In this study, an evaluation of food waste generation was conducted, using images taken before an... more In this study, an evaluation of food waste generation was conducted, using images taken before and after the daily meals of people aged between 20 and 30 years in Serbia, for the period between 1 January and 31 April in 2022. A convolutional neural network (CNN) was employed for the tasks of recognizing food images before the meal and estimating the percentage of food waste according to the photographs taken. Keeping in mind the vast variates and types of food available, the image recognition and validation of food items present a generally very challenging task. Nevertheless, deep learning has recently been shown to be a very potent image recognition procedure, while CNN presents a state-of-the-art method of deep learning. The CNN technique was implemented to the food detection and food waste estimation tasks throughout the parameter optimization procedure. The images of the most frequently encountered food items were collected from the internet to create an image dataset, covering...
The paper presents an original research regarding the incidence of polychlorinated biphenyls comp... more The paper presents an original research regarding the incidence of polychlorinated biphenyls compounds (PCBs) and organochlorine insecticides (HCH and DDT) on the urban area of Ploiesti. Due to the high level of toxicity, international legislation provides the list of PCBs compounds to be monitored: PCB28, 52, 101, 118, 138, 153, 180. Sample collection was made in 27 points located in ornamental garden, parks, and street intersections. The chemical analyses were conducted in the Laboratory of National Research and Development Institute for Soil Science, AgroChemistry and Environment of Bucharest, according to an own analytical method adapted after EPA. There were determined physical properties and chemical concentrations for humus, organic carbon, mobile phosphorus and potassium, total nitrogen, as well as the PCBs, DDT and �. -, �� - and �� - HCH. According to the Romanian standards, the concentrations of PCBs overcome the normal values in all sampling points and intervention thres...
“Agriculture for Life, Life for Agriculture” Conference Proceedings, 2018
The paper presents an original research regarding the risk for human health in the area of Ploies... more The paper presents an original research regarding the risk for human health in the area of Ploiesti city using SADA software - Spatial Analysis and Decision Assistance. Due to the high level of toxicity, international legislation provides the list of PCBs compounds to be monitored: PCB28, 52, 101, 118, 138, 153, 180. Sample collection was made in 22 points including public green gardens, residential areas, roadsides and industrial areas. The chemical analyses were conducted in the Laboratory of National Research and Development Institute for Soil Science, Agro-Chemistry and Environment from Bucharest, according to an own analytical method adapted after EPA. According to the Romanian standards, PCBs were elevated across industrial regions near urban and industrial sources. The concentrations of PCBs overcome the normal values in the most sampling points and the area presents a potential of risk for people. Local authorities should address the human health threats from urban and indus...
Agriculture and Agricultural Science Procedia, 2015
A fully distributed, physically-based hydrologic modelling system, MIKE SHE, was used in this stu... more A fully distributed, physically-based hydrologic modelling system, MIKE SHE, was used in this study to simulate surface flow as runoff and subsurface flow drainage routed through tile drainage infrastructure within the Argesel River watershed. MIKE SHE, Système Hydrologique Européen, is a sub-model under the collection of models within the MIKE framework from the Danish Hydraulic Institute (DHI). It covers the major processes in the hydrologic cycle and includes process models for evapotranspiration, overland flow, unsaturated flow, groundwater flow, and channel flow and their interactions. The study's focus was the development of a MIKE SHE model based on available data that can be used in land use management decisions and assessment of hydrological mitigation measures. Sensitivity analyses show that a few individual parameters play an important role in the hydrologic modelling. Vegetation parameters and the root depth as well as empirical parameters influence evapotranspiration, transpiration and recharge, in the unsaturated zone, the type of the soil has an effect on the infiltration/evapotranspiration and recharge functions and at the saturated zone level, the hydraulic conductivity of the matrix represents the dominant parameters.
Uploads
Papers by Mirela Sandu