Phase-to-pattern inverse design paradigm for fast realization of functional metasurfaces via transfer learning

Metasurfaces have provided unprecedented freedom for manipulating electromagnetic waves. In metasurface design, massive meta-atoms have to be optimized to produce the desired phase profiles, which is time-consuming and sometimes prohibitive. In this paper, we propose a fast accurate inverse method of designing functional metasurfaces based on transfer learning, which can generate metasurface patterns monolithically from input phase profiles for specific functions. A transfer learning network based on GoogLeNet-Inception-V3 can predict the phases of 28×8 meta-atoms with an accuracy of around 90%. This method is validated via functional metasurface design using the trained network. Metasurface patterns are generated monolithically for achieving two typical functionals, 2D focusing and abnormal reflection. Both simulation and experiment verify the high design accuracy. This method provides an inverse design paradigm for fast functional metasurface design, and can be readily used to establish a meta-atom library with full phase span.

Remote Control, Protection and Monitoring of Pump for Agricultural Purposes

With the increasing pressure on our natural resources and diminishing soil quality, there is a need to make better efforts to conserve them. This project aims to help control the irrigation in a small field. The motor pump set equipped at the field is prone to a variety of operational issues like Power Quality issues, Reverse run of the pump, Irregular Power Supply. Using an ATMEGA Microcontroller equipped with GSM Module for connectivity, this model is able to provide the user with remote control for the motor pump set equipped at his field. Additionally, this model comes with protection schemes for detection of Input Phase Sequence Supply and protection against Over Voltage and Over Current. This system aims to reduce the man power requirement in the field by providing remote or at home control of the pump set applied on the field with cost effective and easy control which can be used by unskilled operators as well.

Rating Faculty for Foreign Student in Egypt by Bloom Filter Classifier and Collaborative Filtering

This paper presents an approach of bloom filter classifier and collaborative filtering to help foreign student to choose the suitable faculty according to his nationality and number of years that need to study. Our approach consist of three phases are: input phase, classification phase, and recommendation phase. In Input phase, the student enters the nationality and number of suggested years study. In classification phase, the approach classifies the student according to input data based on bloom filter classifier. In recommendation phase, the approach recommended the top five faculty if exists based on collaborative filtering technique (CF). Our dataset collected from Misr University for Science and Technology (MUST) and the results of our approach suitable and has a good manner for the student with accuracy 90%.