scholarly journals An Expert System for the Prognostication of the Brain and Nerve Diseases in Children with Convulsion Signs Based on Certainty Factors (Preprint)

2018 ◽  
Author(s):  
Narges Roozitalab ◽  
Hamid Nemati
Keyword(s):  
Expert System ◽  
Naive Bayes ◽  
Neurological Diseases ◽  
Naïve Bayes ◽  
Rule Based ◽  
Forward Chaining ◽  
Two Systems ◽  
The One ◽  
Time Required ◽  
Expert Physician

BACKGROUND Nowadays, the importance of the treatment of neurological diseases in children is well known to everybody. Currently, there are only 60 neurological specialists in Iran. Due to the lack of necessary equipment, we need to send lab. Samples to the countries which have advanced laboratories for diagnosis. Therefore, a diagnostic expert system can significantly prevent deaths of children. In this paper, we design and implement a rule-based expert system in CLIPS language using certainty factors and forward chaining inference in order to help physicians. Naïve Bayes and Logistic algorithm and the experiences of the expert person have been considered to estimate the certainty factors. The accuracy of this system is 94% for detecting diseases. Performances of these two systems are compared and the results confirm that the certainty factors that are specified by the expert physician have 6.2 percent prediction improvement over the one with Naïve Bayes. It is worth noting that an automatic rule generating program has been developed to reduce the time required to produce rules manually and minimize errors. OBJECTIVE Nowadays, the importance of the treatment of neurological diseases in children is well known to everybody. Currently, there are only 60 neurological specialists in Iran. Due to the lack of necessary equipment, we need to send lab. Samples to the countries which have advanced laboratories for diagnosis. Therefore, a diagnostic expert system can significantly prevent deaths of children. In this paper, we design and implement a rule-based expert system in CLIPS language using certainty factors and forward chaining inference in order to help physicians. Naïve Bayes and Logistic algorithm and the experiences of the expert person have been considered to estimate the certainty factors. The accuracy of this system is 94% for detecting diseases. Performances of these two systems are compared and the results confirm that the certainty factors that are specified by the expert physician have 6.2 percent prediction improvement over the one with Naïve Bayes. It is worth noting that an automatic rule generating program has been developed to reduce the time required to produce rules manually and minimize errors. METHODS Nowadays, the importance of the treatment of neurological diseases in children is well known to everybody. Currently, there are only 60 neurological specialists in Iran. Due to the lack of necessary equipment, we need to send lab. Samples to the countries which have advanced laboratories for diagnosis. Therefore, a diagnostic expert system can significantly prevent deaths of children. In this paper, we design and implement a rule-based expert system in CLIPS language using certainty factors and forward chaining inference in order to help physicians. Naïve Bayes and Logistic algorithm and the experiences of the expert person have been considered to estimate the certainty factors. The accuracy of this system is 94% for detecting diseases. Performances of these two systems are compared and the results confirm that the certainty factors that are specified by the expert physician have 6.2 percent prediction improvement over the one with Naïve Bayes. It is worth noting that an automatic rule generating program has been developed to reduce the time required to produce rules manually and minimize errors. RESULTS Nowadays, the importance of the treatment of neurological diseases in children is well known to everybody. Currently, there are only 60 neurological specialists in Iran. Due to the lack of necessary equipment, we need to send lab. Samples to the countries which have advanced laboratories for diagnosis. Therefore, a diagnostic expert system can significantly prevent deaths of children. In this paper, we design and implement a rule-based expert system in CLIPS language using certainty factors and forward chaining inference in order to help physicians. Naïve Bayes and Logistic algorithm and the experiences of the expert person have been considered to estimate the certainty factors. The accuracy of this system is 94% for detecting diseases. Performances of these two systems are compared and the results confirm that the certainty factors that are specified by the expert physician have 6.2 percent prediction improvement over the one with Naïve Bayes. It is worth noting that an automatic rule generating program has been developed to reduce the time required to produce rules manually and minimize errors. CONCLUSIONS Nowadays, the importance of the treatment of neurological diseases in children is well known to everybody. Currently, there are only 60 neurological specialists in Iran. Due to the lack of necessary equipment, we need to send lab. Samples to the countries which have advanced laboratories for diagnosis. Therefore, a diagnostic expert system can significantly prevent deaths of children. In this paper, we design and implement a rule-based expert system in CLIPS language using certainty factors and forward chaining inference in order to help physicians. Naïve Bayes and Logistic algorithm and the experiences of the expert person have been considered to estimate the certainty factors. The accuracy of this system is 94% for detecting diseases. Performances of these two systems are compared and the results confirm that the certainty factors that are specified by the expert physician have 6.2 percent prediction improvement over the one with Naïve Bayes. It is worth noting that an automatic rule generating program has been developed to reduce the time required to produce rules manually and minimize errors.

