Classification Algorithm Research Articles

Empowering the rapid authentication of the botanical origin of monofloral honey by coated blade spray mass spectrometry (CBS-MS)

In the quest for a rapid and cost-effective tool for determining the botanical origin of monofloral honey, the analytical capabilities of coated blade spray mass spectrometry (CBS-MS) were investigated. To this aim, the chemical profiles of 64 honey samples from seven different botanical origins (acacia, dandelion, chestnut, rhododendron, citrus, sunflower, and linden) were captured by the absorbent of the coated blades and then analyzed by mass spectrometry. An exploratory analysis was performed by principal component analysis (PCA) to generate a graphical representation of the CBS-MS data that allows the discovery of patterns, outliers, or relations between types of honey in an unsupervised manner. Additionally, the performances of four different classification algorithms (least absolute shrinkage and selection operator (LASSO), random forest (RF), and neural network (NNET) partial least squares discriminant analysis (PLS-DA)) were built up and compared. The performances of the four classifiers were verified by a 50 times-repeated, 5-fold-cross-validation and permutation test. Although all classifiers performed well, the RF showed significantly higher performances in cross-validation (with area under the curve (AUC) of 0.99, overall accuracy 0.94, Kappa 0.93, sensitivity 0.94, and specificity 0.99). Moreover, the permutation tests showed the models were not overfitted. Finally, to determine the molecular identities of the ions that most contribute to the classification, extracts from the same honey samples were prepared, analyzed by liquid chromatography coupled to high resolution tandem mass spectrometry (LC-HRMS/MS), and the most significant features were annotated. This proof-of-principle work warrants a future large-scale study to validate and challenge this CBS-MS-based method with a greater number of honeys from different years and geographical origins.

Thigh-worn accelerometry: a comparative study of two no-code classification methods for identifying physical activity types

BackgroundThe more accurate we can assess human physical behaviour in free-living conditions the better we can understand its relationship with health and wellbeing. Thigh-worn accelerometry can be used to identify basic activity types as well as different postures with high accuracy. User-friendly software without the need for specialized programming may support the adoption of this method. This study aims to evaluate the classification accuracy of two novel no-code classification methods, namely SENS motion and ActiPASS.MethodsA sample of 38 healthy adults (30.8 ± 9.6 years; 53% female) wore the SENS motion accelerometer (12.5 Hz; ±4 g) on their thigh during various physical activities. Participants completed standardized activities with varying intensities in the laboratory. Activities included walking, running, cycling, sitting, standing, and lying down. Subsequently, participants performed unrestricted free-living activities outside of the laboratory while being video-recorded with a chest-mounted camera. Videos were annotated using a predefined labelling scheme and annotations served as a reference for the free-living condition. Classification output from the SENS motion software and ActiPASS software was compared to reference labels.ResultsA total of 63.6 h of activity data were analysed. We observed a high level of agreement between the two classification algorithms and their respective references in both conditions. In the free-living condition, Cohen’s kappa coefficients were 0.86 for SENS and 0.92 for ActiPASS. The mean balanced accuracy ranged from 0.81 (cycling) to 0.99 (running) for SENS and from 0.92 (walking) to 0.99 (sedentary) for ActiPASS across all activity types.ConclusionsThe study shows that two available no-code classification methods can be used to accurately identify basic physical activity types and postures. Our results highlight the accuracy of both methods based on relatively low sampling frequency data. The classification methods showed differences in performance, with lower sensitivity observed in free-living cycling (SENS) and slow treadmill walking (ActiPASS). Both methods use different sets of activity classes with varying definitions, which may explain the observed differences. Our results support the use of the SENS motion system and both no-code classification methods.

Using Machine Learning for Endoscopic Detection of Low-Grade Subglottic Stenosis: A Proof of Principle.

The current study trains, tests, and evaluates a deep learning algorithm to detect subglottic stenosis (SGS) on endoscopy. A retrospective review of patients undergoing microlaryngoscopy-bronchoscopy was performed. A pretrained image classifier (Resnet50) was retrained and tested on 159 images of airways taken at the glottis, 106 normal-sized airways, and 122 with SGS. Data augmentation was performed given the small sample size to prevent overfitting. Overall model accuracy was 73.3% (SD: 3.8). Precision and recall for stenosis were 77.3% (SD: 4.0) and 72.7 (SD: 4.0). F1 score for the detection of stenosis was 0.75 (SD: 0.04). Precision and recall for normal-sized images were lower at 69% (SD: 4.35) and 74% (SD: 4), with an F1 score of 0.71 (SD: 0.04). This study demonstrates that an image classification algorithm can identify SGS on endoscopic images. Work is needed to improve diagnostic accuracy for eventual deployment of the algorithm into clinical care.

