Knowledge-based Expert System Research Articles

Selection of optimal conversion path for willow biomass assisted by near infrared spectroscopy

Willow (Salix sp.) is one of the most common hardwood species suitable for short-rotation coppice. It can be converted to different products, including chemicals, fuels, fibers or furniture. It may also be used in agriculture and environmental engineering. Molecular composition of biomass and its physical properties highly influence effectiveness of its chemical, thermo-chemical or mechanical-chemical conversion. Therefore, it is challenging to provide biomass feedstock with optimized properties, best suited for further downstream conversion. The goal of this research was to establish a procedure for determination of the willow biomass optimal use cultivated in four different plantations in Poland. A special attention has been paid to the application of the near infrared spectroscopy for evaluation of biomass chemical composition and its physical properties. Near infrared spectroscopy (NIR) could be an alternative to standard analytical methods supporting the research and development of biomass production technologies. Partial least squares regression models for quantitative prediction of wood chemical components (lignin, cellulose, holocellulose, hemicellulose and extractives) and high heating values were developed. The residual prediction deviation (RPD) values confirm the applicability of chemometric models for screening in breeding programmes (for lignin, cellulose and extractives content) and for research in the case of high heating value. The analysis of NIR spectra highlighted several peculiarities in the chemical composition of the investigated willow clones. Finally, a knowledge-based expert system and a prototype automatic NIR system allowing the computation of a “suitability index” based on PLS models and dedicated to selection of optimal biomass conversion path, was developed.

Innovative Maintenance Model: Methodology of Decision Making and Global Economic Cost – Based Choice Using Fuzzy Logic Concepts

Background:In this paper, we propose the Development of a knowledge-based expert system applied to Electricity distribution Network maintenance.Method:The expert system utilizes the Matlab®platform, using its proprietary Fuzzy Logic Toolbox. The inputs to the expert system are the different situations related to cost variables to and the implementation of one of the maintenance optimizing solutions pertaining to the Live Work-Redundancy-Simultaneity-Security model as defined by the maintenance unit during a the global life cycle of the equipment. The output of the system indicates the economic feasibility and benefit of the solution to be adopted of for our Maintenance model. Application of the expert system methodology is shown as a simulation.Conclusion:The expert system may be of valuable assistance to utility engineers or asset managers in making strategic maintenance decisions such as “Economic solution”.

Measurement’s noise, filtered by a type-1 neuro-fuzzy technique in quality assurance

Measurements are the core of quality systems. The calibration of the measurement devices is a form of evaluating it. The variability of these measurement devices is verified to know the variation inherited in the measurement tool. Additionally, the dynamics of the actual production systems cannot be satisfied by the classic approaches of the human visual inspection. This happens because they exceed the human capacities, and this phenomenon causes the loss of reliability at the outputs of the system. This paper presents a hybrid model of adaptive neuro-fuzzy inference system (ANFIS) to evaluate quality features. Also, for this purpose, it offers knowledge-based expert system able to do the quality assurance tasks by learning and adaptation. The obtained results provide an acceptable error rate for this class of systems to run at the speed of the actual manufacturing system.

