Classification Methodology Research Articles

Novel efficient reservoir computing methodologies for regular and irregular time series classification

AbstractTime series is a data structure prevalent in a wide range of fields such as healthcare, finance and meteorology. It goes without saying that analyzing time series data holds the key to gaining insight into our day-to-day observations. Among the vast spectrum of time series analysis, time series classification offers the unique opportunity to classify the sequences into their respective categories for the sake of automated detection. To this end, two types of mainstream approaches, recurrent neural networks and distance-based methods, have been commonly employed to address this specific problem. Despite their enormous success, methods like Long Short-Term Memory networks typically require high computational resources. It is largely as a consequence of the nature of backpropagation, driving the search for some backpropagation-free alternatives. Reservoir computing is an instance of recurrent neural networks that is known for its efficiency in processing time series sequences. Therefore, in this article, we will develop two reservoir computing based methods that can effectively deal with regular and irregular time series with minimal computational cost, both while achieving a desirable level of classification accuracy.

An intelligent solvent selection approach in carbon capturing process: A comparative study of machine learning multi-class classification models

Carbon capture is crucial for mitigating climate change and achieving global emissions reduction targets. Among various technologies, absorption-based methods using aqueous solvents are among the most common and efficient, offering high capture rates and retrofit capabilities for existing industrial facilities. However, selecting the optimal solvent is challenging due to its direct impact on the performance, efficiency, and cost-effectiveness of the carbon capture process. This research introduces a novel multi-class classification methodology for solvent selection in carbon capture. Leveraging a dataset of 656 data points, including features such as temperature, pressure, molar ratio, and CO2 solubility, the study employs nine machine learning algorithms—traditional models (Naïve Bayes, k-Nearest Neighbors, Decision Tree) and ensemble methods (Gradient Boosted Tree, Random Forest, Bagging, AdaBoost, Stacking, Voting)—to develop robust classification models. The results highlight the superior performance of the Stacking ensemble classifier, achieving 99.24 % accuracy, 0.76 % error rate, 99.04 % weighted mean recall, 98.08 % weighted mean precision, a 98.56 % F1 score, and a 0.9911 Cohen's Kappa coefficient on the test set. The effectiveness of ensemble techniques over traditional models underscores their ability to capture the complex relationships inherent in solvent selection. This approach streamlines the decision-making process for designers and engineers, enabling rapid identification of the most suitable solvent class based on operational conditions. Integrating this methodology into chemical engineering software could offer practical benefits, facilitating real-time solvent selection and optimization in industrial carbon capture, ultimately contributing to more sustainable and efficient processes.

Novel glassbox based explainable boosting machine for fault detection in electrical power transmission system.

The reliable operation of electrical power transmission systems is crucial for ensuring consumer's stable and uninterrupted electricity supply. Faults in electrical power transmission systems can lead to significant disruptions, economic losses, and potential safety hazards. A protective approach is essential for transmission lines to guard against faults caused by natural disturbances, short circuits, and open circuit issues. This study employs an advanced artificial neural network methodology for fault detection and classification, specifically distinguishing between single-phase fault and fault between all three phases and three-phase symmetrical fault. For fault data creation and analysis, we utilized a collection of line currents and voltages for different fault conditions, modelled in the MATLAB environment. Different fault scenarios with varied parameters are simulated to assess the applied method's detection ability. We analyzed the signal data time series analysis based on phase line current and phase line voltage. We employed SMOTE-based data oversampling to balance the dataset. Subsequently, we developed four advanced machine-learning models and one deep-learning model using signal data from line currents and voltage faults. We have proposed an optimized novel glassbox Explainable Boosting (EB) approach for fault detection. The proposed EB method incorporates the strengths of boosting and interpretable tree models. Simulation results affirm the high-efficiency scores of 99% in detecting and categorizing faults on transmission lines compared to traditional fault detection state-of-the-art methods. We conducted hyperparameter optimization and k-fold validations to enhance fault detection performance and validate our approach. We evaluated the computational complexity of fault detection models and augmented it with eXplainable Artificial Intelligence (XAI) analysis to illuminate the decision-making process of the proposed model for fault detection. Our proposed research presents a scalable and adaptable method for advancing smart grid technology, paving the way for more secure and efficient electrical power transmission systems.

