Scalable and Efficient Multi-Class Brain Tumor Classification with a Compact Hybrid Deep Learning Model for Real-Time Applications

Convolutional neural network with transfer learning approach for detection of unfavorable driving state using phase coherence image

PurposeTuberculosis (TB) is a severe bacterial infectious lung disease. Millions of people die or experience severe health complications due to TB each year. Accurate, automated, and effective detection of TB is key to curing and preventing person-to-person transmission. In this regard, deep learning (DL) and machine learning (ML) techniques applied to chest X-ray (CXR) images have proved effective. Here, we present our DL- and ML-based approach for TB detection using CXR images.Material and methodsWe implemented convolutional neural network (CNN)-based pre-trained DL models, such as DenseNet121, DenseNet169, DenseNet201, ResNet152, and VGG19, as feature extractors. ML models, including support vector machine (SVM), XGBoost, logistic regression, and a DL-based custom model, were used as classifiers. A total of 2,391 CXR images from three publicly available datasets were considered.ResultsWe found three models achieving the highest value in different evaluation metrics: accuracy (99.91%) with ResNet152 and SVM; recall (99.22%), precision (99.23%), and F1-score (99.22%) with DenseNet169 and the custom classifier; and area under the curve (99.99%) with DenseNet201 and the custom classifier. Among these models, we propose DenseNet169 with the custom classifier as the best performer for potential clinical application, as it reflected a high and well-balanced performance across all evaluation metrics.ConclusionsThis study evaluated pre-trained CNN-based DL and ML models on pre-processed CXR images for the detection of TB. The DenseNet169 model with a custom classifier stands out with its high and well-balanced performance, offering a significant contribution to the effective and automated detection of TB.

Small and Medium-sized Enterprises (SMEs) in Sri Lanka are increasingly turning to social media to gain insights into consumer preferences; however, they frequently lack sophisticated analytical tools to derive actionable insights. This research introduces a hybrid deep learning framework aimed at sentiment and emotion analysis specifically for the Sri Lankan cake sector. Customer reviews and social media comments were gathered and processed through various methods including text cleaning, emoji translation, stopword elimination, tokenization, and sequence padding. Several deep learning models— Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and Gated Recurrent Units (GRU) were assessed, along with hybrid models that combined CNN and BiLSTM with GPT-2 embeddings. The CNN+GPT-2 model achieved the highest accuracy in sentiment classification at 96.14%, while BiLSTM performed best in emotion classification with an accuracy of 91.57%. In terms of trend forecasting, Long Short-Term Memory (LSTM) outshone both SARIMA and Prophet, yielding the lowest error metrics and the most reliable sentiment predictions. These results underscore the potential of hybrid deep learning and transformer-based models to effectively capture complex consumer sentiments and provide SMEs with practical, AI-driven insights. This study is among the first to implement such hybrid NLP models within a localized Sri Lankan context, presenting a scalable approach for business intelligence and informed decision-making.

Water quality prediction (WQP) plays an essential role in water quality management for aquaculture to make aquaculture production profitable and sustainable. In this work, we propose hybrid deep learning (DL) models, convolutional neural network (CNN) with the long short-term memory (LSTM) and gated recurrent unit (GRU) for aquaculture WQP. CNN can effectively fetch the aquaculture water quality characteristics, whereas GRU and LSTM can learn long-term dependencies in the time series data. We conduct experiments using the two different water quality datasets and present an extensive study on the impact of hyperparameters on the performance of the proposed hybrid DL models. Furthermore, the performance of hybrid CNN-LSTM and CNN-GRU models are compared with different baseline LSTM, GRU and CNN DL models and also with attention-based LSTM and attention-based GRU DL models. The results show that the hybrid CNN-LSTM outperformed all other models in terms of prediction accuracy and computation time.

