Outputs (400)

Temporal classification for fault-prediction in a real-world telecommunications network (2005)
Presentation / Conference Contribution
Jaudet, M., Iqbal, N., Hussain, A., & Sharif, K. (2005, September). Temporal classification for fault-prediction in a real-world telecommunications network. Presented at IEEE 2005 International Conference on Emerging Technologies, Islamabad, Pakistan

This paper presents a new temporal classification approach for fault-prediction in a Telecommunications Network. The countrywide data network of Pakistan Telecom (PTCL) has been selected as a basis for the investigation of classification algorithms t... Read More about Temporal classification for fault-prediction in a real-world telecommunications network.

Blind image deconvolution using space-variant neural network approach (2005)
Journal Article
Cheema, T., Qureshi, I., & Hussain, A. (2005). Blind image deconvolution using space-variant neural network approach. Electronics Letters, 41(6), 308-309

A novel space-variant neural network based on an autoregressive moving average process is proposed for blind image deconvolution. An extended cost function motivated by human visual perception is developed simultaneously to identify the blur and to r... Read More about Blind image deconvolution using space-variant neural network approach.

Hybrid HOS-SOS approach for blind equalisation of communication channels (2005)
Journal Article
Hussain, A., Naveed, A., & Qureshi, I. (2005). Hybrid HOS-SOS approach for blind equalisation of communication channels. Electronics Letters, 41(6), 376-377. https://doi.org/10.1049/el%3A20057272

A new hybrid higher-order statistics (HOS) and second-order statistics (SOS) based approach to improve the performance of the standard Bussgang algorithm for blind equalisation of digital communication channels is presented. An additional term, based... Read More about Hybrid HOS-SOS approach for blind equalisation of communication channels.

A new multivariable generalized minimum-variance controller with pole-zero placement (2004)
Journal Article
Zayed, A. S., Hussain, A., & Smith, L. (2004). A new multivariable generalized minimum-variance controller with pole-zero placement. Control and Intelligent Systems, 32(1), 35-44. https://doi.org/10.2316/Journal.201.2004.1.201-1307

This article presents the derivation of a new robust multivariable adaptive controller, which minimizes a cost function, incorporating system input, system output, and set point. It provides an adaptive mechanism that ensures that both the closed-loo... Read More about A new multivariable generalized minimum-variance controller with pole-zero placement.

Neural networks for fault-prediction in a telecommunications network (2004)
Presentation / Conference Contribution
Jaudet, M., Iqbal, N., & Hussain, A. (2004). Neural networks for fault-prediction in a telecommunications network. In 8th International Multitopic Conference, 2004. Proceedings of INMIC 2004 (315-320). https://doi.org/10.1109/INMIC.2004.1492896

The main topic of this paper is fault prediction from large alarm records stored in different databases of non-cooperating network management systems. We have chosen the countrywide data network of Pakistan Telecom (PTCL) as a basis for the investiga... Read More about Neural networks for fault-prediction in a telecommunications network.

New neural network based mobile location estimation in urban propagation models (2003)
Presentation / Conference Contribution
Muhammad, J., Hussain, A., & Ahmed, W. (2003). New neural network based mobile location estimation in urban propagation models. . https://doi.org/10.1109/INMIC.2003.1416679

Location estimation finds its applications in many important decisions in cellular networks. Hand offs, cellular fraud detection and location sensitive billing are some of the examples. Many different techniques are currently in use. This work first... Read More about New neural network based mobile location estimation in urban propagation models.

Novel non-linear PID based multiple-controller incorporating a neural network learning sub-model (2003)
Presentation / Conference Contribution
Zayed, A., & Hussain, A. (2003). Novel non-linear PID based multiple-controller incorporating a neural network learning sub-model. In 7th International Multi Topic Conference, 2003. INMIC 2003 (283-289). https://doi.org/10.1109/INMIC.2003.1416729

The paper proposes a new non-linear adaptive PID based multiple-controller incorporating a neural network learning sub-model. The unknown non-linear plant is represented by an equivalent model consisting of a linear time-varying sub-model plus a non-... Read More about Novel non-linear PID based multiple-controller incorporating a neural network learning sub-model.

Stability analysis of a new non-linear pole-zero placement controller incorporating neural networks (2003)
Presentation / Conference Contribution
Zayed, A., & Hussain, A. (2003, December). Stability analysis of a new non-linear pole-zero placement controller incorporating neural networks. Presented at 7th International Multi Topic Conference, 2003 (INMIC 2003), Islamabad, Pakistan

The stability analysis and parameter convergence of a newly reported self-tuning pole-zero placement controller algorithm for non-linear dynamic systems are studied. The original controller overcomes the shortcomings of other linear designs and provi... Read More about Stability analysis of a new non-linear pole-zero placement controller incorporating neural networks.

Attempting to Reduce the Vanishing Gradient Effect through a novel Recurrent Multiscale Architecture (2003)
Presentation / Conference Contribution
Squartini, S., Hussain, A., & Piazza, F. (2003, July). Attempting to Reduce the Vanishing Gradient Effect through a novel Recurrent Multiscale Architecture. Presented at International Joint Conference on Neural Networks, 2003, Portland, OR, US

This paper proposes a possible solution to the vanishing gradient problem in recurrent neural networks, occurring when such networks are applied to solving tasks where detection of long term dependencies is required. The main idea consists of pre-pro... Read More about Attempting to Reduce the Vanishing Gradient Effect through a novel Recurrent Multiscale Architecture.

Preprocessing based solution for the vanishing gradient problem in recurrent neural networks (2003)
Presentation / Conference Contribution
Squartini, S., Hussain, A., & Piazza, F. (2003). Preprocessing based solution for the vanishing gradient problem in recurrent neural networks. . https://doi.org/10.1109/ISCAS.2003.1206412

In this paper, a possible solution to the vanishing gradient problem in recurrent neural networks (RNN) is proposed. The main idea consists of pre-processing the signal (a time series typically) through a wavelet decomposition, in order to separate t... Read More about Preprocessing based solution for the vanishing gradient problem in recurrent neural networks.