Case-based Reasoning Approach Research Articles

An improved case-based reasoning approach for sustainable rural development applied to strategic responses

Sustainable development has become a worldwide consensus in recent years. It has become increasingly important to study how to make effective management decisions in rural areas to achieve sustainable development. In this paper, we develop a new approach to strategic responses for sustainable rural development by using case-based reasoning (CBR), the bi-direction Choquet integral (BDCI), and the Shapley index (SI). First, to deal with the complexity of sustainable rural development, we develop an ontology-based sustainable rural development domain model. Second, we propose a case retrieval algorithm based on BDCI to improve the case retrieval method used in CBR to solve the problem of the relationship between the features. Third, we propose a case reuse method that is inspired by SI, in which each solution is evaluated relative to its value, and the implementation step for the response strategy is determined based on its priority. The proposed strategy response method for sustainable rural development is demonstrated through a case study and its effectiveness is demonstrated empirically.

Study on the methodology of emergency decision-making for water transfer project contingencies: A case-based reasoning and regret theory approach.

To tackle the global water imbalance problem, a multitude of inter-basin water transfer projects have been built worldwide in recent decades. Nevertheless, given the complexity and safety challenges associated with project operation, effective emergency decision-making is crucial for addressing unforeseen incidents. Hence, this research has developed a two-stage emergency decision-making framework to tackle the uncertainty in the development trends of emergencies in inter-basin water transfer projects. (1) The first stage mainly utilizes case-based reasoning techniques to extract historical case information and disposal plans for inter-basin water transfer projects. Subsequently, a holistic similarity model is built by employing structural similarity and local attribute similarity algorithms to identify highly similar historical cases. (2) The second stage involves the optimization and adjustment of decision-making plans based on the dynamic evolution characteristics of emergencies. It utilizes the theory of decision-makers regret psychology and combines it with practical case studies to verify the scientific rationality of the method. This enables it to achieve effective multidimensional expression and rapid matching of scenarios, satisfying the decision-making requirements of "scenario response". Finally, this study compares the results obtained from this method with those computed using the traditional TOPSIS method and fuzzy comprehensive evaluation method, further validating its feasibility and effectiveness. In practice, this method can provide effective support for decision-makers work.

Teaching clinical reasoning to medical students: A brief report of case-based clinical reasoning approach.

Case-based clinical reasoning (CBCR) is the proposed method to improve clinical reasoning. This brief report aimed to evaluate CBCR effectiveness to improve clinical reasoning via an online course. This study is a brief report of a before-after quasi-experimental study to evaluate CBCR in medical students of Shahid Beheshti University of Medical Sciences. Ten online weekly 2-hour sessions of CBCR presentations were instructed to medical students. Each session started with an illness script, and then, the instructor posed the students' five clinical questions in five steps according to the CBCR approach. The clinical reasoning ability of students was evaluated before and 2 weeks after the online courses using four types of standard clinical questions. A Wilcoxon signed-rank test was used to assess the difference between pretest and posttest examination scores. This brief report revealed that twenty-one medical students participated in all ten sessions of the CBCR online course and were evaluated in pretest and posttest examinations. A significant improvement in the clinical reasoning total scores in the posttest examination compared with the pretest examination was observed (P = 0.001). In terms of specific types of clinical questions, the mean posttest scores for clinical reasoning problem (CRP) and key feature (KF) examinations were higher than the pretest scores (P = 0.001 and P = 0.005, respectively). Applying the CBCR approach improved the total clinical reasoning score of medical students during the course. Further studies are needed to evaluate whether this improvement would persist in workplace settings or not.

How to predict the entry mode of international construction contractor: a case-based reasoning approach

