Expert-based System Research Articles

DIAGNOSE OF MENTAL ILLNESS USING FORWARD CHAINING AND CERTAINTY FACTOR

The prevalence of mental disorders in Indonesia is increasingly significant, as seen from the 2018 Riskesdas data. Riskesdas records mental, emotional health problems (depression and anxiety) as much as 9.8%. This shows an increase when compared to the 2013 Riskesdas data of 6%. Based on these data, it can be said that many people still suffer from mental disorders. Meanwhile, the number of medical personnel, medicines and public treatment facilities for people with mental disorders is still limited. In addition, the lack of public awareness, concern and knowledge about mental health causes a lack of public interest in consulting a psychologist, so people tend to self-diagnose. One solution for self-diagnosis is to use an expert system. This study developed an expert system using the forward chaining method and certainty factor. Based on the research conducted, the results are as follows. First, the expert-based system that has been developed can help provide the results of a diagnosis that is carried out before there are complaints and will be detected early by efforts to increase awareness of the prevention of mental illness and reduce the tendency to self-diagnose. Second, applying the forward chaining method and certainty factor to this expert system can produce an accuracy rate of 95.918%. An expert has also validated these results; in this study, the expert was a psychologist at a hospital in Yogyakarta.

An expert-based system to predict population survival rate from health data.

Timely detection and understanding of causes for population decline are essential for effective wildlife management and conservation. Assessing trends in population size has been the standard approach, but we propose that monitoring population health could prove more effective. We collated data from 7 bottlenose dolphin (Tursiops truncatus) populations in the southeastern United States to develop a method for estimating survival probability based on a suite of health measures identified by experts as indices for inflammatory, metabolic, pulmonary, and neuroendocrine systems. We used logistic regression to implement the veterinary expert system for outcome prediction (VESOP) within a Bayesian analysis framework. We fitted parameters with records from 5 of the sites that had a robust network of responders to marine mammal strandings and frequent photographic identification surveys that documented definitive survival outcomes. We also conducted capture-mark-recapture (CMR) analyses of photographic identification data to obtain separate estimates of population survival rates for comparison with VESOP survival estimates. The VESOP analyses showed that multiple measures of health, particularly markers of inflammation, were predictive of 1- and 2-year individual survival. The highest mortality risk 1year following health assessment related to low alkaline phosphatase (odds ratio [OR]=10.2 [95% CI: 3.41-26.8]), whereas 2-year mortality was most influenced by elevated globulin (OR=9.60 [95% CI: 3.88-22.4]); both are markers of inflammation. The VESOP model predicted population-level survival rates that correlated with estimated survival rates from CMR analyses for the same populations (1-year Pearson's r=0.99, p=1.52×10-5 ; 2-year r=0.94, p=0.001). Although our proposed approach will not detect acute mortality threats that are largely independent of animal health, such as harmful algal blooms, it can be used to detect chronic health conditions that increase mortality risk. Random sampling of the population is important and advancement in remote sampling methods could facilitate more random selection of subjects, obtainment of larger sample sizes, and extension of the approach to other wildlife species.

Assessment of Land Use Land Cover Changes for Predicting Vulnerable Agricultural Lands in River Basins of Bangladesh Using Remote Sensing and a Fuzzy Expert System

The aim of this study was to assess the LULC changes over 26 years from 1995 to 2021 to find the most changed land use conditions within the 25 km territory of the main river systems of Bangladesh. In addition, the prediction of vulnerable areas for agricultural land use in terms of inundation by river water was also analyzed. The study area includes river networks distributed through eight administrative divisions (Rangpur, Rajshahi, Mymensingh, Sylhet, Dhaka, Khulna, Barishal and Chittagong) of Bangladesh, covering an area of 64,556 km2. The study was conducted by identifying permanent water bodies from NDWI indices and preparing LULC maps that include the five main land use classes (water body, bare land, vegetation, agricultural land, and urban area) in the Google Earth Engine platform using supervised classification. The LULC maps were then analyzed in the ArcGIS® environment. A vulnerability map for agricultural land use was also prepared using a fuzzy expert-based system applying multicriteria analysis. From the land use land cover map of the study area, it was found that among the five land use classes, water bodies, bare land, vegetation, and urban areas increased in size by 3.65%, 2.18%, 3.31% and 2.55%, respectively, whereas agricultural land use significantly decreased by 11.68%. This decrease in agricultural land use was common for the analyzed area of all administrative divisions. According to the vulnerable area map of the eight divisions, more than 50% of the analyzed area of the Khulna and Dhaka divisions and more than 40% of the analyzed area of the Rajshahi, Mymensingh, Sylhet, Barishal and Chittagong divisions were highly vulnerable to agricultural land use due to the possibility of inundation by water. However, approximately 44% of the analyzed area of the Rangpur division was not vulnerable for agricultural land use. The prepared LULC and vulnerability maps can be helpful for the future land use planning of Bangladesh to meet the increasing demand for food production and livelihoods for increasing populations.

Which Innovative Cropping System for Which Farmer? Supporting Farmers' Choices Through Collective Activities

Designing innovative cropping systems is an active field of agricultural research challenged by the agroecological transition. One of the challenges is to adapt cropping systems to the diversity of farms and contexts. For instance, in the cotton production zone of Burkina Faso differences between farm resources, agricultural situations and agronomic constraints have resulted in a wide range of farming systems. In this context, to break with the trend toward cotton production, we co-designed eight legume-based innovative cropping systems (ICS) likely to meet the objectives sought and the constraints faced by a wide range of local farmers, thus constituting a “basket of options”. Our approach was to enable each farmer to choose the option they considered best suited to their conditions. To that end, the ICSs were implemented and discussed with farmers in participatory prototyping trials. After one season of co-evaluating the different ICSs, the farmers taking part in the co-evaluation were able to test an ICS on their own farm, by choosing and adapting one of the options. Thirty-nine farmers out of seventy-three chose an ICS to test. They were asked the reasons for their choice. Their selection criteria were analyzed in relation to comments made during collective activities organized in the participatory prototyping trials. To complete this analysis, we built an expert-based farming system typology and a statistical typology based on data collected in a rural household multi-indicator survey (RHoMIS) of 63 farms participating in this study. The two farming system typologies were compared, and the relationships between farming system types and the ICS tested on the farm were analyzed. We found that farmers did not really base their choice on their farming system. Rather, they used a wide range of criteria that varied from farmer to farmer, and they were influenced by what they had learned during the collective activities organized in the participatory prototyping trials.

Development of an online condition monitoring based system for the partial demagnetization fault diagnosis of SPM‐type BLDC motor

This study investigates partial demagnetization faults arising from stator interturn faults in a surface-mounted permanent-magnet-type brushless direct current motor. Because of rotor demagnetization, the fault severity increases significantly owing to an increase in the stator phase current and temperature. The effect of such a fault is reflected in machine parameters such as the motor back-EMF and radial magnetic flux, which are used to analyse the characteristics of faults. A mathematical model of a machine under possible fault conditions is developed using the finite element method and advanced hybrid model approaches. Experimental investigations are conducted to validate the proposed methodology. Subsequently, the machine parameters used for fault diagnosis are employed to develop an online expert-based system that can detect, classify and estimate the percent increase in the values of the parameters to determine the fault severity of the machine under fault conditions. It is discovered that the proposed approach is suitable for industrial and commercial applications in electric vehicles, where the machine's state-of-health estimation is crucial for avoiding major faults that may result in its failure.

Predicting the tensile strength of bleach washed denim garments by using fuzzy logic modeling

The prime intention of this study is to develop and validate the efficiency of a fuzzy logic model to predict the tensile strength of bleach washed denim garments. Denim washing is nowadays a widely used technology to give a worn-out appearance to denim garments and thus add esthetic to that garments’ appearance and outlook. In the case of regular overall fading of denim, bleach washing is very popular. At the same time, it is also a matter of concern that the process optimization of bleach washing is critical as bleaching agents have an adverse effect on the fabrics. Among others, bleach concentration, time, and temperature are the primary process parameters in bleach washing, which directly impact the final strength of the treated denim garments. Though their relationship is nonlinear, a fuzzy expert-based system has been constructed to model and illustrate the complex relationship among bleach concentration, time, and temperature in the input side, whereas tensile strength is the output. Strength is the most critical parameter of the final denim product, as it dominates the serviceability of that garments. Therefore, predicting the tensile strength without the trial-and-error method, which is being practiced now, can be a blessing for industrial practitioners. With the help of a laboratory trial, the developed model has been evaluated, and it has been found that the mean relative error was 2.82 and 3.92 for warp and weft direction tensile strength, respectively. On the other hand, the comparison exhibited a coefficient of determination ( R2) of 0.99 for both warp and weft direction tensile strengths. The authors found that the performance of the developed model is satisfactory enough to predict the tensile strength of the bleach washed denim garments.

