https://www.mdu.se/

mdu.sePublications
Change search
Link to record
Permanent link

Direct link
Ahmed, Mobyen Uddin, DrORCID iD iconorcid.org/0000-0003-3802-4721
Alternative names
Biography [swe]

Mobyen Uddin Ahmed is Senior Lecturer/Assistant Professor in Computer Science and Artificial Intelligence at Artificial Intelligence and Intelligent Systems and a member of ESS-H - Embedded Sensor Systems for Health Research Profile. Mobyen has 100+ scientific publication and more than 1173 citations.

He is involved in research and development since 2005 after completing his M.Sc. in Computer Engineering (thesis) from Dalarna University, Sweden. He received his PhD (thesis) in computer science in 2011 from Mälardalen University. He has completed one postdoctoral study between the years 2012 and 2014 in Computer Science and Engineering (Center for Applied Autonomous Sensor Systems) at School of Science and Technology, Örebro University, Sweden

To mention some courses those, I am involved in teaching: Applied Artificial Intelligence, Project in intelligent embedded systemsMachine Learning With Big Data (a distance course for industrial professionals), Databases, Deep learning for industrial imaging (comming), Predictive analytics (comming) etc.

Publications (10 of 142) Show all publications
D'Cruze, R. S., Ahmed, M. U., Bengtsson, M., Rehman, A. U., Funk, P. & Sohlberg, R. (2024). A Case Study on Ontology Development for AI Based Decision Systems in Industry. In: Lecture Notes in Mechanical Engineering: . Paper presented at 7th International Congress and Workshop on Industrial AI and eMaintenance, IAI 2023, Luleå, Sweden, 13 June 2023 through 15 June 2023 (pp. 693-706). Springer Science and Business Media Deutschland GmbH
Open this publication in new window or tab >>A Case Study on Ontology Development for AI Based Decision Systems in Industry
Show others...
2024 (English)In: Lecture Notes in Mechanical Engineering, Springer Science and Business Media Deutschland GmbH , 2024, p. 693-706Conference paper, Published paper (Refereed)
Abstract [en]

Ontology development plays a vital role as it provides a structured way to represent and organize knowledge. It has the potential to connect and integrate data from different sources, enabling a new class of AI-based services and systems such as decision support systems and recommender systems. However, in large manufacturing industries, the development of such ontology can be challenging. This paper presents a use case of an application ontology development based on machine breakdown work orders coming from a Computerized Maintenance Management System (CMMS). Here, the ontology is developed using a Knowledge Meta Process: Methodology for Ontology-based Knowledge Management. This ontology development methodology involves steps such as feasibility study, requirement specification, identifying relevant concepts and relationships, selecting appropriate ontology languages and tools, and evaluating the resulting ontology. Additionally, this ontology is developed using an iterative process and in close collaboration with domain experts, which can help to ensure that the resulting ontology is accurate, complete, and useful for the intended application. The developed ontology can be shared and reused across different AI systems within the organization, facilitating interoperability and collaboration between them. Overall, having a well-defined ontology is critical for enabling AI systems to effectively process and understand information.

Place, publisher, year, edition, pages
Springer Science and Business Media Deutschland GmbH, 2024
Keywords
Custom NER, Industrial AI, Machine failures prediction, Ontology development, Artificial intelligence, Decision support systems, Interoperability, Iterative methods, Knowledge management, AI systems, Case-studies, Decision systems, Failures prediction, Machine failure, Machine failure prediction, Ontology's, Ontology
National Category
Computer Sciences
Identifiers
urn:nbn:se:mdh:diva-65369 (URN)10.1007/978-3-031-39619-9_51 (DOI)2-s2.0-85181980940 (Scopus ID)9783031396182 (ISBN)
Conference
7th International Congress and Workshop on Industrial AI and eMaintenance, IAI 2023, Luleå, Sweden, 13 June 2023 through 15 June 2023
Available from: 2024-01-17 Created: 2024-01-17 Last updated: 2024-01-17Bibliographically approved
Begum, S. & Ahmed, M. U. (2024). Artificial Intelligence in Predictive Maintenance: A Systematic Literature Review on Review Papers. In: Lecture Notes in Mechanical Engineering: . Paper presented at 7th International Congress and Workshop on Industrial AI and eMaintenance, IAI 2023, Luleå, Sweden, 13 June 2023 through 15 June 2023 (pp. 251-261). Springer Science and Business Media Deutschland GmbH
Open this publication in new window or tab >>Artificial Intelligence in Predictive Maintenance: A Systematic Literature Review on Review Papers
2024 (English)In: Lecture Notes in Mechanical Engineering, Springer Science and Business Media Deutschland GmbH , 2024, p. 251-261Conference paper, Published paper (Refereed)
Abstract [en]