Enthalpic Classification of Water Molecules in Target-Ligand Binding.

Water molecules play various roles in target-ligand binding. For example, they can be replaced by the ligand and leave the surface of the binding pocket or stay conserved in the interface and form bridges with the target. While experimental techniques supply target-ligand complex structures at an increasing rate, they often have limitations in the measurement of a detailed water structure. Moreover, measurements of binding thermodynamics cannot distinguish between the different roles of individual water molecules. However, such a distinction and classification of the role of individual water molecules would be key to their application in drug design at atomic resolution. In this study, we investigate a quantitative approach for the description of the role of water molecules during ligand binding. Starting from complete hydration structures of the free and ligand-bound target molecules, binding enthalpy scores are calculated for each water molecule using quantum mechanical calculations. A statistical evaluation showed that the scores can distinguish between conserved and displaced classes of water molecules. The classification system was calibrated and tested on more than 1000 individual water positions. The practical tests of the enthalpic classification included important cases of antiviral drug research on HIV-1 protease inhibitors and the Influenza A ion channel. The methodology of classification is based on open source program packages, Gromacs, Mopac, and MobyWat, freely available to the scientific community.

Electroretinogram Analysis Using a Short-Time Fourier Transform and Machine Learning Techniques.

Electroretinography (ERG) is a non-invasive method of assessing retinal function by recording the retina's response to a brief flash of light. This study focused on optimizing the ERG waveform signal classification by utilizing Short-Time Fourier Transform (STFT) spectrogram preprocessing with a machine learning (ML) decision system. Several window functions of different sizes and window overlaps were compared to enhance feature extraction concerning specific ML algorithms. The obtained spectrograms were employed to train deep learning models alongside manual feature extraction for more classical ML models. Our findings demonstrated the superiority of utilizing the Visual Transformer architecture with a Hamming window function, showcasing its advantage in ERG signal classification. Also, as a result, we recommend the RF algorithm for scenarios necessitating manual feature extraction, particularly with the Boxcar (rectangular) or Bartlett window functions. By elucidating the optimal methodologies for feature extraction and classification, this study contributes to advancing the diagnostic capabilities of ERG analysis in clinical settings.

Joint coordinate attention mechanism and instance normalization for COVID online comments text classification.

The majority of extant methodologies for text classification prioritize the extraction of feature representations from texts with high degrees of distinction, a process that may result in computational inefficiencies. To address this limitation, the current study proposes a novel approach by directly leveraging label information to construct text representations. This integration aims to optimize the use of label data alongside textual content. The methodology initiated with separate pre-processing of texts and labels, followed by encoding through a projection layer. This research then utilized a conventional self-attention model enhanced by instance normalization (IN) and Gaussian Error Linear Unit (GELU) functions to assess emotional valences in review texts. An advanced self-attention mechanism was further developed to enable the efficient integration of text and label information. In the final stage, an adaptive label encoder was employed to extract relevant label information from the combined text-label data efficiently. Empirical evaluations demonstrate that the proposed model achieves a significant improvement in classification performance, outperforming existing methodologies. This enhancement is quantitatively evidenced by its superior micro-F1 score, indicating the efficacy of integrating label information into text classification processes. This suggests that the model not only addresses computational inefficiencies but also enhances the accuracy of text classification.