Accurate detection and classification of brain tumors are essential for timely diagnosis and effective treatment planning. This study presents an integrated framework leveraging both machine learning (ML) and deep learning (DL) models for brain tumor detection and classification using MRI images. Two publicly available datasets are utilized: one for binary classification (tumor vs. no tumor) and another for multiclass classification (glioma, meningioma, and pituitary tumors). Comprehensive preprocessing steps, including resizing, feature extraction using the Gray Level Co-occurrence Matrix (GLCM), and feature selection via Chi-square testing, were employed to optimize the dataset for modeling. Machine learning models such as Decision Trees, K-Nearest Neighbors (KNN), Support Vector Machines (SVM), and AdaBoost were compared with deep learning architectures like Convolutional Neural Networks (CNNs) and the pre-trained VGG16 model. Hyperparameter optimization techniques, including grid search and the Adam optimizer, were used to enhance model performance. The models were evaluated using metrics such as accuracy, precision, recall, F1-score, Mean Squared Error (MSE), and Mean Absolute Error (MAE). Results indicate that the VGG16 model consistently outperformed other approaches, achieving high validation accuracy. This study highlights the potential of integrating ML and DL techniques for accurate and efficient brain tumor detection and classification, offering valuable tools for medical diagnostics.

Though large amounts of work with artificial intelligence are used in typhoon rainfall forecasting, the predictive skills of existing models are unsatisfactory. To address this problem, this study aims to propose an improved cluster‐wise typhoon rainfall forecasting model that integrates the grid‐search cross‐validation method with machine learning and deep learning (DL) models including support vector machine (SVM), random forest (RF), adaptive boosting (AdaBoost), convolutional neural network (CNN), and long short‐term memory (LSTM). Grid‐search cross‐validation is a modified parameterization technique that helps to find the best parameters for machine/DL models. In the first stage, a second‐order polynomial regression model was used to cluster the typhoon track; and in the second stage, cluster‐wise typhoon rainfall was recognized within a 500 km radius from each typhoon center. After that, a modified cluster‐wise typhoon rainfall forecasting model was proposed using cluster‐wise antecedent hourly typhoon rainfall within this distance for 1–6 hr lead time. Results show that the proposed model based on the SVM, RF, AdaBoost, CNN, and LSTM is capable of providing more accurate forecasts (the efficiency of the forecast is increased by 45%–90%) than the existing typhoon rainfall forecasting models that are based on SVM with a genetic algorithm, RF, artificial neural network, multilayer perceptron network, and deep neural network. Therefore, the current study recommends using cluster‐wise typhoon rainfall forecasting model with a grid‐search cross‐validation method for disaster prevention and mitigation.

Background: Classification of brain tumors is an integral aspect of medical imaging studies as different tumor features require multiclassification which aids in making the diagnosis. However, this task is of great difficulty owing to the nature of the brain MRI images. Recent deep learning (DL) models have made it possible to have a brain tumor classification with high accuracy, which is very useful to neurologists. Based on these new capabilities, this study intends to enhance brain tumor detection with the help of a hybrid transfer learning approach. Methods: This study developed a brain tumor diagnosis system using five advanced DL architectures: Xception, ResNet164, DenseNet121, DenseNet201, and Inception-ResNetV2. A hybrid DL model was created by integrating a deep-dense block and a softmax activation function in the final layers of these architectures. The proposed approach enhances classification accuracy and precision. Two experiments were conducted: Three-class classification, involving images from patients with gliomas, meningiomas, and pituitary tumors. Four-class classification, which included gliomas, meningiomas, pituitary tumors, and normal brain images. Results: The Xception architecture emerged as the most effective model in detecting brain tumors when implemented with the proposed hybrid DL modifications. The system achieved an accuracy of 99.71% on the three-class dataset and 96.17% on the four-class dataset, outperforming state-ofthe- art methods in brain tumor classification. Conclusion: This research shows that hybrid DL models can enhance the capabilities of brain tumor classification systems in the context of complex MRI datasets. The optimization of activation functions and the inclusion of deep-dense blocks increase both accuracy and precision, providing adequate solutions for neurologists. These results lead to the recognition of the Xception-based hybrid model as a robust and efficient model for detecting brain tumors.

