Iris research is focused on developing techniques for identifying and locating relevant biometric features, accurate segmentation and efficient computation while lending themselves to compression methods. Most iris segmentation methods are based on complex modelling of traits and characteristics which, in turn, reduce the effectiveness of the system being used as a real time system. This paper introduces a novel parameterized technique for iris segmentation. The method is based on a number of steps starting from converting grayscale eye image to a bit plane representation, selection of the most significant bit planes followed by a parameterization of the iris location resulting in an accurate segmentation of the iris from the origin

Infrastructure, especially wastewater projects, plays an important role in the life of residential communities. Due to the increasing population growth, there is also a significant increase in residential and commercial facilities. This research aims to develop two models for predicting the cost and time of wastewater projects according to independent variables affecting them. These variables have been determined through a questionnaire distributed to 20 projects under construction in Al-Kut City/ Wasit Governorate/Iraq. The researcher used artificial neural network technology to develop the models. The results showed that the coefficient of correlation R between actual and predicted values were 99.4% and 99 %, MAPE was

In Automatic Speech Recognition (ASR) the non-linear data projection provided by a one hidden layer Multilayer Perceptron (MLP), trained to recognize phonemes, and has previous experiments to provide feature enhancement substantially increased ASR performance, especially in noise. Previous attempts to apply an analogous approach to speaker identification have not succeeded in improving performance, except by combining MLP processed features with other features. We present test results for the TIMIT database which show that the advantage of MLP preprocessing for open set speaker identification increases with the number of speakers used to train the MLP and that improved identification is obtained as this number increases beyond sixty.

In this paper a WLAN network that accesses the Internet through a GPRS network was implemented and tested. The proposed network is managed by the Linux based server. Because of the limited facilities of GPRS such as dynamic IP addressing besides to its limited bandwidth a number of techniques are implemented to overcome these limitations.

      Dynamic Host Configuration Protocol (DHCP) server was added to provide a single central control for all TCP/IP resources. Squid Proxy  was added to provide caching of the redundant accessed Web content to reduce the Internet bandwidth usage and speeding up the client’s download time. Network Address Translation (NAT) service was configured to share one IP ad

The objective of this work is to design and implement a cryptography system that enables the sender to send message through any channel (even if this channel is insecure) and the receiver to decrypt the received message without allowing any intruder to break the system and extracting the secret information. In this work, we implement an interaction between the feedforward neural network and the stream cipher, so the secret message will be encrypted by unsupervised neural network method in addition to the first encryption process which is performed by the stream cipher method. The security of any cipher system depends on the security of the related keys (that are used by the encryption and the decryption processes) and their corresponding le

 

            This paper presents a study of wavelet self-organizing maps (WSOM) for face recognition. The WSOM is a feed forward network that estimates optimized wavelet based for the discrete wavelet transform (DWT) on the basis of the distribution of the input data, where wavelet basis transforms are used as activation function.

 

 

Due to that the Ultra Wide Band (UWB) technology has some attractive features like robustness to multipath fading, high data rate, low cost and low power consumption, it is widely use to implement cognitive radio network. Intuitively, one of the most important tasks required for cognitive network is the spectrum sensing. A framework for implementing spectrum sensing for UWB-Cognitive Network will be presented in this paper. Since the information about primary licensed users are known to the cognitive radios then the best spectrum sensing scheme for UWB-cognitive network is the matched filter detection scheme. Simulation results verified and demonstrated the using of matched filter spectrum sensing in cognitive radio network with UWB and pro

Car drivers hear many kinds of noise inside their vehicles' cabins, and the most annoying ones are the noise generated by tires, engines, and outside winds. Noise affects the comfort of the passengers inside the cabin, and it’s sad to say that modern cars are noisier in many kinds of noise signals due to using a lot of plastic materials in new budget cars. For expensive and luxury cars, the problem is solved by using better sound insulation materials, but for the budget ones, the approach used here is effective. It is called Active Noise Cancellation and can be done using analog or digital electronics. An operational amplifier and filters are used for the analog one, and in the digital one, signal processor chips are used. In engineeri