Differential impact of climate and land use change on habitat suitability of migrant passerines according to habitat preferences

Our study contributes to the ongoing dialogue on the impact of climate and habitat changes on migratory bird species, particularly focusing on how these effects vary based on species’ habitat preferences. We used citizen science data for 22 African-Eurasian migratory bird species and categorized them into five groups based on habitat preferences, following the classification methodology of Atkinson et al. (2014). Using ensemble species distribution modeling (SDM), we projected changes in potentially suitable habitats across Africa from 2040 to 2100 under contrasting climate and land use scenarios. Our results indicate a differential impact of climate and land use changes on habitat suitability, with species preferring habitats with shrubs and trees being the most vulnerable. Conversely, other group species, such as open country-grassland and farmland birds could experience a significant increase in suitable habitat. We anticipate a profound change in habitat suitability, with the western part of South Africa becoming unsuitable for most species, while an increase in suitable habitat is expected in the Sahel. Bioclimatic rather than land use variables emerged as the primary drivers of these changes. The extent of change in habitat suitability will be strongly influenced by the Shared Socio-economic Pathways followed by human societies.

Orchid2024: A cultivar-level dataset and methodology for fine-grained classification of Chinese Cymbidium Orchids

BackgroundChinese Cymbidium orchids, cherished for their deep-rooted cultural significance and significant economic value in China, have spawned a rich tapestry of cultivars. However, these orchid cultivars are facing challenges from insufficient cultivation practices and antiquated techniques, including cultivar misclassification, complex identification, and the proliferation of counterfeit products. Current commercial techniques and academic research primarily emphasize species identification of orchids, rather than delving into that of orchid cultivars within species.ResultsTo bridge this gap, the authors dedicated over a year to collecting a cultivar image dataset for Chinese Cymbidium orchids named Orchid2024. This dataset contains over 150,000 images spanning 1,275 different categories, involving visits to 20 cities across 12 provincial administrative regions in China to gather pertinent data. Subsequently, we introduced various visual parameter-efficient fine-tuning (PEFT) methods to expedite model development, achieving the highest top-1 accuracy of 86.14% and top-5 accuracy of 95.44%.ConclusionExperimental results demonstrate the complexity of the dataset while highlighting the considerable promise of PEFT methods within flower image classification. We believe that our work not only provides a practical tool for orchid researchers, growers and market participants, but also provides a unique and valuable resource for further exploring fine-grained image classification tasks. The dataset and code are available at https://github.com/pengyingshu/Orchid2024.

Optimizing Facial Expression Recognition with Biogeography-Based Feature Selection

Facial expression recognition is a challenging research field in computer vision due to various issues such as occlusion, lighting conditions, camera pose angles, and the selection of relevant features. Extracting and selecting pertinent features from facial images is crucial in achieving efficient expression recognition. This paper proposes a metaheuristic-based feature selection and classification methodology using the Biogeography-Based Optimization (BBO) algorithm to select the best-performing features and optimize the recognition accuracy of the classifier. The cross-validation recognition accuracy of the Support Vector Machine (SVM) is used as the evaluation criterion in the BBO algorithm to choose the optimal feature subset from the extracted features. The performance of the proposed BBO-SVM feature selection model is compared with other filter-based approaches. Experiments are conducted on three publicly available databases: JAFFE, MUG, and CK+, to validate the performance of the proposed system. The model achieves promising recognition accuracy across all datasets, with results compared to similar works presented in the literature.

Ensemble CNN Model for Computer-Aided Knee Osteoarthritis Diagnosis

Osteoarthritis (OA) is a multifaceted ailment posing challenges in its diagnosis and treatment due to the intricate nature of the disease. Particularly, Knee Osteoarthritis (KOA) significantly impacts the knee joint, manifesting through symptoms such as pain, stiffness, and limited movement. Despite its prevalence and debilitating effects, early detection of KOA remains elusive, often hindered by subjective diagnostic methods and the absence of reliable biomarkers. This research aims to address these challenges by leveraging deep learning techniques and ensemble methodologies for accurate KOA classification using knee X-ray images. This paper utilized a dataset sourced from the Osteoarthritis Initiative (OAI), comprising a large collection of knee X-ray images graded according to the Kellgren-Lawrence (KL) grading system. The proposed design methodology involves preprocessing the input X-ray images and training multiple pre-trained Convolutional Neural Network (CNN) models, including ResNet50, InceptionResNetV2, and Xception to classify KOA severity grades. Additionally, this work introduced an ensemble model by combining predictions from these base models to improve overall performance of the Computer-Aided Diagnosis (CAD) system. The obtained results demonstrate the effectiveness of the ensemble approach, outperforming individual algorithms in terms of accuracy, precision, recall, F1-score, and balanced accuracy. However, challenges persist in accurately distinguishing between adjacent KL grades, particularly grades#1 and #2, highlighting the need for further refinement. Notably, the proposed CAD model showcases superior predictive accuracy compared to various state-of-art methods, offering a promising avenue for early KOA diagnosis and personalized treatment strategies.

