International Conference on Innovation & Research in Engineering, Science & Technology (ICIREST-19)

Paper Type :: Research Paper
Title :: Identifying and Ranking Current News Topics Using Media Focus, User Attention and User Interaction of SMF
Country :: India
Authors :: Neha Vijay Manwatkar || Prof. Jayant Adhikari || Prof.Rajesh Babu
Page No. :: 01-06

Recently, social media services such as Twitter on it enormous amount of user-generated data, which has a great potential to contain informative news-related content, Now a days, web based social networking administrations, for instance, Twitter give a huge measure of client generateddata, which consistessential news-related material. Twitter as a new form of social media consist much neat information, but content analysis on Twitter has not been well considered. Broad communications sources, for example, news media used to illuminate us about day by day events. For these advantages for be useful, we should figure out how to filter noise and just catch the substance that, in perspective on its closeness to the news media.........

Keywords – Information filtering, social computing, social network analysis, topic identification, topic ranking.

[1]. D. M. Blei, A. Y. Ng, and M. I. Jordan, "Latent Dirichlet allocation," J. Mach. Learn. Res., vol. 3, pp. 993–1022, Jan. 2003.
[2]. T. Hofmann, "Probabilistic latent semantic analysis," in Proc. 15th Conf. Uncertainty Artif. Intell., 1999, pp. 289–296.
[3]. T. Hofmann, "Probabilistic latent semantic indexing," in Proc. 22ndAnnu. Int. ACM SIGIR Conf. Res. Develop. Inf. Retrieval, Berkeley,CA, USA, 1999, pp. 50–57.
[4]. Mario Cataldi, Luigi Di Caro" Emerging Topic Detection on Twitter based on Temporal and Social Terms Evaluation" MDMKDD'10, July 25th, Washington, DC, USACopyright 2010 ACM 978-1-4503-0220-3
[5]. F. Archetti, P. Campanelli, E. Fersini, and E. Messina, "A hierarchical document clustering environment based on the induced bisecting k-means," in Proc. 7th Int. Conf. Flexible Query Answering Syst., Milan, Italy, 2006, pp. 257–269. [Online]. Available:

Paper Type :: Research Paper
Title :: Implementation of Data Mining Techniques in CRM of Pharmaceutical Industry
Country :: India
Authors :: Durga Sadanand Tembhurne || Prof. Jayant Adhikari || Prof.Rajesh Babu
Page No. :: 07-12

Customer relationship management (CRM) is a data mining technology, CRM is utilized in enterprise of medical industry and its applications for that it utilizes classification tree algorithm. The data flow in the pharmaceutical industry was simple and the application of technology was veryquiet in last two decades. However, now a day's technology has become most vital part of the business processes, the process of transfer of information becomes more complicated. Today enhanced technology is being utilized to help the pharmaceutical firms manage their inventories and to develop new product and services. Here we present role of data mining (DM) in pharmaceutical industry.......

Keywords: Data mining; CRM, Selection tree algorithm, Frequent pattern algorithm.

[1]. song guijuan "Application of Data Mining Techniques in the CRM of Pharmaceutical Industry" 2018 International Conference on Intelligent Transportation, Big Data & Smart City
[2]. JiaweiHan,"Data Mining: Concept and Technology Beijing: Machinery Industry" Press, 2012.8.(in Chinese)
[3]. U.M.Fayyad, G.Piatetsky,P.Smyth and R.Uthurusamy, "Advances in Knowledge Discovery and Data Mining", AAAI/MT Press,1996.
[4]. He rongqin," CRM Principle, Design, Implementation, Beijing: Machinery Industry", Press 2002(in Chinese).
[5]. Cody, W.F. Kreulen, J.T. Krishna, V. & Spangler, "The integration of business intelligence and knowledge management." IBM Systems Journal, 41(4), 697-713 W.S. (2002).

