Gul Muhammad Khan

Fast learning neural networks using Cartesian genetic programming

A fast learning neuroevolutionary algorithm for both feedforward and recurrent networks is proposed. The method is inspired by the well known and highly effective Cartesian genetic programming (CGP) technique. The proposed method is called the CGP-based Artificial Neural Network (CGPANN). The basic idea is to replace each computational node in CGP with an artificial neuron, thus producing an artificial neural network. The capabilities of CGPANN are tested in two diverse problem domains. Firstly, it has been tested on a standard benchmark control problem: single and double pole for both Markovian and non-Markovian cases. Results demonstrate that the method can generate effective neural architectures in substantially fewer evaluations in comparison to previously published neuroevolutionary techniques. In addition, the evolved networks show improved generalization and robustness in comparison with other techniques. Secondly, we have explored the capabilities of CGPANNs for the diagnosis of Breast Cancer from the FNA (Finite Needle Aspiration) data samples. The results demonstrate that the proposed algorithm gives 99.5% accurate results, thus making it an excellent choice for pattern recognitions in medical diagnosis, owing to its properties of fast learning and accuracy. The power of a CGP based ANN is its representation which leads to an efficient evolutionary search of suitable topologies. This opens new avenues for applying the proposed technique to other linear/non-linear and Markovian/non-Markovian control and pattern recognition problems.

Evolution of neural networks using Cartesian Genetic Programming

A novel Neuroevolutionary technique based on Cartesian Genetic Programming is proposed (CGPANN). ANNs are encoded and evolved using a representation adapted from the CGP. We have tested the new approach on the single pole balancing problem. Results show that CGPANN evolves solutions faster and of higher quality than the most powerful algorithms of Neuroevolution in the literature.

Efficient representation of Recurrent Neural Networks for markovian/non-markovian non-linear control problems

A novel representation of Recurrent Artificial neural network is proposed for non-linear markovian and non-markovian control problems. The network architecture is inspired by Cartesian Genetic Programming. The neural network attributes namely weights, topology and functions are encoded using Cartesian Genetic Programming. The proposed algorithm is applied on the standard benchmark control problem: double pole balancing for both markovian and non-markovian cases. Results demonstrate that the network has the ability to generate neural architecture and parameters that can solve these problems in substantially fewer number of evaluations in comparison to earlier neuroevolutionary techniques. The power of Recurrent Cartesian Genetic Programming Artificial Neural Network (RCGPANN) is its representation which leads to a thorough evolutionary search producing generalized networks.

Coevolution of intelligent agents using cartesian genetic programming

A coevolutionary competitive learning environment for two antagonistic agents is presented. The agents are controlled by a new kind of computational network based on a compartmentalised model of neurons. We have taken the view that the genetic basis of neurons is an important [27] and neglected aspect of previous approaches. Accordingly, we have defined a collection of chromosomes representing various aspects of the neuron: soma, dendrites and axon branches, and synaptic connections. Chromosomes are represented and evolved using a form of genetic programming known as Cartesian Genetic Programming. The network formed by running the chromosomal programs has a highly dynamic morphology in which neurons grow, and die, and neurite branches together with synaptic connections form and change in response to environmental interactions. The idea of this paper is to demonstrate the importance of the genetic transfer of learned experience and life time learning. The learning is a consequence of the complex dynamics produced as a result of interaction (coevolution) between two intelligent agents. Our results show that both agents exhibit interesting learning capabilities.

M2M communication in Smart Grids: Implementation scenarios and performance analysis

The idea of mass deployment of an Advanced Metering Infrastructure (AMI) for Smart Grids has been explored and evaluated in this paper. Since smart meters with a wireless interface that can connect to the utility providers server via a backhaul network forms the basic building block of an AMI, it is a good paradigm for an M2M application in Smart Grids. The relevant standardization efforts by 3GPP and ETSI are discussed along with other perceived application scenarios for M2M communication. An example architecture is then proposed and evaluated with clusters of smart meters that transfer their data via UMTS network to a server. The performance evaluation is carried out considering network throughput, latency, and the data generated by the smart meters using both TCP and UDP traffic. The results indicate that there is a substantial reduction in delay when UDP traffic is considered when compared to TCP traffic generated by the smart meters.

