Classification problems and their corresponding solving approaches constitute one of the fields of machine learning. Among them classification approaches are categorized into two major types: Two way classification and multi way classification methods are there to analyze the given data. First type of binary or binomial classification is the task of classifying the elements of a given set into two groups (predicting which group each one belongs to) on the basis of a classification rule. In general binary classification is not suitable for all practical problems. Classification problems and their corresponding solving approaches constitute one of the fields of machine learning.............

[1]. Amancio, D.R., Comin, C.H., Casanova, D., Travieso, G., Bruno, O.M., Rodrigues, F.A. and da Fontoura Costa, L., 2014. A systematic comparison of supervised classifiers. PloS one, 9(4), p.e94137.
[2]. Bosch, A., Zisserman, A. and Munoz, X., 2007, Image classification using random forests and ferns. IEEE 11th International Conference on Computer Vision, pp. 1-8.
[3]. Bourel, M. and Segura, A.M., 2018. Multiclass classification methods in ecology. Ecological Indicators, 85, pp.1012-1021.
[4]. Cao, M.D. and Zukerman, I., 2012. Experimental evaluation of a lexicon-and corpus-based ensemble for multi-way sentimen analysis. In Proceedings of the Australasian Language Technology Association Workshop ,pp. 52-60
[5]. Cheong, S., Oh, S.H. and Lee, S.Y., 2004. Support vector machines with binary tree architecture for multi-class classification. Neural Information Processing-Letters and Reviews, 2(3), pp.47-51.

Data is growing every day. Now we are having lot of data from various e-components and social media, medical field and finance domains. Analysing the data gives us most useful information to face the future in various ways. The term data science is a broad place to provide a deep insight on the huge amount of data. Data science is gathering knowledge from data with the computational algorithms and statistical methods or mathematical models with effective visualization of data. This paper explores the comparison of various classification methods and various statistical models for the autism data.

Keywords: Data Analytics, Autism Spectrum Disorder, Classification, Statistical Models.

[1]. V.Bhuvaneswari, T.Devi,"Big data analytics-A Practioner's Approach",2016.
[2]. Dr.M.Manimekalai, A.E.Arthipriya,"Evaluating the behavioural and developmental interventions for autism spectrum disorder", International journal of information science and application, 2014.
[3]. Richa misra, Divya bhatnagar,"Analysing the social awareness in autistic children trained through multimedia intervention tool using data mining",International journal of Advanced computer science and applications,2017.
[4]. Dr.Yamini, M.Premasundari,"A Review on classification technique with autism spectrum disorder and agriculture", International journal of advanced research in computer science",2017.
[5]. Adham Beyikhoshk," Data mining and Autism Spectrum Disorder: A pilot study",International Conference on Advances in Social Networks Analysis and Mining, 2014.

Now-a-days Knowledge Discovery is the major problem to the people and it is a difficult task to overcome these problems by using CF algorithms and look for the accurate information at the acceptable time. It is also in the library Science environment to improve the user count and to take positive decisions. Moreover, the library users will be evaluated based on the some quality features such as OBE (Outcome Based Education), Readers' Forum (RF) and Library Orientation Programme (LOP). This study is mainly focuses an analysis using the existing similarity learning models and those are compared with the proposed model, Multidirectional Collaborative Filtering Decision Support Model.

Keywords: Knowledge Discovery in Database (KDD), OBE (Outcome Based Education), Multidirectional Collaborative Filtering (MDCF), RF (Readers' Forum), LOP (Library Orientation Programme),SVD(Singular Value Decomposition),PCA(Principal Component Analysis)

