Classifier System Research Articles

Evaluation of Multiple Classifier Systems for Mapping Different Hierarchical Levels of Forest Ecosystems in the Mediterranean Region Using Sentinel-2, Sentinel-1, and ICESat-2 Data

The conservation and management of forest areas require knowledge about their extent and attributes on multiple scales. The combination of multiple classifiers has been proposed as an attractive classification approach for improved accuracy and robustness that can efficiently exploit the complementary nature of diverse remote sensing data and the merits of individual classifiers. The aim of this study was to develop and evaluate multiple classifier systems (MCSs) within a cloud-based computing environment for multi-scale forest mapping in Northeastern Greece using passive and active remote sensing data. Five individual machine learning base classifiers were used for class discrimination across the three different hierarchy levels, and five ensemble approaches were used for combining them. In the case of the binary classification scheme in the upper level of the hierarchy for separating woody vegetation (forest and shrubs) from other land, the overall accuracy (OA) slightly increased with the use of the MCS approach, reaching 94%. At the lower hierarchical levels, when using the support vector machine (SVM) base classifier, OA reached 84.13% and 74.89% for forest type and species mapping, respectively, slightly outperforming the MCS approach. Yet, two MCS approaches demonstrated robust performance in terms of per-class accuracy, presenting the highest average F1 score across all classification experiments, indicating balanced misclassification errors across all classes. Since the competence of individual classifiers is dependent on individual scene settings and data characteristics, we suggest that the adoption of MCS systems in efficient computing environments (i.e., cloud) could alleviate the need for algorithm benchmarking for Earth’s surface cover mapping.

Early Prognostication of Critical Patients With Spinal Cord Injury: A Machine Learning Study With 1485 Cases.

A retrospective case-series. The study aims to use machine learning to predict the discharge destination of spinal cord injury (SCI) patients in the intensive care unit. Prognostication following SCI is vital, especially for critical patients who need intensive care. Clinical data of patients diagnosed with SCI were extracted from a publicly available intensive care unit database. The first recorded data of the included patients were used to develop a total of 98 machine learning classifiers, seeking to predict discharge destination (eg, death, further medical care, home, etc.). The microaverage area under the curve (AUC) was the main indicator to assess discrimination. The best average-AUC classifier and the best death-sensitivity classifier were integrated into an ensemble classifier. The discrimination of the ensemble classifier was compared with top death-sensitivity classifiers and top average-AUC classifiers. In addition, prediction consistency and clinical utility were also assessed. A total of 1485 SCI patients were included. The ensemble classifier had a microaverage AUC of 0.851, which was only slightly inferior to the best average-AUC classifier ( P =0.10). The best average-AUC classifier death sensitivity was much lower than that of the ensemble classifier. The ensemble classifier had a death sensitivity of 0.452, which was inferior to the top 8 death-sensitivity classifiers, whose microaverage AUC were inferior to the ensemble classifier ( P <0.05). In addition, the ensemble classifier demonstrated a comparable Brier score and superior net benefit in the DCA when compared with the performance of the origin classifiers. The ensemble classifier shows an overall superior performance in predicting discharge destination, considering discrimination ability, prediction consistency, and clinical utility. This classifier system may aid in the clinical management of critical SCI patients in the early phase following injury. Level 3.

Phylogenetic analyses for the origin of sortal classifiers in Mongolic, Tungusic, and Turkic languages

AbstractNumeral classifiers are one of the most common types of nominal classification systems. Their geographical distribution worldwide is concentrated in Asia, which infers a scheme of diffusion from a linguistic innovation. This study investigates the origin of classifier systems in the Mongolic, Tungusic, and Turkic languages in the Altaic region with a phylogenetic analysis based on data from 55 languages. The Single Origin Hypothesis suggests that Sinitic is the most probable original source of classifier systems found in Asia (Her &amp; Li 2023). Under this hypothesis, classifiers are unlikely to be an indigenous feature of the Altaic region, and indeed their phylogenetic signal turns out to be weak. We also conduct a qualitative analysis on the classifier inventory of the studied languages to assess the robustness of phylogenetic methods. The results also indicate that classifiers are most likely a borrowed feature in the Mongolic, Tungusic, and Turkic languages.