The fourth industrial revolution, colloquially referred to as “industry 4.0”, has garnered substantial global attention in recent years. There, Artificial intelligence (AI) driven industrial intelligence has been increasingly deployed in predictive maintenance (PdM), emerging as a vital enabler of smart manufacturing and industry 4.0. Since in recent years the number of articles focusing on Artificial Intelligence (AI) in PdM is high a review on the available literature reviews in this domain would be useful for the future researchers who would like to advance the research in this area and also for the persons who would like to apply PdM in their application domains. Therefore, this study identifies the AI revolution in PdM and focuses on the next stages available in the literature reviews in this area by quality assessment of secondary study. A well-known structured review approach (Systematic Literature Review, or SLR) was employed to perform this tertiary study. In addition, the Scale for the Assessment of Narrative Review Articles (SANRA) approach for evaluating the quality of review papers has been employed to support a few of the research questions. Here, This tertiary study scrutinizes four crucial aspects of secondary articles: (1) their specific research domains, (2) the annual trends in the quantity, variety, and quality (3) a footsteps of top researchers, and (4) the research constraints that review articles face during the time frame of 2015 to 2022. The results show that the majority of the application areas are applied to the manufacturing industry. It also leads to the identification of the revolution of AI in PdM as well. Our final findings indicate that Dr. Cheng et al.’s (2022) review has emerged as the predominant source of information in this field. As newcomers or industrial practitioners, we can benefit greatly from following his insights. The final outcome is that there is a lack of progress in SLR formulation and in adding explainable or interpretive AI methodologies in secondary studies.

Place, publisher, year, edition, pages
Springer Science and Business Media Deutschland GmbH, 2024
Keywords
Artificial Intelligence, Predictive maintenance, Systematic literature review, Industry 4.0, Maintenance, Applications domains, Industrial revolutions, Literature reviews, Quality assessment, Review papers, Smart manufacturing, Structured review, Tertiary study
National Category
Other Engineering and Technologies
Identifiers
urn:nbn:se:mdh:diva-65371 (URN)10.1007/978-3-031-39619-9_18 (DOI)2-s2.0-85181976041 (Scopus ID)9783031396182 (ISBN)
Conference
7th International Congress and Workshop on Industrial AI and eMaintenance, IAI 2023, Luleå, Sweden, 13 June 2023 through 15 June 2023
Available from: 2024-01-17 Created: 2024-01-17 Last updated: 2024-02-26Bibliographically approved
Bengtsson, M., D'Cruze, R. S., Ahmed, M. U., Sakao, T., Funk, P. & Sohlberg, R. (2024). Combining Ontology and Large Language Models to Identify Recurring Machine Failures in Free-Text Fields. In: Advances in Transdisciplinary Engineering: . Paper presented at 9 April 2024 11th Swedish Production Symposium, SPS2024. Trollhattan. 23 April 2024 through 26 April 2024 (pp. 27-38). IOS Press BV, 52
Open this publication in new window or tab >>Combining Ontology and Large Language Models to Identify Recurring Machine Failures in Free-Text Fields
Show others...
2024 (English)In: Advances in Transdisciplinary Engineering, IOS Press BV , 2024, Vol. 52, p. 27-38Conference paper, Published paper (Refereed)
Abstract [en]

Companies must enhance total maintenance effectiveness to stay competitive, focusing on both digitalization and basic maintenance procedures. Digitalization offers technologies for data-driven decision-making, but many maintenance decisions still lack a factual basis. Prioritizing efficiency and effectiveness require analyzing equipment history, facilitated by using Computerized Maintenance Management Systems (CMMS). However, CMMS data often contains unstructured free-text, leading to manual analysis, which is resource-intensive and reactive, focusing on short time periods and specific equipment. Two approaches are available to solve the issue: minimizing free-text entries or using advanced methods for processing them. Free-text allows detailed descriptions but may lack completeness, while structured reporting aids automated analysis but may limit fault description richness. As knowledge and experience are vital assets for companies this research uses a hybrid approach by combining Natural Language Processing with domain specific ontology and Large Language Models to extract information from free-text entries, enabling the possibility of real-time analysis e.g., identifying recurring failure and knowledge sharing across global sites.

