iosr-JEEE   International Conference on Advances in Engineering & Technology – 2014 (ICAET-2014)

Abstract: In the past 10 years many speech synthesis systems has shown remarkable improvements in speech quality .Instead of monotonous and mechanical sounding utterances .For the better sounding pattern and more appealing sound synthesis few elements need to be taken care. Improvements in quality of synthetic speech and improvement in naturalness of the signal plays major contribution in the advancements in the synthetic speech technology. Improvement in signal quality can be technologically attended by concatenative synthesis. Naturalness is improved with the help of prosodic modelling. The proposed work mainly aims towards developing classifier for the input text with the help of linguistic model. Input to the system is pure text and which contains little or no explicit information about meaning, even though it may have punctuation marks in it. Its realization as a prosody is a major challenge and that has been undertaken by this project.

Keywords - Concatenative Speech Synthesis, prosodic modelling, sound synthesis, training set, vocal emotion.

[1] Iain R. Murray and John L. Arnott, " Synthesizing Emotions In Speech: Is It Time To Get Excited?", In Proceedings of the Fourth International Conference on ICSLP, Philadelphia, PA , USA, Vol. 3, pp. 1816-1819, 1996 [2] Jerneja Zganec Gros, Ales Mihelic, Nikola Pavesic, Mario Zganec and Stanislav Gruden, "Slovenian Text-to-Speech Synthesis for Speech User Interfaces", World Academy of Science, Engineering and Technology, Vol.11, No.1, pp.1-5, 2005 [3] M.L. Tomokoyo, W.A. Black and K.A. Lenzo, "Arabic in my hand: small footprint synthesis of Egyptian Arabic," In Proceedings of the Eurospeech‟03, Geneva, Switzerland, pp. 2049-2052, 2003 [4] Montero, Gutierrez-Arriola, Palazuelos, Enriquez, Aguilera and Pardo, "Emotional Speech Synthesis: From Speech Database to TTS", In Proceedings of the 5th international conference on spoken language processing, Sidney, pp. 923-926, 1998 [5] Ibon Saratxaga, Eva Navas, Inmaculada Hernaez and Iker Luengo, "Designing and Recording an Emotional Speech Database for Corpus Based Synthesis in Basque", In Proceedings of the fifth international conference on Language Resources and Evaluation (LREC), pp. 2126–2129, 2006 [6] Selma Yilmazyildiz, Wesley Mattheyses, Yorgos Patsis and Werner Verhelst, "Expressive Speech Recognition and Synthesis as Enabling Technologies for Affective Robot-Child Communication", In Proceedings of 7th Pacific Rim Conference on Multimedia, Springer Lecture Notes in Computer Science, Hangzhou, China, Vol. 4261, pp. 1-8, 2006

Abstract: In Now days we domestic uses of hot water include cooking, cleaning, bathing, and space heating. In industry, hot water and water heated to steam have many uses. There is need to develop wireless sensor network for temperature controlling of water for save fuel and for to save electricity. In this Paper, we present wireless sensor network for Temperature controlling of water. Which can Control the temperature, this can use for number of applications Temperature controllers are used in a wide variety of industries to manage manufacturing processes or operations. Some common uses for temperature controllers in industry include plastic extrusion and injection molding machines, thermo-forming machines, packaging machines, food processing, food storage, and blood banks, control the temperature of water , control the temperature of industrial machines, in the industry where temperature Controlling of water is necessary.

Keywords: IEEE 802.15.4, Temperature Controlling, WSN, Zigbee, TCN75, PIC Microcontroller

Build an IEEE 802.15.4 Wireless Sensor Network for Emergency Response Notification for Indoor Situations by V.A. Victor, C. Khadar, C. Rao and A. Mehta march 2008 Wireless sensor for home monitoring by gourab s. gupta,subhas c. mukhopadhay recent patent on Electrical Engg. 2008 Zigbee wireless network by Carl binkies 17th Telecommunications forum TELEFOR 2009 Serbia, Belgrade, November 24-26, 2009. Routing in Zigbee by Francesca Cuomo IEEE Communication Society Subject matter expert for publication in the ICC 2007 Proceeding. Johann lonn and Jonas Olsson,Zigbee for wireless network 15th March2005.A. William Stallings, Wireless Communication and Networking, Prenctice Hall 2002, ISBN 0-13-040864-6. IEEE standard 802.15.4,IEEE 2003,ISBN-0-7381-3677-5 SS95127 Zigbee Aliance,http:/zigbee.org,2005-03

