Case-based Reasoning Research Articles

INTELLECTUAL SUPPORT OF THE PROCESSES OF SEARCHING AND EXTRACTION OF PRECEDENTS IN CASE-BASED REASONING APPROACH

Context. The situational approach is based on the real-time decision-making methods for solving current problem situation. An effective tool for implementing the concept of a situational approach is an experience-based technique that widely known as сasebased reasoning approach. Reasoning by precedents allows solving new (latest) problems using knowledge and accumulated experience of previously solved problems. Since cases (precedents) describing a scenario for solving a certain problem situation are stored in the case library, their search and retrieval directly determine the system response time. In these conditions, there is a need to find ways of solving an actual scientific and practical problem aimed at optimizing case searching and extracting processes. The object of the paper is the processes of searching and extracting of cases from the case library. Objective. The purpose of the article is to improve the process of cases searching in CBR approach by narrowing down the set of cases permissible for solving the current target situation, and excluding from further analysis such cases that do not correspond to the given set of parameters of the target situation. Method. The research methodology is based on the application of rough set theory methods to improve the decision-making procedure based on reasoning by precedents. The proposed two-stage procedure for narrowing the initial set of cases involves preliminary filtering of precedents whose parameter values belong to the given neighborhoods of the corresponding parameters of the target situation at the first stage, and additional narrowing of the obtained subset of cases by the methods of rough set theory at the second stage. The determination of the R-lower and R-upper approximations of a given target set of cases within the notation of rough set theory allows dividing (segmenting) the original set of cases available for solving the current problem stored in case library into three subgroups (segments). The search for prototype solutions can be performed among a selected subset of cases that can be accurately classified as belonging to a given target set; which with some degree of probability can be attributed to the given target set, or within the framework of the union of these two subsets. The third subset contains cases that definitely do not belong to the given target set and can be excluded from further consideration. Results. The problem of presentation and derivation of knowledge based on precedents has been considered. The procedure for searching for precedents in case library has been improved in order to reduce the system response time required to find the solution closest to the current problem situation by narrowing the initial set of cases. Conclusions. The case-based reasoning approach is received the further development by segmenting cases in terms of their belonging to a given target set of precedents uses methods of the rough set theory, then the search for cases is carried out within a given segment. The proposed approach, in contrast to the classic CBR framework, uses additional knowledge derived from obtained case segment; allows modeling the uncertainty regarding the belonging / non-belonging of a case to a given target set; removing from further consideration cases that do not correspond to a given target set.

Financing mode and scheme decision support for large urban rail transit projects: a revised case-based reasoning approach

Financing mode and scheme decision support for large urban rail transit projects: a revised case-based reasoning approach

Evaluating early predictive performance of machine learning approaches for engineering change schedule – A case study using predictive process monitoring techniques

By applying machine learning algorithms, predictive business process monitoring (PBPM) techniques provide an opportunity to counteract undesired outcomes of processes. An especially complex variation of business processes is the engineering change (EC) process. Here, failing to adhere to planned implementation dates can have severe impacts on assembly lines, and it is paramount that potential negative cases are identified as early as possible. Current PBPM research, however, has seldomly investigated the predictive performance of machine learning approaches and their applicability at early process steps, let alone for the EC process. In our research, we show that given adequate feature encoding, shallow learners can accurately predict schedule adherence after process initialisation. Based on EC data from an automotive manufacturer, we provide a case sensitive performance overview on algorithm-encoding combinations. For that, three algorithms (XGBoost, Random Forest, LSTM) were combined with four encoding techniques. The encoding techniques used were the two common aggregation-based and index-based last state encoding, and two new combinations of these, which we term advanced aggregation-based and complex aggregation-based encoding. The study indicates that XGBoost-index-encoded approaches outclass regarding average predictive performance, whereas Random-Forest-aggregation-encoded approaches perform better regarding temporal stability due to reduced influence by dynamic features. Our research provides a case-based reasoning approach for deciding on which algorithm-encoding combination and evaluation metrics to apply. In doing so, we provide a blueprint for an early warning and monitoring method within the EC process and other similarly complex processes.

A Fortiori Case-Based Reasoning: From Theory to Data

The widespread application of uninterpretable machine learning systems for sensitive purposes has spurred research into elucidating the decision-making process of these systems. These efforts have their background in many different disciplines, one of which is the field of AI & law. In particular, recent works have observed that machine learning training data can be interpreted as legal cases. Under this interpretation, the formalism developed to study case law, called the theory of precedential constraint, can be used to analyze the way in which machine learning systems draw on training data—or should draw on them—to make decisions. In the present work, we advance the theory underlying these explanation methods, by relating it to order theory and logic. This allows us to write a software implementation of the theory that can be used to compute with the definitions and give automatic proofs of the properties of the model. We use this implementation to evaluate the model on a series of datasets. Through this analysis, we characterize the types of datasets that are more, or less, suitable to be described by the theory.

