iosr-JCE   Volume-16 ~ Issue-5 ~ Sep-Oct 2014

Abstract: Ant Colony System (ACS) is competitive with other nature-inspired algorithms on some relatively simple problems. This project proposes an ant colony optimization algorithm for tuning generalization of fuzzy rule. The use of Ant Colony Optimization (ACO) for classification is investigated in depth, with the development of the AntMiner+ algorithm. AntMiner+ builds rule based classifiers, with a focus on the predictive accuracy and comprehensibility of the final models. The key differences between the proposed AntMiner+ and previous AntMiner versions are the usage of the better performing MAX-MIN ant system, a clearly defined and augmented environment for the ants to walk through, with the inclusion of the class variable to handle multi-class problems, and the ability to include interval rules in the rule list. Ant system is a general purpose algorithm inspired by the study of behavior of ant colonies. It is based on cooperative search paradigm that is applicable to the solution of combinatorial optimization problem. The institutions concern the routing network studies the application of data mining techniques for network traffic risk analysis. The proposed work aims at spatial feature of the traffic load and demand requirements and their interaction with the geo routing environment. In previous work, the system has implemented some spatial data mining methods such as generalization and characterization. The proposal of this work uses intelligent ant agent to evaluate the search space of the network traffic risk analysis along with usage of genetic algorithm for risk pattern.

[1]. Holden, N., Freitas, A. A Hybrid PSO/ACO Algorithm for is covering Classification Rules in Data Mining, In Journal of Artificial Evolution and Applications (JAEA), 2008.
[2]. D. Martens, M. De Backer, R. Haesen, M. Snoeck, J. Vanthienen, and B. Baesens. Classification with ant colony optimization IEEE Transaction on Evolutionary Computation, 11(5):651–665, 2007.
[3]. Ruckert, U., Richter, L., and Kramer, S. Quantitative association rules based on half-spaces: An optimization approach. In Proceedings of the Fourth IEEE International Conference on Data Mining (ICDM'04), pages 507–510, 2004.
[4]. Parpinelli, R.S., Lopes, H.S., and Freitas, A.A. Data Mining with an Ant Colony Optimization Algorithm, IEEE Trans. on Evolutionary Computation, special issue on Ant Colony algorithms, 6(4), p. 321-332, 2002.
[5]. Parsopoulos, K. E., and Vrahatis, M. N. On the computation of all global minimizers through particle swarm optimization. IEEE Transactions on Evolutionary Computation, 8(3):211-224. 2004

Abstract : Plastic surgery provide a way to enhance the facial appearance. The non-linear variations introduced by the plastic surgery has raised a challenge for face recognition algorithms. In this research we match the face image before and after the plastic surgery. First generate non-disjoint face granules at multiple levels of granularity. The feature extractors are used to extract features from the face granules. The features are then processed by using principal component analysis (PCA) algorithm. Evaluate the weighted distance and match the pre and post surgery images based on weighted distance. The proposed system yield high identification accuracy and take less time for recognition as compared to the existing system.

Keywords: Plastic surgery;face recognition;Granular Computing;PCA Algorithm

[1]. H. S. Bhatt, S. Bharadwaj, R. Singh, and M. Vatsa, "Recognizing surgically altered face images using multi-objective evolutionary algorithm" in Proc. Int. Conf. Biometrics:Theory Applications and Systems, 2013
[2]. G. Aggarwal, S. Biswas, P. J. Flynn, and K. W. Bowyer, "A sparse representation approach to face matching across plastic surgery," in Proc.Workshop on the Applications of Computer Vision, 2012, pp. 1–7.
[3]. M. De Marsico, M. Nappi, D. Riccio, and H. Wechsler, "Robust face recognition after plastic surgery using local region analysis," in Proc. Int. Conf. Image Analysis and Recognition, 2011, vol. 6754, pp. 191–200.
[4]. H. S. Bhatt, S. Bharadwaj, R. Singh, and M. Vatsa, "On matching sketches with digital face images," in Proc. Int. Conf. Biometrics:Theory Applications and Systems, 2010, pp. 1–7.
[5]. D. G. Lowe, "Distinctive image features from scale-invariant keypoints," Int. J. Comput. Vis., vol. 60, no. 2, pp. 91–110, 2004.

Abstract : Reducing noise from the various images like Real images, medical images and satellite images etc. is a challenging task in digital image processing. Noises are removed as pre processing which are needed for image enhancement, restoration, compression, registration, analysis as well as feature extraction and texture analysis. Several approaches are there for noise reduction. The proposed filtering technique in this paper removes speckle noise from the real images effectively. Quantitative analysis is done by various measures like Noise Variance, Mean Square Error, Noise Mean Value, Noise Standard Deviation, Equivalent Number of Looks (ENL) and PSNR and the results exhibit the performance of the proposed filter.

Keywords: ENL, frost filter, lee filter, PSNR, Speckle noise, speckle filters

[1]. P. Shanmugavadivu, A. Shanthasheela, Performance Analysis of Localized Texture-Based Decomposition Using Gabor Filter, National Conference on Information Technology and its Applications, A.V.C College of Engineering, Mayiladuthurai, Oct. 09, 2009
[2]. Gonzalez, R. C. and Woods, E. "Digital Image Processing", 3nd ed.,Pearson Education (South Asia) 2009.
[3]. Pei-Yin Chen, Chih-Yuan Lien: An Efficient Edge-Preserving Algorithm for Removal of Salt-and-Pepper Noise. IEEE Signal Process. Lett. (SPL) 15:833-836 (2008)
[4]. Florian Luisier, Thierry Blu, Michael Unser: Image Denoising in Mixed Poisson-Gaussian Noise. IEEE Transactions on Image Processing (TIP) 20(3):696-708 (2011)
[5]. Russo F. A method for estimation and filtering of Gaussian noise in images. IEEE Transactions on Instrumentation and Measurement. 2003;52(4):1148–1154

Abstract : Probabilistic topic models are used for analyzing and extracting content-related annotations from noisy annotated discrete data like WebPages on WWW and these WebPages are stored using social bookmarking services with the help of social bookmarking services, reason behind this process most of time users can attach annotations freely, some annotations do not describe the semantics of the content, therefore they are noisy, simply they are not content related. The extraction of content-related annotations can be used as a prepossessing step in machine learning. Prepossessing step in machine learning is like text classification and image recognition, and can improve information retrieval performance. The proposed model is a generative model for content and annotations, where annotations are assumed to be originated either from topics that generated the content or from a general distribution unrelated to the content. We demonstrate the effectiveness of the proposed method with the help of synthetic data and real social annotation data for text and images. Keywords: Book marking services, machine learning, social annotation , text classification

[1] S. Golder and B.A. Huberman, "Usage Patterns of Collaborative Tagging Systems," J. Information Science institute, vol. 32, no. 2, pp. 198-208, 2006.
[2] K. Barnard, P. Duygulu, D. Forsyth, N. de Freitas, D.M. Blei, and M.I. Jordan, "Matching Words and Pictures," J. Machine Learning Research, vol. 3, pp. 1107-1135, 2003.
[3] D.M. Blei and M.I. Jordan, "Modeling Annotated Data," Proc. 26th Ann. Int‟l ACM SIGIR Conf. Research and Development in Information Retrieval (SIGIR ‟03), pp. 127-134, 2003
[4] S. Feng, R. Manmatha, and V. Lavrenko, "Multiple Bernoulli Relevance Models for Image and Video Annotation," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition (CVPR ‟04), vol. 2, pp. 1002-1009, 2004.
[5] J. Jeon, V. Lavrenko, and R. Manmatha, "Automatic Image Annotation" and "Retrieval Using Cross-Media Relevance Models," Proc. 26th Ann. Institutes‟ ACM SIGIR Conf. Research and Development in Information Retrieval (SIGIR ‟03), pp. 119-126, 2003.