scholarly journals Accuracy Level of Diagnosis of ENT Diseases in Expert System

KOMTEKINFO ◽  
2019 ◽  
Vol 6 (2) ◽  
pp. 127-134
Author(s):  
Dede Wira Trise Putra ◽  
Ade Oka Utami ◽  
Minarni ◽  
Ganda Yoga Swara
Keyword(s):  
Expert System ◽  
Early Detection ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Test Results ◽  
Forward Chaining ◽  
Accuracy Level ◽  
Nose And Throat ◽  
Delay In Treatment

Purpose of this study is to test the accuracy of ear, nose and throat (ENT) diseases with an expert system. The expert system is designed to help people make early detection of illnesses so that the possibility of delay in treatment can be minimized. The method used is Naive Bayes with Forward Chaining Inference for 14 types of diseases with 42 symptoms originating from ENT specialists. The method was tested on 25 patients who used an expert system and adjusted the results of expert diagnoses. The test results are influenced by the number of symptoms, so that the accuracy obtained is only 88%. So this research is needed to be further developed to find a more reliable expert system in diagnosing ENT diseases.

scholarly journals Diagnosa Penyakit Tanaman Cabai menggunakan Metode Forward Chaining dan Naïve Bayes

2021 ◽  
Vol 5 (2) ◽  
pp. 164
Author(s):  
Riyo Efendi ◽  
Fauziah Fauziah ◽  
Aris Gunaryati
Keyword(s):  
Expert System ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Plant Diseases ◽  
Web Based ◽  
Bayes Methods ◽  
Forward Chaining ◽  
Speed Up ◽  
Handling Methods ◽  
The Web

The purpose of this research is to design a web-based expert system application to provide information about chili plant diseases and to diagnose the symptoms of diseases that attack chili plants and to provide solutions for appropriate handling methods, which can be accessed anywhere and utilized by the wider community and can speed up the time to deal with diseases that attack chili plants. This study uses the Forward Chaining and Naïve Bayes Methods in order to know the facts/signs of chili disease so that you can get the best quality chili. Based on the results of the discussion and calculation of the web-based expert system for diagnosing chili disease using the Forward Chaining and Naïve Bayes methods, it can be concluded that a simple application it can make it easier for users to diagnose chili disease and find out the causes and solutions. And can find out the total number of all comparisons of the 2 methods.Keywords:Chili disease, Expert System, Forward Chaining, Naïve Bayes.

scholarly journals Prediction of Heart Disease Using Machine Learning Algorithms

2018 ◽  
Vol 7 (2.32) ◽  
pp. 363 ◽  
Author(s):  
N Rajesh ◽  
Maneesha T ◽  
Shaik Hafeez ◽  
Hari Krishna
Keyword(s):  
Risk Factors ◽  
Heart Disease ◽  
Decision Trees ◽  
Naive Bayes ◽  
Heart Diseases ◽  
Naïve Bayes ◽  
Machine Learning Algorithms ◽  
Common Disease ◽  
Bayes Algorithm ◽  
The One

Heart disease is the one of the most common disease. This disease is quite common now a days we used different attributes which can relate to this heart diseases well to find the better method to predict and we also used algorithms for prediction. Naive Bayes, algorithm is analyzed on dataset based on risk factors. We also used decision trees and combination of algorithms for the prediction of heart disease based on the above attributes. The results shown that when the dataset is small naive Bayes algorithm gives the accurate results and when the dataset is large decision trees gives the accurate results.  

scholarly journals SISTEM PAKAR DIAGNOSA PENYAKIT DAN HAMA PADA TANAMAN JAGUNG MENGGUNAKAN METODE NAIVE BAYES

2021 ◽  
Vol 2 (3) ◽  
pp. 390-398
Author(s):  
Bayu Bastiyan Suherman
Keyword(s):  
Expert System ◽  
Expert Systems ◽  
Preventive Measures ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Agricultural Commodities ◽  
Bayes Method ◽  
Mathematical Basis ◽  
Lack Of Information ◽  
Corn Plants

