Rule-based Classification Research Articles

Software-assisted structured reporting and semi-automated TNM classification for NSCLC staging in a multicenter proof of concept study

ObjectivesIn this multi-center study, we proposed a structured reporting (SR) framework for non-small cell lung cancer (NSCLC) and developed a software-assisted tool to automatically translate image-based findings and annotations into TNM classifications. The aim of this study was to validate the software-assisted SR tool for NSCLC, assess its potential clinical impact in a proof-of-concept study, and evaluate current reporting standards in participating institutions.MethodsA framework for SR and staging of NSCLC was developed in a multi-center collaboration. SR annotations and descriptions were used to generate semi-automated TNM classification. The SR and TNM classification tools were evaluated by nine radiologists on n = 20 representative [18F]FDG PET/CT studies and compared to the free text reporting (FTR) strategy. Results were compared to a multidisciplinary team reference using a generalized linear mixed model (GLMM). Additionally, participants were surveyed on their experience with SR and TNM classification.ResultsOverall, GLMM analysis revealed that readers using SR were 1.707 (CI: 1.137–2.585) times more likely to correctly classify TNM status compared to FTR strategy (p = 0.01) resulting in increased overall TNM correctness in 71.9% (128/178) of cases compared to 62.8% (113/180) FTR. The primary source of variation in classification accuracy was explained by case complexity. Participants rated the potential impact of SR and semi-automated TNM classification as positive across all categories with improved scores after template validation.ConclusionThis multi-center study yielded an effective software-assisted SR framework for NSCLC. The SR and semi-automated classification tool improved TNM classification and were perceived as valuable.Critical relevance statementSoftware-assisted SR provides robust input for semi-automated rule-based TNM classification in non-small-cell lung carcinoma (NSCLC), improves TNM correctness compared to FTR, and was perceived as valuable by radiology physicians.Key PointsSR and TNM classification are underutilized across participating centers for NSCLC staging.Software-assisted SR has emerged as a promising strategy for oncologic assessment.Software-assisted SR facilitates semi-automated TNM classification with improved staging accuracy compared to free-text reports in NSCLC.Graphical

Extraction of Canal Distribution Information Based on UAV Remote Sensing System and Object-Oriented Method

At present, the extraction of irrigation canal network distribution information is of great significance for developing a digital twin irrigation district. However, due to the low resolution of remote sensing images, it is difficult to effectively identify the canal networks, especially for channels with a width of less than 1 m, where recognition is insufficient. Therefore, the purpose of this study is to extract canal networks of different widths in an irrigation district in Shaanxi Province as the research area. A rule-based object-oriented classification method was employed, utilizing image data collected by the DJI Mavic 3 multispectral UAV (Unmanned Aerial Vehicle) to explore the accuracy of this method in extracting canal distribution information. Based on UAV multispectral remote sensing imagery, the segmentation parameters for the remote sensing imagery were determined using ENVI 5.6 software, with the segmentation threshold set at 60 and the merging threshold set at 80. By combining the spectral and spatial differences between the canals and other ground objects, rules for extracting canal network distribution information were established, and the information on the distribution of channels in this irrigation area was finally obtained. The experimental results showed a maximum recall rate of 91.88% and a maximum precision rate of 57.59%. The overall recall precision rates for the irrigation district were 85.74% and 55.08%, respectively. This method provides a new solution for identifying and extracting canal systems in irrigation districts, offering valuable insights for acquiring canal distribution information and providing a scientific basis for precision irrigation.

