Rule-based Knowledge Research Articles

Research on Face Recognition Algorithm Based on Convolutional Nerve

Facial expression can truly reflect people’s inner activities, human emotions can be fully reflected through the expression, facial expression recognition in the field of artificial intelligence has important research significance, in daily life also has its application value. At present, facial expression recognition technology has become a very promising frontier technology, but also the current research focus in the field of computer vision.In this paper, facial expression recognition based on convolution neural network is studied. The concrete work has the following several parts: For the part of face detection, this paper introduces the common methods of knowledge-based rules, feature-based, template-based matching, and statistical model-based, and V-J detector is used for face detection in this paper. In the part of expression recognition, we study the recognition of happiness, sadness, anger, depression, fear and surprise by convolution neural network. This paper uses keras to build a deep learning framework. The neural network consists of volume base layer, pool layer, activation layer and full connection layer. The classifier uses softmax. Using the image data in the standard database as input, after the processing of each layer in the neural network, and finally outputting the probability corresponding to six expressions through softmax, it is generally believed that the expression with the highest probability is the facial expression in the input image.

A Safety Prediction System for Lunar Orbit Rendezvous and Docking Mission

In view of the characteristics of the guidance, navigation and control (GNC) system of the lunar orbit rendezvous and docking (RVD), we design an auxiliary safety prediction system based on the human–machine collaboration framework. The system contains two parts, including the construction of the rendezvous and docking safety rule knowledge base by the use of machine learning methods, and the prediction of safety by the use of the base. First, in the ground semi-physical simulation test environment, feature extraction and matching are performed on the images taken by the navigation surveillance camera. Then, the matched features and the rendezvous and docking deviation are used to form training sample pairs, which are further used to construct the safety rule knowledge base by using the decision tree method. Finally, the safety rule knowledge base is used to predict the safety of the subsequent process of the rendezvous and docking based on the current images taken by the surveillance camera, and the probability of success is obtained. Semi-physical experiments on the ground show that the system can improve the level of intelligence in the flight control process and effectively assist ground flight controllers in data monitoring and mission decision-making.

Phenotyping of clinical trial eligibility text from cancer studies into computable criteria in electronic health records.

6592 Background: Clinical trial phenotyping is the process of extracting clinical features and patient characteristics from eligibility criteria. Phenotyping is a crucial step that precedes automated cohort identification from patient electronic health records (EHRs) against trial criteria. We establish a clinical trial phenotyping pipeline to transform clinical trial eligibility criteria into computable criteria and enable high throughput cohort selection in EHRs. Methods: Formalized clinical trial criteria attributes were acquired from a natural-language processing (NLP)-assisted approach. We implemented a clinical trial phenotyping pipeline that included three components: First, a rule-based knowledge engineering component was introduced to annotate the trial attributes into a computable and customizable granularity from EHRs. The second component involved normalizing annotated attributes using standard terminologies and pre-defined reference tables. Third, a knowledge base of computable criteria attributes was built to match patients to clinical trials. We evaluated the pipeline performance by independent manual review. The inter-rater agreement of the annotation was measured on a random sample of the knowledge base. The accuracy of the pipeline was evaluated on a subset of randomly selected matched patients for a subset of randomly selected attributes. Results: Our pipeline phenotyped 2954 clinical trials from five cancer types including Non-Small Cell Lung Cancer, Small Cell Lung Cancer, Prostate Cancer, Breast Cancer, and Multiple Myeloma. We built a knowledge base of 256 computable attributes that included comorbidities, comorbidity-related treatment, previous lines of therapy, laboratory tests, and performance such as ECOG and Karnofsky score. Among 256 attributes, 132 attributes were encoded using standard terminologies and 124 attributes were normalized to customized concepts. The inter-rater agreement of the annotation measured by Cohen’s Kappa coefficient was 0.83. We applied the knowledge base to our EHRs and efficiently identified 33258 potential subjects for cancer clinical trials. Our evaluation on the patient matching indicated the F1 score was 0.94. Conclusions: We established a clinical trial phenotyping pipeline and built a knowledge base of computable criteria attributes that enabled efficient screening of EHRs for patients meeting clinical trial eligibility criteria, providing an automated way to efficiently and accurately identify clinical trial cohorts. The application of this knowledge base to patient matching from EHR data across different institutes demonstrates its generalization capability. Taken together, this knowledge base will be particularly valuable in computer-assisted clinical trial subject selection and clinical trial protocol design in cancer studies based on real-world evidence.

