems during the observation of the work of experts on the formation of facilitative competence in the course of professional training of students-humanists.

An Entire Strategy for Control of a Calender Roller System. Part III: Intelligent Settling Time-optimal Control

In the transient response of the calender roller system, the settling time is expected to be short, the non-overshoot controller design needs to be reached, and good tracking property achieved. In Part I [1], the regular proportional-integral-derivative (PID) controller was designed to expedite the response of the calender roller system without steady-state error. However, the overshoot still existed. In Part II [2], the shaping input scheme together with the designed regular PID controller were employed to regulate the calender roller system input, so as to generate system non-overshoot and shorten the settling time. In this paper, the expert system (ES) method combined with the designed regular PID controller, as designed in Part I [1], were used to design the calender roller system. It could be shown that it not only effectively eliminated the steady state error, but also shortened the settling time. The effectiveness of achieving settling time-optimal of the calender system from the expert system could be shown from the computer simulation.

Algorithms and an extended STEP-NC-compliant data model for wire electro discharge machining based on 3D representations

The current paper describes the implementation of the wire electro discharge machining (EDM) algorithms for the STEP-NC project and some possible extensions. Wire EDM uses many working parameters (parameters for spark generation, speed of penetration, etc.) the setting of which needs expert system methods. These expert systems are a coded form of the company knowledge and are based on their experience. The higher information level provided by STEP-NC allows the development of new algorithms to drive the wire. The current way of programming the wire motion is to consider it as a milling tool for 2.5 axis machining operations: the wire trajectory is computed using 2D planar curve offsetting and collision detection algorithms. The use of explicit ruled surfaces allows real 3D offsetting and collision detection. The paper starts by describing the data model and architecture of the demonstration system which was developed during the project. This can be thought of as a simplified process planning phase. The second part of the paper describes algorithms that have been implemented in the STEP-NC environment for prototype software running on the wire EDM NC controller. The final part describes some open questions that remain at the end of the project.

Site selection to test an integrated approach to agricultural research for development: combining expert knowledge and participatory Geographic Information System methods

The sub-Saharan Africa challenge programme is designed to address the problems of failures of agricultural markets, inappropriate policies and natural resource degradation, that contribute to the continuing deterioration of livelihoods and food security in the region. It is seeking to do this by redefining the roles of scientists and farmers through collaborative learning processes, addressing questions about the level, timing, type and formof participation, as well as themost effective approaches andmethods to foster them. The research domains of the programme deal with sustainable intensification of smallholder agriculture, the sustainable management of natural resources, the development of efficient markets, and the promotion of enabling policies. One question that was addressed in designing the initiative was deciding where to work so as to maximize the chances of successful testing of this new approach, so that it would lead to significant reductions of rural poverty. A participatory process was put in place to design a framework to accomplish this site selection, and then to apply it in west, east and southern Africa. A mixture of spatial data analysis and expert knowledge on spatial and non-spatial factors was used, and one primary site in each region was identified to form the basis for the next phase of the challenge programme. Several lessons were learnt from the process, including the importance of adapting themethods to actual conditions, the increased utility of targetting when the quantitative and the qualitative are freely combined, and the continued need for baseline spatial and non-spatial data to improve the targeting of research in the future that is designed to alleviate poverty in sub-Saharan Africa.

Expert-system method for automatic reconfiguration for restoration of shipboard power systems

The electric-power systems in US Navy ships supply energy to sophisticated systems for weapons, communications, navigation and operation. Faults in a shipboard power system (SPS) may occur owing to material casualties of electrical components or widespread faults owing to battle damage. These faults may interrupt the supply of electrical energy to loads that are not faulty or damaged. To enhance survivability of naval ships and meet reduced manning requirements, automatic reconfiguration for service restoration may be performed to restore the de-energised loads. The paper presents an automatic rule-based expert-system method for reconfiguration of electric-power systems on naval ships which determines the control operations necessary to restore power supply to de-energised loads after battle damage or cascading faults. A case study is presented to illustrate the effectiveness of the proposed method.

A review of explanation methods for heuristic expert systems

Explanation of reasoning is one of the most important abilities an expert system should provide in order to be widely accepted. In fact, since MYCIN, many expert systems have tried to include some explanation capability. This paper reviews the methods developed to date for explanation in heuristic expert systems.

Optimal stiffness design of composite laminates for a train carbody by an expert system and enumeration method

This paper expounds the development of an expert system for the optimal stiffness design of composite laminates subjected to the various strain and rules constraints. The optimal stacking sequence and total ply numbers are obtained by means of an enumeration method, an expert system shell and the classical laminate theory. The optimal stacking sequence combination for the application of interest is drawn from the discrete ply angles and design rules stored in the knowledge base of the expert system. Results of this study showed good agreements with previous studies. The total number of plies in the optimized laminate could be reduced when compared with non-optimized laminates possibly rendering an economical advantage.

OPTIMAL LOAD SHEDDING FOR MINIMUM UNDER FREQUENCY USING EXPERT SYSTEMS

The under-frequency problem due to disturbances in large interconnected power systems, may lead - if not corrected -to an extensive serious damage. Disturbances in large power systems sometimes cause this interconnected systems to become separated into isolated subsystems, and this may lead to excess load, however, overloads the generating units causing the frequency to drop to levels that may cause permanent damage to steam turbines. Load shedding are often applied throughout the system to avoid the turbine damage by restoring the frequency. It helps in restoring frequency in appropriate amount taking into consideration that there is no need in shedding excessive amounts of load. So minimum load shedding for under-frequency is needed which is the main aim of this paper with the help of an expert system.This paper treats the under-frequency problem by using an adaptive traditional method for setting of the under-frequency relays. And an expert system is then suggested and developed as a perfect and fast method to accelerate the optimal shedding process for minimum frequency limit. These methods are implemented and applied on a simple power system. The obtained results are presented and discussed with a comparison between the traditional and suggested expert system methods.