Download now Matlab codes for biometric recognition

Software Info    About us     

» Home

Biometric recognition: techniques, applications and challenges

21.06.2005 A biometric system can be viewed as a pattern recognition system consisting of three main modules: the sensor module, the feature extraction module and the feature matching module. The design of such a system is studied in the context of many commonly used biometric modalities - fingerprint, face, speech, hand, iris. Various algorithms that have been developed for each of these modalities will be presented.

» Free Downloads

Download now Matlab codes for biometric recognition

	Download Matlab code for fingerprint recognition. Fingerprint Recognition System - Release 5.3
	Download Matlab code for face recognition. Face Recognition System - Release 2.1
	Download Matlab code for speech recognition. Speech Recognition System - Release 1.0
	Download Matlab code for speaker recognition. Speaker Recognition System - Release 1.0

» Neural Networks

Neural Networks and Artificial Intelligence

16.05.2006 A neural network is an interconnected group of biological neurons. In modern usage the term can also refer to artificial neural networks, which are constituted of artificial neurons. Thus the term 'Neural Network' specifies two distinct concepts:

- A biological neural network is a plexus of connected or functionally related neurons in the peripheral nervous system or the central nervous system. In the field of neuroscience, it most often refers to a group of neurons from a nervous system that are suited for laboratory analysis.

- Artificial neural networks were designed to model some properties of biological neural networks, though most of the applications are of technical nature as opposed to cognitive models.

Neural networks are made of units that are often assumed to be simple in the sense that their state can be described by single numbers, their "activation" values. Each unit generates an output signal based on its activation. Units are connected to each other very specifically, each connection having an individual "weight" (again described by a single number). Each unit sends its output value to all other units to which they have an outgoing connection. Through these connections, the output of one unit can influence the activations of other units. The unit receiving the connections calculates its activation by taking a weighted sum of the input signals (i.e. it multiplies each input signal with the weight that corresponds to that connection and adds these products). The output is determined by the activation function based on this activation (e.g. the unit generates output or "fires" if the activation is above a threshold value). Networks learn by changing the weights of the connections. In general, a neural network is composed of a group or groups of physically connected or functionally associated neurons. A single neuron can be connected to many other neurons and the total number of neurons and connections in a network can be extremely large. Connections, called synapses are usually formed from axons to dendrites, though dendrodentritic microcircuits and other connections are possible. Apart from the electrical signalling, there are other forms of signaling that arise from neurotransmitter diffusion, which have an effect on electrical signaling. Thus, like other biological networks, neural networks are extremely complex.

While a detailed description of neural systems seems currently unattainable, progress is made towards a better understanding of basic mechanisms. Artificial intelligence and cognitive modeling try to simulate some properties of neural networks. While similar in their techniques, the former has the aim of solving particular tasks, while the latter aims to build mathematical models of biological neural systems. In the artificial intelligence field, artificial neural networks have been applied successfully to speech recognition, image analysis and adaptive control, in order to construct software agents (in computer and video games) or autonomous robots. Most of the currently employed artificial neural networks for artificial intelligence are based on statistical estimation, optimisation and control theory. The cognitive modelling field is the physical or mathematical modelling of the behaviour of neural systems; ranging from the individual neural level (e.g. modelling the spike response curves of neurons to a stimulus), through the neural cluster level (e.g. modelling the release and effects of dopamine in the basal ganglia) to the complete organism (e.g. behavioural modelling of the organism's response to stimuli).