Abstract : The area of Wireless Sensor Networks (WSNs) is one of the fast growing and emerging field in the scientific and engineering world. It is an ad-hoc network that consists of small nodes with sensing, computing and communicating wireless abilities. These sensor nodes are densely deployed in the sensor field environments. The environment can be an Information Technological framework, a physical world, or a biological system.The main objective of WSN is to sense the crucial information from the environment depending on the type of application for which it is deployed and send this information to its Base Station (BS) so that it can take corrective actions. These Sensor Nodes communicate with each other via various Routing Protocols. Protocols in WSNs are broadly classified as Flat, Hierarchical and Location Based routing protocols. This paper presentshierarchical routing protocol, Power Efficient Gathering in Sensor Information Systems (PEGASIS) and a comparative study on various versions of PEGASIS protocols.

Keywords: WSN, MANET, LEACH, PEGASIS, EEPB, PEGASIS-ANT, H-PEGASIS, PDCH, IEEPB.

[1]. J. Al-Karaki, and A. Kamal, .Routing Techniques in Wireless Sensor Networks: A Survey., IEEE Communications Magazine, vol 11, no. 6, pp. 6-28, Dec. 2004.
[2]. Wireless Sensor Networks. (2014,March,20). MDPI[Online].Available: www.mdpi.com/journal/sensors
[3]. S. Singh, M. Singh, D. Singh, "A Survey of Energy-Efficient Hierarchical Cluster-Based Routing in Wireless Sensor Networks", Int. J. of Advanced Networking and Applications Volume: 02, Issue: 02, Pages: 570-580, 2010.
[4]. W.R. Heinzelman, A. Chandrakasan, and H. Balakrishnan, .Energy-efficient Communication Protocol for Wireless Microsensor Networks., in IEEE Computer Society Proceedings of the Thirty ThirdHawaii International Conference on System Sciences(HICSS '00), Washington DC, USA, , vol. 8, pp. 8020, Jan. 2000.
[5]. Wireless Sensor Networks. (2013,December,16). Mdpi [Online]. Available http://www.nhu.edu.tw/~cmwu/Lab/Routing%20protocol%20on%20wireless%20sensor%20network.ppt.

Abstract : Data security has become an important issue in recent times. Confidential data needs to be protected from unauthorized users. Various image encryption techniques have been proposed for the secure transmission of images to protect the authenticity, integrity and confidentiality of images. Fractal images can be used as a strong key for the encryption due to the random and chaotic nature of fractals. The infinite boundaries of fractals provide highly complex structure that leads to confusion and it becomes a tedious task for an unauthenticated user to crack the exact secret fractal key. In this paper, a review of various techniques used for image encryption using fractal geometry has been illustrated. All these techniques have their own advantages and disadvantages in terms of execution time, key generation time and Peak Signal to Noise Ratio.
Index terms: Cryptography, Fractal geometry, Image encryption, PSNR, Security, SSIM.

[1] National Institute of Standards and Technology, Data Encryption Standard (DES), Technical Report, Federal Information Processing Standards Publication 46-3, 1999.
[2] National Institute of Standards and Technology Advanced Encryption Standard (AES), Technical Report, Federal Information Processing Standards Publication 197, 2001.
[3] D. Hearn, M. P. Baker, Computer Graphics C Version (Second Edition, Prentice Hall, pp. 362-387).
[4] W. S. Maki, Simple Geometric Fractals, Behavior Research Methods, Instruments and Computers, Psychonomic Society, Inc. 23(2), pp. 160-165, 1991.
[5] V. Rozouvan, Symmetry of the Modified Mandelbrot Set, Pi in the Sky, Pacific Institute for Mathematical Sciences (PIMS), Issue 9, December 2005.