Place, publisher, year, edition, pages
IOS Press BV, 2024
Keywords
Artificial Intelligence, Experience Reuse, Industrial Maintenance, Large Language Models, Natural Language Processing, Computational linguistics, Decision making, Failure (mechanical), Natural language processing systems, Ontology, Computerized maintenance management system, Free texts, Language model, Language processing, Large language model, Natural languages, Text entry, Maintenance
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:mdh:diva-66565 (URN)10.3233/ATDE240151 (DOI)2-s2.0-85191305248 (Scopus ID)9781643685106 (ISBN)
Conference
9 April 2024 11th Swedish Production Symposium, SPS2024. Trollhattan. 23 April 2024 through 26 April 2024
Available from: 2024-05-14 Created: 2024-05-14 Last updated: 2024-05-14Bibliographically approved
Islam, M. R., Ahmed, M. U. & Begum, S. (2024). iXGB: improving the interpretability of XGBoost using decision rules and counterfactuals. In: Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART: . Paper presented at 16th International Conference on Agents and Artificial Intelligence (ICAART 2024) (pp. 1345-1353). , 3
Open this publication in new window or tab >>iXGB: improving the interpretability of XGBoost using decision rules and counterfactuals
2024 (English)In: Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, 2024, Vol. 3, p. 1345-1353Conference paper, Published paper (Other academic)
Abstract [en]

Tree-ensemble models, such as Extreme Gradient Boosting (XGBoost), are renowned Machine Learning models which have higher prediction accuracy compared to traditional tree-based models. This higher accuracy, however, comes at the cost of reduced interpretability. Also, the decision path or prediction rule of XGBoost is not explicit like the tree-based models. This paper proposes the iXGB--interpretable XGBoost, an approach to improve the interpretability of XGBoost. iXGB approximates a set of rules from the internal structure of XGBoost and the characteristics of the data. In addition, iXGB generates a set of counterfactuals from the neighbourhood of the test instances to support the understanding of the end-users on their operational relevance. The performance of iXGB in generating rule sets is evaluated with experiments on real and benchmark datasets which demonstrated reasonable interpretability. The evaluation result also supports that the interpretability of XGBoost can be improved without using surrogate methods.

Keywords
Counterfactuals, Explainability, Explainable Artificial Intelligence, Interpretability, Regression, Rule-based Explanation, XGBoost.
National Category
Computer Sciences
Identifiers
urn:nbn:se:mdh:diva-64916 (URN)10.5220/0012474000003636 (DOI)2-s2.0-85190810293 (Scopus ID)978-989-758-680-4 (ISBN)
Conference
16th International Conference on Agents and Artificial Intelligence (ICAART 2024)
Available from: 2023-11-30 Created: 2023-11-30 Last updated: 2024-05-08Bibliographically approved
Barua, A., Ahmed, M. U., Barua, S., Begum, S. & Giorgi, A. (2024). Second-Order Learning with Grounding Alignment: A Multimodal Reasoning Approach to Handle Unlabelled Data. In: International Conference on Agents and Artificial Intelligence: . Paper presented at 16th International Conference on Agents and Artificial Intelligence, ICAART 2024. Rome 24 February 2024 through 26 February 2024 (pp. 561-572). Science and Technology Publications, Lda, 2
Open this publication in new window or tab >>Second-Order Learning with Grounding Alignment: A Multimodal Reasoning Approach to Handle Unlabelled Data
Show others...
2024 (English)In: International Conference on Agents and Artificial Intelligence, Science and Technology Publications, Lda , 2024, Vol. 2, p. 561-572Conference paper, Published paper (Refereed)
Abstract [en]