» Genetic Algorithms

Genetic Algorithms: the Next Generation

11.06.2007 Genetic algorithms constitute a class of search, adaptation, and optimization techniques based on the principles of natural evolution. Genetic algorithms were developed by Holland. Other evolutionary algorithms include evolution strategies, evolutionary programming, classifier systems, and genetic programming. An evolutionary algorithm maintains a population of solution candidates and evaluates the quality of each solution candidate according to a problem-specific fitness function, which defines the environment for the evolution. New solution candidates are created by selecting relatively fit members of the population and recombining them through various operators. Specific evolutionary algorithms di¤er in the representation of solutions, the selection mechanism, and the details of the recombination operators. In a genetic algorithm, solution candidates are represented as character strings from a given (often binary) alphabet. In a particular problem, a mapping between these genetic structures and the original solution space has to be developed, and a fitness function has to be defined. The fitness function measures the quality of the solution corresponding to a genetic structure. In an optimization problem, the fitness function simply computes the value of the objective function. In other problems, fitness could be determined by a coevolutionary environment consisting of other genetic structures. For instance, one could study the equilibrium properties of game-theoretic problems whereby a population of strategies evolves with the fitness of each strategy defined as the average payoff against the other members of the population. A genetic algorithm starts with a population of randomly generated solution candidates. The next generation is created by recombining promising candidates. The recombination involves two parents chosen at random from the population, with the selection probabilities biased in favor of the relatively fit candidates. The parents are recombined through a crossover operator, which splits the two genetic structures apart at randomly chosen locations, and joins a piece from each parent to create an offspring (as a safeguard against the loss of genetic diversity, random mutations are occasionally introduced into the offspring). The algorithm evaluates the fitness of the offspring and replaces one of the relatively unfit members of the population. New genetic structures are produced until the generation is completed. Successive generations are created in the same manner until a well-defined termination criterion is satisfied. The final population provides a collection of solution candidates, one or more of which can be applied to the original problem. Even though evolutionary algorithms are not guaranteed to find the global optimum, they can find an acceptable solution relatively quickly in a wide range of problems.

Evolutionary algorithms have been applied to a large number of problems in engineering, computer science, cognitive science, economics, management science, and other fields. The number of practical applications has been rising steadily, especially since the late 1980s. Typical business applications involve production planning, job-shop scheduling, and other difficult combinatorial problems. Genetic algorithms have also been applied to theoretical questions in economic markets, to time series forecasting, and to econometric estimation. String-based genetic algorithms have been applied to finding market-timing strategies based on fundamental data for stock and bond markets.

» Free Software

Free software available on the web for numerical computations

23.04.2006 A list of matrix-based programming languages:

Scilab - Scilab is a scientific software package for numerical computations providing a powerful open computing environment for engineering and scientific applications. Developed since 1990 by researchers from INRIA and ENPC, it is now maintained and developed by Scilab Consortium since its creation in May 2003.

The R Project for Statistical Computing - R is a free software environment for statistical computing and graphics. It compiles and runs on a wide variety of UNIX platforms, Windows and MacOS.

Octave - Octave is a high-level language, primarily intended for numerical computations. It provides a convenient command line interface for solving linear and nonlinear problems numerically, and for performing other numerical experiments using a language that is mostly compatible with Matlab. It may also be used as a batch-oriented language.

Python - Python is a dynamic object-oriented programming language that can be used for many kinds of software development. It offers strong support for integration with other languages and tools, comes with extensive standard libraries, and can be learned in a few days. Many Python programmers report substantial productivity gains and feel the language encourages the development of higher quality, more maintainable code.