An algorithm for belief rule induction with partial ignorance

Belief rules are an extension of fuzzy rules that consider belief degrees. They are widely applied due to their traceability, interpretability, and flexibility. However, current belief rules only consider residual support and global ignorance while ignoring partial ignorance. In this paper, we proposed a novel belief rule-based classification system called partial ignorance belief rule induction algorithm (PIBRIA). The consequent part of belief rules takes into account not only the residual support and global ignorance but also partial ignorance of evidence. The belief degrees in the consequent part of each belief rule collectively form a genuine basic probability assignment (BPA). Based on fuzzy unordered rule induction algorithm (FURIA), we propose the learning algorithm for belief rules with partial ignorance, which helps the novel proposed PRIBIA achieve a balance between accuracy and complexity. The inference method employs the Dempster’s combination rule and Shafer’s discounting operation, where the discounting operation can resolve evidence conflicts in the combination rule. The effectiveness and superiority of PIBRIA in handling classification tasks have been validated by comparing it to some state-of-the-art rule-based models. The results of statistical tests show that PIBRIA outperforms all other methods in terms of classification accuracy. Whereas its computational complexity and model complexity are moderate.

Improving rule-based classifiers by Bayes point aggregation

The widespread adoption of artificial intelligence systems with continuously higher capabilities is causing ethical concerns. The lack of transparency, particularly for state-of-the-art models such as deep neural networks, hinders the applicability of such black-box methods in many domains, like the medical or the financial ones, where model transparency is a mandatory requirement, and hence white-box models are largely preferred over potentially more accurate but opaque techniques.For this reason, in this paper, we focus on ruleset learning, arguably the most interpretable class of learning techniques. Specifically, we propose Bayes Point Rule Classifier, an ensemble methodology inspired by the Bayes Point Machine, to improve the performance and robustness of rule-based classifiers. In addition, to improve interpretability, we propose a technique to retain the most relevant rules based on their importance, thus increasing the transparency of the ensemble, making it easier to understand its decision-making process.We also propose FIND-RS, a greedy ruleset learning algorithm that, under mild conditions, guarantees to learn hypothesis with perfect accuracy on the training set while preserving a good generalization capability to unseen data points.We performed extensive experimentation showing that FIND-RS achieves state-of-the-art classification performance at the cost of a slight increase in the ruleset complexity w.r.t. the competitors. However, when paired with the Bayes Point Rule Classifier, FIND-RS outperforms all the considered baselines.

Digital mapping of dates of transplanting and accumulated thermal requirement of rice (Oryza sativa L.) in the subtropics of North Eastern Hill Region, India

ABSTRACT Accurate and timely mapping of rice areas is crucial for effective agricultural planning and food security management in the North Eastern Hill Region of India, especially amid changing climate conditions. This study developed a method to estimate rice transplanting dates by utilizing VH polarized backscattering-coefficients rom Sentinel-1A SAR data and also assessed thermal requirements for rice productivity in Ri-Bhoi district, Meghalaya during kharif 2021. The methodology involved 3 steps- (i) preprocessing data to construct time-series SAR images (ii) rule-based classification of SAR data integrating phenological and topographical information to identify transplanting windows (iii) assessing mapping accuracy. The results when compared with field data, revealed five distinct transplanting windows from early June to early August across 9031 ha of rice area. Overall accuracy was 85%, with a kappa coefficient of 0.74. User and producer accuracies ranged from 0.74 to 0.93 and 0.75 to 0.92, respectively for various transplanting windows. GDD varied between 1432.8°C day and 3290.4°C day, with higher values corresponding to earlier planting dates. This study formulates a robust methodology for rice mapping in hilly, small-field landscapes with multiple transplanting dates by integrating Sentinel-1A SAR data with ancillary and crop phenology information, contributing to improved crop management and climate change adaptations.

Application of the Sugeno integral in Fuzzy Rule-Based Classification

Fuzzy Rule-Based Classification System (FRBCS) is a well-known technique to deal with classification problems. Recent studies have considered the usage of the Choquet integral and its generalizations (e.g.: CT-integral, CF-Integral and CC-integral) to enhance the performance of such systems. Such fuzzy integrals were applied to the Fuzzy Reasoning Method (FRM) to aggregate the fired fuzzy rules when classifying new data. However, the Sugeno integral, another well-known aggregation operator, obtained good results in other applications, such as brain–computer interfaces. These facts led to the present study, in which we consider the Sugeno integral in classification problems. That is, the Sugeno integral is applied in the FRM of a widely used FRBCS, and its performance is analyzed over 33 different datasets from the literature, also considering different fuzzy measures. To show the efficiency of this new approach, the results obtained are also compared with previous studies that involved the application of different aggregation functions. Finally, we perform a statistical analysis of the application.