Corn is one of the leading agricultural commodities that can be used as a staple plant other than rice. Constraints faced by corn farmers include the lack of information about diseases that attack the corn plants, which causes less productivity. In this study a system was developed that can automatically detect disease that attacks corn plants so that preventive measures can be taken to prevent corn plants from dying. Expert systems are designed to solve certain problems by imitating the work of experts. In addition, this expert system also helps farmers who are experiencing problems regarding diseases and pests and their solutions without relying on an expert. The method used is the Naive Bayes method, Naive Bayes is a method used to predict probabilities and has several characteristics that are istitively in accordance with the way of thinking of an expert and accompanied by a strong mathematical basis. From the tests carried out with diagnoses obtained from the comparison between the results of expert diagnoses and the diagnosis of the system to diagnose diseases and pests in corn plants is 90%.

scholarly journals SISTEM PAKAR DIAGNOSA PENYAKIT KULIT PADA BALITA MENGGUNAKAN METODE NAÏVE BAYES DAN FORWARD CHAINING STUDI KASUS PUSKESMAS CEMPAKA SUNGKAI SELATAN

2021 ◽  
Vol 9 (2) ◽  
pp. 144-153
Author(s):  
Sidik Rahmatullah ◽  
Rima Mawarni
Keyword(s):  
Naive Bayes ◽  
Unified Modeling Language ◽  
Naïve Bayes ◽  
Modeling Language ◽  
Class Diagram ◽  
Use Case ◽  
Activity Diagram ◽  
Unified Modeling ◽  
Forward Chaining

Pusat Kesehatan Masyarakat (Puskesmas) merupakan kesatuan organisasi fungsional yang menyelenggarakan upaya kesehatan yang bersifat menyeluruh, terpadu, merata dapat diterima dan terjangkau oleh masyarakat. Tujuan penelitian ini adalah membuat Aplikasi Sistem Pakar untuk mendeteksi penyakit kulit pada balita sesuai dengan data-data yang ada pada Puskesmas. Metode pengembangan sistem yang digunakan yaitu metode Extreme Programing (XP) dengan tahapan pengerjaan meliputi planning, design, coding dan testing. Sistem dirancang dengan menggunakan Unified Modeling Language (UML) yang meliputi use case, activity diagram, dan class diagram, perangkat lunak yang digunakan adalah PHP (Hypertext Preprocessor) dengan database MySQL dan menggunakan metode Naïve Bayes dan Forward Chaining. Hasil akhir dari pembuatan Aplikasi ini adalah memudahkan pasien, dokter dan bidan mendeteksi penyakit kulit pada balita di Puskesmas

scholarly journals Nonlinear Methodologies for Identifying Seismic Event and Nuclear Explosion Using Random Forest, Support Vector Machine, and Naive Bayes Classification

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Longjun Dong ◽  
Xibing Li ◽  
Gongnan Xie
Keyword(s):  
Predictive Power ◽  
Seismic Event ◽  
Naive Bayes ◽  
Nuclear Explosion ◽  
Naïve Bayes ◽  
Support Vector ◽  
Bayes Classifier ◽  
Vector Machines ◽  
The One ◽  
Calculated Distance

The discrimination of seismic event and nuclear explosion is a complex and nonlinear system. The nonlinear methodologies including Random Forests (RF), Support Vector Machines (SVM), and Naïve Bayes Classifier (NBC) were applied to discriminant seismic events. Twenty earthquakes and twenty-seven explosions with nine ratios of the energies contained within predetermined “velocity windows” and calculated distance are used in discriminators. Based on the one out cross-validation, ROC curve, calculated accuracy of training and test samples, and discriminating performances of RF, SVM, and NBC were discussed and compared. The result of RF method clearly shows the best predictive power with a maximum area of 0.975 under the ROC among RF, SVM, and NBC. The discriminant accuracies of RF, SVM, and NBC for test samples are 92.86%, 85.71%, and 92.86%, respectively. It has been demonstrated that the presented RF model can not only identify seismic event automatically with high accuracy, but also can sort the discriminant indicators according to calculated values of weights.