[1]. Dou ,Yingtong, Yang, Hao and Xiolong Deng,Bejing,China, "A Survey of Collaborative filtering algorithms for Social Recommender Systems",IEEE Explore, 40-46 ,(2017).
[2]. Beel, Joeran, Langer, Stefan, and Gipp, Bela, "TF-IDuF: A Novel Term-Weighting Scheme for User Modeling based on Users' Personal Document Collections", iConference (2017).
[3]. Rao,,Muralikrishna "Collaborative Filtering Recommender System with Randomized learning rate and regularized parameter",IEEE Explore, DOI: 10.1109/ICCTAC.2016.7567331, (2016).
[4]. Ponnam , Lakshmi Tharun, Punyasamudram , Sreenivasa Deepak, Nallagulla , Siva Nagaraju and Yellamati, Srikanth "Movie Recommender System using item based collaborative filtering technique",IEEE Explore, DOI: 10.1109/ICETETS.2016.7602983 ,(2016).
[5]. Liu,Haifeng, Kong,Xiangjie ,Bai,Xiaomei, Wang,Wei, Megersa Bekele,Teshome ,and Xia,Feng, "Context-Based Collaborative Filtering for Citation Recommendation",IEEE Access, 1695 - 1703 (2015).

The Electrocardiogram is a measurement used to evaluate of the electrical activity of the heart. An Electrocardiogram, mentioned as ECG, signals becomes a vital role in diagnosing Cardiovascular Diseases. A variety of Cardiovascular Diseases like, Arrhythmia, Atrial Fibrillation, Atrio Ventricular Dysfunctions, and Coronary Arterial Disease, etc. may be detected non-invasively by means of ECG monitoring devices. Among these types of cardiovascular diseases, here Cardiac Arrhythmias is particularly taken as a problem domain. The techniques that classify cardiac arrhythmias based on the features that present in ECG measures still have poor accuracy and need much more learning time. With the arrival of contemporary Signal Processing, Data Mining and Machine Learning techniques, the diagnostic power of the ECG has prolonged exponentially............

Keywords: Electrocardiogram, P-QRS-T wave, Clustering, FCM, EM.

[1]. J. C. Bezdec. "Pattern recognition with fuzzy objective function algorithms", Plenum Press, New York, 1981.
[2]. M. Zbancioc and M. Feraru, "A study about the statistical parameters used in the emotion recognition", Proc. of the 10th International Conference on Development and Application Systems, Suceava, Romania, ISSN: 1844-5020, pp. 187-190, 2012.
[3]. M. Murugappan, M. Rizon, R. Nagarajan and S. Yaacob. "EEG Feature Extraction for Classifying Emotions using FCM and FKM‟, Proc. of the 7th WSEAS Int. Conf. on Applied Computer and Applied Computational Science 1, pp. 299-304, 2008.
[4]. Y. Yang, Ch. Zheng and P. Lin, "Fuzzy C-means clustering algorithm with a novel penalty term for image segmentation," Opto Electronics Rev., vol. 13, no. 4, 2005.
[5]. Richard A. Redner and Homer F. Walker. Mixture densities, maximum likelihood and the EM algorithm. SIAM Review, 26(2):195- 239, 1984.

Cloud computing is a technology, which provides the on-demand Information Technology services for the customer through the internet. Cloud computing facilitates the user by providing the resources of third party in the name of infrastructure, hardware and software irrespective of the physical position over the internet network. Cloud computing infrastructures allow the user to access the data anywhere at any time as long as the user's device has access with the internet. Such activity improves the use of internet application which provides "pay as you go" facility. Hence this flexibility creates an impact upon the user and made them to transfer their data to cloud. But it may lay some security issues also.............

Keywords : Cloud Computing, Cryptography, Encryption, Decryption, AES, RSA, MD5

[1]. Alexa Huth and James Cebula "The Basics of Cloud Computing", United States Computer Emergency Readiness Team. 2011.
[2]. Farzad Sabahi, "Virtualization-Level Security in Cloud Computing", Faculty of Computer Engineering Azad University Iran, 978- 1-61284-486-2/11, IEEE Transaction, 2011.
[3]. G Devi, Pramod Kumar "Cloud Computing: A CRM Service Based on a Separate Encryption and Decryption using Blowfish algorithm", IJCTT, 2012.
[4]. Huaglory Tian_eld, Security Issues In Cloud Computing, School of Engineering and Built Environment Glasgow Caledonian
University, United Kingdom, 978-1-4673-1714-6/12, IEEE Transaction, 2012.
[5]. A. Iosup, S. Ostermann, N. Yigitbasi, R. Prodan, T. Fahringer, D. Epema, Performance analysis of cloud computing services for many-tasks scientific computing, IEEE Transactions on Parallel and Distributed Systems 22 (6), P.no: 931–945, 2011.

