KWHO-CNN: A Hybrid Metaheuristic Algorithm Based Optimzed Attention-Driven CNN for Automatic Clinical Depression Recognition

A convolutional neural network (CNN) architecture, NutriFoodNet, enhanced through Particle Swarm Optimization (PSO) is suggested in this paper to optimize data augmentation parameters and key hyperparameters, specifically designed for food image recognition. Accurate food image classification plays a vital function in various applications, including nutrition management, dietary assessment, and healthcare, as it aids in the automated recognition and analysis of food items from images. The implementation aimed to improve classification accuracy on the Food101 dataset. Initially, the NutriFoodNet model achieved an accuracy of 97.3%. By applying PSO, the model's performance was further refined, resulting in an increased accuracy of 98.5%. This optimized system was benchmarked against state-of-the-art architectures, including ResNet-18, ResNet-50, and Inception V3, showcasing its exceptional performance. The proposed system highlights the efficiency of PSO in fine-tuning augmentation parameters and CNN hyperparameters, leading to significant improvements in model accuracy for food image classification tasks. This advancement underscores the potential of enhanced food image classification systems in contributing to better dietary monitoring and healthcare outcomes.

Enhancing Food Image Classification with Particle Swarm Optimization on NutriFoodNet and Data Augmentation Parameters

Sreetha E S,

G Naveen Sundar,

D Narmadha

2024

Deep Learning Empowered Water Quality Assessment: Leveraging IoT Sensor Data with LSTM Models and Interpretability Techniques

Achuthankutty,

et al. 2024

Addressing the imperative demand for accurate water quality assessment, this paper delves into the application of deep learning techniques, specifically leveraging IoT sensor datasets for the classification and prediction of water quality parameters. The utilization of LSTM (Long Short-Term Memory) models navigates the intricacies inherent in environmental data, emphasizing the balance between model accuracy and interpretability. This equilibrium is achieved through the deployment of interpretability methods such as LIME, SHAP, Anchor, and LORE. Additionally, the incorporation of advanced parameter optimization techniques focuses on fine-tuning essential parameters like learning rates, batch sizes, and epochs to optimize model performance. This comprehensive approach ensures not only precise predictions but also enhances the transparency and interpretability of the model, addressing the critical need for actionable information in water quality management. The research significantly contributes to the convergence of deep learning, IoT, and environmental science, offering valuable tools for informed decision-making while highlighting the importance of fine-tuning parameters for optimal model performance

Hybrid Deep Learning Based Model for Removing Grid-Line Artifacts from Radiographical Images

U. S. Pavitha,

S. Nikhila,

Mohan

2024

The digital imaging technique known as Computed Radiography (CR) has transformed the medical imaging industry by providing a number of advantages. It eliminates the need for traditional film-based methods, making it more efficient and convenient. A common issue faced with CR images is the presence of grid artifacts and other pattern artifacts, which can have a significant impact on the quality of the images when viewed on a computer screen, especially if a clinic-grade display is not accessible. This paper presents a novel framework for removing grid line artifacts from X-ray images, which is a critical challenge in medical imaging. The framework proposes a hybrid Deep Grid model that combines a Gaussian band-stop filter with ADAM optimization to produce high-quality, grid-line free X-ray images that are suitable for further analysis and diagnosis. Deep learning (DL) models for instance the Convolutional Neural Network (CNN), DenseNet, VGG-Net, and Fast R-CNN were utilized to classify images, and the grid-by-grid removal of grid lines in the image was performed. The proposed framework achieved a high accuracy rate of 98% in eliminating grid line artifacts from X-ray images, demonstrating its possibility for a big improvement the accuracy and reliability of diagnostics for medical based on X-ray images