Abstract : Uterine cancer is one of the conspicuous cancers for women in both developed and developing countries including Bangladesh. Now, in the world it is the sixth most common cancer among women and fourteenth most common cancer overall. The high occurrence of uterine cancer in women has increased significantly in the last years. This involves many factors to be measured and evaluated, which are related to the signs and symptoms of this disease. These factors usually expressed in quantitative and qualitative ways. In addition, a hierarchical relationship exists among these factors. Since qualitative factors cannot be measured in a quantitative way, resulting various types of uncertainties such as incompleteness, vagueness, imprecision. Therefore, it is necessary to address the issue of uncertainty by using appropriate methodology; otherwise, the conclusion to detect uterine cancer will become inaccurate. There exist many systems to address the issue presented in this paper. However, none of them is able to address the issue of uncertainty. Therefore, this paper demonstrates the application of a novel method, named belief rule-based inference methodology-RIMER, which is capable of addressing the uncertainties in both clinical domain knowledge and clinical data. This paper reports the development of a Belief Rule Based Expert System (BRBES) using RIMER approach, which is capable of detecting the presence of uterine cancer by taking account of signs and symptoms. The system has been validated by using real patient data and it has been observed that the results generated by the BRBES are more reliable than the manual system usually carried out by a physician.

Keywords: Expert System, Evidential Reasoning, RIMER, Signs and Symptoms, Uncertainty, Uterine Cancer

[1] World Cancer Statistics April,2014 http://www.wcrf.org/cancer_statistics/world_cancer_statistics.php#Women.
[2] Cancer Statistics According to Specific Cancer April, 2014 http://www.wcrf.org/cancer_statistics/data_specific_cancers/endometrial_cancer_statistics.php.
[3] Cancer Statistics by Country April, 2014 http://www.rightdiagnosis.com/e/endometrial_cancer/statscountry.html. [4] Uterine or Endometrial Cancer Treatment April, 2014,:http://www.uabmedicine.org/conditions-and.../cancer-gyn-uterine-endometrial.

[5] Information and Resources for Various Types of Cancer April, 2014:http://www.cancer.org.
[6] Information about Uterine Cancer and its Diagnosis April, 2014 http://www.cancer.org/cancer/endometrialcancer/detailedguide/endometrial-uterine-cancer-diagnosis.

Abstract : Ranking is a technique to categorize & finding the best option in the market. When number of best option is available in the market so its difficult to getting the best option is always a problem. In this paper we proposed a technique to optimize the ranking and its availability to check performance factor in order to maintained high ranking and quality of popular option in the market. We enhanced the line-up algorithm for ranking optimization approached, so, we used to line-up technique is demonstration to check other factor which affect to ranking of products, we are finding research to get factor detail which to improve the ranking of product.

Keywords: Ranking technique, line-up technique, data analysis, data visualization

[1] LineUp: Visual Analysis of Multi-Attribute Rankings Samuel Gratzl, Alexander Lex, Nils Gehlenborg, HanspeterPfister, and Marc Streit.
[2] A. P. Sawant and C. G. Healey. Visualizing multidimensional query results using animation. In Electronic Imaging 2008, page 680904, 2008.
[3] L. Byron and M. Wattenberg. Stacked graphs - geometry &aesthetics.IEEE Transactions on Visualization and Computer Graphics, 14(6):1245–1252, 2008.
[4] C. Shi, W. Cui, S. Liu, P. Xu, W. Chen, and H. Qu. RankExplorer: visualization of ranking changes in large time series data. IEEE Transactions on Visualization and Computer Graphics, 18(12):2669 –2678, 2012.
[5] P. Kidwell, G. Lebanon, andW. S. Cleveland. Visualizing incomplete and partially ranked data. IEEE Transactions on Visualization and Computer Graphics, 14(6):1356–1363, 2008.