Проектирование базы знаний экспертной системы управления научными проектами

Проектирование базы знаний экспертной системы управления научными проектами

Stock market one-day ahead movement prediction using disparate data sources

There are several commercial financial expert systems that can be used for trading on the stock exchange. However, their predictions are somewhat limited since they primarily rely on time-series analysis of the market. With the rise of the Internet, new forms of collective intelligence (e.g. Google and Wikipedia) have emerged, representing a new generation of “crowd-sourced” knowledge bases. They collate information on publicly traded companies, while capturing web traffic statistics that reflect the public’s collective interest. Google and Wikipedia have become important “knowledge bases” for investors. In this research, we hypothesize that combining disparate online data sources with traditional time-series and technical indicators for a stock can provide a more effective and intelligent daily trading expert system. Three machine learning models, decision trees, neural networks and support vector machines, serve as the basis for our “inference engine”. To evaluate the performance of our expert system, we present a case study based on the AAPL (Apple NASDAQ) stock. Our expert system had an 85% accuracy in predicting the next-day AAPL stock movement, which outperforms the reported rates in the literature. Our results suggest that: (a) the knowledge base of financial expert systems can benefit from data captured from nontraditional “experts” like Google and Wikipedia; (b) diversifying the knowledge base by combining data from disparate sources can help improve the performance of financial expert systems; and (c) the use of simple machine learning models for inference and rule generation is appropriate with our rich knowledge database. Finally, an intelligent decision making tool is provided to assist investors in making trading decisions on any stock, commodity or index.

ADME/Tox Properties and Biochemical Interactions of Silybin Congeners: In silico Study

Silymarin, the active constituent of Silybum marianum (milk thistle), and its main component, silybin, are products with well-known hepatoprotective, cytoprotective, antioxidant, and chemopreventative properties. Despite substantial in vitro and in vivo investigations of these flavonolignans, their mechanisms of action and potential toxic effects are not fully defined. In this study we explored important ADME/Tox properties and biochemical interactions of selected flavonolignans using in silico methods. A quantitative structure-activity relationship (QSAR) model based on data from a parallel artificial membrane permeability assay (PAMPA) was used to estimate bioavailability after oral administration. Toxic effects and metabolic transformations were predicted using the knowledge-based expert systems Derek Nexus and Meteor Nexus (Lhasa Ltd). Potential estrogenic activity of the studied silybin congeners was outlined. To address further the stereospecificity of this effect the stereoisomeric forms of silybin were docked into the ligand-binding domain of the human estrogen receptor alpha (ERa) (MOE software, CCG). According to our results both stereoisomers can be accommodated into the ERa active site, but different poses and interactions were observed for silybin A and silybin B.

A Multi-Objective Decision Analysis of Plants for Maintenance Expert System Development

Effective decision making with evidence of possibility is important when faced with alternatives that are begging for attention. The alternative which proved to be most possible is given preference over the others. This paper applied the fuzzy mathematics based on Multi-Objective Decision Analysis (MODA) technique to solve the challenge of selecting a plant out of four alternatives to be considered for knowledge-based maintenance expert system development. The goal is to ensure the limited resources available is channeled towards developing the expert system for one production plant. Consequently, objectives were set and given preference ranks. Each plant was also ranked based on its performance under each objective. A fuzzy MODA technique was used to analyse the data derived from ranking of the objectives and plant. The silicate glass plant emerged as the plant that satisfied the set objectives optimally and was selected as the most preferred of the four plants.

Fuzzy Knowledge Based Expert System for Prediction of Color Strength of Cotton Knitted Fabrics

The present study is intended to develop an intelligent model for the prediction of color strength of cotton knitted fabrics using fuzzy knowledge based expert system (FKBES). The factors chosen for developing the prediction model are dye concentration, dyeing time and process temperature. Besides, such factors are nonlinear and have mutual interactions among them; so it is not easy to create an exact correlation between the inputs variables and color strength using mathematical or statistical methods. In contrast, artificial neural network and neural-fuzzy models require massive amounts of experimental data for model parameters optimization which are challenging to collect from the dyeing industries. In this context, fuzzy knowledge based expert system is the most efficient modeling tool which performs exceptionally well in a non-linear complex domain with lowest amount of trial data like human experts. In this study, laboratory scale experiments were conducted for three types of cotton knitted fabrics to verify the developed fuzzy model. It was found that actual and predicted values of color strength of the knitted fabrics were in good agreement with each other with less than 5% absolute error.

