scholarly journals An Intelligent Spatial Proximity System Using Neurofuzzy Classifiers and Contextual Information

2014 ◽  
Vol XL-2 ◽  
pp. 107-114 ◽  
Author(s):  
F. Barouni ◽  
B. Moulin
Keyword(s):  
Fuzzy Systems ◽  
Expert Knowledge ◽  
Contextual Information ◽  
Complete Solution ◽  
Fuzzy Rules ◽  
Training Data ◽  
Spatial Proximity ◽  
Membership Functions ◽  
Data Set ◽  
Neurofuzzy Systems

In this paper, we propose a novel approach to reason with spatial proximity. The approach is based on contextual information and uses a neurofuzzy classifier to handle the uncertainty aspect of proximity. Neurofuzzy systems are a combination of neural networks and fuzzy systems and incorporate the advantages of both techniques. Although fuzzy systems are focused on knowledge representation, they do not allow the estimation of membership functions. Conversely, neuronal networks use powerful learning techniques but they are not able to explain how results are obtained. Neurofuzzy systems benefit from both techniques by using training data to generate membership functions and by using fuzzy rules to represent expert knowledge. Moreover, contextual information is collected from a knowledge base. The complete solution that we propose is integrated in a GIS, enhancing it with proximity reasoning. From an application perspective, the proposed approach was used in the telecommunication domain and particularly in fiber optic monitoring systems. In such systems, a user needs to qualify the distance between a fiber break and the surrounding objects of the environment to optimize the assignment of emergency crews. The neurofuzzy classifier has been used to compute the membership function parameters of the contextual information inputs using a training data set and fuzzy rules.

An Intelligent Spatial Proximity System Using Neurofuzzy Classifiers and Contextual Information

GEOMATICA ◽  
2015 ◽  
Vol 69 (3) ◽  
pp. 285-296 ◽  
Author(s):  
F. Barouni ◽  
B. Moulin
Keyword(s):  
Fuzzy Systems ◽  
Expert Knowledge ◽  
Contextual Information ◽  
Complete Solution ◽  
Spatial Relations ◽  
Training Data ◽  
Spatial Proximity ◽  
Membership Functions ◽  
Novel Approach ◽  
Neurofuzzy Systems

In this paper, we propose a novel approach to reasoning with the concepts of spatial proximity. The approach is based on contextual information and uses a neurofuzzy classifier to handle the uncertainty aspect of proximity. Neurofuzzy systems are a combination of neural networks and fuzzy systems and effectively incor porate the advantages of both techniques. Although fuzzy systems are focused on knowledge rep re sen ta tion, they do not allow for the estimation of membership functions. Conversely, neuronal networks use powerful learning techniques but are not able to explain how results are obtained. Neurofuzzy systems ben e fit from both techniques by using neuronal network training data to generate membership functions and by using fuzzy rules to represent expert knowledge. Moreover, contextual information is collected from a knowl edge base. The neurofuzzy classifier is used to compute the membership function parameters of the spatial relations fuzzy quantifiers. The complete solution that we propose is integrated in a geographic information sys tem (GIS), enhanced with proximity-reasoning. Our approach is used in the telecommunication domain and particularly in fiber optic monitoring systems. In such systems, a user needs to qualify the distance between events reported by sensors and the surrounding objects of the environment, in order to form spatiotemporal pat terns. These patterns are defined to help users making decisions pertaining to operations, such as optimizing the assignment of emergency crews.

scholarly journals Lost in Space: Geolocation in Event Data

2018 ◽  
Vol 7 (04) ◽  
pp. 871-888 ◽  
Author(s):  
Sophie J. Lee ◽  
Howard Liu ◽  
Michael D. Ward
Keyword(s):  
Learning Algorithm ◽  
Text Processing ◽  
Contextual Information ◽  
Training Data ◽  
Supervised Machine Learning ◽  
Model Parameters ◽  
Event Data ◽  
Data Set ◽  
N Gram ◽  
Automated Text Processing

Improving geolocation accuracy in text data has long been a goal of automated text processing. We depart from the conventional method and introduce a two-stage supervised machine-learning algorithm that evaluates each location mention to be either correct or incorrect. We extract contextual information from texts, i.e., N-gram patterns for location words, mention frequency, and the context of sentences containing location words. We then estimate model parameters using a training data set and use this model to predict whether a location word in the test data set accurately represents the location of an event. We demonstrate these steps by constructing customized geolocation event data at the subnational level using news articles collected from around the world. The results show that the proposed algorithm outperforms existing geocoders even in a case added post hoc to test the generality of the developed algorithm.

