University of Tabriz

About: University of Tabriz is a education organization based out in Tabriz, Iran. It is known for research contribution in the topics: Population & Nanocomposite. The organization has 12141 authors who have published 20976 publications receiving 313982 citations.

A New Multilevel Converter Topology With Reduced Number of Power Electronic Components

Abstract: In this paper, a new topology for cascaded multilevel converter based on submultilevel converter units and full-bridge converters is proposed. The proposed topology significantly reduces the number of dc voltage sources, switches, IGBTs, and power diodes as the number of output voltage levels increases. Also, an algorithm to determine dc voltage sources magnitudes is proposed. To synthesize maximum levels at the output voltage, the proposed topology is optimized for various objectives, such as the minimization of the number of switches, gate driver circuits and capacitors, and blocking voltage on switches. The analytical analyses of the power losses of the proposed converter are also presented. The operation and performance of the proposed multilevel converter have been evaluated with the experimental results of a single-phase 125-level prototype converter.

Fast and fully-scalable synthesis of reduced graphene oxide

Abstract: Exfoliation of graphite is a promising approach for large-scale production of graphene. Oxidation of graphite effectively facilitates the exfoliation process, yet necessitates several lengthy washing and reduction processes to convert the exfoliated graphite oxide (graphene oxide, GO) to reduced graphene oxide (RGO). Although filtration, centrifugation and dialysis have been frequently used in the washing stage, none of them is favorable for large-scale production. Here, we report the synthesis of RGO by sonication-assisted oxidation of graphite in a solution of potassium permanganate and concentrated sulfuric acid followed by reduction with ascorbic acid prior to any washing processes. GO loses its hydrophilicity during the reduction stage which facilitates the washing step and reduces the time required for production of RGO. Furthermore, simultaneous oxidation and exfoliation significantly enhance the yield of few-layer GO. We hope this one-pot and fully-scalable protocol paves the road toward out of lab applications of graphene.

Evaluation of Different Machine Learning Methods and Deep-Learning Convolutional Neural Networks for Landslide Detection

Abstract: There is a growing demand for detailed and accurate landslide maps and inventories around the globe, but particularly in hazard-prone regions such as the Himalayas. Most standard mapping methods require expert knowledge, supervision and fieldwork. In this study, we use optical data from the Rapid Eye satellite and topographic factors to analyze the potential of machine learning methods, i.e., artificial neural network (ANN), support vector machines (SVM) and random forest (RF), and different deep-learning convolution neural networks (CNNs) for landslide detection. We use two training zones and one test zone to independently evaluate the performance of different methods in the highly landslide-prone Rasuwa district in Nepal. Twenty different maps are created using ANN, SVM and RF and different CNN instantiations and are compared against the results of extensive fieldwork through a mean intersection-over-union (mIOU) and other common metrics. This accuracy assessment yields the best result of 78.26% mIOU for a small window size CNN, which uses spectral information only. The additional information from a 5 m digital elevation model helps to discriminate between human settlements and landslides but does not improve the overall classification accuracy. CNNs do not automatically outperform ANN, SVM and RF, although this is sometimes claimed. Rather, the performance of CNNs strongly depends on their design, i.e., layer depth, input window sizes and training strategies. Here, we conclude that the CNN method is still in its infancy as most researchers will either use predefined parameters in solutions like Google TensorFlow or will apply different settings in a trial-and-error manner. Nevertheless, deep-learning can improve landslide mapping in the future if the effects of the different designs are better understood, enough training samples exist, and the effects of augmentation strategies to artificially increase the number of existing samples are better understood.

Deep Learning--based Text Classification: A Comprehensive Review

Abstract: Deep learning--based models have surpassed classical machine learning--based approaches in various text classification tasks, including sentiment analysis, news categorization, question answering, and natural language inference. In this article, we provide a comprehensive review of more than 150 deep learning--based models for text classification developed in recent years, and we discuss their technical contributions, similarities, and strengths. We also provide a summary of more than 40 popular datasets widely used for text classification. Finally, we provide a quantitative analysis of the performance of different deep learning models on popular benchmarks, and we discuss future research directions.