A Spatio-Temporal Data-Mining Approach for Identification of Potential Fishing Zones Based on Oceanographic Characteristics in the Eastern Indian Ocean

The traditional approach for determining potential fishing zones (PFZs) relies on oceanographic factors (biological, physical, and chemical) and fishermen’s expertise. This approach has disadvantages particularly when it comes to the analysis of combining these factors to find an exact PFZ spatially and temporally. In this study, we proposed a framework for identifying PFZs based on a data-mining approach in the Eastern Indian Ocean. We utilized a spatio-temporal clustering method to identify clusters of zones with data on the largest number of fish catch, which were then integrated with the sea surface temperature (SST) and the sea surface chlorophyll a (SSC) data derived from Moderate Resolution Imaging Spectroradiometer (MODIS) satellite imagery. The results of this data integration method were used as training data in the classification process, which was then used to determine PFZs. During the classification process, we utilized the $k$ -nearest neighbor (KNN) classification method. The result gave an average accuracy of 87.11%, which showed that the proposed framework can be used effectively to determine PFZs. To validate the framework, we compared its performance against the heuristic rules taken from the knowledge-based expert system model on the SST and chlorophyll a data. The results showed that the proposed data-mining framework outperformed the heuristic rules from the knowledge-based expert system model.

A knowledge-based expert rule system for predicting mutagenicity (Ames test) of aromatic amines and azo compounds.

Cancer is one of the main causes of death in Western countries, and a major issue for human health. Prolonged exposure to a number of chemicals was observed to be one of the primary causes of cancer in occupationally exposed persons. Thus, the development of tools for identifying hazardous chemicals and the increase of mechanistic understanding of their toxicity is a major goal for scientific research. We constructed a new knowledge-based expert system accounting the effect of different substituents for the prediction of mutagenicity (Ames test) of aromatic amines, a class of compounds of major concern because of their widespread application in industry. The herein presented model implements a series of user-defined structural rules extracted from a database of 616 primary aromatic amines, with their Ames test outcomes, aimed at identifying mutagenic and non-mutagenic chemicals. The chemical rationale behind such rules is discussed. Besides assessing the model's ability to correctly classify aromatic amines, its predictivity was further evaluated on a second database of 354 azo dyes, another class of chemicals of major concern, whose toxicity has been predicted on the basis of the toxicity of aromatic amines potentially generated from the metabolic reduction of the azo bond. Good performance in classification on both the amine (MCC, Matthews Correlation Coefficient=0.743) and the azo dye (MCC=0.584) datasets confirmed the predictive power of the model, and its suitability for use on a wide range of chemicals. Finally, the model was compared with a series of well-known mutagenicity predicting software. The good performance of our model compared with other mutagenicity models, especially in predicting azo dyes, confirmed the usefulness of this expert system as a reliable support to in vitro mutagenicity assays for screening and prioritization purposes. The model has been fully implemented as a KNIME workflow and is freely available for downstream users.

Development of an evolutionary fuzzy expert system for estimating future behavior of stock price

The stock market has always been an attractive area for researchers since no method has been found yet to predict the stock price behavior precisely. Due to its high rate of uncertainty and volatility, it carries a higher risk than any other investment area, thus the stock price behavior is difficult to simulation. This paper presents a “data mining-based evolutionary fuzzy expert system” (DEFES) approach to estimate the behavior of stock price. This tool is developed in seven-stage architecture. Data mining is used in three stages to reduce the complexity of the whole data space. The first stage, noise filtering, is used to make our raw data clean and smooth. Variable selection is second stage; we use stepwise regression analysis to choose the key variables been considered in the model. In the third stage, K-means is used to divide the data into sub-populations to decrease the effects of noise and rebate complexity of the patterns. At next stage, extraction of Mamdani type fuzzy rule-based system will be carried out for each cluster by means of genetic algorithm and evolutionary strategy. In the fifth stage, we use binary genetic algorithm to rule filtering to remove the redundant rules in order to solve over learning phenomenon. In the sixth stage, we utilize the genetic tuning process to slightly adjust the shape of the membership functions. Last stage is the testing performance of tool and adjusts parameters. This is the first study on using an approximate fuzzy rule base system and evolutionary strategy with the ability of extracting the whole knowledge base of fuzzy expert system for stock price forecasting problems. The superiority and applicability of DEFES are shown for International Business Machines Corporation and compared the outcome with the results of the other methods. Results with MAPE metric and Wilcoxon signed ranks test indicate that DEFES provides more accuracy and outperforms all previous methods, so it can be considered as a superior tool for stock price forecasting problems.