Heart disease is one of the leading causes of mortality worldwide, emphasizing the need for early and accurate diagnosis. Traditional machine learning (ML) models such as Random Forest (RF) and Support Vector Machines (SVM) have been widely used for heart disease classification. However, these models often lack the ability to extract hierarchical patterns and long-range dependencies present in complex medical data. To address this limitation, we propose a hybrid deep learning framework that integrates XGBoost with Capsule Networks (XGBoost-CapsNet) and Convolutional Neural Networks (CNN) with Transformer Encoders (CNN-TE) to enhance classification performance.The study utilizes a structured dataset containing essential heart disease indicators. Feature selection is performed using XGBoost, which ranks attributes based on importance. The Capsule Network (CapsNet) is then used to preserve spatial relationships and hierarchical dependencies among features. Meanwhile, the CNN-TE model extracts spatial features through convolutional layers and captures long-range dependencies using a Transformer Encoder with multi-head self-attention mechanisms. The models are trained using optimized hyperparameters and evaluated against baseline ML models (Random Forest, SVM, and standalone CNN). Performance metrics such as accuracy, precision, recall, F1-score, and AUC-ROC are used for comparison.Experimental evaluations demonstrate that the proposed hybrid models significantly outperform traditional approaches. The XGBoost-CapsNet model achieves an accuracy of 98.2%, while CNN-TE reaches 97.4%, both surpassing standalone CNN (95.1%), Random Forest (94.2%), and SVM (91.8%). The AUC-ROC scores further validate the robustness of the models, with XGBoost-CapsNet scoring 0.99 and CNN-TE achieving 0.98. The use of feature selection with XGBoost improves interpretability and computational efficiency, while the hybrid deep learning models enable better feature extraction and classification accuracy.

Aim: Hepatic steatosis is a recognised major risk factor for primary graft failure in liver transplantation. In general, the global fat burden is measured by the surgeon using a visual assessment. However, this can be augmented by a histological assessment, although there is often inter-observer variation in this regard as well. In many situations the assessment of the liver relies heavily on the experience of the observer and more experienced surgeons will accept organs that more junior surgeons feel are unsuitable for transplantation. Often surgeons will err on the side of caution and not accept a liver for fear of exposing recipients to excessive risk of death. Methods: In this study, we present the use of deep learning for the non-invasive evaluation of donor liver organs. Transfer learning, using deep learning models such as the Visual Geometry Group (VGG) Face, VGG16, Residual Neural Network 50 (ResNet50), Dense Convolutional Network 121 (DenseNet121) and MobileNet are utilised for effective pattern extraction from partial and whole liver. Classification algorithms such as Support Vector Machines, k-Nearest Neighbour, Logistic Regression, Decision Tree and Linear Discriminant Analysis are then used for the final classification to identify between acceptable or non-acceptable donor liver organs. Results: The proposed method is distinct in that we make use of image information both from partial and whole liver. We show that common pre-trained deep learning models can be used to quantify the donor liver steatosis with an accuracy of over 92%. Conclusion: Machine learning algorithms offer the tantalising prospect of standardising the assessment and the possibility of using more donor organs for transplantation.

Identify suitable artificial groundwater recharge zones using hybrid deep learning models

The human brain is one of the body's most major organs. If there are problems within the human brain, they may cause serious consequences, and even endangers the human life. One of the most fatal diseases for humans is a brain tumor. In the old days, tumor detection was done manually by doctors through reading magnetic resonance images, which might not be time efficient, and sometimes may even produce inaccurate results. Nowadays, with the development of science and technology, Artificial Intelligence (AI) is present in many fields in human life, including medical field. Tumor detection with AI is one of the applications that technology changes human life. The Convolution Neural Network (CNN), a prominent algorithm in deep learning, is widely employed in tumor identification. In this study, a CNN model is proposed. Over 7000 brain tumor magnetic resonance images, including glioma, meningioma, no tumor and pituitary are used in this study. The images are also preprocessed to improve the accuracy of the proposed models. In this study, the well-known VGG16 model, which is a pretrained deep learning model, is utilized to compare with the proposed model. The proposed model and the VGG16 model are trained and evaluated using both the original (uncropped) images and preprocessed (cropped) images. The results of the experiment indicate that the suggested model exceeds the VGG16 model in the light of loss and accuracy.