Assessing Model Requirements for Explainable AI: A Template and Exemplary Case Study.

In sociotechnical settings, human operators are increasingly assisted by decision support systems. By employing such systems, important properties of sociotechnical systems, such as self-adaptation and self-optimization, are expected to improve further. To be accepted by and engage efficiently with operators, decision support systems need to be able to provide explanations regarding the reasoning behind specific decisions. In this article, we propose the use of learning classifier systems (LCSs), a family of rule-based machine learning methods, to facilitate and highlight techniques to improve transparent decision-making. Furthermore, we present a novel approach to assessing application-specific explainability needs for the design of LCS models. For this, we propose an application-independent template of seven questions. We demonstrate the approach's use in an interview-based case study for a manufacturing scenario. We find that the answers received do yield useful insights for a well-designed LCS model and requirements for stakeholders to engage actively with an intelligent agent.

Lateralized Learning to Solve Complex Boolean Problems.

Modern classifier systems can effectively classify targets that consist of simple patterns. However, they can fail to detect hierarchical patterns of features that exist in many real-world problems, such as understanding speech or recognizing object ontologies. Biological nervous systems have the ability to abstract knowledge from simple and small-scale problems in order to then apply it to resolve more complex problems in similar and related domains. It is thought that lateral asymmetry of biological brains allows modular learning to occur at different levels of abstraction, which can then be transferred between tasks. This work develops a novel evolutionary machine-learning (EML) system that incorporates lateralization and modular learning at different levels of abstraction. The results of analyzable Boolean tasks show that the lateralized system has the ability to encapsulate underlying knowledge patterns in the form of building blocks of knowledge (BBK). Lateralized abstraction transforms complex problems into simple ones by reusing general patterns (e.g., any parity problem becomes a sequence of the 2-bit parity problem). By enabling abstraction in evolutionary computation, the lateralized system is able to identify complex patterns (e.g., in hierarchical multiplexer (HMux) problems) better than existing systems.

Automated Recognition Systems: Theoretical and Practical Implementation of Active Learning for Extracting Knowledge in Image-based Transfer Learning of Living Organisms

In our research, we propose a model that leverages transfer learning and active learning techniques to accumulate knowledge and effectively solve complex problems in the field of artificial intelligence. This model operates within a parallel learning paradigm, aiming to mimic the continuous learning and improvement observed in human beings. To facilitate knowledge accumulation, we introduce a convolutional deep classification auto encoder that extracts spatially localized features from images. This enhances the model’s ability to extract relevant information. Additionally, we propose a learning classification system based on a code fragment, enabling effective representation and transfer of knowledge across different domains. Our research culminates in a theoretical and practical prototype for active learning-based knowledge extraction in various living organisms, including humans, plants, and animals. This knowledge extraction is achieved through image-based learning transfer, focusing on advancing activity recognition in image processing. Experimental results confirm that our method outperforms both baseline approaches and state-of-the-art convolutional neural network methods, underscoring its effectiveness and potential.

Comprehensive DNA Methylation Profiling of Medullary Thyroid Carcinoma: Molecular Classification, Potential Therapeutic Target, and Classifier System.