Multimodal machine learning is a critical aspect in the development and advancement of AI systems. However, it encounters significant challenges while working with multimodal data, where one of the major issues is dealing with unlabelled multimodal data, which can hinder effective analysis. To address the challenge, this paper proposes a multimodal reasoning approach adopting second-order learning, incorporating grounding alignment and semi-supervised learning methods. The proposed approach illustrates using unlabelled vehicular telemetry data. During the process, features were extracted from unlabelled telemetry data using an autoencoder and then clustered and aligned with true labels of neurophysiological data to create labelled and unlabelled datasets. In the semi-supervised approach, the Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) algorithms are applied to the labelled dataset, achieving a test accuracy of over 97%. These algorithms are then used to predict labels for the unlabelled dataset, which is later added to the labelled dataset to retrain the model. With the additional prior labelled data, both algorithms achieved a 99% test accuracy. Confidence in predictions for unlabelled data was validated using counting samples based on the prediction score and Bayesian probability. RF and XGBoost scored 91.26% and 97.87% in counting samples and 98.67% and 99.77% in Bayesian probability, respectively.

Place, publisher, year, edition, pages
Science and Technology Publications, Lda, 2024
Keywords
Autoencoder, Multimodal Reasoning, Semi-Supervised, Supervised Alignment
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:mdh:diva-66579 (URN)10.5220/0012466500003636 (DOI)2-s2.0-85190658759 (Scopus ID)
Conference
16th International Conference on Agents and Artificial Intelligence, ICAART 2024. Rome 24 February 2024 through 26 February 2024
Available from: 2024-05-08 Created: 2024-05-08 Last updated: 2024-05-08Bibliographically approved
Barua, A., Ahmed, M. U. & Begum, S. (2023). A Systematic Literature Review on Multimodal Machine Learning: Applications, Challenges, Gaps and Future Directions. IEEE Access, 11, 14804-14831
Open this publication in new window or tab >>A Systematic Literature Review on Multimodal Machine Learning: Applications, Challenges, Gaps and Future Directions
2023 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 11, p. 14804-14831Article, review/survey (Refereed) Published
Abstract [en]

Multimodal machine learning (MML) is a tempting multidisciplinary research area where heterogeneous data from multiple modalities and machine learning (ML) are combined to solve critical problems. Usually, research works use data from a single modality, such as images, audio, text, and signals. However, real-world issues have become critical now, and handling them using multiple modalities of data instead of a single modality can significantly impact finding solutions. ML algorithms play an essential role in tuning parameters in developing MML models. This paper reviews recent advancements in the challenges of MML, namely: representation, translation, alignment, fusion and co-learning, and presents the gaps and challenges. A systematic literature review (SLR) was applied to define the progress and trends on those challenges in the MML domain. In total, 1032 articles were examined in this review to extract features like source, domain, application, modality, etc. This research article will help researchers understand the constant state of MML and navigate the selection of future research directions.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2023
Keywords
alignment, co-learning, fusion, Multimodal machine learning, representation, systematic literature review, translation, Machine learning applications, Machine-learning, Multi-disciplinary research, Multi-modal, Multiple modalities, Machine learning
National Category
Mechanical Engineering
Identifiers
urn:nbn:se:mdh:diva-62038 (URN)10.1109/ACCESS.2023.3243854 (DOI)000936312800001 ()2-s2.0-85149020788 (Scopus ID)
Available from: 2023-03-08 Created: 2023-03-08 Last updated: 2023-03-15Bibliographically approved
Rehman, A. U., Ahmed, M. U. & Begum, S. (2023). Cognitive Digital Twin in Manufacturing: A Heuristic Optimization Approach. In: IFIP Advances in Information and Communication Technology: . Paper presented at IFIP Advances in Information and Communication Technology (pp. 441-453). Springer Science and Business Media Deutschland GmbH
Open this publication in new window or tab >>Cognitive Digital Twin in Manufacturing: A Heuristic Optimization Approach
2023 (English)In: IFIP Advances in Information and Communication Technology, Springer Science and Business Media Deutschland GmbH , 2023, p. 441-453Conference paper, Published paper (Refereed)
Abstract [en]

Complex systems that link virtualization and simulation platforms with actual data from industrial processes are vital for the next generation of production. Digital twins are such systems that have several advantages, notably in manufacturing where they can boost productivity throughout the whole manufacturing life-cycle. Enterprises will be able to creatively, efficiently, and effectively leverage implicit information derived from the experience of current production processes, thanks to cognitive digital twins. The development of numerous technologies has made the digital twin notion more competent and sophisticated throughout time. This article proposes a heuristic approach for cognitive digital twin technology as the next development in a digital twin that will aid in the realization of the goal of Industry 4.0. In creating cognitive digital twins, this article suggests the use of a heuristic approach as a possible route to allowing cognitive functionalities. Here, heuristic optimization is proposed as a feature selection tool to enhance the cognitive capabilities of a digital twin throughout the product design phase of production. The proposed approach is validated using the use-case of Power Transfer Unit (PTU) production, which resulted in an improvement of 8.83% in classification accuracy to predict the faulty PTU in the assembly line. This leads to an improved throughput of the PTU assembly line and also saves the resources utilized by faulty PTUs.