Pharmacophore modeling and in silico toxicity assessment of potential anticancer agents from African medicinal plants.

Molecular modeling has been employed in the search for lead compounds of chemotherapy to fight cancer. In this study, pharmacophore models have been generated and validated for use in virtual screening protocols for eight known anticancer drug targets, including tyrosine kinase, protein kinase B β, cyclin-dependent kinase, protein farnesyltransferase, human protein kinase, glycogen synthase kinase, and indoleamine 2,3-dioxygenase 1. Pharmacophore models were validated through receiver operating characteristic and Güner–Henry scoring methods, indicating that several of the models generated could be useful for the identification of potential anticancer agents from natural product databases. The validated pharmacophore models were used as three-dimensional search queries for virtual screening of the newly developed AfroCancer database (~400 compounds from African medicinal plants), along with the Naturally Occurring Plant-based Anticancer Compound-Activity-Target dataset (comprising ~1,500 published naturally occurring plant-based compounds from around the world). Additionally, an in silico assessment of toxicity of the two datasets was carried out by the use of 88 toxicity end points predicted by the Lhasa’s expert knowledge-based system (Derek), showing that only an insignificant proportion of the promising anticancer agents would be likely showing high toxicity profiles. A diversity study of the two datasets, carried out using the analysis of principal components from the most important physicochemical properties often used to access drug-likeness of compound datasets, showed that the two datasets do not occupy the same chemical space.

Fuzzy Based Decision Support System for Condition Assessment and Rating of Bridges

In this work, a knowledge based decision support system has been developed to efficiently handle the issues such as distress diagnosis, assessment of damages and condition rating of existing bridges towards developing an exclusive and robust Bridge Management System (BMS) for sustainable bridges. The Knowledge Based Expert System (KBES) diagnoses the distresses and finds the cause of distress in the bridge by processing the data which are heuristic and combined with site inspection results, laboratory test results etc. The coupling of symbolic and numeric type of data has been successfully implemented in the expert system to strengthen its decision making process. Finally, the condition rating of the bridge is carried out using the assessment results obtained from the KBES and the information received from the bridge inspector. A systematic procedure has been developed using fuzzy mathematics for condition rating of bridges by combining the fuzzy weighted average and resolution identity technique. The proposed methodologies and the decision support system will facilitate in developing a robust and exclusive BMS for a network of bridges across the country and allow the bridge engineers and decision makers to carry out maintenance of bridges in a rational and systematic way.

Design and implementation of an expert system for updating thematic maps using satellite imagery (case study: changes of Lake Urmia)

Thematic maps are fundamental for decision-making in natural resources and ecosystem management and planning. Thematic information, land cover in particular, is dynamic and changeable with the passage of time. Hence, providing up-to-date and precise data in a short period of time is considered as a key factor for successful utilization of these maps. Field inspection and visual interpretation of satellite images and topographic maps are necessary for this purpose. These processes are labor intensive, time consuming, and costly. An expert system, as a computer system with the capability of an expert’s performance simulation, could be an assistant for experts involved with the thematic map updating process. In this paper, a knowledge-based expert (KBE) system was designed, implemented, and tested to automate, facilitate, and expedite the conventional thematic map updating procedure. The developed system in this research is based on using existing thematic map and satellite images together with the new acquired satellite image of the desired region. It entails the following five major steps: (1) relative radiometric normalization, (2) change detection, (3) spectral database construction, (4) identifying the content of the changes, and (5) cartographic operations. In order to assess the effectiveness of the proposed KBE system for automatic updating of thematic maps, two different case studies related to Urmia Lake and surrounding areas were considered. Near-anniversary bi-temporal Landsat TM 4,5 imagery, acquired on 30 June 1989 and 24 June 2007 over the eastern coast of the lake alongside the existing land cover map of 1989, were used in the first case study. Utilized data sets in the second case study were near-anniversary Landsat 8 satellite images (OLI sensor) taken on 20/7/2014 and 23/7/2015 over the southern coast of lake alongside the outdated land cover map of interest region in 2014. Test results of different parts of the system were confirmed by the experts, and finally the system could satisfy the assessment criteria from the experts’ point of view in this particular application. Overall accuracy of the updated thematic map in the first and second case studies was 97.18 and 87.81 %, respectively.

