Comparative Analysis of Time-Frequency Representations for Pediatric Respiratory Sound Classification Using Deep Learning

Pest infestation is a significant challenge in agriculture, causing substantial economic losses and impacting crop yields. Manual pest identification is time-consuming and error-prone, especially in large-scale farming. This study presents a hybrid deep learning approach to automate pest detection and classification using image data. It employs a pre-trained VGG16 model for robust feature extraction, followed by a custom Convolutional Neural Network (CNN) for classification. The VGG16 model leverages transfer learning to capture high-level visual patterns from pest images, while the custom CNN is trained on these features to distinguish between multiple pest classes. The proposed pipeline is optimized using data augmentation, early stopping, and adaptive learning techniques. Performance is evaluated using metrics such as accuracy, precision, recall, and F1-score. The model demonstrates high accuracy and robustness on agricultural image datasets, making it a scalable solution for smart farming systems. Index Terms: Pest Detection, Deep Learning, VGG16, Convolutional Neural Network, Transfer Learning, Image Classification, Precision Agriculture, Feature Extraction.

Leaf disease detection is a crucial task in modern agriculture, aiding in early diagnosis and prevention of crop infections. In this research paper, authors present a comprehensive study comparing nine widely used pre-trained models, namely DenseNet201, EfficientNetB3, EfficientNetB4, InceptionResNetV2, MobileNetV2, ResNet50, ResNet152, VGG16, and Xception, with our newly developed custom CNN (Convolutional Neural Network) for leaf disease detection. The objective is to determine if our custom CNN can match the performance of these established pre-trained models while maintaining superior efficiency. The authors trained and fine-tuned each pre-trained model and our custom CNN on a large dataset of labeled leaf images, covering various diseases and healthy states. Subsequently, the authors evaluated the models using standard metrics, including accuracy, precision, recall, and F1-score, to gauge their overall performance. Additionally, the authors analyzed computational efficiency regarding training time and memory consumption. Surprisingly, our results indicate that the custom CNN performs comparable to the pre-trained models, despite their sophisticated architectures and extensive pre-training on massive datasets. Moreover, our custom CNN demonstrates superior efficiency, outperforming the pre-trained models regarding training speed and memory requirements. These findings highlight the potential of custom CNN architectures for leaf disease detection tasks, offering a compelling alternative to the commonly used pre-trained models. The efficiency gains achieved by our custom CNN can be beneficial in resource-constrained environments, enabling faster inference and deployment of leaf disease detection systems. Overall, our research contributes to the advancement of agricultural technology by presenting a robust and efficient solution for the early detection of leaf diseases, thereby aiding in crop protection and yield enhancement.

Classification of respiratory sounds between normal and abnormal is very crucial for screening and diagnosis purposes. Lung associated diseases can be detected through this technique. With the advancement of computerized auscultation technology, the adventitious sounds such as crackles can be detected and therefore diagnostic test can be performed earlier. In this paper, Mel-frequency Cepstral Coefficient (MFCC) is used to extract features from normal and crackles respiratory sounds. By using statistical computation such as mean and standard deviation (SD) of cepstral based coefficients it can differentiate between crackles and normal sounds. The result shows that the first three statistical values of SD of coefficients provide distinctive feature between normal and crackles respiratory sounds. Hence, MFCCs can be used as feature extraction method of respiratory sounds to classify between normal and crackles as screening and diagnostic tool.

Automatic detection of knee medial collateral ligament (MCL) tear from magnetic resonance imaging using deep neural network.

Background/Objectives: Identifying and classifying abnormal lung sounds is essential for diagnosing patients with respiratory disorders. In particular, the simultaneous recording of auscultation signals from multiple clinically relevant positions offers greater diagnostic potential compared to traditional single-channel measurements. This study aims to improve the accuracy of respiratory sound classification by leveraging multichannel signals and capturing positional characteristics from multiple sites in the same patient. Methods: We evaluated the performance of respiratory sound classification using multichannel lung sound data with a deep learning model that combines a convolutional neural network (CNN) and long short-term memory (LSTM), based on mel-frequency cepstral coefficients (MFCCs). We analyzed the impact of the number and placement of channels on classification performance. Results: The results demonstrated that using four-channel recordings improved accuracy, sensitivity, specificity, precision, and F1-score by approximately 1.11, 1.15, 1.05, 1.08, and 1.13 times, respectively, compared to using three, two, or single-channel recordings. Conclusions: This study confirms that multichannel data capture a richer set of features corresponding to various respiratory sound characteristics, leading to significantly improved classification performance. The proposed method holds promise for enhancing sound classification accuracy not only in clinical applications but also in broader domains such as speech and audio processing.