Sustaining User Experience in a Smart System in the Retail Industry

Retail enterprises are embracing new technologies to provide innovative services to customers and engage them. Unmanned retail stores offer a completely new seamless shopping experience for customers. Moreover, artificial intelligence (AI) technology and sophisticated customer behavior should be explored in depth to develop a smart system to serve customers. This study focused on achieving a sustainable user experience with a smart system installed in an autonomous store. The development of core functions and a rule-based knowledge set are regarded as the most important tasks in designing autonomous services. In the case study, the core functions were developed on the basis of the design science concept and the rule-based knowledge set was constructed using the action research approach. The developed smart system was optimized to understand in-store customer behavior by continuously observing and refining the user experience. The practical experience of this study provides insights into AI technology use in retailing and can guide enterprises in developing smart systems.

Level-wise driving knowledge induction for embedded automatic train driving system

Automatic driving of trains can significantly reduce the energy cost and enhance the operating efficiency and safety. The automatic train driving system has to be an embedded system that can run onboard with low power, which necessitates an efficient inference model. In this article, a level-wise driving knowledge induction approach is proposed for embedded automatic train driving systems. The coincident driving patterns in the records of drivers with different experience levels suggest the suitability of a driving experience knowledge rule induction approach. We design a two-level learning approach to obtain both the driving experience pattern in fuzzy rule-based knowledge form and the detailed parameters of velocity and gear by regression learning methods. With 8.93% energy consumption reduction compared with average human drivers, the experiments indicate the effectiveness of our approach.

APPLICATION OF NEURO-FUZZY MODELS IN THE SYSTEM FOR ASSESSING THE PROFESSIONAL ABILITIES OF APPLICANTS

The work is devoted to solving a problem of assessing the professional abilities of entrants to higher education institutions. The subject of the study is the process of automatic support of entrants' decisions in conditions of fuzzy uncertainty caused by the need to communicate "online". The object of the study is a supporting means of the decisions of applicants to choose the direction of study "online". The main purpose of the work is to substantiate the technology of decision support for choosing a direction of study using an infocommunication system, the work of which has based on a neuro-fuzzy output system. Particular attention has paid to overcoming the problems that accompany the creation of infocommunication systems, which has designed to support decision-making on the choice of field of study in conditions of unclear uncertainty caused by the limitation of offline communication. The article presents the results of a study of the criteria for admission to higher education institutions in different countries. The structural model of the Specialized Intellectual System of Identification of Abilities of Entrants has offered. The system has designed to support the decision to choose a specialty of higher education institution. It has shown that to substantiate the recommendation conclusion based on the results of professional game; it is advisable to use a fuzzy neural network Takagi-Sugeno-Kanga. To solve the problem of substantiation of expert decisions at the stage of formation of a priori base of rules of fuzzy knowledge base of fuzzy inference system, it is expedient to use Mamdani model, which operates with linguistic variables and fuzzy sets.

Clinical evaluation of an interoperable clinical decision-support system for the detection of systemic inflammatory response syndrome in critically ill children