PurposeThis study aimed to identify a specific taxonomy of entry modes for international construction contractors and to develop a decision-making mechanism based on case-based reasoning (CBR) to facilitate the selection of the most suitable entry modes.Design/methodology/approachAccording to the experience orientation of the construction industry, a CBR entry mode decision model was established, and based on successful historical cases, a two-step refinement process was carried out to identify similar situations. Then the validity of the model is proved by case analysis.FindingsThis study identified an entry mode taxonomy for international construction contractors (ICCs) and explored their decision-making mechanisms. First, a two-dimension model of entry mode for ICCs was constructed from ownership and value chain dimensions; seven common ICC entry modes were identified and ranked according to market commitment. Secondly, this study reveals the impact mechanism of the ICC entry mode from two aspects: the external environment and enterprise characteristics. Accordingly, an entry mode decision model is established.Practical implicationsFirstly, sorting out the categories of entry mode in the construction field, which provide an entry mode list for ICCs to select. Secondly, revealing the impact mechanism of ICC entry mode, which proposes a systematic decision-making system for the selection of ICC entry mode. Thirdly, constructing a CBR entry mode decision-making model from an empirical perspective, which offers tool support and reduces transaction costs in the decision-making process.Originality/valueThe study on entry modes for ICCs is still in the preliminary exploratory stage. The authors investigate the entry mode categories and decision-making mechanisms for ICCs based on Uppsala internationalization process theory. It widens the applied scope of Uppsala and promotes cross-disciplinary integration. In addition, the authors creatively propose a two-stage retrieval mechanism in the CBR model, which considers the order of decision variables. It refines the influence path of the decision variables on ICCs' entry mode.

Intelligent acquisition of single-valued neutrosophic numbers based on emotional tendency analysis and its application in emergency decision making

With the rising incidences of emergencies, it is both challenging and meaningful to study how to make decisions quickly and take appropriate measures to control the spread and evolution of the situation. However, most current emergency decision-making focuses on mathematical model construction, whereas fuzzy decision-making is biased towards subjective assumptions, which are both insufficient for practicability. We studied the intelligent acquisition of single-valued neutrosophic numbers based on emotional tendency analysis and applied them to emergency decision-making. First, Python programming technology was used to crawl, preprocess, and statistically analyse the network comment data of emergencies, and a quantised single-value neutrosophic number was obtained. Second, the attribute values, represented as neutrosophic numbers, were uniformly converted into cloud droplets, and the weight of the attribute values was objectively determined according to the digital feature entropy in the cloud droplets. Subsequently, a case-based reasoning approach was used to calculate the combined weighted similarity between the alternatives and ideal solution (target case) to obtain a ranking of the alternatives and historical cases in the case base that best matches the target case. Finally, a typhoon disaster assessment was considered as an example to verify the feasibility and effectiveness of the proposed method, and the advantages of the proposed method were emphasised through multi-aspect and multi-angle comparative analyses. The relevant research can be used for public opinion monitoring during emergencies and emergency handling.

Visual analytics and intelligent reasoning for smart manufacturing defect detection and judgement: A meta-learning approach with knowledge graph embedding case-based reasoning

Visual inspection is an important procedure in manufacturing industries to guarantee product quality and reduce costs of poor quality. Several challenges exist for manufacturing inspection automation, including the false positive and false negative trade-off, autonomous decision-making, and inspection algorithm selection. This paper addresses these challenges by proposing a two-level visual analytics and intelligent reasoning system, where machine vision identifies and locates potential defects and convolutional neural network models further classify them into acceptable and defective features. Symbolic reasoning techniques are applied for autonomous decision making on part-level judgement to enhance the system reasoning capability, including part judgement (accept, reject, rework) and rework operation assignment. Furthermore, a case-based reasoning approach for meta-learning of inspection algorithm selection is proposed, which uses knowledge graph embedding (TransR embedding) to embed cases into a two-dimensional space for case similarity estimation and case retrieval. A case of smart assembly inspection is presented to validate the feasibility of the proposed system.

E-Commerce Product Recommendation System Using Case-Based Reasoning (CBR) and K-Means Clustering

This research proposes and implements an e-commerce product recommendation system that combines Case-Based Reasoning (CBR) and K-Means Clustering algorithms. The main aim of this research is to provide more personalized and relevant product recommendations to e-commerce users. The CBR approach leverages users' transaction history to provide customized recommendations, whereas K-Means Clustering groups users with similar preferences increase the relevance of recommendations. This study assesses the effectiveness of the system by conducting a comprehensive evaluation by comparing system recommendations with actual user preferences. The results of this study reveal that the combined approach of CBR and K-Means Clustering can improve the performance of e-commerce product recommendations, ensure the accuracy of recommendations, and produce a more satisfying shopping experience for users. Although there are limitations in terms of the dataset used and the choice of algorithm parameters, this research makes an important contribution in developing a more adaptive and personalized recommendation system for e-commerce platforms.

