CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A Novel Explainable Belief Rule-Based Prediction Framework under Uncertainty
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.ORCID iD: 0000-0001-5283-6641
2024 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Traditional Machine Learning (ML) and Deep Learning (DL) models provide very accurate predictions because of their intricate mathematical operations. However, these models do not explain the reasons in support of the predictive outputs. Therefore, there is no trust between humans and AI when it produces such obtuse results. The widespread adoption of AI models heavily relies on the trust that humans place in the decisions made by AI. This trust holds great importance in safety-critical sectors like healthcare, autonomous vehicles, and the energy domain. Several post-hoc tools can help elucidate the results of AI models. The use of training datasets rather than domain knowledge renders such an explanation as a proxy. A misleading explanation will be produced by a biased training dataset. In contrast, an end user is more likely to believe an explanation that is grounded in domain knowledge. Motivated by this, we propose a novel framework, consisting of Belief Rule Based Expert System (BRBES), to predict output and explain it with reference to domain knowledge. BRBES effectively utilizes its rule base to represent domain knowledge and adeptly handles uncertainty resulting from a lack of information. We also fine-tune the parameters and structure of BRBES to enhance the accuracy of the prediction. Therefore, the output of our proposed framework is not only accurate, but also easily explainable.

This licentiate thesis delves into the challenges and opportunities surrounding eXplainable ArtificialIntelligence (XAI) in order to provide a comprehensive understanding of AI output. It presents a new XAI framework that can effectively predict an output and provide explanations based on domain knowledge. In addition, it shows how effective BRBES integration can be by integrating it with a deep learning model to forecast air quality phenomenon using ground and satellite data.

This thesis presents four significant contributions. First, we conduct a comprehensive examination ofthe existing literature on XAI, delving into the numerous challenges and opportunities it offers. Extensive research has been conducted to explore the definition, classification, and practical use of XAI. In addition, this complex study highlights the significance of the user interface in effectively communicating explanations in a way that is comprehensible to humans. It also brings up the tradeoff between explainability and accuracy in XAI. Secondly, we present an innovative explainable BRBES (eBRBES) model that offers accurate predictions of building energy consumption phenomenon while providing insightful explanations based on domain knowledge. As part of eBRBES, we also present a novel Belief Rule Based adaptive Balance Determination (BRBaBD) algorithm to assess the optimal balance between explainability and accuracy. Thirdly, we propose a mathematical model to integrate BRBES with the Convolutional Neural Network (CNN). We leverage the domain knowledge of BRBES, and hidden data patterns discovered by CNN with this integrated approach. We predict air quality withthis integrated model using outdoor ground images and sensor data. Fourth, we integrate two-layer BRBES with CNN to monitor air quality using satellite images, and relevant environmental parameters, such as cloud, relative humidity, temperature, and wind speed. The two-layer BRBES showcases the strength of BRBES in conducting reasoning across multiple layers.

Based on the research findings of this thesis applied on two different phenomena, it can be argued that utilizing a belief rule-based framework can enhance predictability with greater clarity and precision. 

Place, publisher, year, edition, pages
Luleå: Luleå University of Technology, 2024.
Series
Licentiate thesis / Luleå University of Technology, ISSN 1402-1757
National Category
Computer Sciences
Research subject
Pervasive Mobile Computing
Identifiers
URN: urn:nbn:se:ltu:diva-105200ISBN: 978-91-8048-554-8 (print)ISBN: 978-91-8048-555-5 (electronic)OAI: oai:DiVA.org:ltu-105200DiVA, id: diva2:1854201
Presentation
2024-06-20, A193, Luleå University of Technology, Skellefteå, 09:00 (English)
Opponent
Supervisors
Funder
Vinnova, 2022-01188
Note

Funder: Rönnbäret Foundation, Sweden

Available from: 2024-04-24 Created: 2024-04-24 Last updated: 2024-05-30Bibliographically approved
List of papers
1. An Advanced Explainable Belief Rule-Based Framework to Predict the Energy Consumption of Buildings
Open this publication in new window or tab >>An Advanced Explainable Belief Rule-Based Framework to Predict the Energy Consumption of Buildings
2024 (English)In: Energies, E-ISSN 1996-1073, Vol. 17, no 8, article id 1797Article in journal (Refereed) Published
Abstract [en]