BackgroundSystemic inflammatory response syndrome (SIRS) is defined as a non-specific inflammatory process in the absence of infection. SIRS increases susceptibility for organ dysfunction, and frequently affects the clinical outcome of affected patients. We evaluated a knowledge-based, interoperable clinical decision-support system (CDSS) for SIRS detection on a pediatric intensive care unit (PICU).MethodsThe CDSS developed retrieves routine data, previously transformed into an interoperable format, by using model-based queries and guideline- and knowledge-based rules. We evaluated the CDSS in a prospective diagnostic study from 08/2018–03/2019. 168 patients from a pediatric intensive care unit of a tertiary university hospital, aged 0 to 18 years, were assessed for SIRS by the CDSS and by physicians during clinical routine. Sensitivity and specificity (when compared to the reference standard) with 95% Wald confidence intervals (CI) were estimated on the level of patients and patient-days.ResultsSensitivity and specificity was 91.7% (95% CI 85.5–95.4%) and 54.1% (95% CI 45.4–62.5%) on patient level, and 97.5% (95% CI 95.1–98.7%) and 91.5% (95% CI 89.3–93.3%) on the level of patient-days. Physicians’ SIRS recognition during clinical routine was considerably less accurate (sensitivity of 62.0% (95% CI 56.8–66.9%)/specificity of 83.3% (95% CI 80.4–85.9%)) when measurd on the level of patient-days. Evaluation revealed valuable insights for the general design of the CDSS as well as specific rule modifications. Despite a lower than expected specificity, diagnostic accuracy was higher than the one in daily routine ratings, thus, demonstrating high potentials of using our CDSS to help to detect SIRS in clinical routine.ConclusionsWe successfully evaluated an interoperable CDSS for SIRS detection in PICU. Our study demonstrated the general feasibility and potentials of the implemented algorithms but also some limitations. In the next step, the CDSS will be optimized to overcome these limitations and will be evaluated in a multi-center study.Trial registration: NCT03661450 (ClinicalTrials.gov); registered September 7, 2018.

An Integrated Data and Knowledge Model Addressing Aleatory and Epistemic Uncertainty for Oil Condition Monitoring

Reliable operation of machinery is very desirable in engineering. To achieve this objective, the assessment of the lubrication oil state is necessary. However, due to the unpredictable variations, uncertainty detection and handling in the oil state has been a bottleneck in practice. A solution strategy is proposed in this paper that integrates information from the monitoring data and expert knowledge. On the other hand, since insufficient data and limited knowledge, two types of uncertainty are present, namely, aleatory and epistemic uncertainty. To handle these uncertainties, an integrated model with a three-layer structure is constructed that incorporates both expert knowledge and data. First, for the detection of stochastic data variation, the initial connection among the layers is assigned by membership probabilities as the characterization evidence. Second, the oil state that produces a unified output with various pieces of evidence is determined by evidential reasoning with knowledge-based rules. Third, to provide consistent monitoring adaptively, a knowledge-integrated neural network is established for determining the initial parameters from measurements. The effectiveness of the proposed model is demonstrated using both simulated and real-world data from industrial vehicles.

The cultivation of self-directed learning in teaching mathematics

This study examined students’ ability to learn mathematics in a self-directed teaching environment. One of the main goals of the educational system is to nurture independent learners who can grow up to be inquisitive, critical, creative, and capable of piloting their own learning. This implies making a change in the way the role of the mathematics teacher is perceived in that the teacher must now become a mentor who supports and mediates learning, enabling students to construct a knowledge base of rules and methods in mathematics and acquire and experience ways of thinking that enable them to construct this knowledge.This qualitative study is based on interviews with four ninth-grade mathematics teachers and on in-class observations of teaching styles and teacher-student interactions. Our findings show that applying self-directed learning methods in class based on a constructivist approach to teach mathematics is an important factor in developing students’ creativity and thinking. These findings suggest that developing this model of teaching should be recommended to teachers. Accordingly, this study also proposes a model for staff development programs that foster self-directed learning in mathematics. The model proposes that increasing teachers’ awareness of their teaching process and training them to prepare learners to cope effectively with unfamiliar mathematical problems are goals to include in teacher training. This model of teaching may have far-reaching effects in pedagogy, e.g.: reducing drop-out numbers, improving achievements, and improving social interactions.Key words: constructivist approach, fostering thinking, self-directed learning, teaching mathematics.

Outliers in Covid 19 data based on Rule representation - the analysis of LOF algorithm

The article concerns the detection of outliers in rule-based knowledge bases containing data on Covid 19 cases. The authors move from the automatic generation of a rule-based knowledge base from source data by clustering rules in the knowledge base to optimize inference processes and to detecting unusual rules allowing for the optimal structure of rule groups. The paper presents a two-phase procedure, wherein in the first phase, we look for the optimal structure of rule clusters when there are outlier rules in the knowledge base. In the second phase, we detect outliers in the rules using the LOF (Local Outlier Factor) algorithm. Then we eliminate the unusual rules from the database and check whether the selected cluster quality measures are responded positively to the elimination of outliers, which would indicate that the rules were rightly considered outliers. The performed experiments confirmed the effectiveness of the LOF algorithm and selected cluster quality measures in the context of detecting atypical rules. The detection of such rules can support knowledge engineers or domain experts in knowledge mining to improve the completeness of the knowledge base, which is usually the basis of the decision support system.