Development of a hybrid expert system-multi criteria analysis on erosion and sediment control in construction industry

Construction activities combined with heavy rainfall can results in severe soil loss which eventually will be deposited into the adjacent water bodies via stormwater. The Best Management Practices (BMPs) adopted to minimise the erosion and sedimentation during construction activities are usually determined by standard guidelines and expert engineers. However, when the expertise and data are limited, knowledge-based systems have been proved as an effective alternative in making decision. A new algorithm of hybrid knowledge-based expert system and Multi-Criteria Analysis (MCA) was developed to minimise erosion and sedimentation due to stormwater in Malaysian construction sites. In this Eco-Friendly Erosion and Sediment Control (ECO-ESC) system, decision tables were developed based on the knowledge acquired from the domain experts specialised in erosion and sedimentation control and guidelines. The MCA was used to identify the best stormwater control measures based on the specific criteria and criterion's weight. The ECO-ESC was validated in three stages: preliminary by the experts, field and statistical validations. Results of comparison have shown high correlation for recommended BMPs, sediment yield, and the water quality monitoring and proved that the ECO-ESC performs as good as the human expert in solving different problems related to the erosion and sediment control.

Bank Credit Authorization Using Fuzzy Expert System

Companies Financial and economic performance is determined by analyzing their financial statements, that includes such important information as growth in sales, return to stockholders, profit margins, return on equity and credit risks. This information is useful for investors, creditors and other external users. To analyze financial condition of company and make decision need more professionalism and good economical and financial background from managers. In many cases financial manager make decision in condition of uncertainty. Economical instability, political situation needs many companies to work in condition of uncertainty, fuzziness of information. In this paper we take a closer look how information in the financial statement can be combined, analyzed and used by fuzzy expert systems to support many important financial decisions in credit analysis and authorization. This is achieved by the development of knowledge base using knowledge of experienced specialists, human experts in this field. In expert system knowledge base is combined with inference engine to make final decision.

某型机载设备故障诊断专家系统知识库的设计

军用飞机装备日趋复杂，其外场维护保障工作难度加大。为及时发现故障，确保飞机完好，以实现正常作战训练工作，本文简单介绍了某型机载设备故障专家系统的基本组成，通过实例详细论述了知识库的构建和知识规则的表示。同时为保证专家系统知识库的一致性和完整性，首先对规则进行了分类，并据此分类对异常规则进行了检测及处理。并通过与维护人员交互处理，使得得到的推理结论更加合理和准确。 The equipment of military aircraft becomes complex gradually, and field work becomes harder. In order to timely detect fault, ensure the aircraft intact and achieve a normal combat training work, this paper introduces the basic components of a certain type of airborne equipment, and the expert system is discussed in detail by showing examples and knowledge database to build the knowledge base rules. At the same time, to ensure the consistency and integrity of the expert system knowledge base, rules are classified first, and then abnormal rules are detected and treated. And through the interactive processing with maintenance personnel, the conclusions become more reasonable and accurate.