Abstract: The Cognitive Radio (CR) technology enables the unlicensed users to share the spectrum with the licensed users on a non-interfering basis. Spectrum sensing is an important function for the unlicensed users to determine availability of a channel in the licensed user's spectrum. However, spectrum sensing consumes considerable energy which can be reduced by employing predictive methods for discovering spectrum holes. Using a reliable prediction scheme, the unlicensed users will sense only those channels which are predicted to be idle. By achieving a low probability of error in predicting the idle channels, the spectrum utilization can also be improved. In this paper, the spectrum predictor using the neural network model, multilayer perceptron (MLP) is designed, which does not require a prior knowledge of the traffic characteristics of the licensed user systems. In cognitive radio networks, it is difficult to obtain the statistics of channel usage by the primary users a priori. The advantage of neural networks over statistical models is that it does not require a priori knowledge of the underlying distributions of the observed process. Therefore, the neural networks offer an attractive choice for modeling the channel status predictor. One of the major goals of cognitive radio (CR) is to alleviate the inefficient use of the spectrum. CR can sense the spectrum steadily and gather information about the evolution of the spectrum in time. Spectrum occupancy information can be used for both learning the usage of the spectrum and predicting the future occupancy status. In this paper, the use of binary time series for spectrum occupancy characterization and prediction is proposed.

Keywords - Cognitive Radio, Spectrum Prediction, Soft Computing techniques, feed forward networks

[1]Federal Communications Commission, "Spectrum policy task force," in Rep. OET Docket No. 02-135, Nov.2002. [2] Federal Communications Commission, "Evaluation of performance of prototype TV-band white space devices Phase II," in Rep. OET Docket No. 08-TR-1005, Oct. 2008. [3] S. Haykin, "Cognitive radio: Brain-empowered wireless communications," IEEE Journal on Selected Areas in Communications, vol. 23, no. 2, pp. 210–230, Feb. 2005. [4] T. V. Krishna and A. Das, "A survey on MAC protocols in OSA networks," Computer Networks, vol. 53, no. 9, pp. 1377–1394, 2009. [5] N. Shah, T. Kamakaris, U. Tureli and M. Buddhikot, "Wideband spectrum sensing probe for distributed measurements in cellular band," in Proceedings of ACM International Workshop on Technology and Policy for Accessing Spectrum, vol. 222, Aug. 2006. [6] Y. Hur, J. Park, et al., "A wide band analog multi-resolution spectrum sensing (MRSS) technique for cognitive radio (CR) systems," in Proceedings of IEEE International Symposium on Circuits and Systems, ISCAS 2006 May 2006. [7] Z. Tian and G. B. Giannakis, "A wavelet approach to wideband spectrum sensing for cognitive radios," in Proceedings of International Conference on Cognitive Radio Oriented Wireless Networks and Communications (CROWNCOM), 2006, pp. 1–5, June 2006. [8] "A Survey of Spectrum Sensing Algorithms for Cognitive Radio Applications", Tevfik Y¨ucek and H¨useyin Arslan, IEEE Communications Surveys & Tutorials, Vol. 11, No. 1, First Quarter 2009.

Abstract: dynamic ANN model to study sensor fault validation scheme in a variable-air-volume-air-conditioning system has been developed. A single network is used for predicting fault in one sensor only whether it is ramp or step or random type fault and system performance is studied after fault is detected. The ANN model used here is a feed-forward multilayer perceptron using Backpropagation Algorithm. The simulation result obtained is found to be in close conformity with the normal values. Keywords – Artificial Neural Network, Backpropagation Algorithm, Feed-forward Multilayer Perceptron, Variable-air-volume-air-conditioning System.