Debugging procedure of the replica class errors in the production knowledge bases

The problem of detecting errors in the production knowledge bases of knowledge - oriented information systems that arise at the stage of formation of the knowledge base by experts is considered. It was determined that such errors related to the conflicting opinions of experts and/or limited (imperfect) description of the subject area. There was analyzed approaches for their debugging. Ways to improve existing approaches for debugging static replica errors was shown. Possible ways of applying the obtained solutions to debug errors "contradiction", "redundancy", "incompleteness" was shown. Solutions for expanding the formalized definition of static error of the production network, considering the requirements for the accuracy of information was suggested. The issues of the influence of errors of the “replica” class on the results of derivation according to the rules of the production knowledge base was considered. The possibility of applying the methods of graph theory to solve the problem of error reduction of the "replica" class is proved. An algorithmic structure for detecting and debugging errors of this class has been developed. It allows, in contrast to existing solutions, to detect duplicate vertices at each rank of the graph to which the production knowledge base is reduced. Software implementation for detection and debugging of static errors of incomplete, partial, and complete duplication was developed, using recursion, which allows to reduce the requirements for preparing an array of input data for processing. The obtained solutions meet the requirements of DSTU ISO / IEC 9126, DSTU ISO / IEC 14598 and consider the requirements of the series of standards Software Quality Requirements and Evaluation as the values of the vertices of the graph of the event tree. During problem solving process specifics of the LMS operation are considered, first of all formalizing possibilities in the various aspects of knowledge (aletic, dissociative, causal, diontic) and ensuring a given level of efficiency in finding solutions.

Developing An Expert System Framework for Supporting Diagnosis and Treatment of Dyspepsia and Gastric Cancer Disease Using Local Language

Dyspepsia is a pain of the upper abdominal and it has the problem of impaired digestion like abdominal disease or other abdominal disease, which has the symptoms of heartburn, nausea, and belching, upper abdominal fullness [1]. It also related to the problem of indigestion for a group of symptoms that cause pain in the abdomen, which affects at least 25% of the world population every year [2]. From related disease of dyspepsia, Gastric cancer is the stomach cancer that develops from the lining of the stomach that affects the cell of digestive system and it is the third leading cause of death worldwide [3]. Both dyspepsia and gastric cancer is diseases that affect gastrointestinal part of human body. Therefore, this type of disease requires timely diagnosis and treatment; otherwise it can cause death and other chronic diseases. In developing countries like Ethiopia, treatment option for dyspepsia and gastric cancer is not readily available which support medical professional and also there is a scarcity of medical professional, to address such medical problems a medical expert system can play a significant role, consequently, the main objective of this research study is to develop an expert system framework for supporting diagnosis and treatment of dyspepsia and gastric cancer using local language (Amharic language). To develop this medical expert system, knowledge was acquired using both structured and unstructured interview from domain expert which are selected using purposive sampling techniques from Arba Minch General Hospital, and from document analysis. Domain knowledge is modeled using decision tree and rule-based knowledge representation was used. This medical expert system is developed by using backward chaining to infer the rule and provide an appropriate diagnosis. Finally, the performance of the system was evaluated by preparing 15 test cases by provided to domain experts and for user acceptance test, users evaluate the system through nine criteria prepared by the researcher and the system has scored 80% system performance and 85.2% user acceptance this result shows that the study has a promising result that achieves the objective of the study. The researchers recommended that to apply data mining techniques and to extract the hidden knowledge. Keywords : Expert System, Dyspepsia and Gastric Cancer, Diagnosis, and Treatment. DOI: 10.7176/CEIS/12-1-03 Publication date: January 31 st 2021

Hedge algebras-based admittance controller for safe natural human–robot interaction