The classification algorithms to support the management of the patient with femur fracture

Effectiveness in health care is a specific characteristic of each intervention and outcome evaluated. Especially with regard to surgical interventions, organization, structure and processes play a key role in determining this parameter. In addition, health care services by definition operate in a context of limited resources, so rationalization of service organization becomes the primary goal for health care management. This aspect becomes even more relevant for those surgical services for which there are high volumes. Therefore, in order to support and optimize the management of patients undergoing surgical procedures, the data analysis could play a significant role. To this end, in this study used different classification algorithms for characterizing the process of patients undergoing surgery for a femoral neck fracture. The models showed significant accuracy with values of 81%, and parameters such as Anaemia and Gender proved to be determined risk factors for the patient’s length of stay. The predictive power of the implemented model is assessed and discussed in view of its capability to support the management and optimisation of the hospitalisation process for femoral neck fracture, and is compared with different model in order to identify the most promising algorithms. In the end, the support of artificial intelligence algorithms laying the basis for building more accurate decision-support tools for healthcare practitioners.

A comparative study of heterogeneous machine learning algorithms for arrhythmia classification using feature selection technique and multi-dimensional datasets

Arrhythmia, a common cardiovascular disorder, refers to the abnormal electrical activity within the heart, leading to irregular heart rhythms. This condition affects millions of people worldwide, with severe implications on cardiac function and overall health. Arrhythmias can strike anyone at any age which is a significant cause of morbidity and mortality on a global scale. About 80% of deaths related to heart disease are caused by ventricular arrhythmias. This research investigated the application of an optimized multi-objectives supervised Machine Learning (ML) models for early arrhythmia diagnosis. The authors evaluated the model’s performance on the arrhythmia dataset from the UCI ML repository with varying train-test splits (70:30, 80:20, and 90:10). Standard preprocessing techniques such as handling missing values, formatting, balancing, and directory analysis were applied along with Pearson correlation for feature selection, all aimed at enhancing model performance. The proposed optimized RF model achieved impressive performance metrics, including accuracy (95.24%), precision (100%), sensitivity (89.47%), and specificity (100%). Furthermore, the study compared the proposed approach to existing models, demonstrating significant improvements across various performance measures.

An online ensemble classification algorithm for multi-class imbalanced data stream

An online ensemble classification algorithm for multi-class imbalanced data stream

An improved random forest model for music genre classification algorithm based on sparrow search algorithm

In this study, a random forest model optimised based on the sparrow search algorithm is explored for the music genre classification problem. By introducing the sparrow search algorithm, the model is able to search the feature space more comprehensively during the training process, which improves the learning ability of complex data relationships. After 15 iterations of optimisation, the fitness value of the model is improved from 0.2002 to 0.197, showing better convergence. The performance on the training set shows that the model predicts 2,543 music genres with an accuracy of 99.59% and only 10 incorrect predictions, which verifies its excellent performance on the training data. While on the test set, the model's prediction accuracy for 623 music genres is 79.78%, which is slightly lower than the result of the training set, but still reflects good generalisation ability. The results of this paper imply that the improved random forest model based on the sparrow search algorithm has potential application prospects in the music genre classification task. By optimising the parameter settings and feature selection, we not only improve the prediction accuracy and generalisation ability of the model, but also provide new ideas for solving other complex data classification problems. In the future, we can further expand the sample size, try different feature combinations, and conduct in-depth research by combining more domain knowledge in order to further improve the model performance and promote the development of related fields.

Machine and Deep Learning Trends in EEG-Based Detection and Diagnosis of Alzheimer’s Disease: A Systematic Review

This article presents a systematic review using PRISMA methodology to explore trends in the use of machine and deep learning in diagnosing and detecting Alzheimer’s disease using electroencephalography. This review covers studies published between 2013 and 2023, drawing on three leading academic databases: Scopus, Web of Science, and PubMed. The validity of the databases is evaluated considering essential factors such as the arrangement of EEG electrodes, data acquisition methodologies, and the number of participants. Additionally, the specific properties of the databases used in the research are highlighted, including EEG signal classification, filtering, segmentation approaches, and selected features. Finally, the performance metrics of the classification algorithms are evaluated, especially the accuracy achieved, offering a comprehensive view of the current state and future trends in the use of these technologies for the diagnosis of Alzheimer’s disease.