A case-based reasoning approach for solving schedule delay problems in prefabricated construction projects

The project schedule delay problem has received considerable attention for its significance in impeding project performance. Compared to conventional projects, prefabricated construction projects could suffer more from schedule delay problems. A possible solution to such problems is to provide countermeasures by referring to valuable experience of historical cases. This paper proposes a case-based reasoning (CBR) model to leverage past experience and knowledge to address the schedule delay problems in prefabricated construction projects. The study explains the development processes of the CBR model in detail, including the case base construction, case retrieval, case reuse and update. Subsequently, the study develops the CBR system and presents a case study to demonstrate the validity and practicality of the proposed approach. This study provides a potential tool to facilitate schedule management of prefabricated construction projects. It offers an effective reference for decision-makers, such as project managers, to tackle schedule delays through experience mining.

Analysis of Availability of Case-Based Reasoning Approaches on Physics Textbooks Class X Semester 1

Learning is strengthened by using an approach to learning. In the 2013 curriculum, it is recommended to use an approach to learning, one of which is the Case-Based Reasoning (CBR) approach. One approach similar to the current process standards is the CBR approach, which helps teachers provide more student involvement in learning activities. There are many physics textbooks that many publishers have circulated, so It is vital to investigate whether or not these books have provided a CBR approach to learning to improve reasoning skills and higher-order thinking as suggested in the 2013 curriculum. This research was done to analyze the CBR approach. CBR is in a physics textbook for class X, semester 1, at Public High Schools in the City of Padang. The research carried out included descriptive research using a qualitative approach. The research population consisted of all physics textbooks for class X high school published in Indonesia and used in the city of Padang. The research samples were three Physics textbooks for Class X High School Semester 1: ER, IP, and TS. The research results showed that no CBR approach was found in the three physics textbooks analyzed. Hence, we concluded that no textbooks are currently available that provide a CBR approach.

Structured Case-Based Reasoning for Inference-Time Adaptation of Text-to-SQL Parsers

Inference-time adaptation methods for semantic parsing are useful for leveraging examples from newly-observed domains without repeated fine-tuning. Existing approaches typically bias the decoder by simply concatenating input-output example pairs (cases) from the new domain at the encoder’s input in a Seq-to-Seq model. Such methods cannot adequately leverage the structure of logical forms in the case examples. We propose StructCBR, a structured case-based reasoning approach, which leverages subtree-level similarity between logical forms of cases and candidate outputs, resulting in better decoder decisions. For the task of adapting Text-to-SQL models to unseen schemas, we show that exploiting case examples in a structured manner via StructCBR offers consistent performance improvements over prior inference-time adaptation methods across five different databases. To the best of our knowledge, we are the first to attempt inference-time adaptation of Text-to-SQL models, and harness trainable structured similarity between subqueries.

Book Recommendation Using Collaborative Filtering Algorithm

The explosive growth in the amount of available digital information in higher education has created a potential challenge of information overload, which hampers timely access to items of interest. The recommender systems are applied in different domains such as recommendations film, tourist advising, webpages, news, songs, and products. But the recommender systems pay less attention to university library services. The most users of university library are students. These users have a lack of ability to search and select the appropriate materials from the large repository that meet for their needs. A lot of work has been done on recommender system, but there are technical gaps observed in existing works such as the problem of constant item list in using web usage mining, decision tree induction, and association rule mining. Besides, it is observed that there is cold start problem in case-based reasoning approach. Therefore, this research work presents matrix factorization collaborative filtering with some performance enhancement to overcome cold start problem. In addition, it presents a comparative study among memory-based and model-based approaches. In this study, researchers used design science research method. The study dataset, 5189 records and 76,888 ratings, was collected from the University of Gondar student information system and online catalogue system. To develop the proposed model, memory-based and model-based approaches have been tested. In memory-based approach, matrix factorization collaborative filtering with some performance enhancements has been implemented. In model-based approach, K-nearest neighbour (KNN) and singular value decomposition (SVD) algorithms are also assessed experimentally. The SVD model is trained on our dataset optimized with a scored RMSE 0.1623 compared to RMSE 0.1991 before the optimization. The RMSE for a KNN model trained using the same dataset was 1.0535. This indicates that the matrix factorization performs better than KNN models in building collaborative filtering recommenders. The proposed SVD-based model accuracy score is 85%. The accuracy score of KNN model is 53%. So, the comparative study indicates that matrix factorization technique, specifically SVD algorithm, outperforms over neighbourhood-based recommenders. Moreover, using hyperparameter tuning with SVD also has an improvement on model performance compared with the existing SVD algorithm.