Paper Type :: Research Paper
Title :: Implementation of Effective Re-Ranking Approach Using Multimedia Search Engine
Country :: India
Authors :: Kamatkar Vinalini Vinayak || Prof. Jayant Adhikari || Prof.Rajesh Babu
Page No. :: 13-18

Recently the detonating growth and comprehensive accessibility of association share media content on web have induce rise of research action in multimedia search. Generally while seeking result not actually coordinates with the search results. Hence the growing images on internet requires the best image retrieval technique that can enhance the image retrieval accuracy. Re-ranking is a viable technique to improve the search results of internet based multimedia search. This is generally adopted by business web crawlers, for example Google. The proposed Re-ranking approach is fit to work with all media types: video, picture, and audio. Techniques that apply text search methods for multimedia search have achieved limited success as they completely ignore visual content as a ranking............

Keywords:Re-ranking, Multimedia Retrieval,OCR, ASR, Audio-Video Feature Extraction.

[1]. Zhu, Y., Xiong, N., Park, J., and He, R., "A Web Image Retrieval Reranking Scheme with Cross-Modal Association Rules", International Symposium on Ubiquitous Multimedia Computing, Issue 13, Pages 83 - 86, 2008.
[2]. Chen, S., Wang, F., Song, Y., and Zhang, C., "Semi-supervised ranking aggregation", Information Processing & Management, Volume 47, Issue 3, Pages 415-425, 2011.
[3]. Singhal, R., & Srivastava, S. R. , "Enhancing the page ranking for search engine optimization based on weightage of in-linked web pages." Recent Advances and Innovations in Engineering (ICRAIE), 2016 International Conference on. IEEE, 2016.
[4]. Lu, M., Huang, Y., Xie, M., and Liu, J., "Rank hash similarity for fast similarity search", Information Processing & Management, Volume 49, Issue 1, Pages 158-168,2013.
[5]. J.Cui, F. Wen,, "Real time Google and live image search reranking", The 16th ACM international conference on Multimedia, Pages 729-732, 2008.

Paper Type :: Research Paper
Title :: Introduction on Selecting A Pair From A Group of Objects Using Data Mining : A Literature Survey
Country :: India
Authors :: Er. Sampada Pongade || Prof. Vanita Tonge
Page No. :: 19-21

The paper is based on research area data mining in computer science. Data mining means knowledge mining from data. From among different approaches in data mining we are going to work on a approach which is "Proximity Measures for Binary Attributes". The paper is about selecting a single pair from all the possible pairs in the data set consisting of objects of same type and having some attributes. Based on those attributes which will be binary in nature the research component i.e. Distance Measure will be calculated and a single pair will be given as output.

[1]. Saurabh Pal, "Is Alcohol Affect Higher Education Students Performance : Searching and Predicting pattern using Data Mining Algorithms", International Research Journal of Engineering and Technology (IRJET)
[2]. Kritika Yadav, "Analysis of Mahatma Gandhi National Rural Employment Guarantee Act using Data Mining Technique", International Journal of Computational Intelligence Research (IJCIR)
[3]. Muneo Kushima, Kenji Araki, Tomoyoshi Yamazaki, Sanae Araki, Taisuke Ogawa, Noboru Sonehara, "Text Data Mining of Care Life Log by the Level of Care Required Using KeyGraph", Proceedings of the International MultiConference of Engineers and Computer Scientists 2017 Vol I, (IMECS) 2017
[4]. Dursun Delen, Enes Eryarsoy, Şadi E. Şeker, "Introduction to Data, Text, and Web Mining for Business Analytics Minitrack", Proceedings of the 50th Hawaii International Conference on System Sciences | 2017
[5]. Sagar Bhise, "Effieient Algorithms to find Frequent Itemset Using Data Mining", International Research Journal of Engineering and Technology (IRJET)

Paper Type :: Research Paper
Title :: Machine Learning for Market Basket Analysis through Association Rules
Country :: India
Authors :: Devashri Raich || Bireshwar Ganguly || Madhavi Tota
Page No. :: 22-27

In the internet world, we all are surrounded with tons of data around us. "Where there is data, there are data mining applications"- which are application driven. Market Basket Analysis is connected with the most popular and successful application of Business Intelligence. (BI). When we deal with BI, the profit or loss depends on finding the exact correlation or association between the items sold. Market Basket Analysis is defined as discovery of frequent patterns and uncovers the association between items. Machine learning and advanced analytics combined with modern BI platform can efficiently discover new patterns and further help in analytics. Machine learning helps improve the performance of computers based on the data. It helps automatically recognize complex patterns and make intelligent decisions based on the data.

Keywords: Data Mining, Association, Correlation, Machine Learning, Business Intelligence.

[1]. Mitchell, T. (1997) Machine Learning, McGraw Hill, ISBN: 0- 07-042807-7
[2]. Business data mining — a machine learning perspective IndranilBose1aRadha K.Mahapatrab, Information & Management Volume 39, Issue 3, 20 December 2001, Pages 211-225
[3]. A Comparison of Different Classification Techniques for Bank Direct Marketing K. Wisaeng, International Journal of Soft Computing and Engineering (IJSCE) ISSN: 2231-2307, Volume-3, Issue-4, September 2013
[4]. Chappell, D. (2015) Introducing Azure Machine Learning: a Guide for Technical Professionals, Chappell & Associates [online] white_papers/Introducing- Azure-ML-v1.0--Chappell.pdf (accessed 11 December 2017). Costantino, M. and Coletti, P. (2008) Information Extraction in Finance, p.13, WIT Press, Southampton, Boston. D'Onfro, J. (2015)
[5]. Business Insider [online] pinterest-acquisition-2015-1 (accessed 10 October 2017). Das, K. and Beher, R.N. (2017)

Paper Type :: Research Paper
Title :: Metamorphic Cryptography: A Technique for Providing Security on Video Files
Country :: India
Authors :: Dhananjay M.Dumbere || Nitin J.Janwe
Page No. :: 28-38

The science of securing a data by encryption is Cryptography whereas the method of hiding secret data inside cover data is Steganography, so that the secret's very existence is concealed. The term Steganography describes the method of hiding cognitive content in another medium to avoid detection by the intruders. This paper introduces an approach wherein cryptography and steganography are combined to encrypt the data as well as to hide the encrypted data in cover medium so the fact that a data being sent is concealed. Combining both cryptography and steganography results to a new technique-Metamorphic Cryptography. The secret video is encrypted using AES algorithm and further encrypted video is embedded with cover video using LSB Algorithm, which results to double layer security to video files being transmitted over the network.

Keywords:Cryptography, Steganography, Secret Video, Encrypted Secret Video, Cover Video, Stego- Encrypted Secret Video, Decrypted Secret Video, PSNR, MSE.

[1]. William Stallings, ―Cryptography and Network Security, Principles and Practice‖, Third edition, Pearson Education, Singapore, 2003.
[2]. B. Chen and G.W. Wornell, ―Quantization Index Modulation:A Class of Provably Good Methods for Digital Watermarking and Information Embedding‖, IEEE Trans. Information Theory, vol. 47, no. 4, 2001, pp.1423–1443.
[3]. Thomas Leontin Philjon, Venkateshvara Rao.‖ Metamorphic Cryptography -A Paradox between Cryptography and Steganography Using Dynamic Encryption‖, IEEE-International Conference on Recent Trends in Information Technology, ICRTIT 2011-978-1-4577-0590-8/11/$26.00 ©2011 IEEE MIT, Anna University, Chennai. June 3-5, 2011
[4]. Eskicioglu, A.M.: ―Protecting intellectual property in digital multimedia networks‖. IEEE Computer, Special Issue on Piracy and Privacy (2003), 39–45.R. Nicole, ―Title of paper with only first word capitalized,‖ J. Name Stand. Abbrev. in press.
[5]. Meyer, J., Gadegast, F.: ―Security mechanisms for multimedia data with the example mpeg-1 video‖, Project description of SECMPEG,Technical University of Berlin.

Paper Type :: Research Paper
Title :: Moving Object Detection and Tracking from Video
Country :: India
Authors :: Sarika S. Wangulkar || RoshaniTalmale || G.Rajesh Babu
Page No. :: 39-44

In video or image, detection and tracking of an object is more widespread and used for motion detection of an object. Identify objects in the video sequence and cluster pixels of these objects is the first step in object detection. To track or observe the moments of a particular object in every frame is the process of tracking. There are many false positive cases in the frame. To reduce these drawbacks Saliency Map Model is used. The proposed method uses the Saliency Map Model for the object detection from video and tracking the moving objects from video using Extended Kalman Filter. Extended Kalman Filter is used for tracking the object. The proposed method evaluated based on evaluation parameter delay and accuracy. Finally, the proposed method compared with existing object tracking method

Keywords: object detection, Saliency Map, object tracking, Extended Kalman Filter

[1]. HAN Sung-ho, JUNG Gye-dong, "Automatic salient object segmentation using saliency map and color segmentation", Springer, 2013.
[2]. AlperYihnaz, Omar Javed, Mubarak Shah,"Object Tracking: A Survey", ACM Computing Surveys, Vol. 38, No. 4, Article 13, 2006.
[3]. Ruolin Zhang, Jian Ding, "Object Tracking and Detecting Based on Adaptive Background Subtraction", International Workshop on Information and Electronics Engineering, 2012, 1351-1355.
[4]. C. Jia, Z. Wang, X. Wu, and B. Cai, "A Tracking-Learning-Detection(TLD) method with local binary pattern improved", IEEE International Conference on Robotics and Biomimetics, IEEE, 2015.
[5]. X. Shi H. Ling W. Hu C. Yuan J. Xing "Multi-target tracking with motion context in tensor power iteration" 2014 IEEE Conference on Computer Vision and Pattern Recognition CVPR 2014 pp. 3518-3525 June 23–28 2014 2014.

Paper Type :: Research Paper
Title :: Multi Cloud (Architechture and Working)
Country :: India
Authors :: Rajat N. Shelke || Monashri S. Dalal || Sagar B. Navghare
Page No. :: 45-51

Multi Cloud allows its user to manipulate data among various distributed administrations. Manipulation includes duplicating, monitoring, and moving the records spread across distributed administrations. Users currently store their documents and data across various cloud service providers such as
Google drive, Apple iCloud, Dropbox. Multi cloud deployment mainly aggregates multiple Software as a Service (SaaS) or Platform as a Service (PaaS). It also can be evaluated as combination of public Infrastructure as a Service (IaaS) environments, such as Amazon Web Services and Microsoft Azure.

Keywords: Multi-Cloud, Amazon Web Services (AWS), Azure

[1]. P. Mell and T. Grance, "The NIST Definition of Cloud Computing," tech. rep., National Institute of Standards and Technology, 2009. def-v15.pdf.
[2]. P. Mell and T. Grance, "The NIST Definition of Cloud Computing," tech. rep., National Institute of Standards and Technology, 2009. def-v15.pdf.
[3]. 0950505_Management_of_Multi- cloud_Computing
[4]. cloud
[5]. and-cons-of-a-multi-cloud-approach- 10c2dfd628e9
[6]. ucture/the-right-approach-to-a-multi-cloud- architecture.html

Paper Type :: Research Paper
Title :: My Finplanner
Country :: India
Authors :: Pradnya G. Mandwe
Page No. :: 52-53

Financial planning is a continuous Process of directing and allocating financial resources to meet strategic goal and objectives. This can be also be viewed as a single process that encompasses both operation and financing . The operating people focuses on sales and production while financial planner are interested on how to finance the operation..

Keywords- Introduction,Types of financialplanning,Advantages,Disadvantages,Conclusion,References


Paper Type :: Research Paper
Title :: Network-on-chip Architecture Latency Analysis of Odd-Even Routing Algorithm for 2D mesh topology
Country :: India
Authors :: Prof. Anuradha A.Dakhane
Page No. :: 54-60

Network on chip is a scalable and flexible communication architecture for the design of core based System-on-Chip. Communication performance of a NOC heavily depends on routing algorithm.. Odd-Even (OE) routing algorithm is distributed adaptive routing algorithm with deadlock-free ability The purpose of NOC to solve communication and clock problem from architecture. Noc architecture includes number of routers to route the packets from sender to receiver. When network is in congestion, packet transmission will produce more time delay to get balance between time delay and throughput the appropriate routing algorithm is used............

Key Words: 2D Mesh topology, ODD-EVEN routing algorithm, Network on Chip (NoC), NIRGAM simulator.