Machine learning reveals the rules governing the efficacy of mesenchymal stromal cells in septic preclinical models

BackgroundMesenchymal Stromal Cells (MSCs) are the preferred candidates for therapeutics as they possess multi-directional differentiation potential, exhibit potent immunomodulatory activity, are anti-inflammatory, and can function like antimicrobials. These capabilities have therefore encouraged scientists to undertake numerous preclinical as well as a few clinical trials to access the translational potential of MSCs in disease therapeutics. In spite of these efforts, the efficacy of MSCs has not been consistent—as is reflected in the large variation in the values of outcome measures like survival rates. Survival rate is a resultant of complex cascading interactions that not only depends upon upstream experimental factors like dosage, time of infusion, type of transplant, etc.; but is also dictated, post-infusion, by intrinsic host specific attributes like inflammatory microniche including proinflammatory cytokines and alarmins released by the damaged host cells. These complex interdependencies make a researcher’s task of designing MSC transfusion experiments challenging.MethodsIn order to identify the rules and associated attributes that influence the final outcome (survival rates) of MSC transfusion experiments, we decided to apply machine learning techniques on manually curated data collected from available literature. As sepsis is a multi-faceted condition that involves highly dysregulated immune response, inflammatory environment and microbial invasion, sepsis can be an efficient model to verify the therapeutic effects of MSCs. We therefore decided to implement rule-based classification models on data obtained from studies involving interventions of MSCs in sepsis preclinical models.ResultsThe rules from the generated graph models indicated that survival rates, post-MSC-infusion, are influenced by factors like source, dosage, time of infusion, pre-Interleukin-6 (IL-6)/ Tumour Necrosis Factor- alpha (TNF-α levels, etc.ConclusionThis approach provides important information for optimization of MSCs based treatment strategies that may help the researchers design their experiments.

Monitoring wheat area using sentinel-2 imagery and In-situ spectroradiometer data in heterogeneous field conditions

Crop statistics are crucial for developing a demand-based export and import strategy to ensure a country’s sustainable food security. Remote sensing efficiently generates essential crop statistics, while ground-based supplementary sensor data offers sufficient information for crop delineation. This study explored the multispectral satellite imagery using in-situ ground-based hyperspectral reflectance phenology information as training data to delineate wheat from other competitive winter crops in Northwestern Bangladesh as a case study. Wheat spectral signatures were primarily obtained through a hand-held Spectroradiometer at various phenological stages, aligned with Sentinel-2 data availability. Five vegetation indices (VIs), namely Normalized Difference Vegetation Index (NDVI), Red-edge NDVI (RENDVI), Enhanced Vegetation Index (EVI), Greenness Chromatic Coordinate (GCC) and Soil-Adjusted Vegetation Index (SAVI), were derived from Spectroradiometer-data across six wheat growth stages: seedling, tillering, booting, flowering, grain development, and maturity. Maximum and minimum threshold values for the VIs at those six growth stages were determined from regression analysis of the values collected from Spectroradiometer and Sentinel-2. A rule-based classification technique was then used to categorize Sentinel-2 for wheat crop delineation based on those threshold values. The results revealed that maps based on NDVI, EVI, and SAVI showed overall accuracies of 83.33%, 85.18%, and 81.48%, respectively. These accuracies were found to be statistically acceptable (p < 0.05) outcomes. A positive agreement was observed when comparing the remotely sensed area at the union (4th tier administrative level) with the officially reported data of Bangladesh. This innovative method has the potential to be extended for developing phenology and area delineation for other major crops locally and globally.