Integrated approach using deep neural network and CBR for detecting severity of coronary artery disease

Despite major diagnostic progress and treatment progress, cardiovascular diseases (CVD) continue to be the world's leading cause of disease and mortality. Artificial intelligence methods provide the ability to drastically alter cardiology healthcare, by improving the reliability and optimizing the CVD prediction and response accuracy. Medical knowledge can also be improved by AI techniques like machine learning and depth learning due to the availability of healthcare data related relevant cardio clinical information. The focus of this research is to diagnose coronary artery disease among patients based on their clinical data using a deep neural network. The paper focuses on the dual approach where in the first phase diagnosis of coronary artery disease (CAD) is carried out using a deep neural network. The Deep learning-based model has achieved the highest prediction accuracy of 96.2% and a lowest error rate of 3.8 %. Further to handle the overfitting Gaussian noise is introduced into the model to improve the performance and in the second phase the severity of the disease is checked using case-based reasoning approach (CBR).

A case-based reasoning tool to recommend drinking water source protection actions

In response to a need expressed by water actors to support them in identifying appropriate actions for protecting drinking water sources, we modelled, designed, implemented, tested, and validated a prototype case-based reasoning (CBR) system. This required an intensive knowledge acquisition and structuring process which we conducted in collaboration with 102 water management and governance actors in Quebec, Canada. Knowledge was organized in a case base containing nearly 200 past experiences implementing water protection actions at different decision-making scales (local, regional, provincial), by various organizations (government, municipalities, water-related associations), over the last two decades. This paper describes our case engineering process to design case attributes based on content analysis. It presents the case edition, the case retrieval process, and the prototype's implementation and validation, conducted through a rigorous and transparent participatory procedure. This is, to our knowledge, the first successful attempt to apply a CBR approach to support water actors in protecting drinking water sources. It provides empirical evidence of the positive potential of such an approach for knowledge sharing and transfer and can be generalized to other similar contexts.

The Development of Intelligent Agents: A Case-Based Reasoning Approach to Achieve Human-Like Peculiarities via Playback of Human Traces

The Development of Intelligent Agents: A Case-Based Reasoning Approach to Achieve Human-Like Peculiarities via Playback of Human Traces

Measuring Control to Dynamically Induce Flow in Tetris

Dynamic difficulty adjustment (DDA) is a set of techniques that aim to automatically adapt the difficulty of a video game based on the player’s performance. This article presents a methodology for DDA using ideas from the theory of flow and case-based reasoning (CBR). In essence, we are looking to generate game sessions with a similar difficulty evolution to previous game sessions that have produced flow in players with a similar skill level. We propose a CBR approach to dynamically assess the player’s skill level and adapt the difficulty of the game based on the relative complexity of the last game states. We develop a DDA system for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Tetris</i> using this methodology and show, in an experiment with 40 participants, that the DDA version has a measurable impact on the perceived flow using validated questionnaires.

Risk response for critical infrastructures with multiple interdependent risks: A scenario-based extended CBR approach

Critical infrastructures (CIs) are elementary utility systems that maintain the normal society functioning. However, various risks constantly emerge, resulting in widespread human and economic losses. Effective risk response for CIs is a challenging task because of extreme time sensitivity. Especially, multiple risks and interdependencies among them also increase the response difficulties. To promptly generate effective response strategies for CIs with multiple interdependent risks, a scenario-based extended case-based reasoning (CBR) approach by combining the risk network and ontological modeling is proposed in this study. First, a three-stage solution framework is constructed. Subsequently, the historical cases are represented based on a scenario analysis and ontology model. A new case retrieval mechanism including three similarity measures and corresponding algorithm is proposed to precisely retrieve the most similar historical case, and the retrieved response strategies are adapted according to the risk loss severity and risk interdependencies. Furthermore, a case study is conducted to verify the practicability and superiorities of the proposed approach, and the necessity of considering multiple interdependent risks in CI risk response. It is indicated that the study provides a more suitable tool for CI risk response in risk interdependent scenarios, which is beneficial to the effectiveness of risk response in reality.