Place, publisher, year, edition, pages
Springer Science and Business Media Deutschland GmbH, 2023
Keywords
Cognitive Digital Twins, Cyber-Physical Systems, Heuristic Optimization, Industrial Manufacturing, Assembly, Cognitive systems, Embedded systems, Energy transfer, Heuristic methods, Life cycle, Optimization, Product design, Simulation platform, Assembly line, Cognitive digital twin, Cybe-physical systems, Heuristics approaches, Optimization approach, Power transfer units, Virtualizations, Cyber Physical System
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:mdh:diva-64546 (URN)10.1007/978-3-031-34107-6_35 (DOI)2-s2.0-85173568013 (Scopus ID)9783031341069 (ISBN)
Conference
IFIP Advances in Information and Communication Technology
Available from: 2023-10-24 Created: 2023-10-24 Last updated: 2023-10-24Bibliographically approved
Jmoona, W., Ahmed, M. U., Islam, M. R., Barua, S., Begum, S., Ferreira, A. & Cavagnetto, N. (2023). Explaining the Unexplainable: Role of XAI for Flight Take-Off Time Delay Prediction. In: AIAI 2023. IFIP Advances in Information and Communication Technology, vol 676.: . Paper presented at 19th IFIP WG 12.5 International Conference, AIAI 2023 León, Spain, June 14–17, 2023 (pp. 81-93). Springer Science and Business Media Deutschland GmbH
Open this publication in new window or tab >>Explaining the Unexplainable: Role of XAI for Flight Take-Off Time Delay Prediction
Show others...
2023 (English)In: AIAI 2023. IFIP Advances in Information and Communication Technology, vol 676., Springer Science and Business Media Deutschland GmbH , 2023, p. 81-93Conference paper, Published paper (Refereed)
Abstract [en]

Flight Take-Off Time (TOT) delay prediction is essential to optimizing capacity-related tasks in Air Traffic Management (ATM) systems. Recently, the ATM domain has put afforded to predict TOT delays using machine learning (ML) algorithms, often seen as “black boxes”, therefore it is difficult for air traffic controllers (ATCOs) to understand how the algorithms have made this decision. Hence, the ATCOs are reluctant to trust the decisions or predictions provided by the algorithms. This research paper explores the use of explainable artificial intelligence (XAI) in explaining flight TOT delay to ATCOs predicted by ML-based predictive models. Here, three post hoc explanation methods are employed to explain the models’ predictions. Quantitative and user evaluations are conducted to assess the acceptability and usability of the XAI methods in explaining the predictions to ATCOs. The results show that the post hoc methods can successfully mimic the inference mechanism and explain the models’ individual predictions. The user evaluation reveals that user-centric explanation is more usable and preferred by ATCOs. These findings demonstrate the potential of XAI to improve the transparency and interpretability of ML models in the ATM domain.

Place, publisher, year, edition, pages
Springer Science and Business Media Deutschland GmbH, 2023
Keywords
Air Traffic Management, DALEX, Explainable Artificial Intelligence, Flight Take-off Time Delay Prediction, LIME, SHAP, Advanced traffic management systems, Air traffic control, Forecasting, Machine learning, Timing circuits, Air traffic controller, Flight take off, Management domains, Take off time, Time-delay predictions, Time delay
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:mdh:diva-64550 (URN)10.1007/978-3-031-34107-6_7 (DOI)2-s2.0-85173565890 (Scopus ID)9783031341069 (ISBN)
Conference
19th IFIP WG 12.5 International Conference, AIAI 2023 León, Spain, June 14–17, 2023
Available from: 2023-10-24 Created: 2023-10-24 Last updated: 2024-02-29Bibliographically approved
Islam, M. R., Ahmed, M. U. & Begum, S. (2023). Interpretable Machine Learning for Modelling and Explaining Car Drivers' Behaviour: An Exploratory Analysis on Heterogeneous Data. In: : . Paper presented at 15th International Conference on Agents and Artificial Intelligence (ICAART 2023).
Open this publication in new window or tab >>Interpretable Machine Learning for Modelling and Explaining Car Drivers' Behaviour: An Exploratory Analysis on Heterogeneous Data
2023 (English)Conference paper, Published paper (Refereed)
Abstract [en]