Sentiment Analysis of Self Driving Car Dataset: A comparative study of Deep Learning approaches

Despite advances in diagnostics, the objective and repeatable assessment of patients with neurological deficits (e.g., stroke) remains a major challenge. Modern methods based on artificial intelligence (AI) are of interest to researchers and clinicians in this area. This study presents a comparative analysis of different AI approaches used to analyze gait of stroke patients using a retrospective dataset of 120 individuals. The main objective is to evaluate the effectiveness, accuracy, and clinical relevance of machine learning (ML) and deep learning (DL) models in identifying gait abnormalities and predicting rehabilitation outcomes. Multiple AI techniques—including support vector machines (SVM), random forests (RF), k-nearest neighbors (k-NN), and convolutional neural networks (CNN)—were trained and tested on time-series gait data with spatiotemporal parameters. Performance metrics such as accuracy, precision, recall, and area under the curve (AUC) were used to compare model results. Initial results indicate that DL models, particularly CNNs, outperform traditional ML methods in capturing complex gait patterns and providing reliable classification. However, simpler models showed advantages in interpretability and computational efficiency. This study highlights the potential and shortcomings of AI-based gait analysis tools in supporting clinical decision-making and planning personalized stroke rehabilitation.

This paper presents a novel and straightforward way of classifying discrete and surface-mount electronic components found on electronic prototypes using transfer learning and deep convolutional neural networks (DCNN). The goal of this study is to precisely classify images of electronic components into six classes: resistor, capacitor, inductor, transformer, diode, or integrated circuit. Each class of electronic components has over 100 images which are augmented and preprocessed to match the input layer requirements of the deep learning models used. The dataset was divided into a ratio of 70:30, where 70% was used for training and 30% was used for testing and validation. Transfer Learning (TL) was done using three pre-trained deep learning models that are available on MATLAB's Neural Network Toolbox: Inception-v3, GoogleNet, and Resnet101. Using this approach provides faster deployment and only requires fewer lines of coding compared to typical deep learning classification methods which make use of Python, Tensorflow, and Keras. The results of the experiment showed that Inception-v3 has the highest validation accuracy of 94.64% in classifying electronic components.

Traditional geological mapping methods, which rely on field observations and rock sample analysis, are inefficient for continuous spatial mapping of geological features such as alteration zones. Deep learning models such as convolutional neural networks (CNNs) have ushered in a transformative era in remote sensing data analysis. CNNs excel in automatically extracting features from image data for classification and regression problems. CNNs have the ability to pinpoint specific mineralogical changes attributed to mineralisation processes by discerning subtle features within remote sensing data. In this study, we deploy CNNs with three sets of remote sensing data, namely Landsat 8, Landsat 9, and ASTER, to delineate diverse alteration zones within a mineral-rich region north of Broken Hill in western New South Wales, Australia. Our methodology involves model training using two distinct sets of training samples generated through ground truth data and a fully automated approach through selective principal component analysis (PCA). We also compare CNNs with conventional machine learning models, including k‑nearest neighbours, support vector machines, and multilayer perceptron. Our findings indicate that training with a ground truth-based dataset produces more reliable alteration maps. Additionally, we find that CNNs perform slightly better when compared to conventional machine learning models, which further demonstrates the ability of CNNs to capture spatial patterns in remote sensing data effectively. We find that Landsat 9 surpasses Landsat 8 in mapping iron oxide areas when employing the CNNs model trained with ground truth data obtained by field surveys. We also observe that using ASTER data with the CNNs model trained on the ground truth-based dataset produces the most accurate maps for two other important types of alteration zones, argillic and propylitic. This underscores the utility of CNNs in enhancing the efficiency and precision of geological mapping, particularly in discerning subtle alterations indicative of mineralisation processes, especially those associated with critical metal resources.