Amirkabir University of Technology

About: Amirkabir University of Technology is a education organization based out in Tehran, Iran. It is known for research contribution in the topics: Nonlinear system & Fuzzy logic. The organization has 15254 authors who have published 31165 publications receiving 487551 citations. The organization is also known as: Tehran Polytechnic & Tehran Polytechnic University.

Multiscroll Chaotic Sea Obtained from a Simple 3D System Without Equilibrium

Abstract: Recently, many rare chaotic systems have been found including chaotic systems with no equilibria. However, it is surprising that such a system can exhibit multiscroll chaotic sea. In this paper, a novel no-equilibrium system with multiscroll hidden chaotic sea is introduced. Besides having multiscroll chaotic sea, this system has two more interesting properties. Firstly, it is conservative (which is a rare feature in three-dimensional chaotic flows) but not Hamiltonian. Secondly, it has a coexisting set of nested tori. There is a hidden torus which coexists with the chaotic sea. This new system is investigated through numerical simulations such as phase portraits, Lyapunov exponents, Poincare map, and frequency spectra. Furthermore, the feasibility of such a system is verified through circuital implementation.

ZnO Photocatalyst Revisited: Effective Photocatalytic Degradation of Emerging Contaminants Using S-Doped ZnO Nanoparticles under Visible Light Radiation

Abstract: Zinc oxide (ZnO) nanoparticles were synthesized by the hydrothermal method and incorporated with diverse amounts of the nonmetal element sulfur (0.5, 0.8, 1.1, 1.3, 2.1, 2.5, 3.2, 6.8, 7.8, 11.9, 1...

Improved churn prediction in telecommunication industry using data mining techniques

Abstract: We have employed Decision Tree, Artificial Neural Networks, K-Nearest Neighbors, and Support Vector Machine to improve churn prediction.Using the data of an Iranian mobile company these techniques were experienced and were compared to each other.We proposed a hybrid methodology which made considerable improvements to the value of some of evaluations metrics.Results showed that above 95% accuracy for Recall and Precision is easily achievable.A new methodology for extracting influential features is introduced and experienced. To survive in today's telecommunication business it is imperative to distinguish customers who are not reluctant to move toward a competitor. Therefore, customer churn prediction has become an essential issue in telecommunication business. In such competitive business a reliable customer predictor will be regarded priceless. This paper has employed data mining classification techniques including Decision Tree, Artificial Neural Networks, K-Nearest Neighbors, and Support Vector Machine so as to compare their performances. Using the data of an Iranian mobile company, not only were these techniques experienced and compared to one another, but also we have drawn a parallel between some different prominent data mining software. Analyzing the techniques' behavior and coming to know their specialties, we proposed a hybrid methodology which made considerable improvements to the value of some of the evaluations metrics. The proposed methodology results showed that above 95% accuracy for Recall and Precision is easily achievable. Apart from that a new methodology for extracting influential features in dataset was introduced and experienced.