A PERSPECTIVE AND CRITIQUE OF ADAPTIVE NEUROFUZZY SYSTEMS USED FOR MODELLING AND CONTROL APPLICATIONS

1995 ◽  
Vol 06 (02) ◽  
pp. 197-220 ◽  
Author(s):  
M. BROWN ◽  
C.J. HARRIS
Keyword(s):  
Fuzzy Systems ◽  
Inductive Learning ◽  
Training Data ◽  
Learning Theories ◽  
Learning Rules ◽  
Research Questions ◽  
And Control ◽  
Neurofuzzy Networks ◽  
Neurofuzzy Systems ◽  
Made In

This paper outlines some of the theoretical and practical developments being made in neurofuzzy systems. As the name suggests, neurofuzzy networks were developed by fusing the ideas that originated in the fields of neural and fuzzy systems. A neurofuzzy network attempts to combine the transparent, linguistic, symbolic representation associated with fuzzy logic with the architecture and learning rules commonly used in neural networks. These hybrid structures have both a qualitative and a quantitative interpretation and can overcome some of the difficulties associated with solely neural algorithms which can usually be regarded as black box mappings, and with fuzzy systems where few modelling and learning theories existed. Both B-spline and Gaussian Radial Basis Function networks can be regarded as neurofuzzy systems and soft inductive learning algorithms can be used to extract unknown, qualitative information about the relationships contained in the training data. In a similar manner, qualitative rules or information about the network’s structure can be used to initialise the system. These areas, coupled with the extensive work being carried out on theoretically analysing their modelling, convergence and stability properties means that this research topic is highly applicable in “intelligent” modelling and control problems. Apart from outlining this work, the paper also discusses a wide variety of open research questions and suggests areas where new efforts may be fruitfully applied.

Co-Evolution of Fuzzy Controller for the Mobile Robot Control

2004 ◽  
Vol 8 (4) ◽  
pp. 356-361 ◽  
Author(s):  
Kwang-Sub Byun ◽  
◽  
Chang-Hyun Park ◽  
Kwee-Bo Sim
Keyword(s):  
Mobile Robot ◽  
Fuzzy Systems ◽  
Fuzzy Inference ◽  
Fuzzy Controller ◽  
Fuzzy Rule ◽  
Fuzzy Rules ◽  
Rule Base ◽  
Membership Functions ◽  
Mobile Robot Control ◽  
Evolution Algorithms

In this paper, we design the fuzzy rules using a modified Nash Genetic Algorithm. Fuzzy rules consist of antecedents and consequents. Because this paper uses the simplified method of Sugeno for the fuzzy inference engine, consequents have not membership functions but constants. Therefore, each fuzzy rule in this paper consists of a membership function in the antecedent and a constant value in the consequent. The main problem in fuzzy systems is how to design the fuzzy rule base. Modified Nash GA coevolves membership functions and parameters in consequents of fuzzy rules. We demonstrate this co-evolutionary algorithm and apply to the design of the fuzzy controller for a mobile robot. From the result of simulation, we compare modified Nash GA with the other co-evolution algorithms and verify the efficacy of this algorithm.

A Multi-Strategy Learning for Recognizing Network Symptoms.

2020 ◽  
Vol 13 ◽  
Author(s):  
Tarek S. Sobh
Keyword(s):  
Domain Knowledge ◽  
Intelligent System ◽  
Heavy Traffic ◽  
Complete Solution ◽  
Network Monitoring ◽  
Training Data ◽  
Domain Theory ◽  
Knowledge Network ◽  
Support Network ◽  
Data Set