[1] A. K. Halm-Owoo and K. O. Suan, Applications of fault detection and diagnostic techniques for refrigeration and air conditioning: A Review of basic principles, Journal of the Institution of Mechanical Engineers, 3, 2002, 121-132. [2] M. A. Akhtacir, O. Buyukalaca and T. YIlmaz, Life-cycle cost analysis for constant-air-volume and variable-air-volume air conditioning system, Applied Energy, 83 (6), 2006, 606-627. [3] Atanu Talukdar and A. Patra. Dynamic model-based fault tolerant control of variable-air-volume-air-conditioning system, Int. J. of HVAC & R Research, 2010. [4] A. Thosar, A. Patra and S. Bhattacharyya, Feedback linearization based control of a variable-air-volume air conditioning system for cooling applications, ISA Transactions, 47, 2008, 339-349. [5] A. Thosar, A. Patra and S. Bhattacharyya, Non-linear control of VAVAC system via Feedback Linearization, Proc. 33rd Annual Conference of the IEEE Industrial Electronics Society (IECON-2007), Nov. 2007. [6] A. Thosar, A. Patra and S. Bhattacharyya, Energy optimization of variable-air-volume-air-conditioning system using Genetic Algorithms, Proc. IEEE Conference on Industrial Technology (ICIT-2006), Dec. 2006. [7] A. Beghi, L. Cecchinato, F. Paggiaro and M. Rampazzo, VAVAC systems modeling and simulation for FDD applications, Proc. 9th IEEE Conference on Control and Automation (ICCA-2011), Dec. 2011. [8] Z. Du, X. Jina and Y. Yanga, Fault diagnosis for temperature, flow rate and pressure sensors in VAV systems using wavelet neural network, Applied Energy, 86 (9), 2009, 1624-1631.

Abstract: Electronic nose is an instrument which is use for automatic detection and classification of odors and gases. An electronic nose is generally composed of a chemical sensing system (array of sensors). This system is used for automatic identification of volatile chemicals for environmental, medical applications, commercial industries, including the agricultural, biomedical, cosmetics, food, manufacturing, military, pharmaceutical, regulatory applications and various scientific research fields. This paper is about development of e-nose using genetic algorithm, comparison of traditional e-nose system and intelligent e-nose system.

Keywords - Artificial intelligence, e-nose, Genetic algorithm.

1] R.L. Ewing,JR. Morrison "Polymorphic Architecture for an Electronic Nose (eNose)" IEEE,551-554, 2006. [2] Amy Loutfi "Odour Recognition using Electronic Noses in Robotic and Intelligent Systems" feb 15,2006. [3] N. Bhattacharyya, R Bandyopadhyay,., M Bhuyan,., B Tudu,., D Ghosh,. and A. Jana, Electronic Nose for Black Tea Classification and Correlation of Measurements With "Tea Taster" Marks. IEEE Transactions on Instrumentation and Measurement, vol. 57, no. 7, pp 1313 – 1321,2008 [4] Tom V. Mathew "Genetic Algorithm"Professor, Department of Civil Engineering, Indian Institute of Technology Bombay, Mumbai [5] Maria Jamal, M R Khan, S A Imam ,Arif Jamal" Artificial Neural Network Based E- Nose And Their Analytical Applications In Various Field" 11th Int. Conf. Control, Automation, Robotics and Vision Singapore,691-698, 7-10th December 2010.[4] K. Arshak, E. Moore, G.M. Lyons, J. Harris and S. Clifford" A review of gas sensors employed in electronic nose applications" ISSN 181-198. [6] A. Far, F. Flitti, B. Guo and A. Bermak" Gas Identication System based on Temperature Modulation tin- oxide sensors and bio-inspired processing" IEEE,1010- 1013,2008

Abstract: As the mobile and IPTV world collides with wireless LANs and Internet-based packet data, new networking approaches will support the integration of voice and data on the composite infrastructure of cellular base stations and Ethernet based wireless access points. Providing efficient quality of service like audio, video and voice over IP besides the traditional data service. Various solutions have been proposed to provide soft QoS over Multihop wireless networks from different layers in the network protocol stack. This article highlights some of the past accomplishment and promising research avenues for an important topic in the creation of future wireless networks.