TinyML-Raman: A novel IoT based field-deployable spectra analysis for accurate identification of pharmaceuticals and trace dye-pesticide mixtures from facile SERS method

BackgroundUpcoming inexpensive, compact Internet of Things (IoT) microcontrollers i.e., tiny-machine learning (TinyML) takes the ML driven Raman spectroscopy one step ahead for realization of more affordable and highly compact field deployable instruments. Further, lack of large spectral datasets and need for numerous specialized SERS substrates impede the development of various ML-based surface enhanced Raman spectroscopy (SERS) applications. The aim is to introduce TinyML analysis on wide range of spectra classes using customized dataset obtained with low-cost SERS. In this regard, it is vital to establish an optimum ML model and efficient data handling methodology for low memory TinyML units. ResultsWe introduce a novel TinyML methodology for accurate classification of large spectra classes with smartphone assistance for data communication and results visualization. To generate large customized spectral dataset, we present a facile, micro-drop SERS using Au colloids and reusable grooved Al substrates. The results demonstrated that memory efficient 8-bit data quantization based convolutional neural network is effective for accurate identification of 22 different spectra classes of trace dye-pesticide mixtures and pharmaceuticals. In this novel quantized data analysis on significantly varied intensity and complex variation spectra classes i.e., many individual, binary-mixtures and some with varied compositions, data normalization is shown to be powerful for improving ML classification accuracy from about 55 % to >99.5 %. Its robustness is demonstrated using inter-instrument driven data variations such as spectral shifts, high noise, and abscissa-flip, with five-fold cross validation of model performance. In addition, on-site quantification of analyte through spectral intensity is also demonstrated. SignificanceThis study opens up a new approach of ML analysis towards realization of next generation field deployable analytical instruments maintaining data privacy. It presents a detailed procedure of quantized spectral data analysis and its implementation in TinyML, attractive for various users and instrument manufacturers. The presented innovative computer-free ML analysis can be employed in all types of spectrometers, meeting the common goal of Raman spectroscopy i.e., accurate identification of complex spectra classes.

Performance enhancement of classifiers through Bio inspired feature selection methods for early detection of lung cancer from microarray genes

Gene expression in the microarray is assimilated with redundant and high-dimensional information. Moreover, the information in the microarray genes mostly correlates with background noise. This paper uses dimensionality reduction and feature selection methods to employ a classification methodology for high-dimensional lung cancer microarray data. The approach is enforced in two phases; initially, the genes are dimensionally reduced through Hilbert Transform, Detrend Fluctuation Analysis and Least Square Linear Regression methods. The dimensionally reduced data is further optimized in the next phase using Elephant Herd optimization (EHO) and Cuckoo Search Feature selection methods. The classifiers used here are Bayesian Linear Discriminant, Naive Bayes, Random Forest, Decision Tree, SVM (Linear), SVM (Polynomial), and SVM (RBF). The classifier's performances are analysed with and without feature selection methods. The SVM (Linear) classifier with the DFA Dimensionality Reduction method and EHO feature selection achieved the highest accuracy of 92.26 % compared to other classifiers.