Background: Many network symptoms may happen due to different reasons in today's computer networks. The finding of a few kinds of these interesting symptoms is not direct. Therefore, an intelligent system is presented for extracting and recognizing that kind of network symptoms based on prior background knowledge. Methods: Here, the main target is to build a network-monitoring tool that can discover network symptoms and provide reasonable interpretations for various operational patterns. These interpretations are discussed with the purpose of supporting network planners/administrators. It introduces Multi-Strategy Learning (MSL) that can recognize network symptoms. Repeated symptoms or sometimes a single event of heavy traffic networks may lead us to recognize various network patterns that maybe expressed for discovering and solving network problems. Results: To achieve this goal an MSL system that can accommodate network observations. The first technique is done in an empirical manner. It focuses on selecting subsets data traffic by using certain fields from a group of records related to database samples using queries. The data abstraction is accomplished and various symptoms are extracted. A second technique is based on explanation-based learning. It produces a procedure that obtains operational rules. These rules may lead to network administrators solving some problems later. By using only one formal training example in the domain knowledge (network), we can learn and analyze in terms of this knowledge. In this work, to store and maintain network-monitoring traffic, network events, and the knowledge base for implementing the above techniques a Hadoop and a relational database are used. Discussion: Using EBL only is not suitable and it cannot take the same props like other types of available training data set as SBL can. EBL does not need only a complete domain theory but also need consistent domain theory. This reduces the suitability of EBL as knowledge acquisition. For this reason, we used EBL for discovering the pattern of network malfunction in case of a single example only in order to take a complete solution for this example. Conclusion: Hence, the proposed system can discover abnormal patterns (symptoms) of the underlying network traffic. A real network using our MSL, as such, could recognize these abnormal patterns. The network administrator can adapt the current configuration according to advice and observations that come from that intelligent system in order to avoid the problems that may currently exist or it may happen in the near future. Finally, the proposed system is capable to extract different symptoms (behaviors and operational patterns) and provide sensible advice in order to support network-planning activity.

Variances in knowledge-based interval type 2 Gaussian fuzzy on linear regression models

2021 ◽  
pp. 1-14
Author(s):  
Kevin Otieno Gogo ◽  
Lawrence Nderu ◽  
Makau Mutua
Keyword(s):  
Artificial Intelligence ◽  
Fuzzy Logic ◽  
Linear Regression ◽  
Predictive Models ◽  
Fuzzy Systems ◽  
Expert Knowledge ◽  
Knowledge Bases ◽  
Training Data ◽  
Interval Type

Fuzzy logic is a branch of artificial intelligence that has been used extensively in developing Fuzzy systems and models. These systems usually offer artificial intelligence based on the predictive mathematical models used; in this case linear regression mathematical model. Interval type 2 Gaussian fuzzy logic is a fuzzy logic that utilizes Gaussian upper membership function and the lower membership function, with a footprint of uncertainty in between the Gaussian membership functions. The artificial intelligence solutions predicted by these interval type 2 fuzzy systems depends on the training and the resultant linear regression mathematical model developed, which usually extract their training data from the expert knowledge stored in their knowledge bases. The variances in the expert knowledge stored in these knowledge-bases usually affect the overall accuracy of the linear regression predictive models of these systems, due to the variances in the training data. This research therefore establishes the extent that these variances in knowledge bases affect the predictive accuracy of these models, with a case study on knowledge bases used to predict learners’ knowledge level abilities. The calculated linear regression predictive models show that for every variance in the knowledge base, there occurs a change in linear regression predictive model with an intercept value factor commensurate to the variances and their respective weights in the knowledge bases.

scholarly journals On the benefits of clustering approaches in digital soil mapping: an application example concerning soil texture regionalization

2021 ◽  
Author(s):  
Istvan Dunkl ◽  
Mareike Ließ
Keyword(s):  
Soil Texture ◽  
Expert Knowledge ◽  
Learning Algorithm ◽  
Model Performance ◽  
Imbalanced Data ◽  
Soil Mapping ◽  
Digital Soil Mapping ◽  
Training Data ◽  
Data Set ◽  
Environmental Covariates

Abstract. High resolution soil maps are urgently needed by land managers and researchers for a variety of applications. Digital Soil Mapping (DSM) allows to regionalize soil properties by relating them to environmental covariates with the help of an empirical model. In this study, a legacy soil data set was used to train a machine learning algorithm in order to predict the particle size distribution within the catchment of the Bode river in Saxony-Anhalt (Germany). The ensemble learning method random forest was used to predict soil texture based on environmental covariates originating from a digital elevation model, land cover data and geologic maps. We studied the usefulness of clustering applications in addressing various aspects of the DSM procedure. To investigate the role of the imbalanced data problem in the learning process, the environmental variables were used to cluster the landscape of the study area. Different sampling strategies were used to create balanced training data and were evaluated on their ability to improve model performance. Clustering applications were also involved in feature selection and stratified cross-validation. Overall, clustering applications appear to be a versatile tool to be employed at various steps of the DSM procedure. Beyond their successful application, further application fields in DSM were identified. One of them is to find adequate means to include expert knowledge.