A Combination of Expert-Based System and Advanced Decision-Tree Algorithms to Predict Air-Overpressure Resulting from Quarry Blasting

This study combined a fuzzy Delphi method (FDM) and two advanced decision-tree algorithms to predict air-overpressure (AOp) caused by mine blasting. The FDM was used for input selection. Thus, the panel of experts selected four inputs, including powder factor, max charge per delay, stemming length, and distance from the blast face. Once the input selection was completed, two decision-tree algorithms, namely extreme gradient boosting tree (XGBoost-tree) and random forest (RF), were applied using the inputs selected by the experts. The models are evaluated with the following criteria: correlation coefficient, mean absolute error, gains chart, and Taylor diagram. The applied models were compared with the XGBoost-tree and RF models using the full set of data without input selection results. The results of hybridization showed that the XGBoost-tree model outperformed the RF model. Concerning the gains, the XGBoost-tree again outperformed the RF model. In comparison with the single decision-tree models, the single models had slightly better correlation coefficients; however, the hybridized models were simpler and easier to understand, analyze and implement. In addition, the Taylor diagram showed that the models applied outperformed some other conventional machine learning models, including support vector machine, k-nearest neighbors, and artificial neural network. Overall, the findings of this study suggest that combining expert opinion and advanced decision-tree algorithms can result in accurate and easy to understand predictions of AOp resulting from blasting in quarry sites.

An image-based system for pavement crack evaluation using transfer learning and wavelet transform

Automatic systems for pavement inspection can significantly enhance the performance of the Pavement Management Systems (PMSs). Cracking is the most current distress in any type of pavement. Progress of various technologies leads to a lot of effort in developing an automatic system for pavement cracking inspection. In the early image-based systems, the feature extraction process for crack classification must be done by using various image processing techniques in an expert-based system. In recent years, the new machine learning techniques such as a deep convolutional neural network (DCNN) provide more efficient models with the ability of automatic feature extracting, but these models need a lot of labeled data for training. Transfer learning is a technique that solves this problem using pre-trained models. In this research, several pre-trained models (AlexNet, GoogleNet, SqueezNet, ResNet-18, ResNet-50, ResNet-101, DenseNet-201, and Inception-v3) have been used to retrain based on pavement images using transfer learning. This study aims to evaluate the efficiency of retrained DCNNs in the detection and classification of the pavement cracking. Also, it presents a more effective algorithm based on a developed wavelet transform module with more regulizer parameters for crack segmentation. The result indicated that retrained classifier models provide reliable outputs with a range of 0.94 to 0.99 in confusion matrix-based performance, but the speed of some models is significantly higher than others. Also, the results clarified that the developed wavelet module could segment crack pixels with a high level of clarity.

A Systematic Literature Review of the Design Approach and Usability Evaluation of the Pain Management Mobile Applications

The increasing popularity of mHealth is a promising opportunity for pain self-management. Mobile apps can be easily developed, but understanding the design and usability will result in apps that can retain more users. This research aims at identifying, analyzing, and synthesizing the current state-of-the-art of: (a) the design approach and (b) usability assessment of pain management mobile applications. A systematic literature review was conducted on 27 studies retrieved from Medline, PubMed, EMBASE, Web of Science, and Scopus. The review revealed that most of the apps were for chronic pain. No app was specifically for men or for the elderly. None of the studies involved expert-based system inspection methods. Only one study used two different approaches of automated and empirical evaluation. We mapped the identified usability issues to ISO 9241-11 and ISO/IEC 25010, and aggregated the recommendations for improvement. Moreover, we also identified certain issues that are solely concerned with the patient’s behavior. We organized the issues into taxonomies of design considerations for building usable pain self-management mobile applications. As pain is prevalent among the elderly, pain management will be much needed while moving toward an aging society. However, we found that the involvement of the elderly in the development of pain management mobile apps is very minimal, which may affect the utility and usability of the apps.

Diagnosis of Common Headaches Using Hybrid Expert-Based Systems.