Abstract : In a Network we have various issues to work with our services & data (maintenances) & today Cloud computing provides convenient on-demand network access to a shared pool of configurable enumerate resources. The resources can be rapidly expand with great efficiency and minimal management atop. Cloud is an afraid computing platform from the view point of the cloud users, the system must design structure that not only assure sensitive information by enabling computations with encrypted data, but also assure users from envious behaviours by permissive the validation of the computation result along with an effective authentication mechanism to the user, from the past timing we have a multiple scheme to authorize any interface- here also in order to access a cloud we use textual password which is not much secure in terms of authentication because textual password might be easy to guess & lot of brute force attack has been already done on textual based attack in current world so that still here we are finding an efficient way where we can get a reliable authentication to original user, one of the way which we got is object password or graphical password to authenticate interface which we have described in existing system In this paper, we propose a technique for authenticating cloud which is advance authentication scheme in terms of graphical password at the same time we are going to propose this scheme for using in cloud & in cloud how we can verify the data integrity which we are storing. It is high-speed data verification scheme with minimal loss probability. The proposed system is highly efficient in order to authenticate in proper manner in order to maintain login security & after authentication again to verify our data integrity correctly.

Keywords: Enhanced Graphical password scheme, Cloud Computing, Data Integrity and Key Generation

[1] C. Wang, Q. Wang, K. Ren, and W. Lou, ―Ensuring data storage security in cloud computing,‖ in Proc. of IWQoS'09, July 2009, pp. 1–9.
[2] Cong Wang, Qian Wang, KuiRen, Wenjing Lou, "Towards Secure and Dependable Storage Services in Cloud Computing," IEEE transactions on Services Computing, 06 May 2011. Rampal Singh, IJECS Volume 2 Issue 3 March 2013 Page No. 825-830 Page 830
[3] A. Juels and J. Burton S. Kaliski, ―PoRs: Proofs of retrievability for large files,‖ in Proc. of CCS'07, Alexandria, VA, October 2007, pp. 584–597.
[4] Sun Microsystems, Inc., ―Building customer trust in cloud computing with transparent security,‖ Online at https://www.sun. Com/offers/details/sun transparency.xml, November 2009.
[5] M. Arrington, ―Gmail disaster: Reports of mass email deletions,‖ online at http: // www. techcrunch.com/2006/12/ 28/ gmail-disasterreports-of- mass-email-deletions/, December 2006

Abstract : Semantic Web Mining combines two fast developing research areas: Semantic Web & Web Mining. In this relation, the research intension is to improve on the one hand, Web mining methods with new needs of semantic strategies and on another hand new strategic rule to make it fast and accurate. With tremendous development of WWW, it is making web experience more time spending to user. Hence semantic web mining has become necessary to apply some strategy so that valuable knowledge can be extracted and consequently returned to the user. Data extraction strategies and techniques when applied with web mining will provide a new way result to user query. Clustering will help to provide better satisfaction to user query with less surfing time.

Key Words: Web mining, data mining, semantic data mining, search query and surfing time

[1] Sharma K., Shrivastava G. & Kumar V., ‗Web Mining: Today and Tommorrow'. In Proceedings of the IEEE 3rd International Conference on Electronics Computer Technology, 2011.
[2] Bhatia C.S. & Jain S., ‗Semantic Web Mining: Using Ontology Learning and Grammatical Rule Interface Technique'. In IEEE 2011.
[3] Kosala R. &Blockeel H., ‗Web Mining Research: A Survey'. Published in ACM SIGKDD, Vol. 2, Issue 1,July 2000.
[4] Eirinaki M. &Vazirgiannis M., ‗Web Mining for Web Personalization'. Published in ACM Transactions on Internet Technology, Vol.3 , No. 1, February 2003, pp. 1-27.
[5] Meirong T. & Xuedong C. , ‗Application of Agent Based Web Mining in E-business'. Published in 2010 IEEE Second International Conference on Intelligent Human-Machine Systems and Cybernetics, pp. 192-195.