Respiratory sound analysis provides vital information of the present condition of the Lungs. It can be used to assist medical professionals in differential diagnosis. In this paper, we intend to distinguish between normal (without any pathological condition), airway obstruction pathology and parenchymal pathology using respiratory sound recordings taken from RALE database. The proposed method uses Mel-frequency cepstral coefficients (MFCC) as features extracted from respiratory sounds. The extracted features are distinguished using support vector machine classifier (SVM). The classifier performance is analysed by using confusion matrix technique. A mean classification accuracy of 90.77% was reported using the proposed method. The performance analysis of the SVM classifier using confusion matrix revealed that normal, airway obstruction and parenchymal pathology are classified at 94.11%, 92.31% and 88.00% classification accuracy respectively. The analysis reveals that the proposed method shows promising outcome in distinguishing between the normal, airway obstruction and parenchymal pathology.

Background Respiratory diseases, including chronic obstructive pulmonary disease (COPD), asthma, and pneumonia, are leading causes of global morbidity and mortality. Early and accurate diagnosis remains challenging, especially in resource-limited settings. Automated respiratory sound classification, supported by machine learning and deep learning, has emerged as a non-invasive and cost-effective diagnostic alternative. This systematic review examines the role of multistage classification frameworks and ensemble learning techniques in improving the accuracy, robustness, and clinical applicability of respiratory sound analysis. Methods A comprehensive literature search was conducted across major scientific databases, focusing on studies employing multistage, machine learning, or ensemble-based approaches for respiratory sound classification. Eligible studies were screened based on predefined inclusion criteria related to pulmonary acoustics, feature extraction, signal processing, and classification models. Extracted data were synthesized to compare methodologies, feature engineering strategies, ensemble algorithms, model architectures, benchmark datasets (ICBHI 2017, PhysioNet), and performance metrics such as accuracy, precision, recall, F1-score, and AUC-ROC. Results Findings indicate that multistage classification pipelines significantly enhance model reliability by integrating sequential preprocessing, feature extraction, dimensionality reduction, and classifier fusion. Ensemble learning methods—including bagging, boosting, random forests, stacking, and deep hybrid models—consistently outperform single-stage classifiers in handling noisy, non-stationary respiratory sounds and imbalanced datasets. Deep learning models such as convolutional neural networks and transformer-based architectures show superior performance when combined with advanced feature representations. However, challenges persist related to dataset variability, limited annotations, lack of standardization, and insufficient real-time or wearable-device compatibility. Explainable AI approaches are increasingly incorporated to support clinical interpretability. Conclusion Multistage and ensemble learning techniques demonstrate strong potential to improve automated respiratory sound classification and support early diagnosis of respiratory diseases. Despite promising results, advancements are needed in dataset standardization, multimodal integration, self-supervised learning, and IoT-enabled real-time monitoring. Future research should prioritize clinically interpretable, scalable, and regulation-ready AI systems to enable widespread deployment in respiratory healthcare.

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that severely impacts memory and cognitive functions. Early diagnosis remains crucial for timely intervention and care. This research aims to explore the use of artificial intelligence, specifically deep learning, for the early prediction and classification of AD using structural magnetic resonance imaging (MRI) images. A dataset comprising approximately 44,000 brain MRI images with four diagnostic classes (mild, moderate, severe, and very severe dementia) was used to train and evaluate multiple convolutional neural network (CNN) architectures. Three deep learning models were developed and tested: a custom CNN built from scratch, a spatial-channel convolutional attention network (SCCAN), and a pre-trained Visual Geometry Group VGG16 model using transfer learning. The methodology included extensive preprocessing, data augmentation, normalization, and a train–validation–test split to ensure robust performance. Evaluation metrics such as accuracy, precision, recall, F1-score, and confusion matrices were used to assess classification efficacy. Among the models tested, the Visual Geometry Group VGG16 model achieved the highest classification accuracy, closely followed by the SCCAN, while the custom CNN demonstrated competitive performance with fewer layers. Grad-CAM visualizations were integrated to provide insight into model decision-making, enhancing interpretability. The results confirm the effectiveness of deep learning in classifying early AD stages with high accuracy and support its integration into clinical diagnostic tools. However, the study also identifies limitations, including dataset diversity, class imbalance, and generalizability across diverse populations. Future research should consider using larger, multi-center datasets (including PET and EEG modalities). This project demonstrates that deep learning can offer reliable, scalable, and interpretable solutions for the early detection of AD, potentially transforming the diagnostic pathway and enabling earlier therapeutic interventions.