Medullary thyroid carcinoma (MTC) presents a distinct biological context from other thyroid cancers due to its specific cellular origin. This heterogeneous and rare tumor has a high prevalence of advanced diseases, making it crucial to address the limited therapeutic options and enhance complex clinical management. Given the high clinical accessibility of methylation information, we construct the largest MTC methylation cohort to date. Seventy-eight fresh-frozen MTC samples constituted our methylation cohort. The comprehensive study process incorporated machine learning, statistical analysis, and in vitro experiments. Our study pioneered the identification of a three-class clustering system for risk stratification, exhibiting pronounced epigenomic heterogeneity. The elevated overall methylation status in MTC-B, combined with the "mutual exclusivity" of hypomethylated sites displayed by MTC-A and MTC-C, distinctively characterized the MTC-specific methylation pattern. Integrating with the transcriptome, we further depicted the features of these three clusters to scrutinize biological properties. Several MTC-specific aberrant DNA methylation events were emphasized in our study. NNAT expression was found to be notably reduced in poor-prognostic MTC-C, with its promoter region overlapping with an upregulated differentially methylated region. In vitro experiments further affirmed NNAT's therapeutic potential. Moreover, we built an elastic-net logistic regression model with a relatively high AUC encompassing 68 probes, intended for future validation and systematic clinical application. Conducting research on diseases with low incidence poses significant challenges, and we provide a robust resource and comprehensive research framework to assist in ongoing MTC case inclusion and facilitate in-depth dissection of its molecular biological features.

A novel continual reinforcement learning-based expert system for self-optimization of soft real-time systems

Virtual globes are soft real-time systems, which stream multi-resolution data sets and render world-scale landscapes in real-time. Such systems require an adaptation mechanism to fulfill user and quality of experience (QoE) requirements. Configuration and tuning of parameters to optimize system performance is challenging due to run-time uncertainties. In this work, we propose a continual reinforcement learning-based expert system for self-optimization of a soft real-time system to meet user and quality objectives. The proposed system is capable of learning continuously by utilizing the previously learned knowledge to fulfill adaptation requirements. The proposed managing system interacts with a managed system and evolves a knowledge base of adaptation rules for run-time optimization of the managed system to meet user and quality objectives. We devise a learning classifier system for the evolution, storage, and transfer of adaptation rules using a code fragments-based rich encoding scheme. We transform user goals, system states, and execution environment conditions into observable states. We validated the proposed system for the same and cross-domain knowledge transfer and reuse scenarios for different user goals and execution environments. The results of the proposed system are compared with baseline and state-of-the-art methods where the proposed system outperformed the methods in terms of adaptation accuracy.

Discovering Rules for Rule-Based Machine Learning with the Help of Novelty Search

Automated prediction systems based on machine learning (ML) are employed in practical applications with increasing frequency and stakeholders demand explanations of their decisions. ML algorithms that learn accurate sets of rules, such as learning classifier systems (LCSs), produce transparent and human-readable models by design. However, whether such models can be effectively used, both for predictions and analyses, strongly relies on the optimal placement and selection of rules (in ML this task is known as model selection). In this article, we broaden a previous analysis on a variety of techniques to efficiently place good rules within the search space based on their local prediction errors as well as their generality. This investigation is done within a specific pre-existing LCS, named SupRB, where the placement of rules and the selection of good subsets of rules are strictly separated—in contrast to other LCSs where these tasks sometimes blend. We compare two baselines, random search and (1, lambda )-evolution strategy (ES), with six novelty search variants: three novelty-/fitness weighing variants and for each of those two differing approaches on the usage of the archiving mechanism. We find that random search is not sufficient and sensible criteria, i.e., error and generality, are indeed needed. However, we cannot confirm that the more complicated-to-explain novelty search variants would provide better results than (1, lambda )-ES which allows a good balance between low error and low complexity in the resulting models.

Designing a Classifying System for Nonprofit Organizations Using Textual Contents from the Mission Statement

ABSTRACT Comparing an entity’s financial indicators with those of similar organizations can provide a better understanding of its operational and financial health. This study describes the design and implementation of a prototype multilabel classification method to categorize nonprofit organizations (NPOs) using the textual content of their mission statements to enable beneficial comparisons. Positive unlabeled learning was used to improve the classification performance of partially labeled data. Naive Bayes, Gradient Boosting, Random Forest, and Support Vector Machine (SVM) algorithms were applied to determine the most effective method for classifying NPOs. The SVM model performed best in identifying “Housing and Shelter” organizations. The SVM classifier identified organizations that were not previously classified as “Housing and Shelter” but provided housing and shelter services as a part of their programs and activities. The new classification method can help donors, grant providers, and researchers to identify similar nonprofit organizations at the operational level.

Fundus-DeepNet: Multi-label deep learning classification system for enhanced detection of multiple ocular diseases through data fusion of fundus images

Detecting multiple ocular diseases in fundus images is crucial in ophthalmic diagnosis. This study introduces the Fundus-DeepNet system, an automated multi-label deep learning classification system designed to identify multiple ocular diseases by integrating feature representations from pairs of fundus images (e.g., left and right eyes). The study initiates with a comprehensive image pre-processing procedure, including circular border cropping, image resizing, contrast enhancement, noise removal, and data augmentation. Subsequently, discriminative deep feature representations are extracted using multiple deep learning blocks, namely the High-Resolution Network (HRNet) and Attention Block, which serve as feature descriptors. The SENet Block is then applied to further enhance the quality and robustness of feature representations from a pair of fundus images, ultimately consolidating them into a single feature representation. Finally, a sophisticated classification model, known as a Discriminative Restricted Boltzmann Machine (DRBM), is employed. By incorporating a Softmax layer, this DRBM is adept at generating a probability distribution that specifically identifies eight different ocular diseases. Extensive experiments were conducted on the challenging Ophthalmic Image Analysis-Ocular Disease Intelligent Recognition (OIA-ODIR) dataset, comprising diverse fundus images depicting eight different ocular diseases. The Fundus-DeepNet system demonstrated F1-scores, Kappa scores, AUC, and final scores of 88.56 %, 88.92 %, 99.76 %, and 92.41 % in the off-site test set, and 89.13 %, 88.98 %, 99.86 %, and 92.66 % in the on-site test set.In summary, the Fundus-DeepNet system exhibits outstanding proficiency in accurately detecting multiple ocular diseases, offering a promising solution for early diagnosis and treatment in ophthalmology.

Building Multiple Classifier Systems Using Linear Combinations of Reduced Graphs

Despite great efforts done in research in the last decades, the classification of general graphs, i.e., graphs with unconstrained labeling and structure, remains a challenging task. Due to the inherent relational structure of graphs it is difficult, or even impossible, to apply standard pattern recognition methods to graphs to achieve high recognition accuracies. Common methods to solve the non-trivial problem of graph classification employ graph matching in conjunction with a distance-based classifier or a kernel machine. In the present paper, we address the specific task of graph classification by means of a novel framework that uses information acquired from a broad range of reduced graph subspaces. Our novel approach can be roughly divided into three successive steps. In the first step, differently reduced graphs are created out of the original graphs relying on node centrality measures. In the second step, we compute the graph edit distance between each reduced graph and all the other graphs of the corresponding graph subspace. Finally, we linearly combine the distances in the third step and feed them into a distance-based classifier to obtain the final classification result. On six graph data sets, we empirically confirm that the proposed multiple classifier system directly benefits from the combined distances computed in the various graph subspaces.

Global Nuclear Explosion Discrimination Using a Convolutional Neural Network

AbstractUsing P‐wave seismograms, we trained a seismic source classifier using a Convolutional Neural Network. We trained for three classes: earthquake P‐wave, underground nuclear explosion (UNE) P‐wave, and noise. With the current absence of nuclear testing by countries that have signed the Comprehensive Test Ban Treaty, high quality seismic data from UNEs is limited. Even with limited training data, our model can accurately characterize most events recorded at regional and teleseismic distances, finding over 95% signals in the validation set. We applied the model on holdout datasets of the North Korean test explosions to evaluate the performance on unique region and station‐source pairs, with promising results. Additionally, we tested on the Source Physics Experiment events to investigate the potential for chemical explosions to act as a surrogate for nuclear explosions. We anticipate that machine‐learning models like our classifier system can have broad application for other seismic signals including volcanic and non‐volcanic tremor, anomalous earthquakes, ice‐quakes or landslide‐quakes.

A Novel Two-Stage Induced Deep Learning System for Classifying Similar Drugs with Diverse Packaging.

Dispensing errors play a crucial role in various medical errors, unfortunately emerging as the third leading cause of death in the United States. This alarming statistic has spurred the World Health Organization (WHO) into action, leading to the initiation of the Medication Without Harm Campaign. The primary objective of this campaign is to prevent dispensing errors from occurring and ensure patient safety. Due to the rapid development of deep learning technology, there has been a significant increase in the development of automatic dispensing systems based on deep learning classification to avoid dispensing errors. However, most previous studies have focused on developing deep learning classification systems for unpackaged pills or drugs with the same type of packaging. However, in the actual dispensing process, thousands of similar drugs with diverse packaging within a healthcare facility greatly increase the risk of dispensing errors. In this study, we proposed a novel two-stage induced deep learning (TSIDL)-based system to classify similar drugs with diverse packaging efficiently. The results demonstrate that the proposed TSIDL method outperforms state-of-the-art CNN models in all classification metrics. It achieved a state-of-the-art classification accuracy of 99.39%. Moreover, this study also demonstrated that the TSIDL method achieved an inference time of only 3.12 ms per image. These results highlight the potential of real-time classification for similar drugs with diverse packaging and their applications in future dispensing systems, which can prevent dispensing errors from occurring and ensure patient safety efficiently.

Current Trends in Feature Extraction and Classification Methodologies of Biomedical Signals.

Biomedical signal and image processing is the study of the dynamic behavior of various bio-signals, which benefits academics and research. Signal processing is used to assess the behavior of analogue and digital signals for the assessment, reconfiguration, improved efficiency, extraction of features, and reorganization of patterns. This paper unveils hidden characteristic information about input signals using feature extraction methods. The main feature extraction methods used in signal processing are based on studying time, frequency, and frequency domain. Feature exaction methods are used for data reduction, comparison, and reducing dimensions, producing the original signal with sufficient accuracy with a structure of an efficient and robust pattern for the classifier system. Therefore, an attempt has been made to study the various feature extraction methods, feature transformation methods, classifiers, and datasets for biomedical signals.

PCSVD: A hybrid feature extraction technique based on principal component analysis and singular value decomposition

&lt;p&gt;Feature extraction plays an important role in accurate preprocessing and real-world applications. High-dimensional features in the data have a significant impact on the machine learning classification system. Relevant feature extraction is a fundamental step not only to reduce the dimensionality but also to improve the performance of the classifier. In this paper, the author proposes a hybrid dimensionality reduction technique using principal component analysis (PCA) and singular value decomposition (SVD) in a machine classification system with a support vector classifier (SVC). To evaluate the performance of PCSVD, the results are compared without using feature extraction techniques or with existing methods of independent component analysis (ICA), PCA, linear discriminant analysis (LDA), and SVD. In addition, the efficiency of the PCSVD method is measured on an increased scale of 1.54% accuracy, 2.70% sensitivity, 3.71% specificity, and 3.58% precision. In addition, reduce the 15% dimensionality and 40.60% RMSE, which are better than existing techniques found in the literature.&lt;/p&gt;