[1]. Review of Odd-Even routing algorithm for 2D Mesh topology of Network on chip Architecture for Bursty traffic, Recent trends in Engineering technology 2013, International Journal of Computer Applications (0975 – 8887),
[2]. Dally W.J. and Towles B., Principles and Practices of Interconnection Networks", Morgan Kaufmann Publishers an Imprint of Elsevier Inc, 2004. [10]
[3]. Performance Comparison of XY, OE and DY Ad Routing Algorithm by Load Variation Analysis of 2- Dimensional Mesh Topology Based Network-on- Chip."Ge-Ming Chiu, Member, IEEE Computer Society"The Odd-Even Turn Model for Adaptive Routing" IEEE transactions on parallel and distributed systems, vol. 11, no.7, july 2000
[4]. Pan Hao,Hong QiI,Du Jiaqin,Pan "Comparison of 2D MESH Routing Algorithm in NOC" IEEE 2011computer society.
[5]. Wang Zhang, Ligang Hou, Jinhui Wang, Shuqin Geng, Wuchen Wu"Comparison Research between XY and Odd-Even Routing Algorithm of a 2-Dimension 3X3 Mesh Topology Network-on-Chip "2009 IEEE computer society.

Paper Type :: Research Paper
Title :: Online Shopping System
Country :: India
Authors :: Miss. Dipali Bhivgade
Page No. :: 61-63

A user module system that permits a customer to submit online orders for items and/or services from a store that serves both walk in customers and online customers. The online shopping system presents an online display of an order cut off time and an associated delivery window for item selected by the customer. The system accepts the customers submission of a purchase order for the item in response to a time of submission being before the order cut off time. The online shopping system does not settle with a credit supplier of the customer until the item selected by the customer is picked from inventory but before it is delivered. Therefore, the customer can go online and make changes to the order.............

Keyword: Introduction,Objective, Advantages, Disadvantages,, Future Scope,Conclusion, References

[1]. Abdul–Mu'min, Alhassan G. (2010). "Transaction Size Effects on Consumers' Retail Payment Mode Choice", International Journal of Retail & Distribution Management, Vol 38 (6), pp 460– 478
[2]. Adkins LaHue, M. L. and Cushman, L. M. (1998). "Time Sensitive Consumers' Preference for Concept Clustering: An Investigation of Mall Tenant Placement Strategy", Journal of Shopping Center Research, Vol 5 (1), pp 33–58.
[3]. Aggarwal, A. (2000). "Current Issues in Indian Retailing", European Retail Digest, Vol 25, pp 70–71.
[4]. Ailawadi, Kusum L., Beauchampb, J. P., Donthu, Naveen,
[5]. Gauri,Dinesh K. and Shankar, Venkatesh (2009).

Paper Type :: Research Paper
Title :: Opinion Analysis of Twitter Data Using Machine Learning Technique
Country :: India
Authors :: Bireshwar Ganguly || Devashri Raich
Page No. :: 64-72

Web based Micro blogging on informal organizations have been utilized for demonstrating opinions about certain substance in extremely short messages. Existing well known micro blogs like twitter, facebook etc, in which twitter achieves greatest measure of consideration in the field of research regions identified with item, film audits, stock trade and so forth. The examination on opinion analysis has been going for quite a while. Supposition analysis in present days turns into the serious issue in field of research and innovation. Because of step by step increment in the quantity of users on the long range informal communication sites, enormous measure of information delivers as content, sound, video and pictures.............

Keywords: Opinion mining, movie reviews, machine learning, SVM

[1]. B. Pang, L. Lee and S. Vaithyanathan, "Thumbs up: opinion classification using machine learning techniques", Proceedings of the ACL-02 conference on Empirical methods in natural language processing-Volume 10, pp. 79--86, 2002.
[2]. L. Jiang, M. Yu, M. Zhou, X. Liu and T. Zhao, "Target-dependent twitter opinion classification", Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 151--160, 2011.
[3]. C. Tan, L. Lee, J. Tang, L. Jiang, M. Zhou and P. Li, "User-level opinion analysis incorporating social networks", Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 1397--1405, 2011.