This paper presents a new technique for wheezes detection in respiratory sounds using a Long Short-Term Memory (LSTM), a specific type of Recurrent Neural Networks (RNNs). The purpose of this work is to develop an LSTM-based system and compare its classification performances to those obtained by a Multilayer Perceptron (MLP) feed-forward network. The MLP is a widely used neural network that has proven its efficiency in respiratory sound classification. Feed-forward networks do not consider time dependencies, while RNNs reach their limit in detecting dependencies when they occur at long time intervals. Because wheezing occurs over several consecutive intervals, we assume that LSTM takes into account the changing characteristics better than MLP and provides better results. Pulmonary sounds are characterized using the Mel-Frequency Cepstral Coefficients (MFCC) method before applying the LSTM-based classifier. As expected, the experimental tests show that LSTM takes advantage of the long-term dependencies observed in wheezing sounds to lead to better classification performances (accuracy of 91%).

Recently, many studies were performed using several techniques to classify and diagnose lung sound, but as a drawback the age category was limited, almost adult only, as well as the insufficient number of samples and this unfortunately leads to an unfair classification of lung sound. While this study deals with different methods to analyze lung sounds and extract distinctive features then classify them to diagnose lung sounds in infant and children to one of the three categories: Normal, Wheeze, or Stridor. Features were extracted using three different techniques in separate ways to compare the effectiveness; these techniques are Discrete Wavelet transform (DWT), Short Time Fourier Transform (STFT) and Mel-Frequency Cepstral Coefficients (MFCCs). After that the sounds are categorized using four different classification techniques which include Artificial Neural Network (ANN), Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Naive Bayes (NB). The main aim of this research is to choose the best signal processing technique with the most suitable classifier to diagnose lung sounds by categorizing 300 lung sounds especially in infants and children to Normal, Wheeze, or Stridor. These sounds are collected from Alexandria University Children Hospital (AUCH) – Egypt as a particular environment which is considered one of the main advantages of this research. Moreover, extra 146 wheezes were used to validate the usefulness of the classifiers. The results were very promising.

In the field of medicine, with the introduction of computer systems that can collect and analyze massive amounts of data, many non-invasive diagnostic methods are being developed for a variety of conditions. In this study, our aim is to develop a non-invasive method of classifying respiratory sounds that are recorded by an electronic stethoscope and the audio recording software that uses various machine learning algorithms.In order to store respiratory sounds on a computer, we developed a cost-effective and easy-to-use electronic stethoscope that can be used with any device. Using this device, we recorded 17,930 lung sounds from 1630 subjects.We employed two types of machine learning algorithms; mel frequency cepstral coefficient (MFCC) features in a support vector machine (SVM) and spectrogram images in the convolutional neural network (CNN). Since using MFCC features with a SVM algorithm is a generally accepted classification method for audio, we utilized its results to benchmark the CNN algorithm. We prepared four data sets for each CNN and SVM algorithm to classify respiratory audio: (1) healthy versus pathological classification; (2) rale, rhonchus, and normal sound classification; (3) singular respiratory sound type classification; and (4) audio type classification with all sound types. Accuracy results of the experiments were; (1) CNN 86%, SVM 86%, (2) CNN 76%, SVM 75%, (3) CNN 80%, SVM 80%, and (4) CNN 62%, SVM 62%, respectively.As a result, we found out that spectrogram image classification with CNN algorithm works as well as the SVM algorithm, and given the large amount of data, CNN and SVM machine learning algorithms can accurately classify and pre-diagnose respiratory audio.

Background/Objectives: Automatic classification of ECG signal arrhythmias plays a vital role in early cardiovascular diagnostics by enabling prompt detection of life-threatening conditions. Manual ECG interpretation is labor-intensive and susceptible to errors, highlighting the demand for automated, scalable approaches. Deep learning (DL) methods are effective in ECG analysis due to their ability to learn complex patterns from raw signals. Methods: This study introduces two models: a custom convolutional neural network (CNN) with a dual-branch architecture for processing ECG signals and demographic data (e.g., age, gender), and a modified VGG16 model adapted for multi-branch input. Using the PTB-XL dataset, a widely adopted large-scale ECG database with over 20,000 recordings, the models were evaluated on binary, multiclass, and subclass classification tasks across 2, 5, 10, and 15 disease categories. Advanced preprocessing techniques, combined with demographic features, significantly enhanced performance. Results: The CNN model achieved up to 97.78% accuracy in binary classification and 79.7% in multiclass tasks, outperforming the VGG16 model (97.38% and 76.53%, respectively) and state-of-the-art benchmarks like CNN-LSTM and CNN entropy features. This study also emphasizes interpretability, providing lead-specific insights into ECG contributions to promote clinical transparency. Conclusions: These results confirm the models’ potential for accurate, explainable arrhythmia detection and their applicability in real-world healthcare diagnostics.