Near-Term Quantum Classification Algorithms Applied to Antimalarial Drug Discovery.

Computational approaches are widely applied in drug discovery to explore properties related to bioactivity, physiochemistry, and toxicology. Over at least the last 20 years, the exploitation of machine learning on molecular data sets has been used to understand the structure-activity relationships that exist between biomolecules and druggable targets. More recently, these methods have also seen application for phenotypic screening data for neglected diseases such as tuberculosis and malaria. Herein, we apply machine learning to build quantum Quantitative Structure Activity Relationship models from antimalarial data sets. There is a continual need for new antimalarials to address drug resistance, and the readily available in vitro data sets could be utilized with newer machine learning approaches as these develop. Furthermore, quantum machine learning is a relatively new method that uses a quantum computer to perform the calculations. First, we present a classical-quantum hybrid computational approach by building a Latent Bernoulli Autoencoder machine learning model for compressing bit-vector descriptors to a size that can be adapted to quantum computers for classification tasks with limited loss of embedded information. Second, we apply our method for feature map compression to quantum classification algorithms, including a completely novel machine learning algorithm with no analogy in classical computers: the Quantum Fourier Transform Classifier. We apply both these approaches to build quantum machine learning models for small-molecule antimalarials with quantum simulation software and then benchmark these quantum models against classical machine learning approaches. While there are many challenges currently facing the development of reliable quantum computers, our results demonstrate that there is potential for the use of this technology in the field of drug discovery.

Spectral sensor‐based device for real‐time detection and severity estimation of groundnut bud necrosis virus in tomato

AbstractA machine learning‐based approach was utilized to develop a device for groundnut bud necrosis virus (GBNV) disease severity detection and estimation in tomato plants (Solanum lycopersicum L.). The study involved inoculating tomato plants with GBNV, monitoring changes in morphological and spectral characteristics, evaluating machine learning algorithms (decision tree [DT] classifier) for analysis and classification of disease severity, and developing and validating a device for disease detection and severity estimation. Spectral data analysis revealed distinct patterns in reflectance, with notable peaks observed in the 680 and 760 nm bands, while reflectance remained low and constant beyond 900 nm. Machine learning techniques, specifically a DT model, were employed to classify disease severity based on spectral data with high accuracy (95.01% training accuracy and 93.65% testing accuracy). The model identified the near‐infrared band as highly correlated (correlation coefficient of 0.82) with disease severity. Furthermore, a compact handheld device integrating a spectral sensor, organic light‐emitting diode display, and Raspberry Pi 3B was developed for real‐time disease severity estimation. The device demonstrated robust performance, accurately predicting disease severity at different growth stages, even in the absence of visible symptoms. Additionally, disease severity percentages obtained via reverse transcription polymerase chain reaction were used to validate the accuracy of the device's estimations. Its responsive nature, with estimated response times ranging from milliseconds to seconds, facilitates timely interventions in agricultural settings. Overall, this interdisciplinary approach, combining spectral analysis, machine learning, and device development, presents a promising solution for efficient disease monitoring and management in agriculture, contributing to enhanced crop health and food security.

Optimizing Convolutional Neural Networks for Image Classification on Resource-Constrained Microcontroller Units

Running machine learning algorithms for image classification locally on small, cheap, and low-power microcontroller units (MCUs) has advantages in terms of bandwidth, inference time, energy, reliability, and privacy for different applications. Therefore, TinyML focuses on deploying neural networks on MCUs with random access memory sizes between 2 KB and 512 KB and read-only memory storage capacities between 32 KB and 2 MB. Models designed for high-end devices are usually ported to MCUs using model scaling factors provided by the model architecture’s designers. However, our analysis shows that this naive approach of substantially scaling down convolutional neural networks (CNNs) for image classification using such default scaling factors results in suboptimal performance. Consequently, in this paper we present a systematic strategy for efficiently scaling down CNN model architectures to run on MCUs. Moreover, we present our CNN Analyzer, a dashboard-based tool for determining optimal CNN model architecture scaling factors for the downscaling strategy by gaining layer-wise insights into the model architecture scaling factors that drive model size, peak memory, and inference time. Using our strategy, we were able to introduce additional new model architecture scaling factors for MobileNet v1, MobileNet v2, MobileNet v3, and ShuffleNet v2 and to optimize these model architectures. Our best model variation outperforms the MobileNet v1 version provided in the MLPerf Tiny Benchmark on the Visual Wake Words image classification task, reducing the model size by 20.5% while increasing the accuracy by 4.0%.

