Entity

Time filter

Source Type


Transmit laser selection (TLS) diversity scheme has been proposed recently for free-space optical communication systems and its bit error rate (BER) performance has been investigated over K-distributed turbulence channels based on lengthy simulations. Moreover, for a limiting case of strong turbulence conditions that have been modelled by negative exponential distribution, a closed-form expression for the average BER has been presented in the open technical literature. In this study, first a novel approximate analytical expression is derived for the probability density function (PDF) of the resulting channel irradiance corresponding to a TLS diversity scheme over the K channel. The approximated PDF accurately estimates the statistics of the channel irradiance over a wide range of channel conditions. Then, based on the derived PDF, an analytical closed-form expression is presented for the average BER, which can be used to estimates the BER of the system very accurately over K-distributed turbulence channels without resorting to lengthy simulations. Additionally, based on the derived analytical results, the effect of using laser pulse shape with increased peak-to-average optical power ratio on the system performance is investigated. Numerical results are further demonstrated to confirm the analytical results. © 2011 The Institution of Engineering and Technology. Source


Tarjoman M.,Islamic Azad University at Abhar | Fatemizadeh E.,Sharif University of Technology | Badie K.,Research Institute for ICT
Journal of Medical Engineering and Technology | Year: 2013

Content-based image retrieval (CBIR) has been one of the most active areas of research. The retrieval principle of CBIR systems is based on visual features such as colour, texture and shape or the semantic meaning of the images. A CBIR system can be used to locate medical images in large databases. This paper presents a CBIR system for retrieving digital human brain magnetic resonance images (MRI) based on textural features and the support vector machine (SVM) learning method. This system can retrieve similar images from the database in two groups: normal and tumoural. This research uses the knowledge of the CBIR approach to the application of medical decision support and discrimination between the normal and abnormal medical images based on features. This study presents and compares the results of the proposed method with the CBIR systems used in recent works. The experimental results indicate that the proposed method is reliable and has high image retrieval efficiency compared with the previous works. © 2013 Informa UK, Ltd. Source


Shourie N.,Islamic Azad University at Tehran | Firoozabadi S.M.P.,Tarbiat Modares University | Badie K.,Research Institute for ICT
2011 18th Iranian Conference of Biomedical Engineering, ICBME 2011 | Year: 2011

In this paper, we extracted scaling exponents of multichannel EEG signals recorded from two groups of artists and non-artists. We compared them to investigate the difference between artists and non-artists. The EEG signals were recorded while the subjects performed four tasks of visual perception, four tasks of mental imagery and at resting condition. We used Davies-Bouldin's index for evaluation of the feature space quality and the discrimination between the two groups. We observed a noticeable similarity in scaling exponents between visual perception and mental imagery. A considerable discrimination in scaling exponents was observed between the two groups at resting condition. However, the differentiation in scaling exponents between visual perceptions of the two groups was low. This result was observed in scaling exponents between the two groups' mental imageries, too. Thereby, the discrimination in scaling exponents between the two groups decreased with performing a same cognitive task. Additionally, we classified the scaling exponents which were related to the resting conditions and the visual perceptions of the two groups by the Neural Gas classifier. The average accuracies were 87.5% and 46.87%, respectively. These results confirmed the discrimination and the similarity in scaling exponents between resting conditions and visual perceptions of the two groups, respectively. © 2011 IEEE. Source


Nazaktabar H.,University of Tehran | Badie K.,Research Institute for ICT | Ahmadabadi M.N.,University of Tehran
Wireless Networks | Year: 2016

In many real world applications of wireless sensor networks, it is enough for the sensors to send just an approximation of their observations. In these networks dual prediction scheme (DPS)—including two predictive models one in the sensor side and its copy in the sink side—is widely used. In DPS, the total data transmission through the network is a function of the model’s prediction power and the size of its free parameters. In this paper, a DPS using a reinforcement learning based signal predictor (RLSP) algorithm is proposed. RLSP learns the environment’s signal and builds the predictive model gradually based on its experiences. At the moment the model gets invalid, RLSP only needs to learn and transmit the environmental data of that moment. As a result, the amount of data transmission in the network and consequently energy consumption is very low. The simulation results on 16 benchmarking signals and comparison with time series-based DPSs confirm these properties of RLSP. © 2016 Springer Science+Business Media New York Source


Tarjoman M.,Islamic Azad University at Tehran | Fatemizadeh E.,Sharif University of Technology | Badie K.,Research Institute for ICT
Biomedical Engineering - Applications, Basis and Communications | Year: 2012

Content-based image retrieval (CBIR) has turned into an important and active potential research field with the advance of multimedia and imaging technology. It makes use of image features, such as color, texture and shape, to index images with minimal human intervention. A CBIR system can be used to locate medical images in large databases. In this paper we propose a CBIR system which describes the methodology for retrieving digital human brain magnetic resonance images (MRI) based on textural features and the Adaptive neuro-fuzzy inference system (ANFIS) learning to retrieve similar images from database in two categories: normal and tumoral. A fuzzy classifier has been used, because of the uncertainty in the results of classifier and capacity of learning. ANFIS is a good candidate for our categorization problem. Our proposed CBIR system can locate a query image in the category of normal or tumoral images in the online retrieval part. Finally, using a relevance feedback, we improve the effectiveness of our retrieval system. This research uses the knowledge of the CBIR approach to the application of medical decision support and discrimination between the normal and abnormal medical images based on features. We present and compare the results of the proposed method with the CBIR systems used in recent works. The experimental results indicate that the proposed method is reliable and has high image retrieval efficiency compared with the previous works. © 2012 National Taiwan University. Source

Discover hidden collaborations