A Fingerprint Technique for Indoor Localization using Autoencoder based Semi-supervised Deep Extreme Learning Machine

Zahra Ezzati Khatab, Amirhosein Hajihoseini Gazestani, Seyed Ali Ghorashi, Mohammad Ghavami

Abstract:

In recent years, because of the growing demand for location based services in indoor environment and development of Wi-Fi, fingerprint-based indoor localization has attracted many researchers’ interest. In Wireless Sensor Networks (WSNs), fingerprint based localization methods estimate the target location by using a pattern matching model for the measurements of the Received Signal Strength (RSS) from the available transmitter sensors, which are collected by a smartphone with internal sensors. Due to the dynamic nature of the environment, the fingerprint database needs to be updated, periodically. Hence, it is better to add new fingerprint data to the primary database in order to update them. However, collecting the labeled data is time consuming and labor intensive. In this paper, we propose a novel algorithm, which uses high level extracted features by an autoencoder to improve the localization performance in the classification process. Furthermore, to update the fingerprint data base, we also add crowd-sourced labeled and unlabeled data in order to improve the localization performance, gradually. Simulation results indicate that the proposed method provides a significant improvement in localization performance, using high level extracted features by the autoencoder, and by increasing the number of unlabeled training data.

Link of Paper

Joint Optimization of Power and Location in Full-Duplex UAV Enabled Systems

 Amirhosein Hajihoseini Gazestani; Seyed Ali Ghorashi; Zhaohui Yang; Mohammad Shikh-Bahaei

Abstract: 

Unmanned aerial vehicles (UAVs) can be used as aerial base stations (BSs) for future small cells. They can increase the spectral efficiency of the small cells due to their higher probability to have line-of-sight (LOS) connections and their mobility as a BS. In this article, in order to show the effectiveness of using full-duplex (FD) technology in UAV networks, we consider a UAV equipped with FD technology (FD-UAV) with imperfect self-interference cancelation as an aerial BS that serves both uplink (UL) and downlink (DL) users simultaneously in a small cell network. We aim to maximize DL sum-rate, whilst prescribing a certain quality of service for UL users, by optimizing the location of FD-UAV and available resources. The problem is nonconvex; so we propose an iterative method by exploiting the difference of convex functions programming to jointly optimize transmission power of users, FD-UAV location, and FD-UAV transmission power. Simulation results are illustrated to show the effectiveness of the proposed method for FD-UAV in comparison with ground BS, in both FD and half-duplex modes.

Link of Paper

Resource Allocation in Full-Duplex UAV Enabled Multi Small Cell Networks

 Amirhosein Hajihoseini Gazestani; Seyed Ali Ghorashi; Zhaohui Yang; Mohammad Shikh-Bahaei

Abstract:

Flying platforms such as Unmanned Aerial Vehicles (UAVs) are a promising solution for future small cell networks. UAVs can be used as aerial Base Stations (BSs) to enhance coverage, capacity and reliability of wireless networks. Also, with recent advances of Self Interference Cancellation (SIC) techniques in Full-Duplex (FD) systems, practical implementation of FD BSs is feasible. In this paper, we investigate the problem of resource allocation for multi-small cell networks with FD-UAVs as aerial BSs with imperfect SIC. We consider three different scenarios: a) maximizing the DL sum-rate, b) maximizing the UL sum-rate, and finally c) maximizing the sum of UL and DL sum-rates. The aforementioned problems result in non-convex optimization problems, therefore, successive convex approximation algorithms are developed by leveraging D.C. (Difference of Convex functions) programming to find sub-optimal solutions. Simulation results illustrated validity and effectiveness of the proposed radio resource management algorithms in comparison with ground BSs, in both FD mode and its half-duplex (HD) counterpart. The results also indicate those situations where using aerial BS is advantageous over ground BS and reveal how FD transmission enhances the network performance in comparison with HD one.

Link of Paper

A compact half butterfly chipless RFID tag based on image theory with DER analysis

 Amirhosein Zarif, Sajad Mohammad-Ali-Nezhad, Sajad Tijeri-Mofrad, Amirhosein Hajihoseini Gazestani

Abstract:

In this paper, a compact RFID chipless structure is designed, simulated, and fabricated. Image theory has been used to reduce the structure of the RFID tag so that it halves the tag and creates a PEC wall having the same resonant frequencies. In other words, each symmetric structure by this method is half the size with features similar to the original structure. The proposed structure has a ratio of area to lambda equal to 0.05 in which there are nine resonances in a frequency band of 4.3–8.5 GHz with dimensions of 14 × 7 mm2 in a bit density of 9.18 bit/cm2 and fabricated on Rog4003 substrate. The bit density for the full structure was equal to 4.59 bit/cm2. The original and proposed structures have similar resonances that indicate the accuracy of the proposed method. Also, this method can be used to create a label with a higher number of bits. The simulation results using HFSS software were in good agreement with the measurement results. Furthermore, the calculated detection error rate of the proposed structure was lower than the original one.

Link of Paper

A Survey on Implementation and Applications of Full Duplex Wireless Communications

Amirhosein Hajihoseini Gazestani, Seyed Ali Ghorashi, Behnaz Mousavinasab, Mohammd Shikh-Bahaei

Abstract

شاخه دانشجویی IEEE دانشکده مهندسی برق دانشگاه شهید بهشتی برگزار می کند:

شاخه دانشجویی IEEE دانشکده مهندسی برق دانشگاه شهید بهشتی برگزار می کند:

پنجشنبه بیست و هفتم مهر و چهار آبان، آمفی تئاتر دانشکده مهندسی برق دانشگاه شهید بهشتی

شاخه دانشجویی IEEE دانشکده مهندسی برق دانشگاه شهید بهشتی برگزار می کند:

پنجشنبه سیزدهم و بیستم مهرماه، آمفی تئاتر دانشکده مهندسی برق دانشگاه شهید بهشتی

پژوهشکده فضای مجازی دانشگاه شهید بهشتی با همکاری شاخه دانشجویی IEEE برگزار می کند: