ABSTRACT
Obesity is a major global health challenge and a risk factor for the leading causes of death, including heart disease, stroke, diabetes, and several types of cancer. Attempts to manage and regulate obesity have led to the implementation of various dietary regulatory initiatives to provide information on the calorie contents of meals. Although knowledge of the calorie content is useful for meal planning, it is not sufficient as other factors, including health status (diabetes, hypertension, etc.) and level of physical activity, are essential in the decision process for obesity management. In this work, we present an artificial intelligence- (AI-) based application that is driven by a genetic algorithm (GA) as a potential tool for tracking a user's energy balance and predicting possible calorie intake required to meet daily calorie needs for obesity management. The algorithm takes the users' input information on desired foods which are selected from a database and extracted records of users on cholesterol level, diabetes status, and level of physical activity, to predict possible meals required to meet the users need. The micro- and macronutrients of food content are used for the computation and prediction of the potential foods required to meet the daily calorie needs. The functionality and performance of the model were tested using a sample of 30 volunteers from the University of Ghana. Results revealed that the model was able to predict both glycemic and non-glycemic foods based on the condition of the user as well as the macro- and micronutrients requirements. Moreover, the system is able to adequately track the progress of the user's weight loss over time, daily nutritional needs, daily calorie intake, and predictions of meals that must be taken to avoid compromising their health. The proposed system can serve as a useful resource for individuals, dieticians, and other health management personnel for managing obesity, patients, and for training students in fields of dietetics and consumer science.
ABSTRACT
We describe data compression in phase-shifting digital holography. We demonstrate by experimentation that an image of a diffusely reflecting object can be reconstructed only by phase data of the derived complex amplitude. It is shown that reduction of the bit depth of the phase data does not seriously damage the image even down to 1 bit. We observe enhancement of halo in the image with low bit depths. This tendency is verified quantitatively by a one-dimensional simulation. Our procedure for smoothing the images that result from the data-compression methods is shown to be effective.
ABSTRACT
We discuss quantization effects of hologram recording on the quality of reconstructed images in phase-shifting digital holography. We vary bit depths of phase-shifted holograms in both numerical simulation and experiments and then derived the complex amplitude, which is subjected to Fresnel transformation for the image reconstruction. The influence of bit-depth limitation in quantization has been demonstrated in a numerical simulation for spot-array patterns with linearly varying intensities and a continuous intensity object. The objects are provided with uniform and random phase modulation. In experiments, digital holograms are originally recorded at 8 bits and the bit depths are changed to deliver holograms at bit depths of 1 to 8 bits for the image reconstruction. The quality of the reconstructed images has been evaluated for the different quantization levels.