Expert System For Diagnosis of Mental Health Disorders in Students Using Case-Based Reasoning Method With a Web-Based Positive Psychology Approach

Mental health issues among students have become a significant concern affecting their quality of life and academic performance. An effective expert system is needed to diagnose and provide appropriate interventions. This research develops a web-based expert system that utilizes the Case-Based Reasoning (CBR) method combined with a positive psychology approach to diagnose mental health disorders in students. The CBR method identifies similarities between new and previous cases, while the positive psychology approach focuses on individual strengths and potential for growth. The system integrates a database of student mental health cases and CBR algorithms to produce relevant diagnoses. This study investigates four types of mental health disorders: panic, anxiety, stress, and depression. The method used for data analysis is Case-Based Reasoning. The diagnosis results are based on calculations from symptom choices within the system, where each symptom has a weight. The highest similarity calculation obtained from past cases is used as a solution to address the problem. System testing, based on expert knowledge with 15 test data samples categorized by mental health disorders and 38 symptoms, achieved an accuracy rate of 85%.

Logistics project risk response decision-making for global supply chain resilience and agility: an optimised case-based reasoning

ABSTRACT Logistics projects are critical to the functioning of the global supply chains (GSC), encountering various disruptions and risks. Sound Risk Response Decisions (RRDs) on logistics projects are imperative to ensure the GSC’s resilience and agility. Besides risk correlations, Project Interdependencies (PIs) and Limited Historical Information (LHI) impede RRDs. To address these challenges, an optimised Case-Based Reasoning combining the Decision-Making Trial and Evaluation Laboratory (DEMATEL) and Stratified Ordinal Priority Approach (SOPA) is proposed. Risks are categorised as referable and non-referable based on LHI using the Jaccard similarity. The strategies for referable risks are derived from similar cases retrieved through the weights of risks and project attributes and three similarities considering PIs. SOPA is developed to find weights with the Interdependent Uncertain Events (IUEs). DEMATEL is employed to access risk centrality degree similarity considering PIs and risk correlations. Expert input is sought for non-referable risk strategies. An optimisation model incorporating secondary risk correlations is built to generate strategies for all risks. The proposed approach is validated through a numerical example. Analysis informs that (1) PIs, LHI, and IUEs are necessary for sound RRDs; (2) decision outcomes are sensitive to logistics project managers who are risk-averse or exhibit moderate consideration of secondary risks.

Personalised decision support in the management of patients with musculoskeletal pain in primary physiotherapy care: a cluster randomised controlled trial (the SupportPrim project).

We developed the SupportPrim PT clinical decision support system (CDSS) using the artificial intelligence method case-based reasoning to support personalised musculoskeletal pain management. The aim of this study was to evaluate the effectiveness of the CDSS for patients in physiotherapy practice. A cluster randomised controlled trial was conducted in primary care in Norway. We randomised 44 physiotherapists to (1) use the CDSS alongside usual care or (2) usual care alone. The CDSS provided personalised treatment recommendations based on a case base of 105 patients with positive outcomes. During the trial, the case-based reasoning system did not have an active learning capability; therefore, the case base size remained the same throughout the study. We included 724 patients presenting with neck, shoulder, back, hip, knee, or complex pain (CDSS; n = 358, usual care; n = 366). Primary outcomes were assessed with multilevel logistic regression using self-reported Global Perceived Effect (GPE) and Patient-Specific Functional Scale (PSFS). At 12 weeks, 165/298 (55.4%) patients in the intervention group and 176/321 (54.8%) in the control group reported improvement in GPE (odds ratio, 1.18; confidence interval, 0.50-2.78). For PSFS, 173/290 (59.7%) patients in the intervention group and 218/310 (70.3%) in the control group reported clinically important improvement in function (odds ratio, 0.41; confidence interval, 0.20-0.85). No significant between-group differences were found for GPE. For PSFS, there was a significant difference favouring the control group, but this was less than the prespecified difference of 15%. We identified several study limitations and recommend further investigation into artificial intelligence applications for managing musculoskeletal pain.

“A safe, non-judgmental space where I can really challenge myself:” learner experiences in a virtual, case-based diagnostic reasoning conference for students

ABSTRACT Case-based diagnostic reasoning conferences, like morning reports, allow undergraduate medical trainees to practice diagnostic reasoning alongside senior clinicians. However, trainees have reported discomfort doing so. Peer-assisted learning offers an alternative approach. We describe the design, implementation, and evaluation of a virtual, student-only diagnostic reasoning conference that leverages peer-assisted learning. Student virtual morning report’s (VMR) design was informed by social and cognitive congruence and experience-based learning. We evaluated participant experiences using a survey focused on participant perceptions of Student VMR’s value, their methods for participation, and their preferences for Student VMR compared with VMR with more senior clinicians. 110 participants (28.9%) completed the survey. 90 participants (81.2%) reported that Student VMR was educational. Compared to VMR, participants reported being more likely to participate in Student VMR by turning on their video (50.0%), presenting a case (43.6%), verbally participating (44.5%), or participating in the chat (70.0%). Strengths included a safe learning environment to practice DR and the opportunity to engage with an international learning community. When asked whether they preferred Student VMR or non-Student VMR, most respondents (64.5%, 71/110) identified that they did not have a preference between the two. A student-focused DR conference may offer a valuable complement to, but not a replacement of, apprenticeship-based DR case conferences.

Landslide susceptibility mapping and similar case matching based on case library: a case study of Xinjing landslide, China

Landslide susceptibility mapping (LSM) predicts potential landslide risks based on historical landslides, playing a crucial role in landslide prevention and control. This study proposes a novel approach for LSM in open-pit mines, leveraging a comprehensive landslide case database. This method addresses the limitations of traditional LSM approaches, such as sensitivity to historical landslide records, low-quality inventories, and limited dataset size. By expanding the training set and incorporating case-based reasoning (CB-LSM) using Long Short-Term Memory (LSTM) for machine learning, the model demonstrated a 10% improvement in predictive accuracy compared to statistical models, showing strong applicability even in areas with low-quality landslide inventories. Additionally, this study enhances the practical utility of LSM by introducing a similar case matching method, employing Fuzzy C-Means (FCM) clustering, which links high-risk areas identified by LSM with specific landslide prevention measures. The proposed approach not only improves the accuracy of landslide predictions but also strengthens the connection between LSM results and effective landslide prevention strategies. Given the higher risks associated with landslides in open-pit mines, the proposed method significantly lowers the threshold for applying LSM in these environments, offering a valuable tool for safeguarding personnel and property.

Integrating Semantic Web, Artificial Intelligence, and Knowledge Management for Enhanced Accounting in SMEs

This study explores the integration of Semantic Web (SW), Artificial Intelligence (AI), and Knowledge Management (KM) to improve accounting practices in small and medium-sized enterprises (SMEs). Recognizing the challenges SMEs face in managing accounting knowledge due to insufficient expertise and fragmented data sources, this research proposes a conceptual model that utilizes SW technologies, such as Resource Description Framework (RDF) and Web Ontology Language (OWL), to create a unified ontology for diverse accounting information. By leveraging AI techniques, including machine learning and natural language processing, the model aims to enhance knowledge retrieval, ontology enrichment, and case-based reasoning, facilitating more efficient and accurate accounting knowledge management. The findings highlight the potential of this integrated approach to support online training, decision-making, and overall competitiveness of SMEs, addressing the limitations of traditional accounting practices. The study concludes with recommendations for further research to refine the integration of SW, AI, and KM in accounting.

Harnessing Vernacular Knowledge for Contemporary Sustainable Design through a Collaborative Digital Platform

Vernacular architecture offers valuable technological and typological solutions rooted in knowledge systems that connect environmental, social, economic, and cultural contexts. This paper introduces the Heritage for People Platform, a collaborative digital tool developed under the VerSus+ project (Creative Europe Program), aimed at organising and disseminating vernacular architectural knowledge with a focus on sustainable practices that are both culturally and environmentally conscious. The platform builds upon lessons learned from similar projects, offering key improvements such as the adoption of a Case-Based Reasoning methodology, which organises examples by geographic location, materials, and intervention types. A structured classification system based on sustainability principles and strategies enables cross-disciplinary research and comparison. The design process was highly participatory, incorporating user feedback at every stage to ensure the platform is accessible to a wide range of users, including designers, scholars, craftspeople, and the general public. A cross-device, user-centered approach further broadens its accessibility. The platform provides a public, web-based geospatial repository where users can create, update, and explore a dynamic collection of artefacts, design models, people, and institutions from across the globe. This tool marks a significant advance in promoting and preserving both physical and intangible heritage, with strong educational and practical applications for sustainable architecture. The paper details the theoretical framework and real-world potential of the platform as a critical resource for promoting sustainability in the built environment.