Employing Iterative Feature Selection in Fuzzy Rule-Based Binary Classification

Employing Iterative Feature Selection in Fuzzy Rule-Based Binary Classification

A Design of Fuzzy Rule-Based Classifier for Multiclass Classification and Its Realization in Horizontal Federated Learning

A Design of Fuzzy Rule-Based Classifier for Multiclass Classification and Its Realization in Horizontal Federated Learning

Efficient Contactless Palmprint Recognition System Based on Deep Rule-Based Classification

Efficient Contactless Palmprint Recognition System Based on Deep Rule-Based Classification

Identifying diseases symptoms and general rules using supervised and unsupervised machine learning

The symptoms of diseases can vary among individuals and may remain undetected in the early stages. Detecting these symptoms is crucial in the initial stage to effectively manage and treat cases of varying severity. Machine learning has made major advances in recent years, proving its effectiveness in various healthcare applications. This study aims to identify patterns of symptoms and general rules regarding symptoms among patients using supervised and unsupervised machine learning. The integration of a rule-based machine learning technique and classification methods is utilized to extend a prediction model. This study analyzes patient data that was available online through the Kaggle repository. After preprocessing the data and exploring descriptive statistics, the Apriori algorithm was applied to identify frequent symptoms and patterns in the discovered rules. Additionally, the study applied several machine learning models for predicting diseases, including stepwise regression, support vector machine, bootstrap forest, boosted trees, and neural-boosted methods. Several predictive machine learning models were applied to the dataset to predict diseases. It was discovered that the stepwise method for fitting outperformed all competitors in this study, as determined through cross-validation conducted for each model based on established criteria. Moreover, numerous significant decision rules were extracted in the study, which can streamline clinical applications without the need for additional expertise. These rules enable the prediction of relationships between symptoms and diseases, as well as between different diseases. Therefore, the results obtained in this study have the potential to improve the performance of prediction models. We can discover diseases symptoms and general rules using supervised and unsupervised machine learning for the dataset. Overall, the proposed algorithm can support not only healthcare professionals but also patients who face cost and time constraints in diagnosing and treating these diseases.

Code smells analysis for android applications and a solution for less battery consumption

In the digitization era, the battery consumption factor plays a vital role for the devices that operate Android software, expecting them to deliver high performance and good maintainability.The study aims to analyze the Android-specific code smells, their impact on battery consumption, and the formulation of a mathematical model concerning static code metrics hampered by the code smells. We studied the impact on battery consumption by three Android-specific code smells, namely: No Low Memory Resolver (NLMR), Slow Loop (SL) and Unclosed Closable, considering 4,165 classes of 16 Android applications. We used a rule-based classification method that aids the refactoring ideology. Subsequently, multi-linear regression (MLR) modeling is used to evaluate battery usage against the software metrics of smelly code instances. Moreover, it was possible to devise a correlation for the software metric influenced by battery consumption and rule-based classifiers. The outcome confirms that the refactoring of the considered code smells minimizes the battery consumption levels. The refactoring method accounts for an accuracy of 87.47% cumulatively. The applied MLR model has an R-square value of 0.76 for NLMR and 0.668 for SL, respectively. This study can guide the developers towards a complete package for the focused development life cycle of Android code, helping them minimize smartphone battery consumption and use the saved battery lives for other operations, contributing to the green energy revolution in mobile devices.

Single sample-oriented attribute reduction for rule learning with formal concept analysis

As an effective tool for data mining, formal concept analysis can yield interpretable decision rules using attribute reduction. Currently, existing reduction methods within the framework of formal concept analysis result in all samples sharing the same conditional attributes, thereby overlooking the distinctions between rules extracted from different samples. To address this problem, we present a novel attribute reduction method for single samples. For this purpose, a single sample-oriented reduction framework is established by incorporating a discernibility attribute vector and an algorithm for calculating reducts based on the matrix representation of the discernibility attribute vector. Furthermore, the process of obtaining a new reduct from the original reduct is discussed by considering incremental learning. Given that attributes included in reducts are crucial conditions for decision-making, intent-minimal granular rules are generated through attribute reduction, and a reduction-based method for measuring the completeness of the rule set is discussed. Finally, to accomplish the classification task, a minimal rule-based classification model (MRCM) is proposed. The experimental results show that the MRCM has the same classification ability as the unreduced rules, and the rules with higher completeness tend to exhibit better classification performance.