Ebinformatics: Ebola fuzzy informatics systems on the diagnosis, prediction and recommendation of appropriate treatments for Ebola virus disease (EVD)

Abstract Ebola Virus Disease (EVD) also known as the Ebola hemorrhagic fever is a very deadly infectious disease to humankind. Therefore, a safer and complementary method of diagnosis is to employ the use of an expert system in order to initiate a platform for pre-clinical treatments, thus acting as a precursor to comprehensive medical diagnosis and treatments. This work presents a design and implementation of informatics software and a knowledge-based expert system for the diagnosis, and provision of recommendations on the appropriate type of recommended treatment to the Ebola Virus Disease (EVD). In this research an Ebola fuzzy informatics system was developed for the purpose of diagnosing and providing useful recommendations to the management of the EVD in West Africa and other affected regions of the world. It also acts as a supplementary resource in providing medical advice to individuals in Ebola – ravaged countries. This aim was achieved through the following objectives: (i) gathering of facts through the conduct of a comprehensive continental survey to determine the knowledge and perception level of the public about factors responsible for the transmission of the Ebola Virus Disease (ii) develop an informatics software based on information collated from health institutions on basic diagnosis of the Ebola Virus Disease-related symptoms (iii) adopting and marrying the knowledge of fuzzy logic and expert systems in developing the informatics software. Necessary requirements were collated from the review of existing expert systems, consultation of journals and articles, and internet sources. Online survey was conducted to determine the level at which individuals are aware of the factors responsible for the transmission of the Ebola Virus Disease (EVD). The expert system developed, was designed to use fuzzy logic as its inference mechanism along with a set of rules. A knowledge base was created to help provide diagnosis on the Ebola Virus Disease (EVD). The Root Sum Square (RSS) was adopted as a fuzzy inference method. The degree of participation of each input parameter was shown using the triangular membership function and the defuzzification technique used is the Center of Gravity (CoG). The resulting software produced a user-friendly desktop-based, Windows-based, application and the tools used were explained in the results section in three (3) separate phases. First, a comprehensive online survey was conducted over a period of about 3–9 months. 100 Participants participated in the survey on the perception and knowledge analysis of different individuals about Ebola Virus Disease (EVD) transmission factors. 31% of the participants didn't know that there is presently no cure for Ebola. 28% believed that there is presently a cure for Ebola. 43% agreed that Ebola is both air-borne and water-borne, while 33% disagreed, 24% do not know. 23% believed that insects and mosquitoes can help in transmitting the Ebola Virus Disease (EVD), while 30% were completely ignorant. We noticed that ignorance was a major limiting factor among some participants. Second, a test was conducted among 45 people. Results from a comprehensive testing of the Ebinformatics software by allowing users to operate and use the software, revealed that 60% of them were satisfied, while 16% were not satisfied with the software, while 24% were indifferent. 69% of the users were in agreement that Ebinformatics was supportive, 20% disagreed, while 11% were indifferent. 67% found the software easy to use, 13% disagreed, while 20% were indifferent. Third, the output of the software, showing the various diagnosis and recommendations interfaces were presented. Recommendations were also given with respect to how the system can be extended, and further improved upon.

Development of a Knowledge-based Expert System for Diagnosis and Treatment of Common Diseases of the Spine

Introduction Back pain is a common musculoskeletal disorder affecting a large part of the young and the elderly population. Acute back pain generally lasts from a few days to a few weeks, while chronic back pain persists for more than three months and if it is not treated, it would pose major ris

MITIGATING AND MANAGING RISKS IN MOBILE TELECOM PROJECTS

Proper risk management is one of the key drivers of successful project delivery. This is more apparent in competitive and fast growing industries such as telecommunication. To better understand the risks faced in construction and deployment of mobile telecom sites (MTS), a research was initiated to: (a) examine risks associated with deploying MTS, and (b) understand the means to mitigate and handle them. The first point was addressed in an earlier publication whilst this paper focuses on the second. Knowledge pertinent to mitigating and handling MTS risks has been acquired via rounds of interviews and questionnaire surveys with a panel of telecom industry experts. Flow charting has been utilized to code the acquired procedural knowledge and provide basis for developing a knowledge base expert system (KBES). The rules technique was selected for knowledge representation. Automation of the KBES is also demonstrated.