Music Emotion Classification: A Literature Review

Music, as an art form, combines rhythm and sound to form a functional melodic structure, uniquely capable of conveying emotions non-verbally. Within the domain of Music Information Retrieval (MIR), Music Emotion Classification (MEC) represents a specialized subset dedicated to the identification and labeling of emotional attributes in songs. This is achieved by extracting and comparing features from musical compositions. This research aims to discern the contemporary landscape of research and its associated research gaps in this domain. The study comprised a collection of publications found through searches conducted on Google Scholar between the years 2006 and 2023, with the search terms: Music Emotion Classification, Music Emotion Classification in Sri Lanka, Music Emotion Recognition, and Emotion Classification in Music. This study was narrowed down to the research that utilized audio files for classification. Among the initial set of 42 studies, 20 were selected for detailed analysis using the purposive sampling method. The review encompassed essential aspects, including acoustic feature analysis, emotional modeling, classification methodologies, and performance evaluation. The findings highlighted a paucity of research considering cultural, regional, and linguistic variations. The most often used acoustic features encompassed rhythm, pitch, timbre, spectral, and harmony whereas the most frequently used emotion categories for the classification were happiness, anger, sadness, and relaxation. Support Vector Machine (SVM) was the most used machine learning algorithm for classification, although regression methods, neural network-based approaches, and fuzzy classifications were also explored. Notably, the adoption of multi-modal approaches for emotion classification, as well as multi-labeled emotion classification, remained limited. These insights underscore the need for future research to address the cultural and language diversity of datasets, explore innovative classification techniques, and embrace multi-modal and multi-labeled emotional classification methodologies in the context of music emotion classification within MIR.

A New Hybrid Classification Framework in Childhoods Allergies with Dataset Slicing Method

Childhood allergies, particularly food allergies, are growing more frequent. Their major influence on children's health and well-being has piqued the interest of worldwide public health officials. The increased prevalence of childhood allergies in Turkey, where these patterns are also relevant, adds urgency to the need for effective classification and management options. This study addresses the shortcomings of simple classification algorithms in obtaining high accuracy by presenting a novel hybrid classification methodology. The research creates a novel method where three different prediction models are built by combining Support Vector Machine and Decision Tree classifiers. This method improves the classification process by taking into account instances that have been incorrectly classified as possible sources of useful information instead of just being noise. This instance filtering-based hybrid classification algorithm that is used in this study maintains the simplicity of interpreting learning outcomes while achieving comparatively high accuracy. Extensive experiments on the allergy dataset show the effectiveness of this hybrid approach, with an impressive accuracy of 0.906. This greatly outperforms the fundamental classification algorithms. The experimental outputs have important implications for medical professionals. This study might add a valuable contribution to the literature by giving a fresh solution to childhood allergy classification.

Flower pollination-enhanced CNN for lung disease diagnosis

Abstract The utilization of automated software tools is imperative to enhance the efficiency of lung diseases through the analysis of X-ray images. The main objective of this study is to employ an analysis of chest X-ray images to diagnose lung disease. This study presents an Optimized Convolutional Neural Network (CNNFPA) designed to automate the diagnosis of lung disease. The Flower pollination technique is employed to optimize the hyperparameters associated with the training of the layers of the Convolutional Neural Network (CNN). In this paper, a novel model called RCNNFPA model is proposed, which makes use of a pre-trained ResNet50 with its layers frozen. Subsequently, CNNFPA architecture is integrated on top of the frozen ResNet-50 layers. This approach allowed us to leverage the knowledge captured by the ResNet-50 model on a large-scale dataset. To assess the efficacy of the proposed model and perform a comparison study using several classification methodologies, various publicly available datasets comprising images of COVID-19, Viral Pneumonia, Normal, and Tuberculosis are employed. As optimized and elaborated upon in this study, the CNN model is juxtaposed with existing state-of-the-art models. The proposed novel RCNNFPA model demonstrates considerable potential in facilitating the automated screening of individuals affected by different lung diseases.

