scholarly journals Knowledge Modeling in Troubleshooting

2021 ◽  
Vol 31 (3) ◽  
pp. 364-379
Author(s):  
Valeriy P. Dimitrov ◽  
Lyudmila V. Borisova
Keyword(s):  
Knowledge Base ◽  
Domain Knowledge ◽  
Expert Knowledge ◽  
Knowledge Modeling ◽  
Optimal Sequence ◽  
Intelligent Information Systems ◽  
Electric Equipment ◽  
Function Table ◽  
Intelligent Information ◽  
Combine Harvesters

Introduction. The article describes the approach to solving the problem of complex technical system troubleshooting based on expert knowledge modeling. Intelligent information systems are widely used to solve the problems of diagnostics of multilevel systems including combine harvesters. The formal description of the subject domain knowledge is the framework for building the knowledge base of these systems. The sequence of creating an expert system knowledge base in accordance with production rules is considered. Materials and Methods. The approach is founded on the fault function table. As the object of diagnostics, one of the subsystems of the combine harvester electric equipment “opening the hopper roof flaps” is considered. The basis for constructing a sequence of elementary checks is a system of logical equations describing both the serviceable and possible faulty states of the subsystem. Results. A structural logic model is developed. As a result of analyzing the fault function table, the sets of elementary checks are determined. Four criteria have been used to analyze the weight of these checks. The authors have determined optimal sequence of checks and have developed a decision tree, which allows finding the cause of the malfunction and is the basis for creating the knowledge base of an intelligent information system. A fragment of the knowledge base is given. Discussion and Conclusion. The proposed approach of expert knowledge modelling increases the efficiency of the unit for troubleshooting of the intelligent decision support system. It makes possible to structure the base of expertise and establishing the optimal sequence of elementary checks. This allows determining the optimal sequence of application of the knowledge base production rule that makes it possible to reduce the time of restoring the serviceability of combines.

scholarly journals The conceptual model of agroecological properties of land. Methods

2020 ◽  
Vol 50 (5) ◽  
pp. 77-86
Author(s):  
V. K. Kalichkin ◽  
R. A. Koryakin ◽  
K. Yu. Maksimovich ◽  
R. R. Galimov
Keyword(s):  
Conceptual Model ◽  
Domain Knowledge ◽  
Farming Systems ◽  
Adaptive Landscape ◽  
Intelligent Information Systems ◽  
Logical Language ◽  
Input Dataset ◽  
Mathematical Formulas ◽  
Intelligent Information ◽  
The Given

To solve the problem of automating the agroecological land estimation (natural resource potential) and creating intelligent information systems for their further programming, the necessary stage is the conceptualization of the domain knowledge (DK), or conceptual modelling. In this work, the conceptual model of DK “Agroecological properties of land”, developed on the basis of the abstract logical language UML and proposed in the previous part of the series of articles by the authors, is supplemented by the type of abstract objects “method”. The methods in UML reflect the types of relationships between data of various nature and are designed to distinguish the ways with which it is possible to fill in the missing data and information when solving practical problems in the framework of designing and building adaptive landscape farming systems. UML methods are considered for one of DK abstract classes – class “Relief”. In this class, 31 groups of input datasets and 23 groups of output datasets are suggested. All 54 datasets are based on the "method – attribute" connection that operate within this class or by abstract relationships between classes previously built into the conceptual model. This means that a class method as an abstract object defines a set of dependencies between data associated with the given class attributes, as input dataset, and data associated with the given or related class attributes, as output dataset. The elements of such set of dependencies can be deterministic or stochastic algorithms, statistical and other data processing methods, data analysis and artificial intelligence methods, as well as specific mathematical formulas. The technology of building a knowledge base by UML methods of class “Relief” is shown, containing 713 groups of UML methods classified by seven types, and also examples of UML methods of three different types are given.

Knowledge Base Refinement Using Limited Amount of Efforts from Experts

2014 ◽  
Vol 4 (2) ◽  
pp. 1-19 ◽  
Author(s):  
Ki Chan ◽  
Wai Lam ◽  
Tak-Lam Wong
Keyword(s):  
Knowledge Base ◽  
Domain Knowledge ◽  
Pattern Mining ◽  
Knowledge Bases ◽  
Target Domain ◽  
Markov Logic ◽  
Source Domain ◽  
Construction Of Knowledge ◽  
Knowledge Base Refinement ◽  
Intelligent Information

Knowledge bases are essential for supporting decision making during intelligent information processing. Automatic construction of knowledge bases becomes infeasible without labeled data, a complete table of data records including answers to queries. Preparing such information requires huge efforts from experts. The authors propose a new knowledge base refinement framework based on pattern mining and active learning using an existing available knowledge base constructed from a different domain (source domain) solving the same task as well as some data collected from the target domain. The knowledge base investigated in this paper is represented by a model known as Markov Logic Networks. The authors' proposed method first analyzes the unlabeled target domain data and actively asks the expert to provide labels (or answers) a very small amount of automatically selected queries. The idea is to identify the target domain queries whose underlying relations are not sufficiently described by the existing source domain knowledge base. Potential relational patterns are discovered and new logic relations are constructed for the target domain by exploiting the limited amount of labeled target domain data and the unlabeled target domain data. The authors have conducted extensive experiments by applying our approach to two different text mining applications, namely, pronoun resolution and segmentation of citation records, demonstrating consistent improvements.