Nowadays, a new agenda of extracting small scale objects as vehicles from high resolution satellite images have been evaluated. Less research is performed using high resolution satellite imagery as it is a challenging task. Though various studies have been performed, still there is a need to develop a fast, robust, and suitable approach. The approach described in this paper gives out the accuracy rate of vehicles captured from satellite images. It simply workout the full numbers of vehicles within the desired space in the satellite image and vehicles are shown underneath the bounding box as a small spots.

Keywords: Image Enhancement, Morphological Image Processing, Segmentation, Otsu Threshold, Edge Detection

[1]. "Digital Image Processing" book, By Rafael C Gonzalez, page no. 29.
[2]. Oscar Firschein and Thomas M Strat, RADIUS: Image Understanding for Imagery Intelligence.: Morgan Kaufmann, 1997.
[3]. Andres Huertas and RamakantNevatia, "Detecting changes in aerial views of man-made structures," in Proc. of International Conference on Computer Vision, 1998.
[4]. Aaron J Heller, Yvan G Leclerc, and Quang-Tuan Luong, "A framework for robust 3-d change detection," in Proceedings for International Symposium on Remote Sensing, SPIE., 2001
[5]. Chris Stauffer and W E Grimson, "Adaptive background mixture models for real time tracking," in Proceedings of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)., vol. 2, 1999, pp. 246-252.

Advanced fuzzy set theoretic techniques play an important role in image processing mostly in medical field. Medical images are inadequately illuminated, where regions are vague or hardly visible, creating uncertainty. Intuitionistic fuzzy sets are more useful in processing the medical images in early days. Cancer is one of most common disease in women worldwide. The final prediction and prognosis of cancer is based on the examination of cells or tissues under the microscope by a pathologist. The digital slides are converted to images, which can be viewed and analyzed on a computer monitor. These are called digital pathology images. These images are then analyzed through various image processing algorithms.............

Keywords - Image processing, digital pathology, TriIFS(Triangular Intuitionistic Fuzzy Set)

[1]. Australian Institute of Health and Welfare. Cancer. [homepage on the internet] Australia: AIHW; 2013 [cited 2014 May 29; updated 2013]. Available from: http://www.aihw.gov.au/cancer/
[2]. National Breast Cancer Centre. Clinical practice guidelines management of early breast cancer: Second edition. Canberra: National Health and Medical Research Clinic; 2001 Available
from: http://www.nhmrc.gov.au/_files_nhmrc/publications/attachments/cp74_management_early_breast_cancer_131223.pdf.
[3]. Anant Madabhushi, ―Digital pathology image analysis: opportunities and challenges‖.
[4]. Krassimir T.Atanassov,‖Intuitionistic Fuzzy Sets‖, Theory and Applications, Springer- Verlag Berlin Heidelberg GmBH.
[5]. Tamalika Chaira, ―Medical Image Processing‖, Advanced Fuzzy set Theoretic Techniques.

This paper presents a design for removing phishing sites or phishingpages that are hosted probably without the knowledge of the website owner or host server. Initially the system assesses and classifies phishing emails using Fuzzy Logic and the RIPPER Data Mining algorithm. In assessing the Phishing email, Fuzzy Logic linguistic descriptors are assigned to a range of values for each key phishing characteristic indicators. The system then sends a notification to the System Administrator of the host server to indicate that it is hosting a Phishing site. The removal success rate of the identified phishing sites is 81.81% based on the notifications sent to the host of the different phishing pages.

Keywords- Data Mining, Fuzzy Logic, Phishing, URL, Classification

[1]. A.-P. W. Group, "Global phishing survey: Domain name use and trends in 2h2010,"
[2]. http://www.antiphishing.org/reports/APWG, GlobalPhishingSurvey 2H2010.pdf.
[3]. A. P. W. Group, "Phishing activity trends report," 2009, http://www. antiphishing.org/reports/apwg report Q4 2009.pdf.
[4]. Anti-Phishing Working Group, "Phishing Activity Trend Report", Jan-March 2008
[5]. Shah, R.; Trevathan, J.; Read, W.; Ghodosi, H.,"A Proactive Approach to Preventing Phishing Attacks Using the Pshark Model", IEEE Sixth International Conference on Information Technology: New Generations, March 2009, pp. 915 - 921

The major cause for decrease in the quality and amount of agricultural productivity is plant diseases. Farmers encounter great difficulties in detecting and controlling plant diseases. Thus, it is of great importance to diagnose the plant diseases at early stages so that appropriate and timely action can be taken by the farmers to avoid further losses.The project focuses on the approach based on image processing for detection of diseases of cashew plants. In this paper, we propose an Android application that help farmers for identifying cashew disease by uploading leaf image to the system. The system has set of algorithms which can identify the type of disease. Input image given by the user undergoes several processing steps to detect the disease and results are returned back to the user via android application.

Keywords- Android, segmentation, k-mean, SVM (Support Vector Machine).

[1]. Vijai Singh, Varsha, Prof. A K Misra.," Detection of unhealthy region of plant leaves using Image Processing and Genetic Algorithm "2015 International Conference on Advances in Computer Engineering and Applications (ICACEA) IMS Engineering College, Ghaziabad, India
[2]. Dheeb Al Bashish, Malik Braik, and SuliemanBani-Ahmad, "A Framework for Detection and Classification of Plant Leaf and Stem Diseases", IEEE International Conference on Signal and Image Processing, 2010
[3]. Sachin D. Khirade, A. B. Patil," Plant Disease Detection Using Image Processing "2015 International Conference on Computing Communication Control and Automation.
[4]. YogeshDandawate,Radhakokare"An Automated Approach for Classification of Plant Diseases Towards Development of Futuristic Decision Support System in Indian Perspective" 2015 InternationalConference on Advances in Computing, Communicationsand Informatics (ICACCI).
[5]. Ramakrishnan.M, SahayaAnselinNisha. A," Groundnut Leaf Disease Detection and Classification by using Back Probagation Algorithm" IEEE ICCSP 2015 conference.

In this paper, we present an integrated framework for keyword-based text data collection and analysis. The integrated framework consists of four types of component: (1) user interface, (2) web crawler, (3) data analyzer, and (4) database (DB). The user interface is used to set input keyword and option values for web crawling and text data analysis through a graphical user interface (GUI). In addition, it provides analysis results through data visualization. The web crawler collects the text data of articles posted on the web based on input keywords. The data analyzer classifies the articles into "relevant articles" and "no relevant articles" using predefined knowledge (i.e., a set of words to be included in the articles). Then, it analyzes the text data of relevant articles and visualizes the results of the data analysis..............

Keywords- Data analysis, integrated framework, intelligent service, text data collection, web crawling.

[1]. C. Dobre and F. Xhafa: Future Gener. Comp. Syst. 37 (2014) 267.
[2]. W. Raghupathi and V. Raghupathi: Health Inf. Sci. Syst. 2 (2014) 1.
[3]. Z. Khan, A. Anjum, and S. L. Kiani: Proc. 2013 IEEE/ACM 6th Int. Conf. Utility and Cloud Computing (IEEE, 2013) 381.
[4]. A. Sheth, C. Henson, and S. S. Sahoo: IEEE Internet Comput. 12 (2008) 78.
[5]. S. Landset, T. M. Khoshgoftaar, A. N. Richter, and T. Hasanin: J. Big Data 2 (2015) 24.

Image Quality Measurement (IQM) aspires to make use of computational algorithms to compute the image quality constantly with individual evaluations. The well-known structural similarity index brings IQM from pixel to construction depending step. A new version of the well-liked IQM step, particularly introduced to yield super-pixel prediction in occurrence of varied types of image distortions. Features from superpixels might increase the results of IQM. Motivated from this, proposed a new Active Semisupervised SuperPixel Clustering based Similarity Measurement (ASSCSIM) measure by mining perceptually important features and correcting similarity results. The proposed method determines the image quality depending of clustering algorithm which makes use of an active step for selection of image pixels to reduce the amount of labeled superpixels, and it utilizes multithreshold to expand superpixels depending on there criteria's such as superpixel luminance, superpixel chrominance, and pixel gradient related similarities............