Background:Headache is one of the most common forms of medical complaints with numerous underlying causes and many patterns of presentation. The first step for starting the treatment is the recognition stage. In this article, the problem of primary and secondary headache diagnosis is considered, and we evaluate the use of intelligence techniques and soft computing in order to predict the diagnosis of common headaches.Methods:A fuzzy expert-based system for the diagnosis of common headaches by Learning-From-Examples (LFE) algorithm is presented, in which Mamdani model was used in fuzzy inference engine using Max–Min as Or–And operators, and the Centroid method was used as defuzzification technique. In addition, this article has analyzed common headache using two classification techniques, and headache diagnosis based on a support vector machine (SVM) and multilayer perceptron (MLP)-based method has been proposed. The classifiers were used to recognize the four types of common headache, namely migraine, tension, headaches as a result of infection, and headaches as a result of increased intra cranial presser.Results:By using a dataset obtained from 190 patients, suffering from primary and secondary headaches, who were enrolled from a medical center located in Mashhad, the diagnostic fuzzy system was trained by LFE algorithm, and on an average, 123 pieces of If-Then rules were produced for fuzzy system, and it was observed that the system had the ability of correct recognition by a rate of 85%. Using the headache diagnostic system by MLP- and SVM-based decision support system, the accuracy of classification into four types improved by 88% when using the MLP and by 90% with the SVM classifier. The performance of all methods is evaluated using classification accuracy, precision, sensitivity, and specificity.Conclusion:As the linguistic rules may be incomplete when human experts express their knowledge, and according to the proximity of common headache symptoms and importance of early diagnosis, the LFE training algorithm is more effective than human expert system. Favorable results obtained by the implementation and evaluation of the suggested medical decision support system based on the MLP and SVM show that intelligence techniques can be very useful for the recognition of common headaches with similar symptoms.

A decision support approach for condition-based maintenance of rails based on big data analysis

In this paper, a decision support approach is proposed for condition-based maintenance of rails relying on expert-based systems. The methodology takes into account both the actual conditions of the rails (using axle box acceleration measurements and rail video images) and the prior knowledge of the railway track. The approach provides an integrated estimation of the rail health conditions to support the maintenance decisions for a given time period. An expert-based system is defined to analyse interdependency between the prior knowledge of the track (defined by influential factors) and the surface defect measurements over the rail. When the rail health conditions is computed, the different track segments are prioritized, in order to facilitate grinding planning of those segments of rail that are prone to critical conditions. In this paper, real-life rail conditions measurements from the track Amersfoort-Weert in the Dutch railway network are used to show the benefits of the proposed methodology. The results support infrastructure managers to analyse the problems in their rail infrastructure and to efficiently perform a condition-based maintenance decision making.

Predication of soil pH using HSI colour image processing and regression over Guwahati, Assam, India

Soil is known to be the most valuable natural source for all agriculture fields. Soil has two properties, namely- physical and chemical. These properties include soil moisture, texture, etc. and the latter include pH value. Soil texture plays an important role in crop cultivation. The physical properties of soil such as texture and granular size determine the water and nutrient holding capacity. Also the chemical property like pH value is very important for plant growth and development. Soil having pH value between 5.5 and 7 is optimal for agricultural purpose. Hence, a detailed study of soil pH property is necessary for cultivation. But laboratory method of soil pH calculation is a very costly and tedious process. Therefore, it is essential to develop an expert-based system that will overcome this issue. However, the system must be able to give correct result and should match with those conducted in laboratory. Farmers analyze pH either in lab or by soil pH card based on soil image color. But this is not an effective method since it relies heavily on human perception. Hence, we have developed an expert based system which can determine the pH of the soil without any human error. For this, we have conducted our experiments with the help of MatLab tool and smart phone as we have concerned about the rural farmers. We have analyzed and compared the proposed system results with the traditional laboratory methods with regression and have found 86 % accuracy in our model.

Speed Management in Rural Two-way Roads: Speed Limit Definition through Expert-based System

Until recently, the design of road infrastructure involved mainly concerns related to the base speed value and to high levels of service. However, it is today consensually accepted that only an integrated approach is able to take into account the interests and needs of all the involved users. This vision led to different approaches on speed management along the road. During the last decade, new speed limits setting methodological approaches have emerged, based on new design models and tools, which take into account road geometric, safety and operational characteristics. This research work aimed to develop a decision-support methodology for the definition of the appropriate maximum speed in each road section, with a widespread use, applied to single carriageway roads in interurban areas, crossing different road environments with a mixed use. An analytical model able to accurately estimate that speed limit was developed based on a set of objective and easily measurable and obtainable explanatory variables characterizing the section under analysis and its surrounding areas. The resulting methodology is a Multinomial Logit model, and it was carried out using a case-study involving four different tracks of interurban roads crossing different environments. The model was estimated resorting to the use of values chosen by four traffic safety experts recorded for each road segment in both directions.