Deep learning system for classification of ploidy status using time-lapse videos

To develop a spatiotemporal model for de prediction of euploid and aneuploid embryos using time-lapse videos from 10-115 hours after insemination (hpi). Retrospective study. The research used an end-to-end approach to develop an automated artificial intelligence system capable of extracting features from images and classifying them, considering spatiotemporal dependencies. A convolutional neural network extracted the most relevant features from each video frame. A bidirectional long short-term memory layer received this information and analyzed the temporal dependencies, obtaining a low-dimensional feature vector that characterized each video. A multilayer perceptron classified them into 2 groups, euploid and noneuploid. The model performance in accuracy fell between 0.6170 and 0.7308. A multi-input model with a gate recurrent unit module performed better than others; the precision (or positive predictive value) is 0.8205 for predicting euploidy. Sensitivity, specificity, F1-Score and accuracy are 0.6957, 0.7813, 0.7042, and 0.7308, respectively. This article proposes an artificial intelligence solution for prioritizing euploid embryo transfer. We can highlight the identification of a noninvasive method for chromosomal status diagnosis using a deep learning approach that analyzes raw data provided by time-lapse incubators. This method demonstrated potential automation of the evaluation process, allowing spatial and temporal information to encode.

Optimizing the Selection of Base Learners for Multiple Classifier System in Liver Cancer Identification Using Contribution-based Iterative Removal Algorithm

Optimizing the Selection of Base Learners for Multiple Classifier System in Liver Cancer Identification Using Contribution-based Iterative Removal Algorithm

Feature Normalization and Cartography-Based Demonstrations for Prompt-Based Fine-Tuning on Emotion-Related Tasks

To train a model in a traditional supervised learning classification system for natural language processing (NLP) tasks, it is essential to have labeled data, which is not present in large amounts for many tasks. Prompt-based learning methods attempt to combat the supervised learning need for labeled data by directly adapting pre-trained language models and modeling the probability of text itself. In this paper, we propose a novel data-agnostic strategy for prompt-based fine-tuning that leverages feature moments (a.k.a., mean and standard deviation) as a data augmentation technique and employs training dynamics (i.e., confidence and variability) to allow more informative samples to be concatenated for generating demonstrations as input context. Our approach is a strong method for few-shot learning that forces the language model to pay special attention to the feature moments and allows more informative samples to be concatenated for generating demonstrations as input context by selecting high confidence and low variance samples. To demonstrate its effectiveness given limited training data, we conduct extensive experiments in different few-shot settings on three empathy and emotion classification datasets (from various domains). We further evaluate our method's robustness by introducing noise to our few-shot input data and labels and show that exchanging moments between samples and incorporating cartography-based demonstrations are beneficial when the available data is limited and noisy.

An IoT-Based Framework for Personalized Health Assessment and Recommendations Using Machine Learning

To promote a healthy lifestyle, it is essential for individuals to maintain a well-balanced diet and engage in customized workouts tailored to their specific body conditions and health concerns. In this study, we present a framework that assesses an individual’s existing health conditions, enabling people to evaluate their well-being conveniently without the need for a doctor’s consultation. The framework includes a kit that measures various health indicators, such as body temperature, pulse rate, blood oxygen level, and body mass index (BMI), requiring minimal effort from nurses. To analyze the health parameters, we collected data from a diverse group of individuals aged 17–24, including both men and women. The dataset consists of pulse rate (BPM), blood oxygen level (SpO2), BMI, and body temperature, obtained through an integrated Internet of Things (IoT) unit. Prior to analysis, the data was augmented and balanced using machine learning algorithms. Our framework employs a two-stage classifier system to recommend a balanced diet and exercise based on the analyzed data. In this work, machine learning models are utilized to analyze specifically designed datasets for adult healthcare frameworks. Various techniques, including Random Forest, CatBoost classifier, Logistic Regression, and MLP classifier, are employed for this analysis. The algorithm demonstrates its highest accuracy when the training and testing datasets are divided in a 70:30 ratio, resulting in an average accuracy rate of approximately 99% for the mentioned algorithms. Through experimental analysis, we discovered that the CatBoost algorithm outperforms other approaches in terms of achieving maximum prediction accuracy. Additionally, we have developed an interactive web platform that facilitates easy interaction with the implemented framework, enhancing the user experience and accessibility.