Using Nighttime Light Data to Explore the Extent of Power Outages in the Florida Panhandle after 2018 Hurricane Michael

The destructive forces of tropical cyclones can have significant impacts on the land, contributing to degradation through various mechanisms such as erosion, debris, loss of vegetation, and widespread damage to infrastructure. Storm surge and flooding can wash away buildings and other structures, deposit debris and sediments, and contaminate freshwater resources, making them unsuitable for both human use and agriculture. High winds and flooding often damage electrical disubstations and transformers, leading to disruptions in electricity supply. Restoration can take days or even weeks, depending on the extent of the damage and the resources available. In the meantime, communities affected by power outages may experience difficulties accessing essential services and maintaining communication. In this study, we used a weighted maximum likelihood classification algorithm to reclassify NOAA’s National Geodetic Survey Emergency Response Imagery scenes into debris, sand, water, trees, and roofs to assess the extent of the damage around Mexico Beach, Florida, following the 2018 Hurricane Michael. NASA’s Visible Infrared Imaging Radiometer Suite (VIIRS) Day/Night Band (DNB) was processed to estimate power outage duration and rate of restoration in the Florida Panhandle based on the 7-day moving averages. Percent loss of electrical service at a neighborhood level was estimated using the 2013–2017 American Community Survey block group data. Spatial lag models were employed to examine the association between restoration rates and socioeconomic factors. The analysis revealed notable differences in power-restoration rates between urbanized and rural areas and between disadvantaged and more affluent communities. The findings indicated that block groups with higher proportions of minorities, multi-family housing units, rural locations, and households receiving public assistance experienced slower restoration of power compared to urban and more affluent neighborhoods. These results underscore the importance of integrating socioeconomic factors into disaster preparedness and recovery-planning efforts, emphasizing the need for targeted interventions to mitigate disparities in recovery times following natural disasters.

An Analysis of Traditional Methods and Deep Learning Methods in SSVEP-Based BCI: A Survey

The brain–computer interface (BCI) is a direct communication channel between humans and machines that relies on the central nervous system. Neuroelectric signals are collected by placing electrodes, and after feature sampling and classification, they are converted into control signals to control external mechanical devices. BCIs based on steady-state visual evoked potential (SSVEP) have the advantages of high classification accuracy, fast information conduction rate, and relatively strong anti-interference ability, so they have been widely noticed and discussed. From k-nearest neighbor (KNN), multilayer perceptron (MLP), and support vector machine (SVM) classification algorithms to the current deep learning classification algorithms based on neural networks, a wide variety of discussions and analyses have been conducted by numerous researchers. This article summarizes more than 60 SSVEP- and BCI-related articles published between 2015 and 2023, and provides an in-depth research and analysis of SSVEP-BCI. The survey in this article can save a lot of time for scholars in understanding the progress of SSVEP-BCI research and deep learning, and it is an important guide for designing and selecting SSVEP-BCI classification algorithms.

An experimental review of the ensemble-based data stream classification algorithms in non-stationary environments

Data streams are sequences of fast-growing and high-speed data points that typically suffer from the infinite length, large volume, and specifically unstable data distribution. Ensemble learning as a prevalent classification approach is widely used in data stream mining studies. Besides the impressive performance of ensemble learning algorithms in providing a collection of diverse and accurate classifiers, they are specifically efficient in handling non-stationary data streams. Due to the component-based nature and the chance of dynamic updates for the components of the ensemble, this category is appropriate for dynamically learning the changing concepts of the data. Several review research have been conducted on the challenges of non-stationary data streams so far. None of the available surveys are dedicated to examine the effect of ensemble learning models on concept drift handling. This paper aims to provide a thorough theoretical and experimental review of the most significant ensemble-based data stream classification approaches in confronting with various types of concept drifts. In this comprehensive experimental analysis, 21 state-of-the-art ensemble algorithms are tested on 30 synthetic datasets under various types and volumes of concept drifts. This experimental analysis involves analyzing the classification accuracy, kappa score and running time of the algorithms, along with performing various statistical tests. In addition to conducting experimental analysis, a comprehensive investigation is carried out on the most significant challenges posed by non-stationary data streams, which provides the reader with valuable insights.

