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.

Background/Objectives: This research work provides a survey on the various clustering algorithms such as k-means, K Harmonic means and Hybrid Fuzzy K Harmonic Means (HFKHM) for grouping similar items in large dataset. To improve the accuracy of clustering the large dataset HFKHM is used. Methods: The task of analyzing the issues in healthcare databases is extremely difficult since healthcare databases are multi-dimensional, comprising the attributes such as the categorization of tumor, radius, texture, smoothness and compactness of the tumor. This paper presents a related work on the existing clustering algorithms for categorizing the tumors as benign or malignant. Hence clustering algorithms are used to categorize the large dataset based on the diagnosis of the tumor. Findings: The efficiency of the various clustering algorithms is compared based on the accuracy and execution time. K means clustering algorithm produces 88% accuracy, 89% accuracy is obtained with the help of K Harmonic Means clustering approach, 90.5% accuracy is achieved using HFKHM clustering approach. Application: This model can be an efficient approach for categorizing similar patient records based on the symptoms, treatments and age.