Towards explainable oral cancer recognition: Screening on imperfect images via Informed Deep Learning and Case-Based Reasoning

Oral squamous cell carcinoma recognition presents a challenge due to late diagnosis and costly data acquisition. A cost-efficient, computerized screening system is crucial for early disease detection, minimizing the need for expert intervention and expensive analysis. Besides, transparency is essential to align these systems with critical sector applications. Explainable Artificial Intelligence (XAI) provides techniques for understanding models. However, current XAI is mostly data-driven and focused on addressing developers’ requirements of improving models rather than clinical users’ demands for expressing relevant insights. Among different XAI strategies, we propose a solution composed of Case-Based Reasoning paradigm to provide visual output explanations and Informed Deep Learning (IDL) to integrate medical knowledge within the system. A key aspect of our solution lies in its capability to handle data imperfections, including labeling inaccuracies and artifacts, thanks to an ensemble architecture on top of the deep learning (DL) workflow. We conducted several experimental benchmarks on a dataset collected in collaboration with medical centers. Our findings reveal that employing the IDL approach yields an accuracy of 85%, surpassing the 77% accuracy achieved by DL alone. Furthermore, we measured the human-centered explainability of the two approaches and IDL generates explanations more congruent with the clinical user demands.

Diagnosa Penyakit Tuber Culosis (TBC) menggunakan Metode Case Based Reasoning (CBR)

Tuberculosis (TB) is one of the infectious diseases caused by Mycobacterium tuberculosis bacteria infection in the human lungs. Tuberculosis is a disease that can be transmitted from people with TB through coughing, sneezing, talking, laughing or singing. Lack of public knowledge about TB and lack of funds for health checks make many people late to be treated. Expert systems are technologies developed based on programs, in accordance with human methods and mindsets. This aims to help people who want to check their health, but are hampered by costs, besides saving time if the examination place is far from the residential environment of the community concerned. Expert systems require a method that can help solve existing problems. In this study, the method used is the Case-Based Reasoning (CBR) method, because the main function of this method is to diagnose the disease. The calculation process of the Case-Based Reasoning (CBR) method which looks for the similarity value or proximity of old cases to new cases of a patient.

Diagnosa Penyakit Malaria Menggunakan Metode Case Base Reasoning (CBR) (Studi Kasus: RSUD Djoelham Kota Binjai)

The application of information technology has been widely used in medicine. This application provides convenience and smoothness in the medical world to detect symptoms of various diseases, especially malaria. Malaria is still included in the endemic diseases suffered by the community in Binjai City, the more malaria patients, of course the more doctors are needed/work to diagnose patients. Artificial intelligence is one solution and helps doctors in supporting decision making for certain diseases. Building a system to diagnose malaria using the Case-Based Reasoning (CBR) method offers various significant advantages. CBR utilizes experience and knowledge from previous cases, allowing the system to provide a more accurate diagnosis based on patterns and symptoms that have occurred in the past.

A Review of the Development and Future Challenges of Case-Based Reasoning

Case-based reasoning (CBR), which is based on the cognitive assumption that similar problems have similar solutions, is an important problem-solving and learning method in the field of artificial intelligence (AI). In this article, the development of CBR is reviewed, and the major challenges of CBR are summarized. The paper is organized into four parts. First, the basic framework and concepts of CBR are introduced. Then, the developed technology and innovative work that were designed to solve problems by CBR are summarized. Then, the application fields of CBR are summarized. Finally, according to the idea of deep learning and interpretable AI, the main challenges for the future development of CBR are proposed.

GS-CBR-KBQA: Graph-structured case-based reasoning for knowledge base question answering

Knowledge Base Question Answering (KBQA) task is an important research direction in natural language processing. Due to the flexibility and ambiguity of natural language, users’ questions often have more complex query types and richer semantic information. To address this issue, this paper proposes the GS-CBR-KBQA model, a Case-Based Reasoning model tailored for KBQA to improve the semantic parsing accuracy and interpretability of natural language questions. The model integrates Knowledge-oriented Programming Language (KoPL) reasoning graphs with query information, employing a Graph Auto-Encoder and the RoBERTa pretrained language model for a highly effective case retrieval. This integration leads to a more robust knowledge retrieval and application approach, particularly innovative in capturing the relationships within KoPL graphs. The model addresses explicitly complex questions such as multi-hop reasoning and questions involving intricate entity relationships. Finally, our extensive experiments show that the model performs excellently in accuracy and F1 metrics on benchmark datasets such as WebQSP and ComplexWebQuestions, particularly in complex question-answering. The code of our model is available at https://anonymous.4open.science/r/GS-CBR-KBQA.