The prediction of building energy consumption is beneficial to utility companies, users, and facility managers to reduce energy waste. However, due to various drawbacks of prediction algorithms, such as, non-transparent output, ad hoc explanation by post hoc tools, low accuracy, and the inability to deal with data uncertainties, such prediction has limited applicability in this domain. As a result, domain knowledge-based explainability with high accuracy is critical for making energy predictions trustworthy. Motivated by this, we propose an advanced explainable Belief Rule-Based Expert System (eBRBES) with domain knowledge-based explanations for the accurate prediction of energy consumption. We optimize BRBES’s parameters and structure to improve prediction accuracy while dealing with data uncertainties using its inference engine. To predict energy consumption, we take into account floor area, daylight, indoor occupancy, and building heating method. We also describe how a counterfactual output on energy consumption could have been achieved. Furthermore, we propose a novel Belief Rule-Based adaptive Balance Determination (BRBaBD) algorithm for determining the optimal balance between explainability and accuracy. To validate the proposed eBRBES framework, a case study based on Skellefteå, Sweden, is used. BRBaBD results show that our proposed eBRBES framework outperforms state-of-the-art machine learning algorithms in terms of optimal balance between explainability and accuracy by 85.08%.

Place, publisher, year, edition, pages
MDPI, 2024
Keywords
accuracy, building energy, explainability, trust, uncertainties
National Category
Computer Sciences
Research subject
Cyber Security; Pervasive Mobile Computing
Identifiers
urn:nbn:se:ltu:diva-105059 (URN)10.3390/en17081797 (DOI)
Funder
Vinnova, 2022-01188
Note

Validerad;2024;Nivå 2;2024-04-11 (signyg);

Full text license: CC BY

Available from: 2024-04-11 Created: 2024-04-11 Last updated: 2024-04-24Bibliographically approved
2. An Integrated Approach of Belief Rule Base and Deep Learning to Predict Air Pollution
Open this publication in new window or tab >>An Integrated Approach of Belief Rule Base and Deep Learning to Predict Air Pollution
2020 (English)In: Sensors, E-ISSN 1424-8220, Vol. 20, no 7, p. 1-25, article id 1956Article in journal (Refereed) Published
Abstract [en]

Sensor data are gaining increasing global attention due to the advent of Internet of Things (IoT). Reasoning is applied on such sensor data in order to compute prediction. Generating a health warning that is based on prediction of atmospheric pollution, planning timely evacuation of people from vulnerable areas with respect to prediction of natural disasters, etc., are the use cases of sensor data stream where prediction is vital to protect people and assets. Thus, prediction accuracy is of paramount importance to take preventive steps and avert any untoward situation. Uncertainties of sensor data is a severe factor which hampers prediction accuracy. Belief Rule Based Expert System (BRBES), a knowledge-driven approach, is a widely employed prediction algorithm to deal with such uncertainties based on knowledge base and inference engine. In connection with handling uncertainties, it offers higher accuracy than other such knowledge-driven techniques, e.g., fuzzy logic and Bayesian probability theory. Contrarily, Deep Learning is a data-driven technique, which constitutes a part of Artificial Intelligence (AI). By applying analytics on huge amount of data, Deep Learning learns the hidden representation of data. Thus, Deep Learning can infer prediction by reasoning over available data, such as historical data and sensor data streams. Combined application of BRBES and Deep Learning can compute prediction with improved accuracy by addressing sensor data uncertainties while utilizing its discovered data pattern. Hence, this paper proposes a novel predictive model that is based on the integrated approach of BRBES and Deep Learning. The uniqueness of this model lies in the development of a mathematical model to combine Deep Learning with BRBES and capture the nonlinear dependencies among the relevant variables. We optimized BRBES further by applying parameter and structure optimization on it. Air pollution prediction has been taken as use case of our proposed combined approach. This model has been evaluated against two different datasets. One dataset contains synthetic images with a corresponding label of PM2.5 concentrations. The other one contains real images, PM2.5 concentrations, and numerical weather data of Shanghai, China. We also distinguished a hazy image between polluted air and fog through our proposed model. Our approach has outperformed only BRBES and only Deep Learning in terms of prediction accuracy.