ABSTRACT In physical human–robot interaction (pHRI), the identification of inertia and damping matrices in the dynamic admittance model is still an open problem. Besides, the natural interaction is rarely considered in previous studies while it is crucial to obtain the effective cooperation. To this end, a fuzzy-based admittance controller is presented, in which the end-effector's velocity is adaptively adjusted via the external wrench and transmitted power without the identification of inertia and damping matrices. Besides, this fuzzy-based admittance controller also guarantees the natural cooperation between human and robot. Unfortunately, there is no formulated linkage of the fuzzy sets with the natural linguistic term semantics. As a consequence, human experts must utilize the order relationships between the terms of interest when formulating the fuzzy rule-based knowledge of the fuzzy controller. This paper presents an alternative admittance controller for pHRI based on an algebraic approach to linguistic hedges in fuzzy logic to overcome the existing shortcomings of previous admittance controllers. In addition, this paper also considers end-effector's full degree of freedom to guarantee the natural human–robot interaction. The proposed admittance controller is experimentally evaluated on a teaching task set-up using 6-DOF manipulator.

Digital Twin of the Distributed Generation Plant

This article describes the concept of building a digital twin of the distributed generation (DG) plant operating on based on a synchronous generator with a fuzzy auto-tuning unit for automatic voltage regulator and automatic speed regulator. The structure of the digital twin is represented as a hierarchal fuzzy model built using experimental data. Programmatically implemented algorithms for optimization of term aggregations membership functions and numerals from knowledge base rules. The results of experiments on obtaining an optimized neuro-fuzzy model for regulating the generator rotor frequency are presented. The proposed algorithms can be used in further research on the construction of a digital twin of the DG plant, as well as for solving the problem of automatic regulators tuning.

Performance advancements of fuzzy controllers over conventional controllers carried out in matlab simulation environment

In this paper, we are used routine three term PID controller, fuzzy PID controller and FPI plus FPD controllers to test the performance characteristics of DC servo motor, modulus non-linear systems and square root nonlinear systems in MATLAB SIMULINK environment. We have developed analytical structures for fuzzy PID and FPI plus FPD controllers with the help of fuzzification, knowledge rule base and defuzzification methods. Simulation results are carried out and show the advancement of fuzzy controllers over conventional controllers in specificatons of rise time, delay time and settling time for DC servo motor, modulus and square root types of non-linear systems. Out of these three types of controllers, the experimental results conclude that the combination of FPI plus FPD controller gives the better results.

A Neural State Pushdown Automata

To learn complex formal grammars, recurrent neural networks (RNNs) require sufficient computational resources to ensure correct grammar recognition. One approach to expand model capacity is to couple an RNN to an external stack memory. Here, we introduce a “neural state” pushdown automaton (NSPDA), which consists of a discrete stack instead of an continuous one and is coupled to a neural network state machine. We empirically show its effectiveness in recognizing various context-free grammars (CFGs). First, we develop the underlying mechanics of the proposed higher order recurrent network and its manipulation of a stack as well as how to stably program its underlying pushdown automaton (PDA). We also introduce a noise regularization scheme for higher-order (tensor) networks and design an algorithm for improved incremental learning. Finally, we design a method for inserting grammar rules into a NSPDA and empirically show that this prior knowledge improves its training convergence time by an order of magnitude and, in some cases, leads to better generalization. The NSPDA is also compared to a classical analog stack neural network pushdown automaton (NNPDA) as well as a wide array of first and second-order RNNs with and without external memory, trained using different learning algorithms. Our results show that for the Dyck languages, prior rule-based knowledge is critical for optimization convergence and for ensuring generalization to longer sequences at test time. We observe that many RNNs with and without memory, but no prior knowledge, struggle to converge and generalize on complex and longer CFGs.

Visual Experience-Based Question Answering with Complex Multimodal Environments

This paper proposes a novel visual experience-based question answering problem (VEQA) and the corresponding dataset for embodied intelligence research that requires an agent to do actions, understand 3D scenes from successive partial input images, and answer natural language questions about its visual experiences in real time. Unlike the conventional visual question answering (VQA), the VEQA problem assumes both partial observability and dynamics of a complex multimodal environment. To address this VEQA problem, we propose a hybrid visual question answering system, VQAS, integrating a deep neural network-based scene graph generation model and a rule-based knowledge reasoning system. The proposed system can generate more accurate scene graphs for dynamic environments with some uncertainty. Moreover, it can answer complex questions through knowledge reasoning with rich background knowledge. Results of experiments using a photo-realistic 3D simulated environment, AI2-THOR, and the VEQA benchmark dataset prove the high performance of the proposed system.

Definition of Phishing Sites Based on the Team Model of Fuzzy Neural Networks

This paper solves the problem of defining phishing sites based on building a team model of fuzzy neural networks (FNNs). The main methods of phishing are analyzed. Attention is drawn to the fact that phishing has become widespread on the Internet through the use of phishing sites. The expediency of identifying phishing sites based on the analysis of their URLs is noted. The main approaches to identifying phishing sites are described. The need toimplement an approach based on machine learning by constructing fuzzy neural networks for the creation of fuzzy knowledge bases and their use to identify phishing sites is actualized. Automating the identification of phishing sites based on the neuro-fuzzy approach required solving the problems of collecting and preparing initial data for analysis,building a team model of fuzzy neural networks, and forming a fuzzy knowledge base, as well as conducting research, and assessing the accuracy of identifying phishing sites based on the constructed model. The initial data was formed from various sources. The total amount of initial data was 50,000. Of these, 10 input features for analysis were selected by an expert. After carrying out the correlation analysis, 4 most informative input features were selected for analysis: site lifetime, site rank, URL length, and the registered status of the site. An output feature of the site was its type: phishing or legitimate. After assessing the quality and cleaning the selected data, the resulting sample was formed of 34718 rows, of which 70% were used for learning (24303 rows), and 30% (10415 rows) for testing. A team model offuzzy neural networks was built and a knowledge base was formed on the basis of the data obtained, including 4608 fuzzy rules. Studies have shown that the number of errors of the 1st type in identifying phishing sites is 2.01%, and 2.89% for errors of the 2nd type. The general classification error based on knowledge base rules is 4.9%. The accuracy of identifying phishing sites was 95.1%, which exceeds the accuracy of other classification methods: multilayer neural network, decision tree, linear and logistic regression. The knowledge base formed on the basis of the team model of fuzzy neural networks can be effectively used to identify phishing sites on the Internet.

Research on Fault Monitoring Technology of Distribution Network Based on Fuzzy Association Rules Mining

In order to monitor the operation status of distribution network in real time and ensure the security and stability of distribution internet of things, a fault monitoring method based on fuzzy association rule mining was proposed. Fuzzy association rules mining was used to build the normal state parameter model of distribution network. The degree of interest index replaced the traditional index, aiming to improve the association degree between the rule parameters and form an effective expert knowledge base. According to the rules in the expert knowledge base, the normal state data of distribution network were obtained by fuzzy reasoning. Further, the state similarity function between the monitoring states and the normal states was used as the state judgement index. When the similarity is lower than the threshold, the fault alert should be triggered. Taking the single-phase ground fault data of distribution network simulated by MATLAB Simulink as an example, it was verified that the proposed method can effectively monitor the single-phase ground fault.

Exploration of Outliers in If-Then Rule-Based Knowledge Bases.

The article presents both methods of clustering and outlier detection in complex data, such as rule-based knowledge bases. What distinguishes this work from others is, first, the application of clustering algorithms to rules in domain knowledge bases, and secondly, the use of outlier detection algorithms to detect unusual rules in knowledge bases. The aim of the paper is the analysis of using four algorithms for outlier detection in rule-based knowledge bases: Local Outlier Factor (), Connectivity-based Outlier Factor (), K-, and . The subject of outlier mining is very important nowadays. Outliers in rules If-Then mean unusual rules, which are rare in comparing to others and should be explored by the domain expert as soon as possible. In the research, the authors use the outlier detection methods to find a given number of outliers in rules (, , ), while in small groups, the number of outliers covers no more than of the rule cluster. Subsequently, the authors analyze which of seven various quality indices, which they use for all rules and after removing selected outliers, improve the quality of rule clusters. In the experimental stage, the authors use six different knowledge bases. The best results (the most often the clusters quality was improved) are achieved for two outlier detection algorithms and .