Interatrial Communications: Prevalence and Subtypes in 12,385 Newborns-a Copenhagen Baby Heart Study.

The prevalence of interatrial communications in newborns, i.e., patent foramen ovale or atrial septal defect, was previously reported to be between 24 and 92%, but the area has been impeded by lack of a universal classification method. A recently published novel echocardiographic diagnostic algorithm for systematic classification of interatrial communications had inter-and intraobserver agreements superior to standard expert assessment. This study aimed to determine the prevalence of subtypes of interatrial communications on transthoracic echocardiography in newborns. Echocardiograms of newborns aged 0-30days were prospectively collected in the population-based cohort study Copenhagen Baby Heart Study in 2017-2018 and analyzed according to the new diagnostic algorithm, classifying interatrial communications into three subtypes of patent foramen ovale and three subtypes of atrial septal defects. Echocardiograms from 15,801 newborns were analyzed; 3416 (21.6%) were excluded due to suboptimal image quality or severe structural heart disease (n = 3), leaving 12,385 newborns (aged 12 [interquartile range 8; 15] days, 48.2% female) included in the study. An interatrial communication was detected in 9766 (78.9%) newborns. According to the algorithm, 9029 (72.9%) had a patent foramen ovale, while 737 (6.0%) fulfilled criteria for an atrial septal defect, further divided into subtypes. An interatrial communication was seen on echocardiography in almost 80% of newborns aged 0-30days. Patent foramen ovale was 12 times more frequent than atrial septal defects. The observed prevalence of atrial septal defects was higher than previously reported. Follow up studies could distinguish which interatrial communications require follow-up or intervention. ClinicalTrial.gov, NCT02753348, posted April 27, 2016, [ https://classic.clinicaltrials.gov/ct2/show/NCT02753348 ].

Fine-Grained Few-Shot Image Classification Based on Feature Dual Reconstruction

Fine-grained few-shot image classification is a popular research area in deep learning. The main goal is to identify subcategories within a broader category using a limited number of samples. The challenge stems from the high intra-class variability and low inter-class variability of fine-grained images, which often hamper classification performance. To overcome this, we propose a fine-grained few-shot image classification algorithm based on bidirectional feature reconstruction. This algorithm introduces a Mixed Residual Attention Block (MRA Block), combining channel attention and window-based self-attention to capture local details in images. Additionally, the Dual Reconstruction Feature Fusion (DRFF) module is designed to enhance the model’s adaptability to both inter-class and intra-class variations by integrating features of different scales across layers. Cosine similarity networks are employed for similarity measurement, enabling precise predictions. The experiments demonstrate that the proposed method achieves classification accuracies of 96.99%, 98.53%, and 89.78% on the CUB-200-2011, Stanford Cars, and Stanford Dogs datasets, respectively, confirming the method’s efficacy in fine-grained classification tasks.

Eigen-entropy based time series signatures to support multivariate time series classification

Most current algorithms for multivariate time series classification tend to overlook the correlations between time series of different variables. In this research, we propose a framework that leverages Eigen-entropy along with a cumulative moving window to derive time series signatures to support the classification task. These signatures are enumerations of correlations among different time series considering the temporal nature of the dataset. To manage dataset’s dynamic nature, we employ preprocessing with dense multi scale entropy. Consequently, the proposed framework, Eigen-entropy-based Time Series Signatures, captures correlations among multivariate time series without losing its temporal and dynamic aspects. The efficacy of our algorithm is assessed using six binary datasets sourced from the University of East Anglia, in addition to a publicly available gait dataset and an institutional sepsis dataset from the Mayo Clinic. We use recall as the evaluation metric to compare our approach against baseline algorithms, including dependent dynamic time warping with 1 nearest neighbor and multivariate multi-scale permutation entropy. Our method demonstrates superior performance in terms of recall for seven out of the eight datasets.

