Asian Journal of Engineering, Sciences & Technology
Abbreviated key title: AJEST
Published by: Iqra University
Months: March & September
Start year: 2011
Title: Comparison of Extreme Learning Machines and Support Vector Machines on Premium and Regular Gasoline Classification for Arson and Oil Spill Investigation. Author(s): Sunday Olusanya Olatunji
Abstract: Extreme Learning Machine (ELM) is a recently introduced learning algorithm for single hiddenlayer feedforward neural network. Compared with classical learning algorithms in neural network, e.g. Back Propagation, ELM can achieve better performance with much shorter learning time. In the existing literature, its better performance and comparison with Support Vector Machine (SVM), over regression and general classification problems catch the attention of many researchers. In this paper, the comparison between ELM and SVM over a particular area of classification, i.e. gasoline classification for arson and oil spill investigation, is conducted. Detection and correct identification of gasoline types during arson and fuel spill investigation are very important in forensic science. As the number of arson and oil spillage increases, it becomes very important to have an accurate means of detecting and classifying gasoline found at such sites of incidence. However, currently only a very few number of classification models have been explore in this germane field of forensic science, particularly for gasoline identification. Comparison of simulation results for SVM and ELM show that, for the different categories of gasoline classification investigated, SVM still outperforms ELM in terms of percentage of correctly classified gasoline while in term of time taken for both training and testing, ELM clearly outperform SVM.
Title: Design of an Ultra Wideband Monopole Antenna for Handheld Devices. Author(s): Faraz Mahmood, Imran Mohsin, Syed M. Usman Ali, Abid Karim
Abstract: The basic motivation behind the choice of ultra wide band based antennas in wireless communication systems is there expedient feeding structure, wide bandwidth along with uncomplicated structure and low cost. Ultra Wideband wireless communication systems are not only serving in enabling applications like wireless monitors, wireless printers and efficient transfer of data from digital electronic devices but this standard is also finding its application in transfer of files among handheld devices such as personal digital assistants and especially for the mobile handsets. With every passing day handheld devices are miniaturizing which has given rise to the need of development of flexible antenna structures. This paper serves to present the design of a two layer monopole antenna with a physically flexible design in order to facilitate the small design and different shapes of the handheld device, under consideration. High frequency structural simulator of Ansoft Corporation has been adopted as the key simulation tool for this design.
Title: Biometric Access Control System Using Automated Iris Recognition. Author(s): Waqas Ahmad, Syed Saad Azhar Ali
Abstract: A biometric access control system is developed using automated iris recognition. Based on the fact that a human iris contains patterns that are best suited for identification, the use of low cost equipment can help iris recognition to become a standard in security systems. In this paper the database containing images from a low cost camera is assessed, and the overall recognition performance was measured. The pattern matching is performed using statistical metrics. The real- time experimental results on a group of 50 persons are presented. The results showed that a system using low cost equipment can be constructed with a promising 95% accuracy rate.
Title: A Mathematical Approach to Charge Injection from Metal into Organic Material in OLEDs. Author(s): Farhad Nobakht
Abstract: A new mathematical method is proposed for deriving charge injection model for Organic Light Emitting Diodes OLEDs). We use drift-diffusion theory and Fermi-Dirac statistics to achieve a new method for modeling the charge injection behavior of OLEDs. Also dependence of current density due to charge injection on temperature, external filed, and barrier height is shown.
Title: Cognitive Radio: Future Research Challenges in Collaborative Spectrum Sensing and their Solutions. Author(s): Nasir Iqbal, Muhammad Moinuddin
Abstract: Cognitive radio (CR) is considered as an innovative approach for improving the utilization of a precious natural resource: the radio electromagnetic spectrum. The CR is an enhancement on the traditional software radio concept wherein the built on a software-defined radio is used which is aware of its environment and its capabilities, is able to independently modify its physical layer behavior, and is capable of following complex adaptation strategies with an objective of efficient utilization of the available radio spectrum. Following the general discussion of CR, this paper provides an overview of the future challenges and some possible solutions for the design of collaborative spectrum sensing in CR networks.
Title: A Comparative Study of MIMO-DFE Receivers. Author(s): Khalid Mahmood, Syed Muhammad Asad, Muhammad Moinuddin
Abstract: A decision feedback equalizer (DFE) is a nonlinear equalizer which utilizes the previous detector assessment to mitigate the intersymbol interference (ISI) on received symbols. Alternatively, we can say that the distortion on the current symbol that was caused by previous symbols is eliminated. While linear equalizer (LE) can be employed on the channels where the ISI is not significantly present but in case when there is a severe ISI channel then DFE’s have been effectively used to mitigate ISI. Different techniques have been proposed to improve the decision feedback equalization performance. In this paper we have reviewed some of the existing equalization techniques and have highlighted their performance gains.
Title: Identification of Multivariable Wiener Model Using Radial Basis Functions Neural Networks. Author(s): Syed Saad Azhar Ali, Hussain N. Al-Duwaish
Abstract: A new method is introduced for the identification of the nonlinear multi input multi output (MIMO) Wiener Model, comprising of linear dynamics in cascade with static nonlinearities. The static nonlinearities are modeled by Radial Basis Function Neural Networks (RBFNN) and the linear part is modeled by MIMO autoregressive moving average (ARMA) model. The new algorithm makes use of the well known mapping ability of RBFNN. The learning algorithm is an extension of SISO identification scheme presented in  . The proposed algorithm estimates the weights of the RBFNN and the coefficients of ARMA model based on least mean squares (LMS) principle simultaneously.
Freely Accesible Scientific Literature. Higher Impact. Global Reach.
Find out more
The submissions will be peerreviewed by two independent reviewers.
Faculty of Engineering, Sciences and Technology, IQRA University, Defence View, Shaheed-e-Millat Road, Karachi-75500
Phone: + 9221 111 264 264
Fax: + 9221 35894806