393-422, March 2002. 2. I. F. Akyildiz, and I. H. Kasimoglu, "Wireless Sensor and Actor Networks: Research Challenges," Ad Hoc Networks Journal (Elsevier), Vol. 2, No. 4, pp. 351-367, October 2004. 3. I. F. Akyildiz, M. C. Vuran, and O. B. Akan, "Cross-Layer Module (XLM) for 4. Low, Z. N., R. Chinga, R. Tseng, and J. Lin, "Design and test of a high-power high-efficiency loosely coupled planar wireless power transfer system," IEEE Transactions on Industrial Elec- tronics, Vol. 56, No. 5, 1801–1812, May 2009. 5. Raval, P., D. Kacprzak, and A. P. Hu, "A wireless power transfer system for low power elec- tronics charging applications," 2011 6th Conference on Industrial Electronics and Applications, 520–525, Jun. 2011. 6. Park, J.-H., B.-C. Park, J.-H. Lee, Y.-H. Ryu, E.-S. Park, and S.-W. Kwon, "Optimum fre- quency of high Q-factor resonator for magnetic resonance coupling," 2011 41st European Mi- crowave Conference, 61–63, Oct. 2011. 7. Kim, N. Y., K. Y. Kim, J. Choi, and C. W. Kim, "Adaptive frequency with power-level tracking system for efficient magnetic resonance wireless power transfer," Electronics Letters, Vol. 48, No. 8, 452–454, Apr. 2012. 8. Imura, T. and Y. Hori, "Maximizing air gap and efficiency of magnetic resonant coupling for wireless power transfer using equivalent circuit and Neumann formula," IEEE Transactions on Industrial Electronics, Vol. 58, No. 10, 4746–4752, Oct. 2011. 9. Witschnig, H., M. Roland, M. Gossar, and H. Enzinger, "Pa- rameter characterisation and automatic impedance matching of 13.56 MHz NFC antennas," Elektrotechnik and Informationstech-nik, SpringerLink, Vol. 126, No. 11, 415–422, Nov. 2009.

Abstract: This research paper aims to be responsible for the upcoming of 3G technology in emerging or developing countries. At the global level 3G technology had reached to the higher level. Hereafter, the study of success factors and the hitches faced is advisable before the launch of this service in developing countries.

Keywords: Mobile Wireless Communication Networks, 1G, 2G, 3G, 4G, Mobile Broadband.

[1] ITU (2009). ―Measuring the Information Society; The ICT Development Index‖, Available:http://www.itu.int/ITUD/ict/publications/idi/2009/material/IDI2009_w5.pdf [2] a free encyclopedia : en.wikipedia.org
[3] http://www.wirelesstoday.com/
[4] http://www.itu.int/imt/what_is/roadto/index.html BOOKS: [1] ITU-R PDNR WP8F. ―Vision, Framework and Overall Objectives of the Future Development of IMT-2000 and Systems beyond IMT-2000‖. [2] Toh,C. K.―Ad Hoc Mobile Wireless Networks: Protocols and Systems‖, Prentice Hall, New Jersey, USA, 2002. [3]―Principle of WCDMA‖ by M.R. Karim [4] ―CDMA RF System Engineering‖ by Samuel C. Yang

Abstract: MANET is a network which is constructed by using a number of mobile devices, through temporary connection. The information should reach all nodes in the network through broadcasting. When broadcasting the message, broadcasting storm problem will occur. In order to get efficient communication the lifetime of the node should be increased. Lifetime of the node will be depend upon the power consumption of the node. The power consumption of every node should be reduced by using multipoint relay selection(MPRs) method. In this method a relay node will be affected by power consumption problem. To make energy efficient, network coding procedure has been introduced. In this paper we propose an algorithm Co-operative Analog Network Coding Algorithm (CANCA) to reduce power consumption of the secondary users. The power consumption of the node should be decreased by using this algorithm. Thus power can be saved upto 80%. The algorithm will be simulated and the result will be compared with the previous methods.

Keywords: network coding, energy efficient, MANET, relay node, multipoint relay (MPR), broadcasting, storm problem

Auon Muhammad Akhtar, Mohammad Reza nakhai, "On the Use of Cooperative Physical Layer Network Coding for Energy Efficient Routing", IEEE Transactions on Communications, Vol.61, No.4, April 2013. S. Rout, A.K. Turuk and B. D. Sahoo, "Energy Efficiency in Wireless Network: Through Alternate path Routing", in proceedings of Fourth Innovative conference on Embedded Systems, Mobile Communication and Computing, July 2009, pp.-3-8. J.-P. Sheu, S.-C. Tu, and C.-H. Hsu. "Location-Free Topology Control Protocol in Wireless Ad Hoc Networks". Computer Communications, 31(14): 3410-3419, 2008.