Breast cancer detection using cartesian genetic programming evolved artificial neural networks

A fast learning neuro-evolutionary technique that evolves Artificial Neural Networks using Cartesian Genetic Programming (CGPANN) is used to detect the presence of breast cancer. Features from breast mass are extracted using fine needle aspiration (FNA) and are applied to the CGPANN for diagnosis of breast cancer. FNA data is obtained from the Wisconsin Diagnostic Breast Cancer website and is used for training and testing the network. The developed system produces fast and accurate results when compared to contemporary work done in the field. The error of the model comes out to be as low as 1% for Type-I (classifying benign sample falsely as malignant) and 0.5% for Type-II (classifying malignant sample falsely as benign).

Evolution of cartesian genetic programs for development of learning neural architecture

Although artificial neural networks have taken their inspiration from natural neurological systems, they have largely ignored the genetic basis of neural functions. Indeed, evolutionary approaches have mainly assumed that neural learning is associated with the adjustment of synaptic weights. The goal of this paper is to use evolutionary approaches to find suitable computational functions that are analogous to natural sub-components of biological neurons and demonstrate that intelligent behavior can be produced as a result of this additional biological plausibility. Our model allows neurons, dendrites, and axon branches to grow or die so that synaptic morphology can change and affect information processing while solving a computational problem. The compartmental model of a neuron consists of a collection of seven chromosomes encoding distinct computational functions inside the neuron. Since the equivalent computational functions of neural components are very complex and in some cases unknown, we have used a form of genetic programming known as Cartesian genetic programming (CGP) to obtain these functions. We start with a small random network of soma, dendrites, and neurites that develops during problem solving by repeatedly executing the seven chromosomal programs that have been found by evolution. We have evaluated the learning potential of this system in the context of a well-known single agent learning problem, known as Wumpus World. We also examined the harder problem of learning in a competitive environment for two antagonistic agents, in which both agents are controlled by independent CGP computational networks (CGPCN). Our results show that the agents exhibit interesting learning capabilities.

Short-term daily peak load forecasting using fast learning neural network

Load forecasting has been an inevitable issue in electric power supply in past. It is always desired to predict the load requirements in order to generate and supply electric power efficiently. In this research, a neuro-evolutionary technique known as Cartesian Genetic Algorithm evolved Artificial Neural Network (CGPANN) has been deployed to develop a peak load forecasting model for the prediction of peak loads 24 hours ahead. The proposed model presents the training of all the parameters of Artificial Neural Network (ANN) including: weights, topology and functionality of individual nodes. The network is trained both on annual as well as quarterly bases, thus obtaining a unique model for each season.

A Survey of Cluster-based Routing Schemes for Wireless Sensor Networks

In recent times, wireless sensor networks (WSNs) have become progressively more attractive and have found their way into a wide variety of applications and systems because of their low cost, self-organizing behavior, and sensing ability in harsh environments. A WSN is a collection of nodes organized into a network. Routing is a vital technology in WSNs and can be roughly divided into two categories: flat routing and hierarchical routing. In a flat routing topology, all nodes have identical functionality and carry out the same task in the network. Nodes in a hierarchical topology do different tasks in WSNs and are usually arranged into clusters. In this paper, a survey on cluster-based routing schemes for WSNs has been done and comparisons made on the basis of performance factors such as latency, scalability, and energy awareness. Strengths and limitations of each scheme are presented, and open issues that must be addressed in the design of cluster-based routing algorithms are discussed.

The Power to Deliver: Trends in Smart Grid Solutions

Looking at the communication industry, one observes how drastically the communication horizon has changed. From letters to e-mails and SMS, from phone calls to video chat and live conferencing, from phone booths to smart phones: since the digitization of communication, a new era of consumer choice has been inaugurated. The potential exists for similar transformation and opportunity in the provision of electricity, embodied in a concept known as the “smart grid”. Smart grid is the electric delivery network from electrical generation to the end user that makes use of the latest advances in wireless communication and intelligent information management systems to ameliorate the electric system robustness, reliability, efficiency, and security. Like the telecommunications and the genesis of the Internet, technology holds the key to the smart grid and its realization.