All Outputs (6)

New neural network based mobile location estimation in urban propagation models (2003)
Conference Proceeding
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)
Conference Proceeding
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)
Conference Proceeding
Zayed, A., & Hussain, A. (2003). Stability analysis of a new non-linear pole-zero placement controller incorporating neural networks. In Proceedings - INMIC 2003: IEEE 7th International Multi Topic Conference (290-294). https://doi.org/10.1109/INMIC.2003.1416731

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)
Conference Proceeding
Squartini, S., Hussain, A., & Piazza, F. (2003). Attempting to Reduce the Vanishing Gradient Effect through a novel Recurrent Multiscale Architecture. In Proceedings of the International Joint Conference on Neural Networks (2819-2824). https://doi.org/10.1109/IJCNN.2003.1224018

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)
Conference Proceeding
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.

A recurrent multiscale architecture for long-term memory prediction task (2003)
Conference Proceeding
Squartini, S., Hussain, A., & Piazza, F. (2003). A recurrent multiscale architecture for long-term memory prediction task. In 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03) (789-792). https://doi.org/10.1109/ICASSP.2003.1202485

In the past few years, researchers have been extensively studying the application of recurrent neural networks (RNNs) to solving tasks where detection of long term dependencies is required. This paper proposes an original architecture termed the Recu... Read More about A recurrent multiscale architecture for long-term memory prediction task.