scispace - formally typeset
Search or ask a question
Author

Aleksandar Atanaskovic

Bio: Aleksandar Atanaskovic is an academic researcher from University of Niš. The author has contributed to research in topics: Amplifier & Linearization. The author has an hindex of 6, co-authored 40 publications receiving 132 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: The design methodologies of two different SSs are compared, with the aim of obtaining both the good performance and a low computational complexity, with a lower number of model parameters and a lower noise sensitivity are obtained when using DBNs.
Abstract: Here, this article reports about the design of a soft sensor (SS) able to monitor the hazardous gases in industrial plants. The SS is designed to estimate the gas concentrations by means of the measurements coming from an array of sensors, avoiding at the same time the humidity and temperature influence on array outputs. The SS has been designed with a data-driven approach, using a set of experimental data acquired in a laboratory. The design methodologies of two different SSs are compared, with the aim of obtaining both the good performance and a low computational complexity. As a first approach, a principal component analysis (PCA) has been performed to exploit the high correlation among some of the measures coming from the sensor array. A classical multilayer perceptron neural network is then trained to estimate the relationships between the PCA outputs and the gas concentrations. As a second approach, a deep belief network (DBN) has been considered. The data here reported show a good accuracy in the evaluation of several gas concentrations, even in the presence of noised measurements, allowing an efficient risk warning. Even if both the methods gave a similar performance, a lower number of model parameters and a lower noise sensitivity are obtained when using DBNs.

56 citations

Journal ArticleDOI
TL;DR: In this article, a single-stage power amplifier and two-way Doherty amplifier are linearized by the technique that uses second harmonics and fourth-order nonlinear signals.
Abstract: In this article, a single-stage power amplifier and two-way Doherty amplifier are linearized by the technique that uses second harmonics and fourth-order nonlinear signals. Measurements of the linearization effects on the third- and fifth-order intermodulation products have been carried out. © 2012 Wiley Periodicals, Inc. Microwave Opt Technol Lett 55:425–430, 2012; View this article online at wileyonlinelibrary.com. DOI 10.1002/mop.27294

12 citations

Proceedings Article
15 Dec 2011
TL;DR: In this paper, a two-way Doherty amplifier with the additional circuit for linearization has been realized and measurements of the linearization influence to the third-and fifth-order intermodulation products have been carried out.
Abstract: In this paper two-way Doherty amplifier with the additional circuit for linearization has been realized and measurements of the linearization influence to the third-and fifth-order intermodulation products have been carried out. The linearization approach uses the fundamental signals' second harmonics and fourth-order nonlinear signals that are extracted at the output of peaking cell, adjusted in amplitude and phase and injected at the output of the carrier cell in Doherty amplifier.

11 citations

Proceedings ArticleDOI
28 Sep 2005
TL;DR: In this paper patch antennas are modeled using neural model based on multi-layer perceptrons (MLP) network, which enables quick and correct calculation of resonant frequency f/sub r/ and minimum value of S/sub 11/ parameter.
Abstract: In this paper patch antennas are modeled using neural model based on multi-layer perceptrons (MLP) network. Neural model is trained by data, which are obtained by electromagnetic simulation of antennas using HFSS 9.0 software. This model has four input parameters: patch antenna length L, patch antenna width W, deep of patch antenna slot l and width of patch antenna slot s and it enables quick and correct calculation of resonant frequency f/sub r/ and minimum value of S/sub 11/ parameter (S/sub 11min/).

9 citations

Proceedings ArticleDOI
20 Apr 2016
TL;DR: A single artificial neural network is used for determination of the gas concentrations based on sensor array measurements, performing at the same time compensation of the temperature and humidity influence on the sensor outputs to show good accuracy in gas concentration estimation.
Abstract: In this paper a new approach for safety monitoring of dangerous gases in the industrial plants is proposed. A single artificial neural network is used for determination of the gas concentrations based on sensor array measurements, performing at the same time compensation of the temperature and humidity influence on the sensor outputs. The obtained results show good accuracy in gas concentration estimation, enabling efficient risk warning.

