Search results for: Samiah Alammari

Authors: Samiah Alammari, Nassim Ammour

Abstract:

When providing a massive number of tasks successively to a deep learning process, a good performance of the model requires preserving the previous tasks data to retrain the model for each upcoming classification. Otherwise, the model performs poorly due to the catastrophic forgetting phenomenon. To overcome this shortcoming, we developed a successful continual learning deep model for remote sensing hyperspectral image regions classification. The proposed neural network architecture encapsulates two trainable subnetworks. The first module adapts its weights by minimizing the discrimination error between the land-cover classes during the new task learning, and the second module tries to learn how to replicate the data of the previous tasks by discovering the latent data structure of the new task dataset. We conduct experiments on hyperspectral image (HSI) dataset on Indian Pines. The results confirm the capability of the proposed method.

Keywords: Continual learning, data reconstruction, remote sensing, hyperspectral image segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 321

Authors: Ruyuf Y. Alnafisah, Nouf S. Alammari, Amani S. Alqahtani

Abstract:

Beverage choice can have implications for the risk of non-communicable diseases. However, there is a lack of knowledge in assessing the nutritional content of these beverages. This study aims to describe the nutrient content of pre-packaged beverages available in the Saudi market. Data were collected from the Saudi Branded Food Database (SBFD). Nutrient content was standardized in terms of units and reference volumes to ensure consistency in analysis. A total of 1490 beverages were analyzed. The highest median levels of the majority of nutrients were found among dairy products; energy (68.4 [43-188] kcal/100 ml in a milkshake); protein (8.2 [0.5-8.2] g/100 ml in yogurt drinks); total fat (2.1 [1.3-3.5] g/100 ml in milk); saturated fat (1.4 [0-1.4]g/100 ml in yogurt drinks); cholesterol (30 [0-30] mg/100 ml in yogurt drinks); sodium (65 [65-65] mg/100 ml in yogurt drinks); and total sugars (12.9 (7.5-27] g/100 ml in milkshake). Carbohydrate level was the highest in nectar (13 [11.8-14.2] g/100 ml); fruits drinks (12.9 [11.9-13.9] g/100 ml), and sparkling juices (12.9 [8.8-14] g/100 ml). The highest added sugar level was observed among regular soft drinks (12(10.8-14] g/100 ml). The average rate of nutrient declaration was 60.95%. Carbohydrate had the highest declaration rate among nutrients (99.1%), and yogurt drinks had the highest declaration rate among beverage categories (92.7%). The median content of vitamins A and D in dairy products met the mandatory addition levels. This study provides valuable insights into the nutrient content of pre-packaged beverages in the Saudi market. It serves as a foundation for future research and monitoring. The findings of the study support the idea of taxing sugary beverages and raise concerns about the health effects of high sugar in fruit juices. Despite the inclusion of vitamins D and A in dairy products, the study highlights the need for alternative strategies to address these deficiencies.

Keywords: Pre-packaged beverages, nutrients content, nutrients declaration, daily percentage value, mandatory addition of vitamins.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 82