Abstract : In today's world, cross platform integration of application plays important role to achieve economic viability and usability of the product. This paper describes technical details of the successfully implemented system whose roots are based on ONVIF platform. System enumerates simulation of various ONVIF capable video surveillance devices and delineates the communication that takes place between user and network devices. ONVIF network discovery and accessibility of various services has been wisely implemented which gives us lucid understanding regarding ONVIF specification

Keywords: Database, JAX-WS, ONVIF, SOAP, Web Service XML

[1] Yogiraj Awati, Rahul Gutal, Abhijeet Bhintade, Saurabh Taware, "Onvifsense: ONVIF Network DeviceAccessibility Application", ISSN 2250-2459, ISO 9001:2008 Certified Journal, Volume 3, Issue 4, April 2014

[2] ONVIF, ONVIF™ Core specification, Version 2.2. May, 2012. [Online] Available: http://www.onvif.org/specs/DocMap.html

[3] J. Beatty et al., XMLSOAP, Web Services Dynamic Discovery (WSDiscovery),April 2005 . ([Online]Available:http://specs.xmlsoap.org/ws/2005/04/discovery/wsdiscovery.pdf)

[4] T. Berners-Lee, et al, "Uniform Resource Identifiers (URI): Generic Syntax,"August 1998. ([Online] Available: http://www.ietf.org/rfc/rfc2396.txt.).

[5] "Port Numbers," February 2005. ([Online] Available: http://www.iana.org/assignments/port-numbers.)

Abstract : Information retrieval is the process of retrieving all the relevant documents that satisfies the user query from large corpora. It is aimed to provide the relevant information and documents that matches the user query. Outcome of the several research results confirms that difficulties in information retrieval are matching the query with corpus. Consequently, the enhanced indexing technique named Document Index Graph (DIG) used for indexing document collection in order to match and retrieve information efficiently. Hence, an enhanced DIG has been constructed that stores all the stemmed sentences of documents in the graph. The words with same stem can be stored only once in DIG. This helps to reduce the size of the graph. The most frequently appearing words are planted into FP (Frequent Pattern) Tree. The FP-tree is a compact representation of all relevant frequently occurring information in a corpus. The enhanced FP tree with a table generates all types of possible term set which satisfy the minimum support. Information is retrieved with the help of FP-Tree and Document Index Graph.

Keyword: Stemming, Document Index Graph, Query Processing, Frequent Pattern Tree and Information Retrieval.

[1] Abebe Rorissa and Xiaojun Yuan, "Visualizing and Mapping the Intellectual Structure of Information Retrieval", Information Processing and Management, Vol.48, No.1, 2012,120–135.

[2] Agbele K. et al "Context-Aware Stemming Algorithm for Semantically Related Root Words", African Journal of Computing & ICT, Vol. 4,No.5, 2012, 33-42.

[3] Barla Cambazoglu B and Cevdet Aykanat, "Performance of query processing implementations in ranking-based text retrieval systems using inverted indices", Information Processing and Management, Vol.42, No.4,2006, 875–898.

[4] Daniel et al, "A topic based indexing approach for searching in documents", 8th International Conference, Electrical, Merida, 2011, 1-6.

[5] Djamal Belazzougui, Gonzalo Navarrob and Daniel Valenzuela, "Improved compressed indexes for full-text document retrieval", Journal of Discrete Algorithms, Vol.8, 2012, 3-13.

Abstract : A new idea is proposed in this paper for improvement in the Low Energy Adaptive Clustering Hierarchy (LEACH) protocol. The cluster heads are selected based on the residual energy at each node at the end of each round. The expected number of cluster heads is kept stable considering the average residual energy of nodes which have not been cluster heads and the initial energy of a node. This work is carried out at each node level at the end of each round. Simulations are carried out considering the modified threshold function and the results are compared with the existing LEACH and family protocols.
Keywords: Data fusion, LEACH, initial energy, residual energy