8 citations


Cited by
More filters
Journal ArticleDOI
22 Apr 2017-Sensors
TL;DR: A weighted belief entropy based on Deng entropy is proposed to quantify the uncertainty of uncertain information in Dempster–Shafer evidence theory and is verified according to an experiment on artificial data and an application on fault diagnosis of a motor rotor.
Abstract: In real applications, how to measure the uncertain degree of sensor reports before applying sensor data fusion is a big challenge. In this paper, in the frame of Dempster–Shafer evidence theory, a weighted belief entropy based on Deng entropy is proposed to quantify the uncertainty of uncertain information. The weight of the proposed belief entropy is based on the relative scale of a proposition with regard to the frame of discernment (FOD). Compared with some other uncertainty measures in Dempster–Shafer framework, the new measure focuses on the uncertain information represented by not only the mass function, but also the scale of the FOD, which means less information loss in information processing. After that, a new multi-sensor data fusion approach based on the weighted belief entropy is proposed. The rationality and superiority of the new multi-sensor data fusion method is verified according to an experiment on artificial data and an application on fault diagnosis of a motor rotor.

84 citations

Journal ArticleDOI
TL;DR: In this article , a wave-driven liquid-solid TENG was developed to construct a self-powered sensing system for marine environmental monitoring, which has an excellent response (ΔU/Ua = 170 % @ 30 ppm) and is 14 times larger than that of the resistive sensor.

74 citations

Journal ArticleDOI
TL;DR: The design methodologies of two different SSs are compared, with the aim of obtaining both the good performance and a low computational complexity, with a lower number of model parameters and a lower noise sensitivity are obtained when using DBNs.
Abstract: Here, this article reports about the design of a soft sensor (SS) able to monitor the hazardous gases in industrial plants. The SS is designed to estimate the gas concentrations by means of the measurements coming from an array of sensors, avoiding at the same time the humidity and temperature influence on array outputs. The SS has been designed with a data-driven approach, using a set of experimental data acquired in a laboratory. The design methodologies of two different SSs are compared, with the aim of obtaining both the good performance and a low computational complexity. As a first approach, a principal component analysis (PCA) has been performed to exploit the high correlation among some of the measures coming from the sensor array. A classical multilayer perceptron neural network is then trained to estimate the relationships between the PCA outputs and the gas concentrations. As a second approach, a deep belief network (DBN) has been considered. The data here reported show a good accuracy in the evaluation of several gas concentrations, even in the presence of noised measurements, allowing an efficient risk warning. Even if both the methods gave a similar performance, a lower number of model parameters and a lower noise sensitivity are obtained when using DBNs.

56 citations

Journal ArticleDOI
TL;DR: A novel supervised DBN (SDBN) is proposed in this article by introducing the quality information into the training phase by ensuring that the learned features are largely quality-related for soft sensor.
Abstract: Deep belief network (DBN) has recently been applied for soft sensor modeling with its excellent feature representation capacity. However, DBN cannot guarantee that the extracted features are quality-related and beneficial for further quality prediction. To solve this problem, a novel supervised DBN (SDBN) is proposed in this article by introducing the quality information into the training phase. SDBN consists of multiple supervised restricted Boltzmann machines (SRBMs) with a stacked structure. In each SRBM, the quality variables are added to the visible layer for network pretraining and feature learning. Thus, the pretrained weights can act as better initializations for the whole network for fine-tuning. Moreover, it can ensure that the learned features are largely quality-related for soft sensor. Finally, the SDBN-based soft sensor model is applied to two industrial plants of a debutanizer column and a hydrocracking process for quality prediction.

41 citations

Journal ArticleDOI
Le Yao1, Zhiqiang Ge1
TL;DR: In this article, a deep dynamic feature extracting (DFE) network is constructed based on the long short-term memory (LSTM) encoder-decoder with attention mechanism, which maps time-sequence samples to a group of hidden dynamic features.
Abstract: Local learning models have been widely applied for time-variant process soft sensor development, where historical samples that are similar to the online testing sample are selected for local modeling and prediction. However, those similarity measurements and local models are commonly established based on the static samples, which are seriously inadequate when process dynamics exist. To tackle this problem, a novel locally weighted deep learning algorithm that takes dynamic features to describe both the similarities and relationships is proposed in this article. First, a deep dynamic feature extracting (DFE) network is constructed based on the long short-term memory (LSTM) encoder–decoder with attention mechanism, which maps time-sequence samples to a group of hidden dynamic features. With the extracted features incorporated into the original input features, a locally weighted autoencoder regression (LWAER) network is proposed for soft sensor modeling. Meanwhile, since both networks consist of unsupervised feature extracting and supervised feature regression, a large scale of unlabeled samples can be utilized in the semisupervised learning of model parameters. Finally, the superiorities of the proposed dynamic features incorporated LWAER (DFI-LWAER) model is verified by the outstanding performances in two real industrial soft sensing cases.

28 citations