Penerapan Metode Case Base Reasoning Dalam Diagnosa Penyakit dan Hama pada Tanaman Hortikultura

Horticultural products are products from the agricultural sub-sector with potential and prospects for development. Horticultural products consist of medicinal products, fruit, vegetables, and ornamental plants. However, some farmers are still not optimal in getting results from their cultivation because they do not understand how to control pests and diseases of horticultural crops. This causes the plant to be susceptible to various diseases. Identification of diseases in these plants is often done manually so it takes a long time. The development of computer technology can be utilized in various branches of science, one of which is the field of artificial intelligence. Expert systems are included in one of the scientific branches of the current artificial intelligence program. Expert systems have the ability to solve a particular problem, usually requiring an expert from an expert. The method that will be used is the case-based reasoning (CBR) approach. This study aims to help farmers diagnose diseases and pests, so that they are more optimal and on target in controlling. In the implementation of the expert system with the CBR method, a diagnosis will be obtained, and it will be recommended for plant control. Case Based Reasoning method is used to process 10 data. This method will process data in the form of symptoms seen in horticultural plants. The test results obtained a percentage value of 80%. Therefore, the application of the Case Based Reasoning method is very relevant in the Diagnosis of Diseases and Pests in Horticultural Crops.

A data-driven explainable case-based reasoning approach for financial risk detection

The rapid development of artificial intelligence methods contributes to their wide applications for forecasting various financial risks in recent years. This study introduces a novel explainable case-based reasoning (CBR) approach without a requirement of rich expertise in financial risk. Compared with other black-box algorithms, the explainable CBR system allows a natural economic interpretation of results. Indeed, the empirical results emphasize the interpretability of the CBR system in predicting financial risk, which is essential for both financial companies and their customers. In addition, our results show that the proposed automatic design CBR system has a good prediction performance compared to other artificial intelligence methods, overcoming the main drawback of a standard CBR system of highly depending on prior domain knowledge about the corresponding field.

Risk-supported case-based reasoning approach for cost overrun estimation of water-related projects using machine learning

PurposeThe present study aims to develop a risk-supported case-based reasoning (RS-CBR) approach for water-related projects by incorporating various uncertainties and risks in the revision step.Design/methodology/approachThe cases were extracted by studying 68 water-related projects. This research employs earned value management (EVM) factors to consider time and cost features and economic, natural, technical, and project risks to account for uncertainties and supervised learning models to estimate cost overrun. Time-series algorithms were also used to predict construction cost indexes (CCI) and model improvements in future forecasts. Outliers were deleted by the pre-processing process. Next, datasets were split into testing and training sets, and algorithms were implemented. The accuracy of different models was measured with the mean absolute percentage error (MAPE) and the normalized root mean square error (NRSME) criteria.FindingsThe findings show an improvement in the accuracy of predictions using datasets that consider uncertainties, and ensemble algorithms such as Random Forest and AdaBoost had higher accuracy. Also, among the single algorithms, the support vector regressor (SVR) with the sigmoid kernel outperformed the others.Originality/valueThis research is the first attempt to develop a case-based reasoning model based on various risks and uncertainties. The developed model has provided an approving overlap with machine learning models to predict cost overruns. The model has been implemented in collected water-related projects and results have been reported.

Strategic response for ease of doing business using case-based reasoning

Sound ease of doing business is essential for building a modernized economy and fostering high-quality growth. Research on the ease of doing business should not only focus on the impact and evaluation system, but also have guiding significance for decision-making related to the ease of doing business, but there are still relatively few studies in this area. Due to the complexity of ease of doing business, to save energy and make the most of the experience knowledge of decision-makers, we have introduced case-based reasoning (CBR) into strategy response, as a possible application of the analysis of case histories. The purpose of this paper is to propose a CBR strategy response method for ease of doing business, which can be used to formulate more intelligent and efficient ease of doing business strategy. The innovation of this research focuses on three key parts. Firstly, a CBR strategy response method for ease of doing business is innovatively developed. Secondly, the ontology method is used to build ease of doing business domain model, including city features, ease of doing business indicators, and response strategy. Thirdly, Missing values are also included in the calculation process. During the calculation process, missing values are also processed, and inappropriate response strategies in similar case sets are adjusted in response to differences between scenarios to generate feasible strategies. Finally, a case study of a city shows that this method can extend the CBR approach to ease of doing business strategy response.