In the realm of computer vision, image classification is a critical issue with many applications, including multimedia content analysis, security and surveillance, and medical imaging. The accuracy of image classification algorithms has considerably increased with the development of deep learning. The discipline of image classification has dramatically benefited from the usage of pre-trained Convolutional Neural Network (CNN) models. In this study, we perform image classification on the Wang dataset composed of 1000 images separated into ten categories, using six different pre-trained CNN models. The research made use of pre-trained versions of VGG16, Densenet, Mobilenet, Inception V3, Resnet50, and Xception models. We assessed the model performances in terms of training and testing accuracy. Testing accuracies for ten unique batches of data were calculated and averaged out. Densenet outperformed state-of-the-art models like Xception by a small margin, mainly due to low data availability. The findings of this study show how pre-trained models have advanced the field of image classification and shed light on how well these models perform in diverse image classification tasks. This study can serve as a valuable reference for researchers and practitioners in the field of computer vision and deep learning and help inform their choices when selecting pre-trained models for image classification, depending on their needs, while also considering data availability and computational constraints.

Pneumonia is a lung infection and causes the inflammation of the small air sacs (Alveoli) in one or both lungs. Proper and faster diagnosis of pneumonia at an early stage is imperative for optimal patient care. Currently, chest X-ray is considered as the best imaging modality for diagnosing pneumonia. However, the interpretation of chest X-ray images is challenging. To this end, we aimed to use an automated convolutional neural network-based transfer-learning approach to detect pneumonia in paediatric chest radiographs. Herein, an automated convolutional neural network-based transfer-learning approach using four different pre-trained models (i.e. VGG19, DenseNet121, Xception, and ResNet50) was applied to detect pneumonia in children (1-5 years) chest X-ray images. The performance of different proposed models for testing data set was evaluated using five performances metrics, including accuracy, sensitivity/recall, Precision, area under curve, and F1 score. All proposed models provide accuracy greater than 83.0% for binary classification. The pre-trained DenseNet121 model provides the highest classification performance of automated pneumonia classification with 86.8% accuracy, followed by Xception model with an accuracy of 86.0%. The sensitivity of the proposed models was greater than 91.0%. The Xception and DenseNet121 models achieve the highest classification performance with F1-score greater than 89.0%. The plotted area under curve of receiver operating characteristics of VGG19, Xception, ResNet50, and DenseNet121 models are 0.78, 0.81, 0.81, and 0.86, respectively. Our data showed that the proposed models achieve a high accuracy for binary classification. Transfer learning was used to accelerate training of the proposed models and resolve the problem associated with insufficient data. We hope that these proposed models can help radiologists for a quick diagnosis of pneumonia at radiology departments. Moreover, our proposed models may be useful to detect other chest-related diseases such as novel Coronavirus 2019. Herein, we used transfer learning as a machine learning approach to accelerate training of the proposed models and resolve the problem associated with insufficient data. Our proposed models achieved accuracy greater than 83.0% for binary classification.

Autism Spectrum Disorder (ASD) is a prevalent neurodevelopmental condition that significantly affects a child’s social and cognitive development. Despite growing awareness, early and accurate diagnosis remains a challenge due to the heavy reliance on time-intensive, observer-dependent behavioral assessments. In response, this paper introduces an automated, non-invasive screening framework that leverages static facial features and state-of-the-art deep learning techniques. The proposed system integrates a custom Convolutional Neural Network (CNN), ResNet-50, and VGG16 models within a modular architecture optimized using transfer learning. Experimental validation on the AFD-10K dataset—comprising 10,000 labeled facial images—demonstrates the framework’s high diagnostic performance, with ResNet-50 achieving an accuracy of 92.4%, F1-score of 91.7%, and AUC-ROC of 0.93. Grad-CAM visualizations confirm the model’s focus on clinically relevant facial asymmetries. The system’s design prioritizes reproducibility, scalability, and interpretability, incorporating audit-friendly logging, hyperparameter standardization, and cross-demographic validation. By significantly reducing diagnostic delays and minimizing subjective bias, this framework offers a practical foundation for AI-assisted ASD screening in real-world clinical settings.