Novel mining conveyor monitoring system based on quasi-distributed optical fiber accelerometer array and self-supervised learning

Belt conveyors in mining are crucial, with downtime leading to significant losses and safety hazards. Unplanned shutdowns often result from idler failures. To address this, an online monitoring system for continuous idler health assessment is proposed. Considering the large number and dense spatial distribution of idlers over long distances, this work presents a system that utilizes a quasi-distributed optical fiber accelerometer array. This array incorporates phase-sensitive optical time domain reflectometry (Phase-OTDR) interrogation technology and ultra-weak fiber Bragg gratings (UWFBGs) to effectively capture idler vibrations. The designed array achieves high-sensitivity vibration sensing with a sensitivity of 2.4 rad/g and a resolution of 1.7 mg/Hz. After collecting the vibrations of idlers by the designed accelerometer array, an automatic fault classification algorithm based on self-supervised learning (SSL) is introduced, which requires only a small number of labeled samples. By leveraging large amount of unlabeled data in the pretext task, the algorithm efficiently extracts latent features from the quasi-distributed accelerometer array. A diagnosis accuracy of 95.37 % can be achieved on a seven-class classification task with only 3.6 % labeled data (16 samples/class). This system offers a promising solution for idler monitoring, combining high sensitivity, distributed measurement capabilities, enhanced security, and superior fault detection accuracy.

Towards electrophysiological measurement of presence in virtual reality through auditory oddball stimuli

Objective. Presence is an important aspect of user experience in virtual reality (VR). It corresponds to the illusion of being physically located in a virtual environment (VE). This feeling is usually measured through questionnaires that disrupt presence, are subjective and do not allow for real-time measurement. Electroencephalography (EEG), which measures brain activity, is increasingly used to monitor the state of users, especially while immersed in VR. Approach. In this paper, we present a way of evaluating presence, through the measure of the attention dedicated to the real environment via an EEG oddball paradigm. Using breaks in presence, this experimental protocol constitutes an ecological method for the study of presence, as different levels of presence are experienced in an identical VE. Main results. Through analysing the EEG data of 18 participants, a significant increase in the neurophysiological reaction to the oddball, i.e. the P300 amplitude, was found in low presence condition compared to high presence condition. This amplitude was significantly correlated with the self-reported measure of presence. Using Riemannian geometry to perform single-trial classification, we present a classification algorithm with 79% accuracy in detecting between two presence conditions. Significance. Taken together our results promote the use of EEG and oddball stimuli to monitor presence offline or in real-time without interrupting the user in the VE.

The use of image classification to estimate flamingo abundance from aerial, drone and satellite imagery

The Lesser Flamingo Phoeniconaias minor is a Near Threatened species known to be highly gregarious and that can concentrate in large numbers at core foraging and breeding sites, yet is also known to disperse widely in search of suitable foraging habitat. The density of flamingos at occupied sites, together with frequent dispersal between foraging sites, poses significant challenges to obtaining reliable counts and associated population estimates. Our study tested the use of unmanned aerial vehicles (drones) imagery and high-resolution satellite imagery for producing density estimates of Lesser Flamingos at the only known breeding site in South Africa (Kamfers Dam, Northern Cape Province). We implemented a supervised classification approach using multiple supervised classification algorithms, including xgbTree, randomForest, nnet and GBM. The four supervised classification models performed very well at classifying flamingos from both drone and satellite imagery, with classification accuracies ranging between 0.98 and 0.99. The inclusion of an additional predictor (other than RGB bands) yielded the highest variable importance score and greatly increased model accuracy and predictive performance. Estimates of adult flamingos from drone imagery acquired across nesting mudflats on 5 February (n = 1 320) and 14 February (n = 330) 2019 suggested a 75% decline in incubating adults. Furthermore, a total of 16 134 (15 973–16 295) flamingos were estimated from drone imagery on 1 March 2019, and 17 291 (17 118–17 290) flamingos from satellite imagery on 19 March 2019. The modelled size of the creche across dates suggested a loss of 234 birds (4.5%) during the period of assessment, with the highest count estimating 5 218 juveniles. Our study successfully implemented machine learning classifiers that were able to detect and derive highly accurate counts of Lesser Flamingos from both drone and satellite imagery. This use of machine learning could greatly improve the efficiency of monitoring and associated conservation efforts underway for the Lesser Flamingo.