Keywords- Full-reference, Image Quality Measurement (IQM), Active Semisupervised SuperPixel Clustering based Similarity Measurement (ASSCSIM), clustering, superpixel, and texture complexity.

[1]. W. Lin and C. C. J. Kuo, "Perceptual visual quality metrics: A survey", Journal of Visual Communication and Image Representation, vol. 22, no. 4, pp. 297-312, 2011.
[2]. H. R. Sheikh, M.F. Sabir, and A.C. Bovik, "A statistical evaluation of recent full reference image quality assessment", IEEE Transactions on Image Processing, vol. 15, no. 11, pp. 3440-3451, 2006.
[3]. M. A Saad, A. C. Bovik, and Charrier C., "A DCT statistics-based blind image quality index", IEEE Signal Processing Letters, vol. 17 , no. 6, pp. 583-586, 2010.
[4]. C. Li, A. C. Bovik, and X. Wu, "Blind image quality assessment using a general regression neural network", IEEE Transactions On Neural Networks, vol. 22 , no. 5, pp. 793-799, 2011.
[5]. X. H. Zhang, W. S. Lin, and P. Xu, "Improved estimation for just-noticeable visual distortion", Signal Processing, vol. 85, no. 4, pp.795-808, 2005.

Generally, the opinions are gathered from the public about an entity like any product, event, movie etc. is very essential because of customer satisfaction for a specific entity. Opinions are statements that represent people's perception or sentiment, which is used to finding the customer feelings or thoughts about a purchasing of a particular product or topic with the use of natural language processing. Consider, if anyone (new user) can purchase any product then they can get an idea from the existing user's opinion or statement whether the product is good, bad or neutral. Based on existing user views the new user can conclude whether the product is purchase or not. It involves building a system to collect and examine opinions about the product made in many online purchasing sites. Opinion mining is a part of web content mining. Web content mining is a part of Data mining. The important role of Sentiment analysis is to train computer to be able to understand, recognize and generate emotions. The objective of this paper is to provide knowledge about how the customer opinions are performed at different levels...............

[1]. K.G. Nandakumar, Dr.T.Christopher "Opinion Mining: A Survey", International Journal of Computer Applications, Volume 113, No.2, March 2015.
[2]. Sindhu C1, Dr. S. ChandraKala, "A Survey on opinion mining and sentiment polarity classification". International Journal of Emerging Technology and Advanced Engineering. , Volume 3, Special Issue 1, January 2013).
[3]. Ziqiong Zhang, Qiang Ye, Zili Zhang, Yijun Li, "Sentiment Classification of Internet Restaurant Reviews written in Cantonese", Expert Systems with Applications, 2011.
[4]. B.Liu. 2010 "Sentiment Analysis and Subjectivity", Second Edition, The Handbook of Natural Lanugage Processing.
[5]. Bing Liu, Sentiment Analysis, Mining opinions, Sentiments, and Emotions, Book, June (2015).

"CANCER BIOLOGY WITH MOLECULAR DOCKING" is carried out to determine the anticancer compounds present in the plant. The software used is BioJava. Molecular structure is viewed through Rasmol. The software BioJava used for molecular study and docking purpose of elements present in the extract.The compounds in the extract are determined by using Rf value of the process using paper, TLC, and column chromatography. Antibacterial activity of the extract is studied against E-coli, BacillusSubtilis, and pneumonia. The Anticancer is activity carried out against HeLaCellines, and studied using MTT Assay [1]. The percentage of cell death is determined using ELISA reader.............

Keywords- Ocimum basilicum, Extraction, Chromatography, Anticancer, Phytochemicals.