Understanding individual car drivers’ behavioural variations and heterogeneity is a significant aspect of developingcar simulator technologies, which are widely used in transport safety. This also characterizes the heterogeneity in drivers’ behaviour in terms of risk and hurry, using both real-time on-track and in-simulator driving performance features. Machine learning (ML) interpretability has become increasingly crucial for identifying accurate and relevant structural relationships between spatial events and factors that explain drivers’ behaviour while being classified and the explanations for them are evaluated. However, the high predictive power of ML algorithms ignore the characteristics of non-stationary domain relationships in spatiotemporal data (e.g., dependence, heterogeneity), which can lead to incorrect interpretations and poor management decisions. This study addresses this critical issue of ‘interpretability’ in ML-based modelling of structural relationships between the events and corresponding features of the car drivers’ behavioural variations. In this work, an exploratory experiment is described that contains simulator and real driving concurrently with a goal to enhance the simulator technologies. Here, initially, with heterogeneous data, several analytic techniques for simulator bias in drivers’ behaviour have been explored. Afterwards, five different ML classifier models were developed to classify risk and hurry in drivers’ behaviour in real and simulator driving. Furthermore, two different feature attribution-based explanation models were developed to explain the decision from the classifiers. According to the results and observation, among the classifiers, Gradient Boosted Decision Trees performed best with a classification accuracy of 98.62%. After quantitative evaluation, among the feature attribution methods, the explanation from Shapley Additive Explanations (SHAP) was found to be more accurate. The use of different metrics for evaluating explanation methods and their outcome lay the path toward further research in enhancing the feature attribution methods.

Keywords
Artificial Intelligence, Driving Behaviour, Feature Attribution, Evaluation, Explainable Artificial Intelligence, Interpretability, Road Safety.
National Category
Computer Sciences
Identifiers
urn:nbn:se:mdh:diva-64912 (URN)10.5220/0011801000003393 (DOI)2-s2.0-85182555765 (Scopus ID)
Conference
15th International Conference on Agents and Artificial Intelligence (ICAART 2023)
Available from: 2023-11-30 Created: 2023-11-30 Last updated: 2024-01-31Bibliographically approved
Islam, M. R., Weber, R. O., Ahmed, M. U. & Begum, S. (2023). Investigating Additive Feature Attribution for Regression.
Open this publication in new window or tab >>Investigating Additive Feature Attribution for Regression
2023 (English)Manuscript (preprint) (Other academic)
Abstract [en]

Feature attribution is a class of explainable artificial intelligence (XAI) methods that produce the contributions of data features to a model's decision. There are multiple accounts stating that feature attribution methods produce inconsistent results and should always be evaluated. However, the existing body of literature on evaluation techniques is still immature with multiple proposed techniques and a lack of widely adopted methods, making it difficult to recognize the best approach for each circumstance. This article investigates an approach to creating synthetic data for regression that can be used to evaluate the results of feature attribution methods. From a real-world dataset, the proposed approach describes how to create synthetic data that preserves the patterns of the original data and enables comprehensive evaluation of XAI methods. This research also demonstrates how global and local feature attributions can be represented in the additive form of case-based reasoning as a benchmark method for evaluation. Finally, this work demonstrates the case where a method that includes a standardization step does not produce feature attributions of the same quality as one that does not use standardization in the context of a regression task.

Keywords
Explainability, Additive Feature Attribution, Regression, Additive CBR, CBR, Evaluation, Interpretability, LIME, SHAP, Synthetic Data, XAI.
National Category
Computer Sciences
Identifiers
urn:nbn:se:mdh:diva-64913 (URN)
Note

Submitted to the journal of Artificial Intelligence (AIJ)

Available from: 2023-11-30 Created: 2023-11-30 Last updated: 2024-04-15Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-3802-4721

Search in DiVA

Show all publications