In this paper, we perform a systematic study about the on-body sensor positioning and data acquisition details for Human Activity Recognition (HAR) systems. We build a testbed that consists of eight body-worn Inertial Measurement Units (IMU) sensors and an Android mobile device for activity data collection. We develop a Long Short-Term Memory (LSTM) network framework to support training of a deep learning model on human activity data, which is acquired in both real-world and controlled environments. From the experiment results, we identify that activity data with sampling rate as low as 10 Hz from four sensors at both sides of wrists, right ankle, and waist is sufficient in recognizing Activities of Daily Living (ADLs) including eating and driving activity. We adopt a two-level ensemble model to combine class-probabilities of multiple sensor modalities, and demonstrate that a classifier-level sensor fusion technique can improve the classification performance. By analyzing the accuracy of each sensor on different types of activity, we elaborate custom weights for multimodal sensor fusion that reflect the characteristic of individual activities.
The effect of microwave and conventional cooking methods, designed to simulate I hose used in home meal preparation, upon nutrient retention in t~olossus Peas (Vigna uniguiculata) was studied. Neither method reslllted in significant changes in the fat, protein, p-carotene and ascor bit acid content of the peas. Microwave cooking resulted in significaritly greater losses of several ammo acids, but resulted in significanily greater retention of thiamin and riboflavin than the conventional treatment. Although each of the mineral components exhibit1 d different magnitudes of loss by the two cooking methods, differ6 rices due to method of cooking were not significant. Both Fe and (:u were completely retained in the peas cooked by both methods. Both cooking methods (1560 min cooking) resulted in 92-97% 18~s of trypsin inhibitor.INTRODUCTION THERE HAS BEEN a widespread increase in the application of microwale processing for both home and institutional meal preparation because of its speed and convenience compared to conventional cooking methods. Microwave cookirrg results in the simultaneous production of heat throughcut the food product when polar molecules, under the influence of rapidly oscillating electromagnetic field (9 .5 or 2,450 MHz) are induced to undergo rapid reorientatio:r, thus, converting electromagnetic energy to thermal energ!' and resulting in a uniform temperature profile throughout the food. Conventional cooking on the other hand, involves surface absorption of thermal energy from exte.nal sources by radiation and conduction, resulting in an mieven temperature profile throughout the product, thus necessitating a longer cooking time to obtain a given internal product temperature.Theoretically, the heating effect of microwave energy upon various foc'd components could differ significantly from that of co,rventional cooking. For example, it has been speculated that reactive free radicals might be formed by exposure to microwave energy, especially in those applications that result in abnormally high temperatures, as with frying and toasting. However, Rosen (1972) concluded that micrc #wave radiation does not possess sufficient energy to produc: free radicals or to break chemical bonds, as is the case with gamma and X-ray radiations.Since peas rep resent a major potential source of protein,
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.