Abstract: Intelligent Transportation System (ITS) applies advanced technologies of communications, in all kinds of transportation system in order to improve monitoring, safety, efficiency and service, and traffic situation through transmitting real-time information. Economical solutions for intelligent transportation system are significant for developing countries. Multicell Wireless Access Gateways And Wireless Access Points For Video Sensor networks along with wireless network becomes an important economical tool to the traffic monitoring and control because of the increasing traffic in terms of congestion and safety. Use of wireless access gateways and wireless access points in Intelligent Transportation System (ITS) can improve the monitoring and security of road transport using high speed broadband internet [1]. Use of Global positioning system receivers can improve chances of finding location of vehicle in particular region. It is proposed to use IP camera for surveillance using wireless media and remote monitoring of location is possible using wireless gateways and access points in multiple cell locations. Images or videos thus captured can further be used for detection of drowsiness of drivers.[2]

[1] Mohammad Amin Assari , Mohammad Rahmati ,Department of Computer Engineering, Kashan Branch, Islamic Azad University et all "Driver Drowsiness Detection Using Face Expression Recognition "2011 IEEE International Conference on Signal and Image Processing Applications [2] European commission report on Intelligent transport System, 2010. [3] T. Semertzidis K. Dimitropoulos A. Koutsia N. Grammalidis et.all "Video sensor network for real-time traffic monitoring and surveillance" Published in IET Intelligent Transport Systems Received on 13th November 2008,Revised on 20th August 2009,doi: 10.1049/iet-its.2008.0092 [4] Lelitha vanajasksji et all IIT Madras Synthesis report on ITS including issues and challenges in India, December 2010.

Abstract: Considering a continuous time LTI system, with impulse response hc t , the uniformly spaced samples hc nT can be identified by using an impulse train input with an arbitrarily small rate 1/NT and sampling the system output with an arbitrarily small rate 1/MT, provided M and N to be coprime for any chosen time spacing T. It is shown that different LTI filters can be identified using the sparse coprime sampling and from input-output measurements. It is also shown that the pattern of random noise corrupting the transmitting signal in the channel can be identified.

[1] Palghat P. Vaidyanathan and Piya Pal, "System Identification With Sparse Coprime Sensing" IEEE Signal Processing Letters, Vol. 17, No. 10, October 2010. [2] P. P. Vaidyanathan, Multirate Systems and Filter Banks. Englewood Cliffs, NJ: Prentice Hall, 1993. [3] A. V. Oppenheim and R. W. Schafer, Discrete Time Signal Processing. Upper Saddle River, NJ: Prentice-Hall, 1999. [4] Alan V. Oppenheim and George C. Verghese, Signals, Systems and Inference, Introduction to Communication, control and Signal Processing. [5] Ahmed I.Zayed, Xiaoping Shen, Multiscale Signal Ananlysis and Modelling, Springer, 2013.

Abstract: In medical, ultrasound imaging techniques are used for diagnosis purposes. Ultrasound image comprises of speckle noise, which often leads to the confusion for making the clinical decisions during diagnosis. In over viewing the difficulty that had encountered, we had come up with a technique which minimizes the speckle noise in ultrasound image to a greater extent. A technique was adapted to accomplish the issues arrived during the imaging was redundant discrete wavelet transform (RDWT), which comprises estimation of generalized gamma distribution method and Bayesian shrinkage function for minimization of noise in ultrasound images. With the use of this algorithm for the proposed technique we can obtain quantitative parameters that are capable of producing the key ultrasound images which in turn makes the things very feasible in analyzing and diagnosing the vital parameters for the clinical examination purpose. Keywords: Ultrasound image, speckle noise, RDWT, Bayesian shrinkage function estimator.

Bhabesh Deka and Prabin Kumar Bora "Wavelet based Despeckling of Medical Ultrasound Images" IETE JOURNAL OF RESEARCH, VOL 59, ISSUE 2, MAR-APR 2013. J.W. Goodman, "Some fundamental properties of speckle," J. Opt. Soc. Amer., vol. 66, pp. 1145–1150, Nov. 1976. E. P. Simoncelli, "Bayesian denoising of visual images in the wavelet domain," in Bayesian Inference in Wavelet Based Models, P. Muller and B. Vidakovic, Eds. New York: Springer-Verlag, June 1999, ch. 18, pp. D L Donoho, "De‑noising by Soft‑Thresholding," IEEE Trans. Inform.Theory, Vol. 41, pp. 613‑27, 1995.11. A K Jain, "Fundamentals of Digital Image Processing", 3rd ed., Engle wood Cliffs, NJ: Prentice Hall; pp. 569, 1989. Brown, R. K. Image Registration using Redundant Wavelet Transforms. MS thesis, Air Force Institute of Technology, Wright-Patterson AFB, OH, March 2001.