scholarly journals Adapting Hidden Naive Bayes for Text Classification

Mathematics ◽  
2021 ◽  
Vol 9 (19) ◽  
pp. 2378
Author(s):  
Shengfeng Gan ◽  
Shiqi Shao ◽  
Long Chen ◽  
Liangjun Yu ◽  
Liangxiao Jiang
Keyword(s):  
Text Classification ◽  
Conditional Independence ◽  
Structure Learning ◽  
Naive Bayes ◽  
Learning Algorithm ◽  
Classification Performance ◽  
Naïve Bayes ◽  
Efficiency And Effectiveness ◽  
The One ◽  
Structure Extension

Due to its simplicity, efficiency, and effectiveness, multinomial naive Bayes (MNB) has been widely used for text classification. As in naive Bayes (NB), its assumption of the conditional independence of features is often violated and, therefore, reduces its classification performance. Of the numerous approaches to alleviating its assumption of the conditional independence of features, structure extension has attracted less attention from researchers. To the best of our knowledge, only structure-extended MNB (SEMNB) has been proposed so far. SEMNB averages all weighted super-parent one-dependence multinomial estimators; therefore, it is an ensemble learning model. In this paper, we propose a single model called hidden MNB (HMNB) by adapting the well-known hidden NB (HNB). HMNB creates a hidden parent for each feature, which synthesizes all the other qualified features’ influences. For HMNB to learn, we propose a simple but effective learning algorithm without incurring a high-computational-complexity structure-learning process. Our improved idea can also be used to improve complement NB (CNB) and the one-versus-all-but-one model (OVA), and the resulting models are simply denoted as HCNB and HOVA, respectively. The extensive experiments on eleven benchmark text classification datasets validate the effectiveness of HMNB, HCNB, and HOVA.

scholarly journals Rancangan Aplikasi Sistem Pakar Diagnosa Penyakit Mononukleosis Dengan Metode Naive Bayes

2020 ◽  
Vol 7 (3) ◽  
pp. 403
Author(s):  
Rizky Hasanah Restari ◽  
Sinar Sinurat ◽  
Suginam Suginam
Keyword(s):  
Expert System ◽  
Health Center ◽  
Naive Bayes ◽  
Disease Diagnosis ◽  
Naïve Bayes ◽  
The Other ◽  
Daily Activities ◽  
Bayes Method ◽  
Other Hand ◽  
Naive Bayes Method

Health is one of the important factors for carrying out daily activities. However, some people do not care about the health of their bodies so that in the end many diseases that are diagnosed late cause the condition at a serious stage. One of the diseases in question is mononucleosis. In general, if the community is exposed to symptoms of mononucleosis, they will go to the nearest hospital or health center to do the examination. But on the other hand they have to sacrifice enough time for that. For this reason, it is necessary to make an application for a disease diagnosis expert system for the community as a means of overcoming these problems. With this design, an expert system of mononucleosis is produced, where this system uses the naive bayes method and the doctor's knowledge into the system. This expert system will produce output / output in the form of the diagnosis of mononucleosis

scholarly journals Sistem Pakar Diagnosa Virus Corona Dengan Metode Naïve Bayes

2021 ◽  
Vol 9 (1) ◽  
pp. 81
Author(s):  
Fareza Aditiyanto Nugroho ◽  
Arif Fajar Solikin ◽  
Mutiara Dwi Anggraini ◽  
Kusrini Kusrini
Keyword(s):  
Expert System ◽  
Natural Disaster ◽  
Naive Bayes ◽  
Virus Disease ◽  
Diagnostic System ◽  
Naïve Bayes ◽  
The Body ◽  
Human Being ◽  
Bayes Method ◽  
The World

Humans being are faced with non-natural disasters which have bad effect for population on the world. This non-natural disaster is called Corona Virus Disease (COVID-19). This COVID-19 will become a pandemic in 2020. This types of COVID-19 is coming from the Orthocronavirinae. It belongs to the Coronaviridae and the Nidovirales. This type of that virus has caused some disease to birds, mammals and also human being. Therefore, the research was conducted. The result of this research will give the information about system which related the classification human being according to their transmission to the body. This research used naïve bayes method. The result of this research is diagnostic system with the level of accuracy 94%. Thus, COVID-19 diagnostic expert system used to know the level of COVID -19 infections to human being. It can help the user knowing the next treatment.Keywords : Expert System, Naïve Bayes, Coronavirus, Covid-19

Sign in / Sign up

Export Citation Format

Share Document