Place, publisher, year, edition, pages
Basel, Switzerland: MDPI, 2020
Keywords
BRBES, Deep Learning, integration, sensor data, predict
National Category
Computer Sciences Media and Communication Technology
Research subject
Pervasive Mobile Computing
Identifiers
urn:nbn:se:ltu:diva-78258 (URN)10.3390/s20071956 (DOI)000537110500152 ()32244380 (PubMedID)2-s2.0-85083042302 (Scopus ID)
Projects
A belief-rule-based DSS to assess flood risks by using wireless sensor networksPERvasive Computing and COMmunications for sustainable development
Funder
Swedish Research Council, 2014-4251
Note

Validerad;2020;Nivå 2;2020-04-01 (cisjan)

Available from: 2020-03-31 Created: 2020-03-31 Last updated: 2024-04-24Bibliographically approved
3. An Integrated Approach of Belief Rule Base and Convolutional Neural Network to Monitor Air Quality in Shanghai
Open this publication in new window or tab >>An Integrated Approach of Belief Rule Base and Convolutional Neural Network to Monitor Air Quality in Shanghai
2022 (English)In: Expert systems with applications, ISSN 0957-4174, E-ISSN 1873-6793, Vol. 206, article id 117905Article in journal (Refereed) Published
Abstract [en]

Accurate monitoring of air quality can reduce its adverse impact on earth. Ground-level sensors can provide fine particulate matter (PM2.5) concentrations and ground images. But, such sensors have limited spatial coverage and require deployment cost. PM2.5 can be estimated from satellite-retrieved Aerosol Optical Depth (AOD) too. However, AOD is subject to uncertainties associated with its retrieval algorithms and constrain the spatial resolution of estimated PM2.5. AOD is not retrievable under cloudy weather as well. In contrast, satellite images provide continuous spatial coverage with no separate deployment cost. Accuracy of monitoring from such satellite images is hindered due to uncertainties of sensor data of relevant enviromental parameters, such as, relative humidity, temperature, wind speed and wind direction . Belief Rule Based Expert System (BRBES) is an efficient algorithm to address these uncertainties. Convolutional Neural Network (CNN) is suitable for image analytics. Hence, we propose a novel model by integrating CNN with BRBES to monitor air quality from satellite images with improved accuracy. We customized CNN and optimized BRBES to increase monitoring accuracy further. An obscure image has been differentiated between polluted air and cloud in our model. Valid environmental data (temperature, wind speed and wind direction) have been adopted to further strengthen the monitoring performance of our proposed model. Three-year observation data (satellite images and environmental parameters) from 2014 to 2016 of Shanghai have been employed to analyze and design our proposed model. The results conclude that the accuracy of our model to monitor PM2.5 of Shanghai is higher than only CNN and other conventional Machine Learning methods. Real-time validation of our model on near real-time satellite images of April-2021 of Shanghai shows average difference between our calculated PM2.5 concentrations and the actual one within ±5.51.

Place, publisher, year, edition, pages
Elsevier, 2022
Keywords
Air quality monitoring, Belief Rule Based Expert System (BRBES), Convolutional Neural Network (CNN), Uncertainty
National Category
Environmental Sciences Other Computer and Information Science Computer Sciences
Research subject
Pervasive Mobile Computing
Identifiers
urn:nbn:se:ltu:diva-91874 (URN)10.1016/j.eswa.2022.117905 (DOI)000832953800008 ()2-s2.0-85132745326 (Scopus ID)
Note

Validerad;2022;Nivå 2;2022-07-05 (joosat);

Available from: 2022-06-23 Created: 2022-06-23 Last updated: 2024-04-24Bibliographically approved

Open Access in DiVA

fulltext(463 kB)41 downloads
File information
File name FULLTEXT01.pdfFile size 463 kBChecksum SHA-512
d279597baa6f2dd6d702063e604ca3f7b9bc74f7efdde5a1ad4c57a506543424ecb83bd598dd1faddc869bfd80f416e1366011daa31921268bbb66bb829c09c4
Type fulltextMimetype application/pdf
The full text will be freely available from 2025-11-30 12:00
Available from 2025-11-30 12:00

Authority records

Kabir, Sami

Search in DiVA

By author/editor
Kabir, Sami
By organisation
Computer Science
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 41 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 501 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf