Average F1 Score Research Articles

End-to-end deep learning patient level classification of affected territory of ischemic stroke patients in DW-MRI.

To develop an end-to-end DL model for automated classification of affected territory in DWI of stroke patients. In this retrospective multicenter study, brain DWI studies from January 2017 to April 2020 from Center 1, from June 2020 to December 2020 from Center 2, and from November 2019 to April 2020 from Center 3 were included. Four radiologists labeled images into five classes: anterior cerebral artery (ACA), middle cerebral artery (MCA), posterior circulation (PC), and watershed (WS) regions, as well as normal images. Additionally, for Center 1, clinical information was encoded as a domain knowledge vector to incorporate into image embeddings. 3D convolutional neural network (CNN) and attention gate integrated versions for direct 3D encoding, long short-term memory (LSTM-CNN), and time-distributed layer for slice-based encoding were employed. Balanced classification accuracy, macro averaged f1 score, AUC, and interrater Cohen's kappa were calculated. Overall, 624 DWI MRIs from 3 centers were utilized (mean age, interval: 66.89 years, 29-95 years; 345 male) with 439 patients in the training, 103 in the validation, and 82 in the test sets. The best model was a slice-based parallel encoding model with 0.88 balanced accuracy, 0.80 macro-f1 score, and an AUC of 0.98. Clinical domain knowledge integration improved the performance with 0.93 best overall accuracy with parallel stream model embeddings and support vector machine classifiers. The mean kappa value for interrater agreement was 0.87. Developed end-to-end deep learning models performed well in classifying affected regions from stroke in DWI. The end-to-end deep learning model with a parallel stream encoding strategy for classifying stroke regions in DWI has performed comparably with radiologists.

A Novel Workflow for Mapping Forest Canopy Height by Synergizing ICESat-2 and Multi-Sensor Data

Precise information on forest canopy height (FCH) is critical for forest carbon stocks estimation and management, but mapping continuous FCH with satellite data at regional scale is still a challenge. By fusing ICESat-2, Sentinel-1/2 images and ancillary data, this study aimed to develop a workflow to obtain an FCH map using a machine learning algorithm over large areas. The vegetation-type map was initially produced by a phenology-based spectral feature selection method. A forest characteristic-based model was then proposed to map spatially continuous FCH after a multivariate quality control. Our results show that the overall accuracy (OA) and average F1 Score (F1) for eight main vegetation types were more than 90% and 89%, respectively, and the vegetation-type map agreed well with the census areas. The forest characteristic-based model demonstrated a greater potential in FCH prediction, with an R-value 60.47% greater than the traditional single model, suggesting that the addition of the multivariate quality control and forest structure characteristics could positively contribute to the prediction of FCH. We generated a 30 m continuous FCH map by the forest characteristic-based model and evaluated the product with about 35 km2 of airborne laser scanning (ALS) validation data (R = 0.73, RMSE = 2.99 m), which were 45.34% more precise than the China FCH, 2019. These findings demonstrate the potential of our proposed workflow for monitoring regional continuous FCH, and will greatly benefit accurate forest resources assessment.

Multi-channel masked autoencoder and comprehensive evaluations for reconstructing 12-lead ECG from arbitrary single-lead ECG

Electrocardiogram (ECG) has emerged as a widely accepted diagnostic instrument for cardiovascular diseases (CVD). The standard clinical 12-lead ECG configuration causes considerable inconvenience and discomfort, while wearable devices offers a more practical alternative. To reduce information gap between 12-lead ECG and single-lead ECG, this study proposes a multi-channel masked autoencoder (MCMA) for reconstructing 12-Lead ECG from arbitrary single-lead ECG, and a comprehensive evaluation benchmark, ECGGenEval, encompass the signal-level, feature-level, and diagnostic-level evaluations. MCMA can achieve the state-of-the-art performance. In the signal-level evaluation, the mean square errors of 0.0175 and 0.0654, Pearson correlation coefficients of 0.7772 and 0.7287. In the feature-level evaluation, the average standard deviation of the mean heart rate across the generated 12-lead ECG is 1.0481, the coefficient of variation is 1.58%, and the range is 3.2874. In the diagnostic-level evaluation, the average F1-score with two generated 12-lead ECG from different single-lead ECG are 0.8233 and 0.8410.

Improving the risk profile of Indonesian enterprise taxpayers using multilabel classification

Optimizing tax revenues is difficult in Indonesia due to obstacles such as tax evasion and tax avoidance. It is closely related to an organization's compliance with tax regulations, known as the taxpayers risk profile. However, this mechanism does not accurately detect tax avoidance and tax evasion risks. To overcome this limitation, we use a multilabel classification machine learning method in this study, which classifies a single observation into one or more labels at once. The approach involves problem transformation (binary relevance and label powerset), algorithm adaptation (multilabel k-nearest neighbor (ML-kNN) and multilabel-adaptive resonance associative map (ML ARAM)), and ensemble (label space partitioning and random k-label sets with disjoint (RAkELd)). Based on the model performance comparisons, we discovered that the ML-ARAM method based on deep learning is the best, with an average F1-score of 95.5% and a hamming loss of 7.4%. We also examine the feature importance of the best model to reduce the dimensions of features so that we can identify the dominant factors that encourage a taxpayer entity to engage in tax avoidance or tax evasion. The findings of this study improve the accuracy of tax avoidance risk detection and tax evasion risk profiles using machine learning methods, ensuring maximum tax revenues in Indonesia.

Multichannel EMG-based gesture recognition utilizing advanced machine learning techniques: A random forest classifier for high-precision signal classification

This research examines how advanced machine learning algorithms can be used to classify multichannel electromyographic (EMG) signals with a high level of accuracy to assist in recognizing hand gestures. The goal is to create a robust and scalable system for gesture-based virtual control using EMG signals with potential applications in assistive technologies, rehabilitation, and human-computer interaction. Data were gathered using a MYO Thalmic bracelet containing eight EMG sensors on thirty-six subjects, and a Random Forest classifier was trained to identify seven distinct types of hand gestures (rest, fist clench, wrist flexion/extension, and radial/ulnar deviations). The machine learning pipeline included extensive preprocessing (i.e., EMG signal normalization and signal feature extraction; root mean square, waveform length, and zero crossing rate) and several hyperparameter tuning procedures to improve model performance. The Random Forest model (100 decision trees) achieved an overall classification accuracy of 98.68%, with a range of accuracies for each class (e.g., 95.2% wrist flexion and 91.8% ulnar deviation) when evaluated using cross-validation (i.e., average F1-score = 0.92, precision = 0.94, recall = .91). Overall, the study provides strong evidence for the effectiveness of ensemble learning methods at analyzing complex, multidimensional EMG signals. The high classification accuracy reported, in particular, demonstrates that the system could function for real-time recognition of hand gestures in a virtual environment. Ultimately, the initial work sets the stage for future exploration of a model that may be integrated with actuation models to control prosthetic limbs, virtual actors/avatars, and robotic devices. By demonstrating a scalable and efficient method of gesture recognition using EMG signals, these early findings enable future pathways and possibilities to design innovative, assistive solutions for digital systems that increase accessibility and interaction for users who are motor impaired or have a limited range of motion.

Enhancing Cardiovascular Disease Prediction Accuracy through an Ensemble Machine Learning Approach

This study explores the efficacy of an ensemble machine learning approach, specifically a Voting Classifier combining Decision Tree, k-Nearest Neighbors, and Gaussian Naive Bayes classifiers, in predicting cardiovascular diseases (CVDs). Utilizing a dataset consisting of 70,000 clinical records, the model was rigorously tested through 5-fold cross-validation, achieving remarkable results with average accuracies, precision, recall, and F1-scores all exceeding 99%. The findings validate the hypothesis that ensemble models, due to their capacity to leverage multiple learning algorithms, provide superior prediction accuracy and reliability compared to single predictor models. This research not only confirms the effectiveness of ensemble methods in medical diagnostics but also highlights their potential to enhance decision-making in clinical settings. Given the model's success in identifying various stages of cardiovascular conditions with high accuracy, it offers significant implications for early intervention and personalized patient management. Future research should aim to validate these results across more diverse populations and explore the integration of additional predictive factors that could refine the model's applicability. This study contributes to the computational health field by demonstrating how advanced machine learning techniques can be effectively applied in predicting health outcomes.

Optimizing Cardiomegaly Detection: A Random Forest Approach to Processed Chest X-ray Imagery

This study explores the application of a Random Forest Classifier for the automated detection of Cardiomegaly from chest X-ray images, utilizing a dataset processed and derived from the NIH Chest X-ray Dataset. Given the crucial need for accurate and timely diagnosis of Cardiomegaly to inform appropriate treatment decisions, this research aims to determine the efficacy of machine learning models in augmenting diagnostic processes. Employing image pre-processing techniques such as Sobel filtering for edge detection and Hu Moments for feature extraction, the study enhances the input features for the model. The performance of the classifier was evaluated using a 5-fold cross-validation approach, yielding results with average accuracy, precision, recall, and F1-scores ranging approximately between 52% and 54%. These findings suggest a moderate level of reliability and consistency, indicating the potential utility of ensemble machine learning methods in medical imaging analysis. However, the variability in performance across different data subsets highlights the challenges and necessitates further optimization. This research contributes to the ongoing discourse on integrating machine learning into clinical settings, demonstrating the potential benefits and current limitations. Future research is recommended to expand the dataset variety, integrate advanced deep learning methodologies, and rigorously test these models in clinical environments. The findings hold significant implications for the development of automated diagnostic tools in healthcare, potentially leading to enhanced diagnostic accuracy and efficiency.

Deep learning-based classifier for carcinoma of unknown primary using methylation quantitative trait loci.

Cancer of unknown primary (CUP) constitutes between 2% and 5% of human malignancies and is among the most common causes of cancer death in the United States. Brain metastases are often the first clinical presentation of CUP; despite extensive pathological and imaging studies, 20%-45% of CUP are never assigned a primary site. DNA methylation array profiling is a reliable method for tumor classification but tumor-type-specific classifier development requires many reference samples. This is difficult to accomplish for CUP as many cases are never assigned a specific diagnosis. Recent studies identified subsets of methylation quantitative trait loci (mQTLs) unique to specific organs, which could help increase classifier accuracy while requiring fewer samples. We performed a retrospective genome-wide methylation analysis of 759 carcinoma samples from formalin-fixed paraffin-embedded tissue samples using Illumina EPIC array. Utilizing mQTL specific for breast, lung, ovarian/gynecologic, colon, kidney, or testis (BLOCKT) (185k total probes), we developed a deep learning-based methylation classifier that achieved 93.12% average accuracy and 93.04% average F1-score across a 10-fold validation for BLOCKT organs. Our findings indicate that our organ-based DNA methylation classifier can assist pathologists in identifying the site of origin, providing oncologists insight on a diagnosis to administer appropriate therapy, improving patient outcomes.

Multiple-Instance Learning for thyroid gland disease classification: A hands-on experience

The morphological diagnosis of thyroid gland neoplasms presents a dual challenge: it requires the expertise of highly trained specialists and considerable time, particularly when evaluating multiple whole slide images (WSIs) from a single patient. The integration of artificial intelligence (AI) techniques into the diagnostic workflow is a hot area of research. However, most studies rely on meticulously curated datasets, the preparation of which is both costly and fraught with complexities. This paper investigates the development of machine learning models using weakly-annotated “real-world” data, devoid of the selective preprocessing typical in common research datasets. Our study demonstrates that a Multiple-Instance Learning (MIL) model, trained on a weak patient-level annotations of 1102 patients encompassing 5104 WSIs, successfully discriminates between benign and malignant conditions at the patient level, achieving an average test set F1-Score of 0.85 with a standard deviation of 0.05. This study is, to our knowledge, the first to report findings from an AI model trained on patient-level data without prior labeling refinement. Additionally, we identify potential pitfalls in data quality that could induce model overfitting, such as the inadvertent inclusion of dye used to highlight resection margins, which correlates with the target variable. We also assessed the impact of detailed slide-level versus coarse patient-level annotations on classification accuracy using a smaller, more precisely annotated dataset of 36 laboratory cases (91 WSIs). The results indicate that detailed annotations substantially enhance classification performance in smaller datasets.

Kolmogorov–Arnold Network in the Fault Diagnosis of Oil-Immersed Power Transformers

Instabilities in energy supply caused by equipment failures, particularly in power transformers, can significantly impact efficiency and lead to shutdowns, which can affect the population. To address this, researchers have developed fault diagnosis strategies for oil-immersed power transformers using dissolved gas analysis (DGA) to enhance reliability and environmental responsibility. However, the fault diagnosis of oil-immersed power transformers has not been exhaustively investigated. There are gaps related to real scenarios with imbalanced datasets, such as the reliability and robustness of fault diagnosis modules. Strategies with more robust models increase the overall performance of the entire system. To address this issue, we propose a novel approach based on Kolmogorov–Arnold Network (KAN) for the fault diagnosis of power transformers. Our work is the first to employ a dedicated KAN in an imbalanced data real-world scenario, named KANDiag, while also applying the synthetic minority based on probabilistic distribution (SyMProD) technique for balancing the data in the fault diagnosis. Our findings reveal that this pioneering employment of KANDiag achieved the minimal value of Hamming loss—0.0323—which minimized the classification error, guaranteeing enhanced reliability for the whole system. This ground-breaking implementation of KANDiag achieved the highest value of weighted average F1-Score—96.8455%—ensuring the solidity of the approach in the real imbalanced data scenario. In addition, KANDiag gave the highest value for accuracy—96.7728%—demonstrating the robustness of the entire system. Some key outcomes revealed gains of 68.61 percentage points for KANDiag in the fault diagnosis. These advancements emphasize the efficiency and robustness of the proposed system.

QuIDS: A Quantum Support Vector machine-based Intrusion Detection System for IoT networks

With the increasing popularity of IoT, there has been a noticeable surge in security breaches associated with vulnerable IoT devices. To identify and counter such attacks. Intrusion Detection Systems (IDS) are deployed. However, these IoT devices use device-specific application layer protocols like MQTT and CoAP, which pose an additional burden to the traditional IDS. Several Machine Learning (ML) and Deep Learning (DL) based IDS are developed to detect malicious IoT network traffic. However, in recent times, a variety of IoT devices have been available on the market, resulting in the frequent installation and uninstallation of IoT devices based on users’ needs. Moreover, ML and DL-based IDS must train with sufficient device-specific attack training data for each IoT device, consuming a noticeable amount of training time. To solve these problems, we propose QuIDS, which utilizes a Quantum Support Vector Classifier to classify attacks in an IoT network. QuIDS requires very little training data compared to ML or DL to train and accurately identify attacks in the IoT network. QuIDS extracts eight flow-level features from IoT network traffic and utilizes them over four quantum bits for training. We experimented with QuIDS on two publicly available datasets and found the average recall rate, precision, and f1-score of the QuIDS as 91.1%, 84.3%, and 86.4%, respectively. Moreover, comparing QuIDS with the ML and DL methods, we found that QuIDS outperformed by 37.7%, 24.4.6%, and 36.9% more average recall and precision rates than the ML and DL methods, respectively.

Enhancing multilabel classification for unbalanced COVID-19 vaccination hesitancy tweets using ensemble learning

Purpose:Vaccination plays a crucial role in public health strategies, particularly in combating contagious diseases like COVID-19. Despite developing and authorizing numerous vaccines, achieving widespread immunity remains a challenge. Understanding individuals’ willingness to receive vaccines is essential, and recent studies have explored acceptance rates across various regions. However, vaccine hesitancy is still considered a significant global health concern, even after the pandemic’s peak. Methods:This article explores the topic of classification in social media networks, specifically in tweets, focusing on the challenges of class imbalance and multilabel multiclass tweet classification. It investigates the effectiveness of oversampling in addressing unbalanced datasets and proposes an ensemble-based framework comprising various BERT models fine-tuned on diverse text corpora. Results:The proposed model was applied to a benchmark dataset containing 12 classes with a highly imbalanced distribution. Compared to recent literature, the model achieved significant improvements in performance metrics. We observed a 2% increase in micro, macro, and weighted average F1 scores, a 4% increase in accuracy, and a 3% increase in average Jaccard index when using the proposed framework on this unbalanced multi-labeled benchmark. Conclusion:The study investigated fine-tuning BERT models for improved classification in tweets on unbalanced datasets related to public health. The proposed ensemble approach with oversampling techniques yielded significant improvements in multiple metrics compared to existing methods. This suggests a promising approach to analyzing vaccine discourse on social media and potentially aiding public health efforts.

A deep neural network model with spectral correlation function for electrocardiogram classification and diagnosis of atrial fibrillation

Atrial Fibrillation (AF) is a common type of irregular heartbeat, and early detection can significantly improve treatment outcomes and prognoses. Single-lead Electrocardiogram (ECG) devices are under extensive scrutiny for monitoring patients' heart health worldwide. Standardized ECG signal monitoring has demonstrated a significant reduction in mortality rates associated with severe cardiovascular diseases. However, the automatic detection method for AF requires significant improvement. This study presents a novel approach that utilizes the cyclostationary analysis of ECG signals, uncovering a spectral hidden periodicity between the QRS-T (the main wave components representing electrical activity in the heart) complexes of the ECG signal through the Spectral Correlation Function (SCF). To validate the proposed method's performance, the single ECG's SCF coefficients are applied to the Convolutional Recurrent Neural Network (CRNN), which consists of convolutional and long short-term memory (LSTM) layers, on the 2017 PhysioNet challenge dataset. The obtained results demonstrate that the proposed approach efficiently represents ECG signals through SCF coefficients, leading to the accurate detection of AF with an average accuracy of 92.76% and an average F1-score of 89.1%.

Graph convolutional network for fast video summarization in compressed domain

Video summarization is the process of generating a concise and representative summary of a video by selecting its most important frames. It plays a vital role in the video streaming industry, allowing users to quickly understand the overall content of a video without watching it in its entirety. Most existing video summarization methods require fully decoding the video stream and extracting the features with a pre-trained deep learning model in the pixel domain, which is time-consuming and computationally expensive. To address this issue, this paper proposes a novel method called Graph Convolutional Network-based Compressed-domain Video Summarization (GCNCVS), which directly exploits the compressed-domain information and leverages graph convolutional network to learn temporal relationships between frames, thereby enhancing its ability to capture contextual and valuable information when generating summarized videos. To evaluate the performance of GCNCVS, we conduct experiments on two benchmark datasets, SumMe and TVSum. Experimental results demonstrate that our method outperforms existing methods, achieving an average F-score of 53.5% on the SumMe dataset and 72.3% on the TVSum dataset. Additionally, the proposed method shows Kendall's τ correlation coefficient of 0.157 and Spearman's ρ correlation coefficient of 0.205 on the TVSum dataset. Our method also significantly reduces computational time, which enhances the feasibility of video summarization in video streaming environments.

Navigating Complexity: GPT-4's Performance in Predicting Earnings and Stock Returns in China's A-Share Market

This study investigates the application of GPT-4, a large language model, in predicting earnings changes and stock returns within China's A-share market from 2000 to 2023. We evaluate the model's performance using various metrics, including prediction accuracy, F1 score, stock returns, Sharpe ratio, and alpha. Our findings reveal significant fluctuations in the model's predictive accuracy, ranging from 10.62% to 48.67%, with an average F1 score of 0.30. Despite inconsistent accuracy, the model maintained high prediction confidence levels between 75% and 90%. Stock returns associated with the model's predictions varied widely, from -4.86% to 13.59%, showing no consistent correlation with prediction accuracy. The study highlights the challenges of applying AI models to financial analysis in emerging markets, particularly given the unique characteristics of China's A-share market, such as frequent policy interventions and a high proportion of retail investors. We discuss the implications of these findings for the future of AI-driven financial analysis, emphasizing the need for improved model calibration, ethical considerations, and regulatory frameworks.

Optimization of Tourism Destination Recommendations in Batang Regency Using Content-Based Filtering

In an era where tourism plays a pivotal role in economic development, the need for effective navigation through diverse attractions has never been more critical. This research presents a cutting-edge tourism recommendation system tailored for Batang Regency, leveraging Content-Based Filtering (CBF) to deliver personalized suggestions that enhance the tourist experience. By categorizing tourist attractions into Culinary, Culture, Accommodation, Nature, and Leisure, and employing the Haversine formula for precise geographical calculations, our system prioritizes recommendations based on user preferences and proximity. Recommendation testing yielded an impressive average F1 Score of 0.965, underscoring the system's accuracy and relevance, particularly in straightforward user scenarios. However, the research also identifies challenges in more complex cases, suggesting the need for future enhancements through hybrid models and the integration of user feedback. This innovative approach not only streamlines the decision-making process for tourists but also aims to boost local tourism, making it an invaluable tool for both visitors and the Batang Regency community. Join us in exploring how technology can transform the way we experience travel, ensuring that every journey is tailored to individual desires and needs.

The use of 4D data-independent acquisition-based proteomic analysis and machine learning to reveal potential biomarkers for stress levels.

Research suggests that individuals who experience prolonged exposure to stress may be at higher risk for developing psychological stress disorders. Currently, psychological stress is primarily evaluated by professional physicians using rating scales, which may be prone to subjective biases and limitations of the scales. Therefore, it is imperative to explore more objective, accurate, and efficient biomarkers for evaluating the level of psychological stress in an individual. In this study, we utilized 4D data-independent acquisition (4D-DIA) proteomics for quantitative protein analysis, and then employed support vector machine (SVM) combined with SHAP interpretation algorithm to identify potential biomarkers for psychological stress levels. Biomarkers validation was subsequently achieved through machine learning classification and a substantial amount of a priori knowledge derived from the knowledge graph. We performed cross-validation of the biomarkers using two batches of data, and the results showed that the combination of Glyceraldehyde-3-phosphate dehydrogenase and Fibronectin yielded an average area under the curve (AUC) of 92%, an average accuracy of 86%, an average F1 score of 79%, and an average sensitivity of 83%. Therefore, this combination may represent a potential approach for detecting stress levels to prevent psychological stress disorders.

Explainable Pre-Trained Language Models for Sentiment Analysis in Low-Resourced Languages

Sentiment analysis is a crucial tool for measuring public opinion and understanding human communication across digital social media platforms. However, due to linguistic complexities and limited data or computational resources, it is under-represented in many African languages. While state-of-the-art Afrocentric pre-trained language models (PLMs) have been developed for various natural language processing (NLP) tasks, their applications in eXplainable Artificial Intelligence (XAI) remain largely unexplored. In this study, we propose a novel approach that combines Afrocentric PLMs with XAI techniques for sentiment analysis. We demonstrate the effectiveness of incorporating attention mechanisms and visualization techniques in improving the transparency, trustworthiness, and decision-making capabilities of transformer-based models when making sentiment predictions. To validate our approach, we employ the SAfriSenti corpus, a multilingual sentiment dataset for South African under-resourced languages, and perform a series of sentiment analysis experiments. These experiments enable comprehensive evaluations, comparing the performance of Afrocentric models against mainstream PLMs. Our results show that the Afro-XLMR model outperforms all other models, achieving an average F1-score of 71.04% across five tested languages, and the lowest error rate among the evaluated models. Additionally, we enhance the interpretability and explainability of the Afro-XLMR model using Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP). These XAI techniques ensure that sentiment predictions are not only accurate and interpretable but also understandable, fostering trust and reliability in AI-driven NLP technologies, particularly in the context of African languages.

ResNet-Transformer deep learning model-aided detection of dens evaginatus.

Dens evaginatus is a dental morphological developmental anomaly. Failing to detect it may lead to tubercles fracture and pulpal/periapical disease. Consequently, early detection and intervention of dens evaginatus are significant to preserve vital pulp. This study aimed to develop a deep learning model to assist dentists in early diagnosing dens evaginatus, thereby supporting early intervention and mitigating the risk of severe consequences. In this study, a deep learning model was developed utilizing panoramic radiograph images sourced from 1410 patients aged 3-16 years, with high-quality annotations to enable the automatic detection of dens evaginatus. Model performance and model's efficacy in aiding dentists were evaluated. The findings indicated that the current deep learning model demonstrated commendable sensitivity (0.8600) and specificity (0.9200), outperforming dentists in detecting dens evaginatus with an F1-score of 0.8866 compared to their average F1-score of 0.8780, indicating that the model could detect dens evaginatus with greater precision. Furthermore, with its support, young dentists heightened their focus on dens evaginatus in tooth germs and achieved improved diagnostic accuracy. Based on these results, the integration of deep learning for dens evaginatus detection holds significance and can augment dentists' proficiency in identifying such anomaly.

Improving the Accuracy of RPA Image Classification in Vegetation Mapping of Magsaysay, Occidental Mindoro using RGB Indices, Canopy Heights, and Feature Importance Weighting

Abstract. Mapping vegetation cover is an important step in generating baseline data for various purposes such as smart agriculture, disaster and hazard monitoring, as well as risk assessment and planning. For this purpose, the use of Remotely Piloted Aircraft (RPA) has become prevalent in recent years as an efficient and cost-effective way of obtaining very-high-resolution images. However, it is limited by its lack of spectral bands used for discriminating between land cover classes, especially vegetation. An object-based approach was used due to its suitability with high-resolution input datasets, as it can recognize complex shapes and patterns aside from spectral characteristics. The drone images were segmented using optimal parameters to produce image objects which were subsequently classified through supervised learning using the Random Forest (RF) algorithm. This study incorporated non-conventional spectral indices that use RGB bands only, such as Triangular Greenness Index (TGI), Excess Green (ExG), and Tree-Grass Differentiation Index (TGDI), as well as the canopy height data derived from RPA photogrammetry to improve classification accuracy. To further improve model performance, appropriate band weights for segmentation were determined by running a RF classifier to obtain band importance values. Accuracy assessments reveal that using additional indices and heights improved the accuracy resulting in a 20% increase in the average f1-score, with the vegetation classes improving by a 25% increase in their f1-scores (8–41% improvement per class). Using the integration of band importance values as weights to the object-based segmentation slightly decreased accuracy values for the vegetation classes by an average of 0.04 in the f-1 score. The methods developed to improve the accuracy of RPA image classification make it more suitable for mapping vegetation.