Fusing Multispectral and LiDAR Data for CNN-Based Semantic Segmentation in Semi-Arid Mediterranean Environments: Land Cover Classification and Analysis

Spectral confusion among land cover classes is quite common, let alone in a complex and heterogenous system like the semi-arid Mediterranean environment; thus, employing new developments in remote sensing, such as multispectral imagery (MSI) captured by unmanned aerial vehicles (UAVs) and airborne light detection and ranging (LiDAR) techniques, with deep learning (DL) algorithms for land cover classification can help to address this problem. Therefore, we propose an image-based land cover classification methodology based on fusing multispectral and airborne LiDAR data by adopting CNN-based semantic segmentation in a semi-arid Mediterranean area of northeastern Aegean, Greece. The methodology consists of three stages: (i) data pre-processing, (ii) semantic segmentation, and (iii) accuracy assessment. The multispectral bands were stacked with the calculated Normalized Difference Vegetation Index (NDVI) and the LiDAR-based attributes height, intensity, and number of returns converted into two-dimensional (2D) images. Then, a hyper-parameter analysis was performed to investigate the impact on the classification accuracy and training time of the U-Net architecture by varying the input tile size and the patch size for prediction, including the learning rate and algorithm optimizer. Finally, comparative experiments were conducted by altering the input data type to test our hypothesis, and the CNN model performance was analyzed by using accuracy assessment metrics and visually comparing the segmentation maps. The findings of this investigation showed that fusing multispectral and LiDAR data improves the classification accuracy of the U-Net, as it yielded the highest overall accuracy of 79.34% and a kappa coefficient of 0.6966, compared to using multispectral (OA: 76.03%; K: 0.6538) or LiDAR (OA: 37.79%; K: 0.0840) data separately. Although some confusion still exists among the seven land cover classes observed, the U-Net delivered a detailed and quite accurate segmentation map.

Enhancing Alzheimer's Disease Classification with Transfer Learning: Finetuning a Pre-trained Algorithm.

The increasing longevity of the population has made Alzheimer's disease (AD) a significant public health concern. However, the challenge of accurately distinguishing different disease stages due to limited variability within the same stage and the potential for errors in manual classification highlights the need for more precise approaches to classifying AD stages. In the field of deep learning, the ResNet50V2 model stands as a testament to its exceptional capabilities in image classification tasks. The dataset employed in this study was sourced from Kaggle and consisted of 6400 MRI images that were meticulously collected and rigorously verified to assure their precision. The selection of images was conducted with great attention to detail, drawing from a diverse array of sources. This study focuses on harnessing the potential of this model for AD classification, a task that relies on extracting disease-specific features. Furthermore, to achieve this, a multi-class classification methodology is employed, using transfer learning and fine-tuning of layers to adapt the pre-trained ResNet50V2 model for AD classification. Notably, the impact of various input layer sizes on model performance is investigated, meticulously striking a balance between capacity and computational efficiency. The optimal fine-tuning strategy is determined by counting layers within convolution blocks and selectively unfreezing and training individual layers after a designated layer index, ensuring consistency and reproducibility. Custom classification layers, dynamic learning rate reduction, and extensive visualization techniques are incorporated. The model's performance is evaluated using accuracy, AUC, precision, recall, F1-score, and ROC curves. The comprehensive analysis reveals the model's ability to discriminate between AD stages. Visualization through confusion matrices aided in understanding model behavior. The rounded predicted labels enhanced practical utility. This approach combined empirical research and iterative refinement, resulting in enhanced accuracy and reliability in AD classification. Our model holds promise for real-world applications, achieving an accuracy of 96.18%, showcasing the potential of deep learning in addressing complex medical challenges.