Combining an Expert-Based Medical Entity Recognizer to a Machine-Learning System: Methods and a Case Study

Medical entity recognition is currently generally performed by data-driven methods based on supervised machine learning. Expert-based systems, where linguistic and domain expertise are directly provided to the system are often combined with data-driven systems. We present here a case study where an existing expert-based medical entity recognition system, Ogmios, is combined with a data-driven system, Caramba, based on a linear-chain Conditional Random Field (CRF) classifier. Our case study specifically highlights the risk of overfitting incurred by an expert-based system. We observe that it prevents the combination of the 2 systems from obtaining improvements in precision, recall, or F-measure, and analyze the underlying mechanisms through a post-hoc feature-level analysis. Wrapping the expert-based system alone as attributes input to a CRF classifier does boost its F-measure from 0.603 to 0.710, bringing it on par with the data-driven system. The generalization of this method remains to be further investigated.

Developing Collaborative Classifiers using an Expert-based Model

This paper presents a hierarchical, multi-stage adaptive strategy for image classification. We iteratively apply various classification methods (e.g., decision trees, neural networks), identify regions of parametric and geographic space where accuracy is low, and in these regions, test and apply alternate methods repeating the process until the entire image is classified. Currently, classifiers are evaluated through human input using an expert-based system; therefore, this paper acts as the proof of concept for collaborative classifiers. Because we decompose the problem into smaller, more manageable sub-tasks, our classification exhibits increased flexibility compared to existing methods since classification methods are tailored to the idiosyncrasies of specific regions. A major benefit of our approach is its scalability and collaborative support since selected low-accuracy classifiers can be easily replaced with others without affecting classification accuracy in high accuracy areas. At each stage, we develop spatially explicit accuracy metrics that provide straightforward assessment of results by non-experts and point to areas that need algorithmic improvement or ancillary data. Our approach is demonstrated in the task of detecting impervious surface areas, an important indicator for human-induced alterations to the environment, using a 2001 Landsat scene from Las Vegas, Nevada.

Growing an ergonomics culture in manufacturing

In today's lean manufacturing environment, resources may be scarce and need to be utilized as economically as possible, especially those personnel in supporting roles, the so-called ‘overhead’. To improve the use of existing resources, a change in the workplace that moves from an expert-based ergonomics system to a culture-based one can be beneficial. The concept of an ‘ergonomics culture’ is one where everyone understands and bears some responsibility for ergonomics. This implies that all members of a work organization are informed and empowered to make improvements appropriate to their level of assigned responsibility. Of course, this concept is not implemented overnight and senior management must understand, endorse and visibly support such an initiative with their time and resources. The eventual result, however, is worthy of significant recognition for its positive workplace effect, with reduced injuries and their related costs and loss reductions, together with increased productivity, improved quality, better workforce stability and morale gains.

Cost-effectiveness analysis of woodland ecosystem restoration

Ecosystem restoration has emerged as an important approach to safe-guarding biodiversity. In Scotland, the government is committed to restoring the natural woodland ecosystem of mountain areas and gives payments to landowners for establishing new woodlands. Although the aim of the policy is to restore a natural woodland ecosystem, the rate of payment available is correlated with the costs of establishment rather than the contribution new woodlands make to restoring the natural ecosystem. In this study, the cost-effectiveness of government expenditure is investigated by comparing the cost of grant aid with the ecosystem restoration potential of new woodlands. An expert-based system for scoring ecosystem restoration potential is described and applied to over 200 new woodlands in a Geographic Information System. New woodlands varied considerably with respect to both cost and ecosystem restoration score, with the most cost-effective woodlands established close to existing woodlands using natural colonisation techniques. Overall ecosystem score was negatively correlated with government expenditure. Alternative approaches to improving the cost-effectiveness of grant aid are discussed.

Artificial Intelligence-Assisted Occupational Lung Disease Diagnosis

An artificial intelligence expert-based system for facilitating the clinical recognition of occupational and environmental factors in lung disease has been developed in a pilot fashion. It utilizes a knowledge representation scheme to capture relevant clinical knowledge into structures about specific objects (jobs, diseases, etc) and pairwise relations between objects. Quantifiers describe both the closeness of association and risk, as well as the degree of belief in the validity of a fact. An independent inference engine utilizes the knowledge, combining likelihoods and uncertainties to achieve estimates of likelihood factors for specific paths from work to illness. The system creates a series of "paths," linking work activities to disease outcomes. One path links a single period of work to a single possible disease outcome. In a preliminary trial, the number of "paths" from job to possible disease averaged 18 per subject in a general population and averaged 25 per subject in an asthmatic population. Artificial intelligence methods hold promise in the future to facilitate diagnosis in pulmonary and occupational medicine.