[1]. https://en.wikipedia.org/wiki/MTT_assay
[2]. http://powo.science.kew.org/taxon/urn:lsid:ipni.org:names:452874-1
[3]. https://www.researchgate.net/publication/259176629_Preparation_of_Plant_Extracts_from_Indigenous_Medicinal_Plants
[4]. http://www.phytochemicals.info/
[5]. https://www.khanacademy.org/test-prep/mcat/chemical-processes/separations-purifications/a/principles-of-chromatography
[6]. http://amrita.olabs.edu.in/?sub=73&brch=8&sim=133&cnt=1

In recent years, agriculture in India is facing numerous challenges due to fast growth of population in urban areas. Research in wireless sensor networks leads to its application in various agricultural activities such as irrigation management, water management, vineyard monitoring, precision farming etc. A novel wireless sensor network architecture is proposed in this paper for most of the crops in Indian environment in order to achieve less water consumption and more productivity. Densely populated sensors with low power are suitable for short term crops and thinly populated sensors with high power are suitable for long term crops.

Keywords - Agricultural crops, nodes sensors, wireless sensor network.

[1]. Y. Zhu, J. Song, and F. Dong, "Applications of Wireless Sensor Network in the agriculture environment monitoring," Procedia Eng., vol. 16, pp. 608–614, 2011.
[2]. L. Zhao, S. Yin, L. Liu, Z. Zhang, and S. Wei, "A crop monitoring system based on wireless sensor network," Procedia Environ. Sci., vol. 11, no. PART B, pp. 558–565, 2011.
[3]. A. Tagarakis, V. Liakos, L. Perlepes, S. Fountas, and T. Gemtos, "Wireless sensor network for precision agriculture," Proc. - 2011 Panhellenic Conf. Informatics, PCI 2011, no. September, pp. 397–402, 2011.
[4]. N. Sakthipriya, "An effective method for crop monitoring using wireless sensor network," Middle - East J. Sci. Res., vol. 20, no. 9, pp. 1127–1132, 2014.
[5]. A. Awasthi and S. R. N. Reddy, "Monitoring for Precision Agriculture using Wireless Sensor Network-A review," GJCST-E Network, Web Secur., vol. 13, no. 7, 2013.

Cloud Computing is one of the most preferable technologies in the current era. Many computing services are moved to Cloud because of that attractive cost saving method. However, they have little fear to move cloud because of some cloud issues. Here, Data Security is one of the main drawback or issue of the cloud technology. The security of data in cloud computing is the most of the essence difficulty in the recent times. A fundamental method of protecting data is encrypting it before outsourcing or third party. In the existing methods (or traditional methods) are only concentrate on the transaction and storage area (or state). In my proposed method also concentrate on processing state, with the use of crossbreed Algorithms. In this data security method is provides (a) key management (b) access control and, (c) computation on cipher text.

Keywords - Cloud Computing, Data Security, Hybrid Algorithms.

[1]. K. W. Miller, J. Voas, and G. F. Hurlburt (2012), "BYOD: Security and Privacy Considerations," IT Professional, vol. 14, no. 5, pp. 53– 55, Sep. 2012.
[2]. Pearson, S., Benameur, A., "Privacy and Security Trust Issues Arises from Cloud Computing", Cloud Computing Technology and Science (CloudCom), IEEE Second International Conference, pp.693-702, 2010.
[3]. Gens, Frank. "IT Cloud Services User Survey, Pt.2: Top Benefits & Challenges." IDC EXchange. 02 Oct. 2008. Web. 14 Dec. 2010.
[4]. Nasrin Khanezaei, Zurina Mohd Hanapi "A Framework Based on RSA and AES Encryption Algorithms for Cloud Computing Services" IEEE Conference on Systems, Process and Control (ICSPC 2014), 12 - 14 December 2014, Kuala Lumpur, Malaysia.
[5]. AL.Jeeva, Dr.V.Palanisamy And K.Kanagaram "Comparative Analysis Of Performance Efficiency And Security Measures Of Some Encryption Algorithms" International Journal Of Engineering Research And Applications (IJERA) ISSN: 2248-9622 Vol. 2, Issue 3, pp.3033-3037, May-Jun 2012