Lung Sound Classification for Respiratory Disease Identification Using Deep Learning: A Survey

Integrating artificial intelligence (AI) into lung sound classification has markedly improved respiratory disease diagnosis by analysing intricate patterns within audio data. This study is driven by the widespread issue of lung diseases, which affect around 500 million people globally. Early detection of respiratory diseases is crucial for delivering timely and effective treatment. Our study consists of a comprehensive survey of lung sound classification methodologies, exploring the advancements made in leveraging AI to identify and classify respiratory diseases. This survey thoroughly investigates lung sound classification models, along with data augmentation, feature extraction, explainable techniques and support tools to improve systems for diagnosing respiratory conditions. Our goal is to provide meaningful insights for healthcare professionals, researchers and technologists who are dedicated to developing methodologies for the early detection of pulmonary diseases. The paper provides a summary of the current status of lung sound classification research, highlighting both advancements and challenges in the use of AI for more accurate and efficient diagnostic methods in respiratory healthcare.

A Comprehensive Framework for Pathology Classification Bridging Precision and Interpretability

Pathology classification is an indispensable component of medical diagnostics, facilitating accurate disease identification, prognosis determination, and treatment planning. However, the increasing complexity and heterogeneity of pathological manifestations pose significant challenges to traditional classification methodologies. This abstract presents a novel framework that integrates advanced machine learning techniques with domain-specific expertise to enhance the precision and interpretability of pathology classification. Our framework adopts a multi-modal approach, leveraging diverse data sources including histopathological images, clinical records, genomic profiles, and molecular biomarkers. Through feature fusion and dimensionality reduction techniques, we effectively capture intricate patterns and latent relationships embedded within the data, enabling robust classification across diverse pathological conditions. Furthermore, interpretability is prioritized through the incorporation of explainable AI methodologies, facilitating the identification of salient features and decision rationales underlying classification outcomes. This ensures transparency and trustworthiness in the diagnostic process, empowering clinicians to make informed decisions and refine treatment strategies. Validation of our framework across various pathological contexts demonstrates superior performance compared to conventional approaches, exhibiting high accuracy, sensitivity, and specificity. Moreover, its modular architecture facilitates customization and scalability, accommodating evolving diagnostic needs and emerging technological advancements. In conclusion, our proposed framework represents a significant advancement in pathology classification, offering a synergistic blend of computational sophistication and clinical relevance. By seamlessly integrating cutting-edge technologies with domain knowledge, it holds promise for revolutionizing diagnostic practices and improving patient outcomes in the realm of precision medicine.

Intelligent classification of maize straw types from UAV remote sensing images using DenseNet201 deep transfer learning algorithm

China has abundant straw resources, but challenges in utilization persist. Utilization rates need improvement, and environmental pollution from straw burning remains a significant issue. Accurate and intelligent remote sensing classification of straw types is crucial for enhancing straw utilization and preventing straw burning. This paper proposed a new approach for the intelligent classification of maize straw types, using the DenseNet201 deep transfer learning algorithm based on RGB images captured by Unmanned Aerial Vehicle (UAV). The sample labels dataset was established for maize straw types, utilizing DenseNet201 deep transfer learning algorithm to pre-train the sample set. This pre-training facilitated model transfer and parameter initialization. Subsequently, the second round of deep transfer learning was performed to construct the final maize straw type remote sensing classification models using DenseNet201 deep transfer learning algorithm. This model and results were subsequently compared with maize straw type classification by the ResNet50 and GoogLeNet deep transfer learning algorithms, as well as maize straw type classification using DenseNet201, ResNet50, and GoogLeNet deep learning algorithms. The results showed that the accuracy of the pre-trained maize straw type deep transfer learning remote sensing classification model surpassed that of the untrained maize straw type deep learning remote sensing classification model, resulting in an enhancement of accuracy by 8.59%, 7.38%, and 1.28%, respectively. The DenseNet201 deep transfer learning model for maize straw types exhibited the highest accuracy with the overall accuracy of 95.57%, and the kappa coefficient of 0.9410. Hence, the DenseNet201 deep transfer learning classification of maize straw types enabled the attainment of intelligent remote sensing recognition of maize straw types. The classification methodology, model, and results presented in this paper can serve as valuable technical references, offering essential information support for agricultural and environmental protection departments actively involved in the comprehensive utilization of straw resources and atmospheric environmental protection efforts.