scholarly journals Rule Insertion Technique for Dynamic Cell Structure Neural Network

2020 ◽  
Vol 7 ◽  
Keyword(s):  
Neural Network ◽  
Flight Control ◽  
Expert Knowledge ◽  
Cell Structure ◽  
Training Data ◽  
Self Organizing Map ◽  
Data Set ◽  
Adaptive Flight Control ◽  
Dynamic Cell ◽  
Iris Data

This paper discusses the idea of capturing an expert’s knowledge in the form of human understandable rules and then inserting these rules into a dynamic cell structure (DCS) neural network. The DCS is a form of self-organizing map that can be used for many purposes, including classification and prediction. This particular neural network is considered to be a topology preserving network that starts with no pre-structure, but assumes a structure once trained. The DCS has been used in mission and safety-critical applications, including adaptive flight control and health-monitoring in aerial vehicles. The approach is to insert expert knowledge into the DCS before training. Rules are translated into a pre-structure and then training data are presented. This idea has been demonstrated using the well-known Iris data set and it has been shown that inserting the pre-structure results in better accuracy with the same training.

scholarly journals Optimal Genetic Design of Type-1 and Interval Type-2 Fuzzy Systems for Blood Pressure Level Classification

Axioms ◽  
2019 ◽  
Vol 8 (1) ◽  
pp. 8 ◽  
Author(s):  
Juan Guzmán ◽  
Ivette Miramontes ◽  
Patricia Melin ◽  
German Prado-Arechiga
Keyword(s):  
Blood Pressure ◽  
Fuzzy Systems ◽  
Blood Pressure Level ◽  
Fuzzy Rules ◽  
Membership Functions ◽  
Fuzzy Classifier ◽  
Classification Rate ◽  
Interval Type

The use of artificial intelligence techniques such as fuzzy logic, neural networks and evolutionary computation is currently very important in medicine to be able to provide an effective and timely diagnosis. The use of fuzzy logic allows to design fuzzy classifiers, which have fuzzy rules and membership functions, which are designed based on the experience of an expert. In this particular case a fuzzy classifier of Mamdani type was built, with 21 rules, with two inputs and one output and the objective of this classifier is to perform blood pressure level classification based on knowledge of an expert which is represented in the fuzzy rules. Subsequently different architectures were made in type-1 and type-2 fuzzy systems for classification, where the parameters of the membership functions used in the design of each architecture were adjusted, which can be triangular, trapezoidal and Gaussian, as well as how the fuzzy rules are optimized based on the ranges established by an expert. The main contribution of this work is the design of the optimized interval type-2 fuzzy system with triangular membership functions. The final type-2 system has a better classification rate of 99.408% than the type-1 classifier developed previously in “Design of an optimized fuzzy classifier for the diagnosis of blood pressure with a new computational method for expert rule optimization” with 98%. In addition, we also obtained a better classification rate than the other architectures proposed in this work.

Cloning Safe Driving Behavior for Self-Driving Cars using Convolutional Neural Networks

2019 ◽  
Vol 12 (2) ◽  
pp. 120-127 ◽  
Author(s):  
Wael Farag
Keyword(s):  
Gradient Descent ◽  
Autonomous Driving ◽  
Driving Behavior ◽  
Training Data ◽  
Stochastic Gradient Descent ◽  
Data Set ◽  
Safe Driving ◽  
Processing Pipeline ◽  
Self Driving Cars ◽  
And Training

Background: In this paper, a Convolutional Neural Network (CNN) to learn safe driving behavior and smooth steering manoeuvring, is proposed as an empowerment of autonomous driving technologies. The training data is collected from a front-facing camera and the steering commands issued by an experienced driver driving in traffic as well as urban roads. Methods: This data is then used to train the proposed CNN to facilitate what it is called “Behavioral Cloning”. The proposed Behavior Cloning CNN is named as “BCNet”, and its deep seventeen-layer architecture has been selected after extensive trials. The BCNet got trained using Adam’s optimization algorithm as a variant of the Stochastic Gradient Descent (SGD) technique. Results: The paper goes through the development and training process in details and shows the image processing pipeline harnessed in the development. Conclusion: The proposed approach proved successful in cloning the driving behavior embedded in the training data set after extensive simulations.

Sign in / Sign up

Export Citation Format

Share Document