[1]. Vidyasagar Potdar, Atif Sharif, Elizabeth Chang, "Wireless Sensor Networks: A Survey", International Conference on Advanced Information Networking and Applications Workshops, 2009, pp. 636-641.
[2]. Gaurav Sharma, Suman Bala, A. K. Verma, "Comparison of Flooding and Directed Diffusion for Wireless Sensor Network", India Conference (INDICON), Annual IEEE, 2009, pp. 1-4.
[3]. Yebin Chen Jian Shu Sheng Zhang Linlan Liu, "Data Fusion In Wireless Sensor Networks", Second International Symposium on Electronic Commerce and Security 2009, pp. 504-509.
[4]. C Li, M Ye, G Chen, and J Wu, "An energy-efficient unequal clustering mechanism for wireless sensor networks," in IEEE International Conference on Mobile Ad hoc and Sensor Systems Conference, pp. 604, 2005.
[5]. C Y Wen and W A Sethares, "Automatic decentralized clustering for wireless sensor networks," EURASIP J.Wireless
[6]. Communication Network., vol. 5, no. 5, pp. 686–697, Oct.2005.

Abstract : Concrete compressive strength prediction is very important in structure and building design, particularly in specifying the quality and measuring performance of concrete as well as determination of its mix proportion. The conventional method of determining the strength of concrete is complicated and time consuming hence artificial neural network (ANN) is widely proposed in lieu of this method. However, ANN is an unstable predictor due to the presence of local minima in its optimization objective. Hence, in this paper we have studied the performance of support vector machine (SVM), a stable and robust learning algorithm, in concrete strength prediction and compare the result to that of ANN. It is found that SVM displayed a slightly better performance compared to ANN and is highly stable.

Keywords: Artificial Neural Network, Compressive Strength of Concrete, Mix Proportion, Robust Learning Algorithm, Support Vector Machine

[1] A. M. Neville, Properties of Concrete. 2012, p. 872.

[2] D. A. Abrams, "Water-Cement Ratio as a Basis of Concrete Quality," ACI, vol. 23, no. 2, pp. 452–457.

[3] "COMPARISON OF CONCRETE STRENGTH PREDICTION TECHNIQUES WITH ARTIFICIAL NEURAL NETWORK," vol. 56, no. 1, pp. 23–36, 2008.

[4] S. Olatunji and H. Arif, "IDENTIFICATION OF ERYTHEMATO-SQUAMOUS SKIN DISEASES USING EXTREME LEARNING MACHINE AND ARTIFICIAL NEURAL NETWORK," ictactjournals.in, vol. 6956, no. October, 2013.

[5] G. D. Magoulas, A. Prentza, N. Technical, and G.- Athens, "MACHINE LEARNING IN MEDICAL APPLICATIONS George D. Magoulas 1 and Andriana Prentza 2 1," vol. 1999, 1999.

Abstract : In the face of economic depression and technological advancements round the world, there is growing need to design a computerized monitoring system in a bid to adapt to the global trend in financial management. The existence of computerized economic growth system in relation to the ministry of finance requires a higher dependent scheme of measure in financial control of the federation. Various departments exhibit responsibilities for revenue generation and financial plan structured to detail projections on income and expenses on long term and short term basis i.e. financial budget. The measure of financial terms is represented by stage processing of input in each sector that makes up the economy. This results to a yearly analysis of a dependent economic report within a country i.e. GDP Gross Domestic Product.

Keywords: Economic growth, financial management, financial budget and GDP.

[1]. Arestis, P., P. and Demetriades, (1997: 783- 799): "Financial Development and Economic Growth: Assessing the Evidence", the Economic Journal, Washington.
[2]. Arestis, P., P.Demetriades and K.Luintel (2001:16-41), "Financial Development and Economic Growth: The Role of Stock Markets," Journal of Money, Credit, and Banking. World Bank, Zurich.
[3]. Aziz, J. and C. Duenwald.(2002): "Growth-Financial Intermediation Nexus" IMF Working Paper, China.
[4]. Afangideh, U. J (June, 2009): "Financial Development and Agricultural Investment in Nigeria: Historical Simulation Approach", West African Journal of Economic and Monetary Integration Vol. 9. Nigeria.
[5]. Agu, C.C. and J.O. Chukwu (2008:189-190): "Toda and Yamamoto causality tests between bank based financial deepening and economic growth in Nigeria".European Journal of Social Science, Calabar.

Abstract : Feature subset selection involves identifying a subset of the most useful features that produces compatible results as the original entire set of features. A feature selection algorithm may be evaluated from both the efficiency and effectiveness points of view. While the efficiency concerns the time required to find a subset of features, the effectiveness is related to the quality of the subset of features. Current existing algorithms for feature sub set selection works only based on conducting statistical test like Pearson test or symmetric uncertainty test to find the correlation between the features and apply threshold to filter redundant and irrelevant features. FAST proposed by Qinbao Song [9] uses symmetric uncertainty test for feature subset selection. In this work we extend the FAST algorithm by applying the domain analysis using semantic Mining to improve the relevance of the feature subset selection.

Index Terms: Feature subset selection, filter method, feature clustering, graph-based clustering

[1]. Kira K. and Rendell L.A., The feature selection problem: Traditional methods and a new algorithm, In Proceedings of Nineth National Conference on Artificial Intelligence, pp 129-134, 1992.
[2]. Koller D. and Sahami M., Toward optimal feature selection, In Proceedings of International Conference on Machine Learning, pp 284-292, 1996.
[3]. Kononenko I., Estimating Attributes: Analysis and Extensions of RELIEF, In Proceedings of the 1994 European Conference on Machine Learning, pp 171-182, 1994.
[4]. Yu L. and Liu H., Feature selection for high-dimensional data: a fast correlation-based filter solution, in Proceedings of 20th International Conference on Machine Leaning, 20(2), pp 856-863, 2003.
[5]. Fleuret F., Fast binary feature selection with conditional mutual Information, Journal of Machine Learning Research, 5, pp 1531-1555, 2004.

Abstract : The development of a vibrant application for analyzing and predicting stock market prices is a basic tool aimed at increasing the rate of investors' interest in stock markets. This paper explains the development and implementation of a stock price prediction application using machine learning algorithm and object oriented approach of software system development. The algorithm was used in training a set of market data collected for the period of one thousand, two hundred and three days. The implementation was done with Java programming language and Neuroph software. From the experiments conducted and observed results from the application indicates a better predictive accuracy and high minimum error. When tested with Nestle Nigerian Plc. recorded a mean squared error (MSE) and regression (R) values of 61876e-6 and 0.99975 respectively, Guinness Nigerian Plc. recorded a mean squared error (MSE) and regression (R) values of 9.95839e-7 and 0.99853 respectively and Total Nigerian Plc. recorded a mean squared error (MSE) and regression (R) values of 8.03493e-6 and 0.992193 respectively.

Keywords: Machine learning, Supervised Learning, Regression value, Mean Square Error.

[1] A. AdebiyiAyodele, K. Ayo Charles., O. Adebiyi Marion., and O. Otokiti Sunday, "Stock Price Prediction using Neural Network with Hybridized Market Indicators," Journal of Emerging Trends in Computing and Information Sciences, Vol3 No 1, Pp 1-9, 2012

[2] T. AkinwaleAdio, O.T. Arogundade and F Adekoya Adebayo. "Translated Nigeria Stock Market Price Using Artificial Neural Network for Effective Prediction," Journal of Theoretical and Applied Information TechnologyVol1 No 1. Pp 36-43. 2009

[3] N. C. Ashioba, E.O. Nwachukwu, and O. Owolobi. "Finding the Optimal Solution for a Transportation Problem Using Neural Network. Microwave," International Journal of Science and Technology, Vol. 3 No 1, Pp 36-40, 2012.

[4] Kyoung-Jae Kimand and Ingoo Han, " Genetic Algorithms Approach to Feature Discretization in Artificial Neural Networks for the Prediction of Stock Price Index," Institute of Science and Technology, " Vol19, .Pp 125-132, 2000

[5] Mahdi PakdamanNaeini, HomaBaradaranHashemiand HamidrezaTaremian, ".Stock Market Value Prediction Using Neural Networks," International Conference on Computer Information Systems and Industrial Management Applications (CISIM), Pp132 – 136 2010