Enhancing Pneumonia Detection in Pediatric Chest X-Rays Using CGAN-Augmented Datasets and Lightweight Deep Transfer Learning Models

Pneumonia ranks as a leading cause of mortality, particularly in children aged five and under. Detecting this disease typically requires radiologists to examine chest X-rays and report their findings to physicians, a task susceptible to human error. The application of Deep Transfer Learning (DTL) for the identification of pneumonia through chest X-rays is hindered by a shortage of available images, which has led to less than optimal DTL performance and issues with overfitting. Overfitting is characterized by a model’s learning that is too closely fitted to the training data, reducing its effectiveness on unseen data. The problem of overfitting is especially prevalent in medical image processing due to the high costs and extensive time required for image annotation, as well as the challenge of collecting substantial datasets that also respect patient privacy concerning infectious diseases such as pneumonia. To mitigate these challenges, this paper introduces the use of conditional generative adversarial networks (CGAN) to enrich the pneumonia dataset with 2690 synthesized X-ray images of the minority class, aiming to even out the dataset distribution for improved diagnostic performance. Subsequently, we applied four modified lightweight deep transfer learning models such as Xception, MobileNetV2, MobileNet, and EfficientNetB0. These models have been fine-tuned and evaluated, demonstrating remarkable detection accuracies of 99.26%, 98.23%, 97.06%, and 94.55%, respectively, across fifty epochs. The experimental results validate that the models we have proposed achieve high detection accuracy rates, with the best model reaching up to 99.26% effectiveness, outperforming other models in the diagnosis of pneumonia from X-ray images.

A Lightweight Convolutional Neural Network with Hierarchical Multi-Scale Feature Fusion for Image Classification

Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.

Advancing Type II Diabetes Predictions with a Hybrid LSTM-XGBoost Approach

In this paper, we explore the ability of a hybrid model integrating Long Short-Term Memory (LSTM) networks and eXtreme Gradient Boosting (XGBoost) to enhance the prediction accuracy of Type II Diabetes Mellitus, which is caused by a combination of genetic, behavioral, and environmental factors. Utilizing comprehensive datasets from the Women in Data Science (WiDS) Datathon for the years 2020 and 2021, which provide a wide range of patient information required for reliable prediction. The research employs a novel approach by combining LSTM’s ability to analyze sequential data with XGBoost’s strength in handling structured datasets. To prepare this data for analysis, the methodology includes preparing it and implementing the hybrid model. The LSTM model, which excels at processing sequential data, detects temporal patterns and trends in patient history, while XGBoost, known for its classification effectiveness, converts these patterns into predictive insights. Our results demonstrate that the LSTM-XGBoost model can operate effectively with a prediction accuracy achieving 0.99. This study not only shows the usefulness of the hybrid LSTM-XGBoost model in predicting diabetes but it also provides the path for future research. This progress in machine learning applications represents a significant step forward in healthcare, with the potential to alter the treatment of chronic diseases such as diabetes and lead to better patient outcomes.

A Hybrid Ensemble Learning Approach Utilizing Light Gradient Boosting Machine and Category Boosting Model for Lifestyle-Based Prediction of Type-II Diabetes Mellitus

Addressing classification and prediction challenges, tree ensemble models have gained significant importance. Boosting ensemble techniques are commonly employed for forecasting Type-II diabetes mellitus. Light Gradient Boosting Machine (LightGBM) is a widely used algorithm known for its leaf growth strategy, loss reduction, and enhanced training precision. However, LightGBM is prone to overfitting. In contrast, CatBoost utilizes balanced base predictors known as decision tables, which mitigate overfitting risks and significantly improve testing time efficiency. CatBoost’s algorithm structure counteracts gradient boosting biases and incorporates an overfitting detector to stop training early. This study focuses on developing a hybrid model that combines LightGBM and CatBoost to minimize overfitting and improve accuracy by reducing variance. For the purpose of finding the best hyperparameters to use with the underlying learners, the Bayesian hyperparameter optimization method is used. By fine-tuning the regularization parameter values, the hybrid model effectively reduces variance (overfitting). Comparative evaluation against LightGBM, CatBoost, XGBoost, Decision Tree, Random Forest, AdaBoost, and GBM algorithms demonstrates that the hybrid model has the best F1-score (99.37%), recall (99.25%), and accuracy (99.37%). Consequently, the proposed framework holds promise for early diabetes prediction in the healthcare industry and exhibits potential applicability to other datasets sharing similarities with diabetes.

A Stacking-Based Ensemble Approach with Embeddings from Language Models for Depression Detection from Social Media Text

Depression is a major public health problem around the world and contributes significantly to poor health and poverty. The rate of the number of people being affected is very high compared to the rate of medical treatment of the disease. Thus, the disease often remains untreated and suffering continues. Machine learning has been widely used in many studies in detecting depressive individuals from their contents on online social networks. From the related reviews, it is apparent that the application of stacking for diagnosing depression has been minimal. The study implements stacking based on Extra Tree, Extreme Gradient Boosting, Light Gradient Boosting and Multi-layer perceptron and compares its performance to state of the art bagging and boosting ensemble learners. To better evaluate the effectiveness of the proposed stacking approach, three pretrain word embeddings techniques including: Word2vec, Global Vectors and Embeddings from language models were employed with two datasets. Also, a corrected resampled paired t-test was applied to test the significance of the stacked accuracy against the baseline accuracy. The experimental results shows that the stacking approach yields favourable results with a best accuracy of 99.54%.