This paper gives an overview of the application of neural networks to telecommunication Systems. Five application areas are discussed, including cloned software identification and the detection of fraudulent use of cellular phones. The systems are summarized and the general results are presented. The conclusions highlight the difficulties involved in using this technology as well as the potential benefits.
In this paper we report on a variety of neural computational systems that have been applied in the telecommunications industry. All the systems described here were developed in collaboration between NORTEL UK and the University of Hertfordshire, UK. In all, five application areas were investigated, resulting in two fully functioning systems, which are incorporated in NORTEL products, two successful prototypes and one application area for which we did not find suitable for a neural computational solution. In the paper we briefly describe the five applications, evaluate our resulting solutions and conclude by reflecting upon the lessons learnt.
What is a system?
System is a set of interacting or interdependent components forming an integrated whole. A system is a set of elements and relationships which are different from relationships of the set or its elements to other elements or sets.
What is a telecommunication system?
In telecommunication, a communications system is a collection of individual communications networks, transmission systems, relay stations, tributary stations, and data terminal equipment (DTE) usually capable of interconnection and interoperation to form an integrated whole. The components of a communications system serve a common purpose, are technically compatible, use common procedures, respond to controls, and operate in unison. Telecommunications is a method of communication.
Telecommunication is the transmission of information over significant distances to communicate. In earlier times, telecommunications involved the use of visual signals, such as beacons, smoke signals, semaphore telegraphs, signal flags, and optical heliographs, or audio messages via coded drumbeats, lung-blown horns, or sent by loud whistles, for example. In the modern age of electricity and electronics, telecommunications now also includes the use of electrical devices such as telegraphs, telephones, and teletypes, the use of radio and microwave communications, as well as fibre optics and their associated electronics, plus the use of the orbiting satellites and the Internet.
A revolution in wireless telecommunications began in the first decade of the 20th century with pioneering developments in wireless radio communications by Nikola Tesla and Guglielmo Marconi, who won the Nobel Prize in Physics in 1909 for his efforts.
Telecommunications play an important role in the world economy and the worldwide telecommunication industry's revenue was estimated to be $3.85 trillion in 2008. The service revenue of the global telecommunications industry was estimated to be $1.7 trillion in 2008, and is expected to touch $2.7 trillion by 2013.
What is an artificial neural network?
An artificial neural network (ANN), usually called neural network (NN), is a mathematical model or computational model that is inspired by the structure and/or functional aspects of biological neural networks. A neural network consists of an interconnected group of artificial neurons, and it processes information using a connectionist approach to computation. In most cases an ANN is an adaptive system that changes its structure based on external or internal information that flows through the network during the learning phase. Modern neural networks are non-linear statistical data modelling tools. They are usually used to model complex relationships between inputs and outputs or to find patterns in data.
The original inspiration for the term Artificial Neural Network came from examination of central nervous systems and their neurons, axons, dendrites, and synapses, which constitute the processing elements of biological neural networks investigated by neuroscience. In an artificial neural network, simple artificial nodes, variously called "neurons", "neurodes", "processing elements" (PEs) or "units", are connected together to form a network of nodes mimicking the biological neural networks — hence the term "artificial neural network".
An ANN is typically defined by three types of parameters:
1. The interconnection pattern between different layers of neurons
2. The learning process for updating the weights of the interconnections
3. The activation function that converts a neuron's weighted input to its output activation.
The study of the human brain is thousands of years old. With the advent of modern electronics, it was only natural to try to harness this thinking process. The first step toward artificial neural networks came in 1943 when Warren McCulloch, a neurophysiologist, and a young mathematician, Walter Pitts, wrote a paper on how neurons might work. They modelled a simple neural network with electrical circuits.
In 1959, Bernard Widrow and Marcian Hoff of Stanford developed models, they called ADALINE and MADALINE. These models were named for their use of Multiple Adaptive Linear Elements. MADALINE was the first neural network to be applied to a real world problem. It is an adaptive filter which eliminates echoes on phone lines, which is still in commercial use.
Hopfield's approach was not to simply model brains but to create useful devices.
Artificial neural networks are loosely based on biology. Current research into the brain's physiology instinct has unlocked only a limited understanding of how neurons work or even what constitutes intelligence in general. Researchers are working in both the biological and engineering fields to further decipher the key mechanisms for how man learns and reacts to everyday experiences. Improved knowledge in neural processing helps create better, more succinct artificial networks.
For parts not yet clear, however, we construct a hypothesis and build a model that follows that hypothesis. We then analyze or simulate the behaviour of the model and compare it with that of the brain. If we find any discrepancy in the behaviour between the model and the brain, we change the initial hypothesis and modify the model. We repeat this procedure until the model behaves in the same way as the brain. This common process has created thousands of network topologies.