http://www.advancedsourcecode.com/

Hot spots at the nanoscale

Hot spots at the nanoscale
	It's murky territory, down at the bottom of physical reality, where sound waves are really warmth-carrying particles and protons from the sun can make atoms scatter like fans fleeing a fat rock singer trying to crowd surf. Welcome to the world of the nanoscale, where nothing seems to behave like it does up here in the everyday world. And nobody seems to know exactly what the rules are and what to expect. Frankly, it's probably not a place you'd want to visit if it weren't so important.
At least, it's important to anyone involved in or affected by such technologies as computing, telecommunications, and electrical powergeneration. Technology's race to the bottom is being driven by the continuing miniaturization of computer systems. As computer components shrink down to the nanoscale (a nanometer is about four atoms long and about 1/1000th the diameter of a human cell), small, formerly trivial particles can have catastrophic effects. Take phonons. They're the smallest unit (quantum) of sound, just like photons are the smallest quantum of light. They produce the vibrations that we experience as heat. Usually we don't worry about phonons-they only travel at the speed of sound and carry only a fraction of the energy of a photon. Compared to the electrical effects of, say, an ion strike by a cosmic ray-which can shut down a computer system if it knocks out the right transistor-the heat produced by radiation has previously seemed to exert a negligible effect on the performance of integrated circuits. But phonons become more problematic as integrated circuits get smaller, particularly in power devices, direct energy-conversion devices and telecommunications switches. Vanderbilt Assistant Professor of Mechanical Engineering and Electrical Engineering Greg Walker has studied various types of transistors used in power and telecommunications systems and has found that the previously overlooked thermal effects from phonon transport can have a significant impact on the devices' performance. His research on phonon production and transport from an ion striking electronic devices showed that highly scaled structures are susceptible to thermally induced failure, regardless of the strength of the cosmic ray's electronic impact. "As energy carried by phonons propagates through semiconductor materials, it will leave a path that experiences extreme temperatures," Professor Walker says. "Our research has shown that thermal energy production may be significant enough to affect nanoscale microelectronics devices."
Professor Walker is working with the Vanderbilt Institute of Nanoscale Science and Engineering (VINSE). VINSE is an interdisciplinary center involved in nanoscale theoretical and experimental research. VINSE conducts a wide range of projects in nano-optics; nano-bio processes; spintronics; nanoscale electronics; nanocrystal fabrication, characterization, and integration; and radiation effects and defect studies. The Institute recently opened a new nano science and engineering laboratory complex and this fall launched a National Science Foundation (NSF)-sponsored Integrative Graduate Education and Research Traineeship (IGERT) Ph.D. program.
Professor Walker is one of the professors involved in the new NSF IGERT doctoral program, but he will spend little of his research time in the new nanolab. Instead you'll find him at the computer, developing models and simulations. "What I'm working on is the theoretical understanding of phonon behavior," Professor Walker says. "We need a more precise way of evaluating thermal effects when predicting the performance of semiconductor devices as they reach nanoscale proportions." Professor Walker hopes that this work will help microelectronics designers develop materials and fabrication techniques that will protect the equipment from, or compensate for, thermal effects. "Vanderbilt's Institute for Space and Defense Electronics (ISDE) is the best research center in the nation for the study of radiation effects in integrated circuits," he notes. "I hope that my colleagues at ISDE will be able to take the models we are developing to augment the research they are doing on radiation effects." The model Professor Walker and his associates have developed produces simulations of nanoscale energy transport throughout the entire thermodynamic cycle. "Current research efforts to integrate models of electronic and thermal transport are limited, so our work represents the first attempt to couple models that include phonon dispersion, polarization and multiple scattering mechanisms with electronic simulation," Professor Walker says. The problem with traditional models of the dynamics of heat produced by electrons scattering throughout semiconductor materials is that these models are based on assumptions that the material itself is in a state of thermodynamic equilibrium. But radiation, particularly from an ion strike, creates non-equilibrium in the system. Power devices are also non-equilibrium systems because they involve large currents, high switching speeds and reduced sizes. "You can't model these phenomena as thermal diffusion processes," Professor Walker says. "We need a new fundamental physics for non-equilibrium transport of phonons." In addition to his work on radiation effects, Professor Walker and his associates have focused their research on direct energy-conversion devices and metal oxide semiconductor field effect transistors (MOSFETs), which are used in power electronics, telecommunications switches, and "smart chip" integrated circuits. Professor Walker analyzed the thermal effects in MOSFET devices by first running a commercial simulation that models the behavior of electrons. Professor Walker then fed these results into a new model he has developed to analyze nonequilibrium thermal effects. This process revealed that the energy carried by the phonons can result in debilitating "hot spots" in the devices. "The confinement of thermal energy causes a higher rate of interaction with electrons, which ultimately causes reduction of electrical current," Professor Walker says. "The findings lead us to believe that devices with similar or smaller dimensions with short time-scale features are susceptible to performance aberrations or failures." This information not only will help microelectronics engineers design new nanoscale devices, but perhaps will explain computer failures that have heretofore been inexplicable. Direct energy-conversion devices, specifically thermoelectric refrigerators and electrical generators, can be used in a wide variety of applications such as power plant bottoming or topping cycles and scaled cooling situations. By understanding and leveraging nonequilibrium phonon transport in these solid state devices, efficiencies can be improved, which will ultimately reduce the world's dependence on fossil fuels. "We don't have all the answers, but understanding that electrical characteristics of devices are closely coupled with thermal nonequilibrium effects is a big step in the right direction," Professor Walker says.