Volume 8, Issue 4, April 2016

 

 

 

Mixed Noise Tolerant Fingerprint Authentication Using Neuro Computing

Pages: 56-62 (7) | [Full Text] PDF (579 KB)
F James, P V Kumar, MK Singh
Asst.Prof. , Dept. Of ISE , Brindavan College of Engineering, Bangalore, Karnataka, India.
Prof., Dept.of IT, R.V.College of Engineering, Bangalore, Karnataka, India.
Director, Manuro Tech Research Pvt.Ltd., Bangalore, Karnataka, India.

Abstract -
In this paper, we have proposed a secure means for fingerprint biometric authentication, which has the capability to deliver the users privacy, their fingerprint template protection, and robustness against the various variations in terms of noise. In this paper, principle based on correlation strength has been presented to defined fingerprint recognition requirement,to achieve the desired objectives and high quality of solution, computational intelligence basedconcept which uses the feed forward architecture of artificial neural network is applied as solution technology. Proposed methods provides numerous advantages like less memory requirement, very high level of security for stored information without any extra means, high speed and simple implementation approach. Proposed method has robustness against various types of noise available with fingerprint image.
 
Index Terms - Biometrics, Authentcation, Fingerprint, Artificial Neural Networks, Noise

Citation - F James, P V Kumar, MK Singh. "Mixed Noise Tolerant Fingerprint Authentication Using Neuro Computing." International Journal of Computer Engineering and Information Technology 8, no. 4 (2016): 56-62.

 

Infrastructure of WDM (Wavelength Division Multiplexer) with Simulations Using Eight Channels

Pages: 63-67 (5) | [Full Text] PDF (402 KB)
E Ali, EN Muslim, EA Suri, EU Khan, EA Iqbal
Nice Education Sytem Peshawar, Pakistan
Electrical Engineering Department Sarhad University of Science and IT, Peshawar Pakistan
Electrical Engineering Department Iqra National University, Peshawar Pakistan

Abstract -
Transmission of high data rate is the main endeavor for next generation optical access network. In this paper we propose a new architecture for a traditional wavelength division multiplexed (WDM). We presented 10Gbps full duplex communication for next generation system. We connected 8 CW lasers having frequency of 193.0 THz to 193.7 THz. In this way a cost effective arrangements for WDM is proposed based on a single light source. 1-8 and 8-1 Multiplexer and de-multiplexer is used where each output is modulated with 10 Gbps user data. Multiplexed data from all four modulators are transmitted and received back via single mode fiber span of 100km. Power losses are calculated with using 100 km and in back to back configurations different bit error rates. Transmission performance with negligible power penalties during downlink and uplink transmissions confirms that the proposed arrangement is deployable in next generation of WDM.
 
Index Terms - WDM, Multiplexing, CW laser and De multiplexing, BER

Citation - E Ali, EN Muslim, EA Suri, EU Khan, EA Iqbal. "Infrastructure of WDM (Wavelength Division Multiplexer) with Simulations Using Eight Channels." International Journal of Computer Engineering and Information Technology 8, no. 4 (2016): 63-67.

 

Cancer Detection Using Gene Expression

Pages: 68-70 (3) | [Full Text] PDF (207 KB)
B Dhayagude, S Karanjkar,S Kamble, K Misal
Computer engineering Department, SAVITRIBAI PHULE PUNE UNIVERSITY, Baramati, Maharashtra, India

Abstract -
Cancer is a major problem in medical science throughout the world. Nowadays detection of Cancer in earlier stages gives very poor results, by the lack of technologies, to get the real idea about the Cancer, reliable and precise classification of Cancer is essential for successful diagnosis and treatment of Cancer. Today DNA microarray based tumor gene expression profiles have been used for Cancer diagnosis. Problems raised this system once the testing is complete, the lab reports the results in writing to the doctor or genetic counselor. So patient gets the results during another counseling session. This may not happen until several weeks after the samples are taken. so to overcome the problem of traditional genetic testing then predicting particular Cancer and giving suggestion for that type of Cancer. Gene expression data can be clustered on both genes and samples. As a result, the clustering algorithms can be divided into two categories: gene-based clustering, sample based clustering. Supervised multi attribute clustering algorithm will be effectively work compared with others. After clustering process Best rule classification used to predict the particular type of Cancer accurately. This technique suggest the final prediction of Cancer and suggest the medicine that needs to be taken up for the Cancer diagnosis.
 
Index Terms - Cancer, Association rules, Classification, Clustering, Data mining, Gene expression data, Gene therapy, Epigenetics

Citation - B Dhayagude, S Karanjkar,S Kamble, K Misal. "Cancer Detection Using Gene Expression." International Journal of Computer Engineering and Information Technology 8, no. 4 (2016): 68-70.