A Spatial Case-Based Reasoning Method for Healthy City Assessment: A Case Study of Middle Layer Super Output Areas (MSOAs) in Birmingham, England

Assessing healthy cities is a crucial strategy for realizing the concept of “health in all policies”. However, most current quantitative assessment methods for healthy cities are predominantly city-level and often overlook intra-urban evaluations. Building on the concept of geographic spatial case-based reasoning (CBR), we present an innovative healthy city spatial case-based reasoning (HCSCBR) model. This model comprehensively integrates spatial relationships and attribute characteristics that impact urban health. We conducted experiments using a detailed multi-source dataset of health environment determinants for middle-layer super output areas (MSOAs) in Birmingham, England. The results demonstrate that our method surpasses traditional data mining techniques in classification performance, offering greater accuracy and efficiency than conventional CBR models. The flexibility of this method permits its application not only in intra-city health evaluations but also in extending to inter-city assessments. Our research concludes that the HCSCBR model significantly improves the precision and reliability of healthy city assessments by incorporating spatial relationships. Additionally, the model’s adaptability and efficiency render it a valuable tool for urban planners and public health researchers. Future research will focus on integrating the temporal dimension to further enhance and refine the healthy city evaluation model, thereby increasing its dynamism and predictive accuracy.

Impact of Artificial Intelligence on Marketing – A Conceptual Study

The marketing field has undergone a considerable transformation with the introduction of AI, leading to enhanced performance. The present study is aimed at finding the effect of AI on marketing. This paper includes an in-depth literature review that offers a complete understanding of the application of AI in marketing. Various studies emphasize significant AI applications in marketing, such as neural networks, case-based reasoning, and expert systems, marking a transformative shift from traditional marketing methods. The integration of AI in marketing leverages technologies like natural language processing, machine learning, and sentiment analysis to enhance decision-making processes, providing precise insights into customer lifecycles and market trends. By combining AI with customer and brand experience data, businesses gain a competitive edge and are better equipped to navigate the dynamic marketplace. The paper underscores the key elements of incorporating AI in marketing functions to enhance overall business performance, leading to increased profitability and a competitive advantage. Its objective is to document insights into the AI ecosystem, elucidating how embedded technologies support marketing processes and contribute to organizational success. Furthermore, the paper delves into the synergy between AI and marketing, highlighting their combined potential as the future driving force for successful business organizations.

Per-Instance Algorithm Configuration in Homogeneous Instance Spaces: A Use Case in Reconfigurable Assembly Systems

The physical capabilities of a reconfigurable assembly system (RAS) increase the agility and responsiveness of the system in highly volatile market conditions. However, achieving optimal RAS utilization entails solving complex optimization problems effectively and efficiently. These optimizations often define homogenous sets of problem instances. While algorithm configuration in such homogeneous contexts traditionally adopts a “one-size-fits-all” approach, recent studies have shown the potential of per-instance algorithm configuration (PIAC) methods in these settings. In this work, we evaluate and compare the performance of different PIAC methods in this context, namely Hydra—a state-of-the-art PIAC method—and a simpler case-based reasoning (CBR) approach. We evaluate the impact of the tuning time budget and/or the number of unique problem instances used for training on each of the method’s performance and robustness. Our experiments show that whilst Hydra fails to improve upon the default algorithm configuration, the CBR method can lead to 16% performance increase using as few as 100 training instances. Following these findings, we evaluate Hydra’s methodology when applied to homogenous instance spaces. This analysis shows the limitations of Hydra’s inference mechanisms in these settings and showcases the advantages of distance-based approaches used in CBR.

Global impact of a virtual neurology morning report

The global shortage and inequitable distribution of neurologists has led to significant gaps not only in neurology care, but also in neurology education. In order to increase access to neurology education, we developed neurology virtual morning report (NVMR), a virtual, open-access, case-based clinical reasoning conference available to learners worldwide. To evaluate NVMR's impact on participants' perception of, interest in, and confidence in neurology, we conducted a survey. Respondents represented 25 different countries of various income levels. The majority of respondents reported that NVMR decreased their perception of difficulty in understanding neurology and increased confidence in various clinical reasoning domains in neurology. Additionally, the majority of medical student participants showed an increased interest in pursuing neurology as a future specialty after participating in NVMR. NVMR represents a potential model for virtual educational conferences and highlights the opportunities digital education has to improve equitable access to neurology education.