Abstract: Previous OTAs seldom worked over 200MHz whereas, the higher frequency OTA can be used as basic building block in several RF as well as microwave applications. The performance analysis of conventional OTA techniques, using advanced process technology that can break the previous frequency barrier is a key objective of this paper. A Fully differential OTA is designed and analyzed in this paper which has Transconductance of approx. 8 ms over GHz Frequency range and worked on supply voltage of 1.4V. The OTA has been simulated by using ADS Tool with 180 nm as target technology. Different topologies of OTA have been studied and analyzed. The appropriate topology which has a perfect balance between complexity and performance is suggested. The research includes analysis and comparison of OTA topologies from the point of view of effect of technology scaling on various performance parameters such as Frequency range, Gain, Power Consumption, Supply Voltage, Temperature, etc.

Keywords – CMOS, frequency range, Operational Transconductance Amplifier (OTA), Supply Voltage, Transconductance.

[1] You Zheng and Carlos E. Saavedra, "Feed forward-Regulated Cascode OTA for Gigahertz Applications", IEEE Transactions on Circuits and Systems, 2008
[2] Anil Kavala, Kondekar P. N, and Yang Sun, "A low voltage, low power linear pseudo Differential OTA for ultra-high frequency applications", IEEE, International workshop on Antenna Technology, 2009.
[3] M.Siripruchyanun & W.Jaikla, "Current controlled current conveyor Transconductance Amplifier (CCTA):a building block for analog signal processing", Electrical Eng (2008) 90:443–453 Springer-Verilog, 2008.
[4] Berg, Y., "Novel ultra low voltage Transconductance amplifier", Proceedings of 2010 IEEE International Symposium on Circuits and Systems, 2010.
[5] N. Raj, R. K. Sharma, A. Jasuja and R. Garg, "A Low Power OTA for Biomedical Applications", Cyber Journal: A multi disciplinary Journal in science & technology, 2010.
[6] Sheng-Wen Pan1, Chiung-Cheng Chuang2, Chung-Huang Yang3, Yu-Sheng Lai., "A novel OTA with dual bulk-driven input stage", IEEE International Symposium on Circuits and Systems, 2009.

Abstract: This project presents a novel automated method for fully automated detection of optic disk boundary in fundus images. The proposed method improves and extends the original snake (deforming-only technique) in two aspects: boundary detection of optic disk and center finding of cup. Morphological operator is used in this algorithm. The contour points are first self-separated into edge-point group or uncertain-point group by clustering after each deformation, and these contour points are then updated by different criteria based on different groups. The updating process combines both the local and global information of the contour to achieve the balance of contour stability and accuracy. The modifications make the proposed algorithm more accurate and robust to blood vessel occlusions, noises, ill-defined edges and fuzzy contour shapes. The comparative results show that the proposed method can estimate the disk boundaries of 30 test images closer to the groundtruth,, with the better success rate when compared to doctors decision. In this project Matlab 7.1 is used.

Keywords: ASM, GVF,Matlab7.5, Morphological operator, glaucoma..

[1] Juan Xu,Opas Chutatape, and Paul Chew,Automated Optic Disk Boundary Detection by Modified Active Countour model, roc. 2 IEEE Transaction on biomedical engineering Vol. 54, No. 3, March 2007 [2] A. Murthi, M Madheswaran, Enhancement of Optic cup to Disk Ratio Detection In Glaucoma diagnosis, IEEE2012 International Conference on Computer Communication and Informatics(ICCCI-2012). Jan 10-12,2012, Coimbatore, India [3] Anonymous CCPR submission, Automated feature Extraction for early Detection of Dianetic Retinopathy in Fundus Images, CVPR 2009 Submission [4] J. Liu, D. W. K. Wong, J. H. Lim, X. Jia, F. Yin, H. Li, and W.Xiong, T. Y. Wong, Optic Cup nd Disk Extraction Fundus Image For Determination of Cup-to-Disk ratio. IEEE 2008,