Factors affecting crash severity in Roundabouts: A comprehensive analysis in the Jordanian context

Roundabouts are widely embraced for their perceived safety advantages over other types of unsignalized intersections. However, there has been an observed increase in crash rates at roundabouts over time in Jordan. This paper delves into modeling traffic crash severity at roundabouts, considering various factors such as weather, lighting, vehicle characteristics, geometric features, and driver age and gender. To comprehensively analyze roundabout crashes in Jordan, we constructed rule-based classifiers and Random Forest models after balancing the dataset. Rule-based models offer interpretability, albeit with some simplicity trade-off, while Random Forest models provide deeper analysis but require additional explanation. Presenting both outputs to subject matter experts and policymakers facilitates a holistic understanding of factors contributing to roundabout crashes in Jordan. Subsequently, CN2 results revealed that injury severity crashes are influenced by the time of the day, driver age, day of the week, speed, and number of vehicles involved. On the other hand, property damage-only crashes are affected by the number of lanes, time of the day, type of driver fault, lighting conditions, speed, and day of the week. The RF model analysis unveiled crucial factors influencing crash severity in roundabouts, notably the varying impact of driver age, time of day, the number of vehicles involved, seasonality, and vehicle speed. This proposed approach is promising, comprehensive, and not only enhances the understanding of roundabout crashes but also informs the development of effective, localized safety interventions.

Automating population dose survey processing-An Australian feasibility study.

A comprehensive collection of data on doses in adult computed tomography procedures in Australia has not been undertaken for some time. This is largely due to the effort involved in collecting the data required for calculating the population dose. This data collection effort can be greatly reduced, and the coverage increased, if the process can be automated without major changes to the workflow of the imaging facilities providing the data. Success would provide a tool to determine a truly national assessment of the dose incurred through diagnostic imaging in Australia. The aims of this study were to develop an automated tool to categorize electronic records of imaging procedures into a standardized set of broad procedure types, to validate the tool by applying it to data collected from nine facilities, and to assess the feasibility of applying the automated tool to compute population dose and determine the data manipulations required. A rule-based classifier was implemented capitalizing on semantic and clinical rules. The keyword list was initially built from 609 unique study descriptions. It was then refined using an additional 414 unique study descriptions. The classifier was then tested on an additional 1198 unique study descriptions. Input from a radiologist provided the ground truth for the refinement of the classifier. From a sample of 238139 studies containing 2794 unique study descriptions, the classifier correctly classified 2789 study types with only five misclassifications, demonstrating the feasibility of automating the process and the need for data pre-processing. Dose statistics for 21 categories were compiled using the 238139 studies. The classifier achieved excellent classification results using the testing data supplied by the facilities. However, since all data supplied were from public facilities, the performance of the classifier may be biased. The performance of the classifier is yet to be tested on a more representative mix of private and public facilities.

Energy Consumption Prediction in Residential Buildings—An Accurate and Interpretable Machine Learning Approach Combining Fuzzy Systems with Evolutionary Optimization