The Central Role of Cognitive Computations in Human-Information Interaction

2018 ◽  
Author(s):  
Wai-Tat Fu ◽  
Jessie Chin ◽  
Q. Vera Liao
Keyword(s):  
Information Systems ◽  
Cognitive Science ◽  
Intelligent Systems ◽  
Intelligent System ◽  
Levels Of Abstraction ◽  
Intelligent Information Systems ◽  
Emergent Behaviour ◽  
Information Interaction ◽  
Intelligent Information

Cognitive science is a science of intelligent systems. This chapter proposes that cognitive science can provide useful perspectives for research on technology-mediated human-information interaction (HII) when HII is cast as emergent behaviour of a coupled intelligent system. It starts with a review of a few foundational concepts related to cognitive computations and how they can be applied to understand the nature of HII. It discusses several important properties of a coupled cognitive system and their implication to designs of information systems. Finally, it covers how levels of abstraction have been useful for cognitive science, and how these levels can inform design of intelligent information systems that are more compatible with human cognitive computations.

scholarly journals Templated Text Synthesis for Expert-Guided Multi-Label Extraction from Radiology Reports

2021 ◽  
Vol 3 (2) ◽  
pp. 299-317
Author(s):  
Patrick Schrempf ◽  
Hannah Watson ◽  
Eunsoo Park ◽  
Maciej Pajak ◽  
Hamish MacKinnon ◽  
...  
Keyword(s):  
Domain Knowledge ◽  
Expert Knowledge ◽  
Medical Image Analysis ◽  
Imaging Data ◽  
Data Synthesis ◽  
Domain Specific ◽  
Radiology Reports ◽  
Training Examples ◽  
Analysis Models ◽  
Difficult Cases

Training medical image analysis models traditionally requires large amounts of expertly annotated imaging data which is time-consuming and expensive to obtain. One solution is to automatically extract scan-level labels from radiology reports. Previously, we showed that, by extending BERT with a per-label attention mechanism, we can train a single model to perform automatic extraction of many labels in parallel. However, if we rely on pure data-driven learning, the model sometimes fails to learn critical features or learns the correct answer via simplistic heuristics (e.g., that “likely” indicates positivity), and thus fails to generalise to rarer cases which have not been learned or where the heuristics break down (e.g., “likely represents prominent VR space or lacunar infarct” which indicates uncertainty over two differential diagnoses). In this work, we propose template creation for data synthesis, which enables us to inject expert knowledge about unseen entities from medical ontologies, and to teach the model rules on how to label difficult cases, by producing relevant training examples. Using this technique alongside domain-specific pre-training for our underlying BERT architecture i.e., PubMedBERT, we improve F1 micro from 0.903 to 0.939 and F1 macro from 0.512 to 0.737 on an independent test set for 33 labels in head CT reports for stroke patients. Our methodology offers a practical way to combine domain knowledge with machine learning for text classification tasks.

Robust methods in analysis of natural language data

2002 ◽  
Vol 8 (2-3) ◽  
pp. 93-96
Author(s):  
AFZAL BALLIM ◽  
VINCENZO PALLOTTA
Keyword(s):  
Information Systems ◽  
Natural Language ◽  
Automated Analysis ◽  
Approximate Analysis ◽  
Robust Methods ◽  
Analysis Techniques ◽  
Intelligent Information Systems ◽  
Recent Interest ◽  
Language Data ◽  
Intelligent Information

The automated analysis of natural language data has become a central issue in the design of intelligent information systems. Processing unconstrained natural language data is still considered as an AI-hard task. However, various analysis techniques have been proposed to address specific aspects of natural language. In particular, recent interest has been focused on providing approximate analysis techniques, assuming that when perfect analysis is not possible, partial results may be still very useful.

scholarly journals Practices and applications in ambient and intelligent information systems

2017 ◽  
Vol 21 (6) ◽  
pp. 1039-1040
Author(s):  
Quan Z. Sheng ◽  
Wei Emma Zhang ◽  
Elhadi Shakshuki
Keyword(s):  
Information Systems ◽  
Intelligent Information Systems ◽  
Intelligent Information
Sign in / Sign up

Export Citation Format

Share Document