This paper addresses the problem of accurate and interpretable prediction of energy consumption in residential buildings. The solution that we propose in this work employs the knowledge discovery machine learning approach combining fuzzy systems with evolutionary optimization. The contribution of this work is twofold, including both methodology and experimental investigations. As far as methodological contribution is concerned, in this paper, we present an original designing procedure of fuzzy rule-based prediction systems (FRBPSs) for accurate and transparent energy consumption prediction in residential buildings. The proposed FRBPSs are characterized by a genetically optimized accuracy–interpretability trade-off. The trade-off optimization is carried out by means of multi-objective evolutionary optimization algorithms—in particular, by our generalization of the well-known strength Pareto evolutionary algorithm 2 (SPEA2). The proposed FRBPSs’ designing procedure is our original extension and generalization (for regression problems operating on continuous outputs) of an approach to designing fuzzy rule-based classifiers (FRBCs) we developed earlier and published in 2020 in this journal. FRBCs operate on discrete outputs, i.e., class labels. The experimental contribution of this work includes designing the collection of FRBPSs for residential building energy consumption prediction using the data set published in 2024 and available from Kaggle Database Repository. Moreover, the comparison with 20 available alternative approaches is carried out, demonstrating that our approach significantly outperforms alternative methods in terms of interpretability and transparency of the energy consumption predictions made while remaining comparable or slightly superior in terms of the accuracy of those predictions.

Matching Patients to Clinical Trials using LLaMA 2 Embeddings and Siamese Neural Network.

Patient recruitment is a key desideratum for the success of a clinical trial that entails identifying eligible patients that match the selection criteria for the trial. However, the complexity of criteria information and heterogeneity of patient data render manual analysis a burdensome and time-consuming task. In an attempt to automate patient recruitment, this work proposes a Siamese Neural Network-based model, namely Siamese-PTM. Siamese-PTM employs the pretrained LLaMA 2 model to derive contextual representations of the EHR and criteria inputs and jointly encodes them using two weight-sharing identical subnetworks. We evaluate Siamese-PTM on structured and unstructured EHR to analyze their predictive informativeness as standalone and collective feature sets. We explore a variety of deep models for Siamese-PTM's encoders and compare their performance against the Single-encoder counterparts. We develop a baseline rule-based classifier, compared to which Siamese-PTM improved performance by 40%. Furthermore, visualization of Siamese-PTM's learned embedding space reinforces its predictive robustness.

Investigation of Issues in Data Anomaly Detection Using Deep-Learning- and Rule-Based Classifications for Long-Term Vibration Measurements

Structural health monitoring (SHM) systems are widely used for civil infrastructure monitoring. Data acquired from the SHM systems play an important role in assessing structural integrity and determining further maintenance activities. Considering that sensors in the SHM systems are installed in a harsh environment for long-term measurements, some sensors can malfunction and produce faulty data. As a large amount of measured data is often desired to be automatically processed and can adversely affect structural assessments, identifying such abnormal data is important. This paper provides critical investigations of the automated detection of data anomalies using existing deep-learning-based classification in conjunction with a simple rule-based approach. The issues investigated in this study include (1) the presence of ambiguous data that cannot be categorized as an anomaly class in the literature, (2) information loss during the conversion of time-series data into images for the deep-learning-based approach, and (3) additional issues, such as misclassification by trained models and requirements of the threshold section in the rule-based approach. The results of these key investigations can be utilized to develop an effective anomaly detection process.

Distance mapping overlap complexity metric for class-imbalance problems

Data complexity for class-imbalance problems is a hot topic in the field of data mining. Classical data complexity measures use techniques such as kNN, which computes the nearest neighbors of each instance. However, the kNN-based method to obtain the nearest neighbors of all instances is an NP-hard problem, which is not conducive to large-scale data complexity calculations. In order to solve this problem, from the global and local perspectives, four distance map complexity metric methods are proposed, and the complexity values is called the distance map overlap index (DMOI). Firstly, we use Mahalanobis distance or standardized Euclidean distance to calculate the distance of the instance to the center point of the data set, and arrange by the distance value of each instance. Then, according to the sequential label vector, iteratively searches the number of map cut-points for each class. Finally, according to the number of map cut-points of different classes, the DMOI of the data set is calculated. Experiments on 50 class-imbalanced datasets show that the DMOI method outperforms state-of-the-art complexity measures for class-imbalanced problems. Although there is still a gap between DMOI and ONB for rule-based or tree-based classifiers, the use of Pearson correlation coefficient shows that DMOI can effectively approximate ONB, and there is a strong positive correlation between them.