2nd National Conference of Recent Trends in Computer Science and Information Technology

Paper Type :: Research Paper
Title :: A Survey on Sentimental Analysis on Social Media using Deep Learning
Country :: India
Authors :: Suhashini Chaurasia || Dr. Swati Sherekar
Page No. :: 01-04
Sentiment analysis is currently treated as a famous topic as well as in the area of research with significant applications in both industry and academia. This paper represents the importance and applications of opinion mining and sentiment analysis in social networks. The paper described the basic concepts, background, methodology, analysis and discussion as different sections of the paper. This paper reflects a survey of deep learning and sentiment analysis in social networks.

Keyword :Sentiment analysis, Deep Learning, Social Media

[1]. Archana Sonagi1, Deipali Gore, "Sentiment analysis and challenges involved A survey", International Journal of Science and Research (IJSR),vol. 5, pp 1928-1932, 2015
[2]. Zhao Jianquang , Gui Xiaolin, Zhang Xuejun, " Deep Learning for Sentiment Analysis A Survey", vol. 6,IEEE Access, pp 23253- 23260, 2017
[3]. Soujanya Poria , Erik Cambria, Alexander Gelbukh, "Aspect extraction for opinion mining with a deep convolutional neural network", Elsevier, 2016
[4]. Muhammad Zubair Asghar, Aurangzeb Khan, Shakeel Ahmad, Fazal Masud Kundi, "A review of feature extraction in sentiment analysis", Journal of Basic and Applied Scientific Research, 2014
[5]. Andreas Kanavos, Nikolaos Nodarakis, Spyros Sioutas, Athanasios Tsakalidis,Dimitrios Tsolis, Giannis Tzimas , "Large sca, le implementations for twitter sentiment classification", MDPI algorithms, pp- 1-22,2017

Paper Type :: Research Paper
Title :: Design of Data Warehouse Model using Decision tree Data Mining Tool for Target Marketing in e-Business
Country :: India
Authors :: Dr. Prashant P Yende || Dr. Pankaj Nimbalkar
Page No. :: 05-10

The data warehouse is set key information that can be used in business management.Target marketing has generated an increasing interest among academics and practitioners over the past few years. This is due to competitive market environment, advancement in technology and changing behavior of customers which are difficult to predict. Despite of numerous studies that have provided important insights into the target marketing, the understanding of this topic of growing interest and importance still remains deficient. Therefore, the objective of this paper is to provide a comprehensive framework to guide research efforts focusing on target marketing strategies in e-Business and aid practitioners in their quest to achieve target marketing success using data mining methods. The framework builds on the literature from target marketing concepts in e-Business and data mining methods that provides a systematic approach to users who have little knowledge in data mining in order to carry out effective marketing campaigns in e-Business

Keywords: Data Mining, Target marketing, Decision Tree, Data warehouse model

[1]. U. M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy, Advances in Knowledge Discovery and Data Mining, MII Press, Mento Park, 1996.
[2]. P. Van der Putten, "Data Mining in Direct Marketing Databases", Complexity and Management: A Collection of Essay, World Scientific. 1999.
[3]. R. Potharst, U. Kaymak, and W. Pijls, Neural networks for Target Selection in Direct Marketing', in K. Smith andJ. Gupta Neural Networks in Business: Techniques and Applications, Idea Group Publishing, London, 2002, pp.89 110.
[4]. C. Rygielski, J. C. Wang, and D.C. Yen, Data Mining Techniques for Customer Relationship Management, Technology in Society, 24, 2002, pp. 483-502.
[5]. C. X. Ling, and C. Li, Data Mining for Direct Marketing: Problems and Solutions, Proceedings of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-98), New York, NY, ACM, 1998, pp. 73-79.

Paper Type :: Research Paper
Title :: Comparative Study and Analysis of Various Privacy Preserving Data Mining Methods and Designing Efficient Method
Country :: India
Authors :: Miss. Shraddha. M. Dolas || Prof. Mr. Y.M. Kurwade || Dr. V.M. Thakare
Page No. :: 11-15

Privacy preserving plays vital role in designing various security related data mining applications. Protecting sensitive information in data mining has become an important issue. Data distortion or data perturbation is a critical component widely used to protect the sensitive data. This paper focused on five different techniques such as Visual crypto, Distributed SVM, Utility mining, ID3 mining over encrypted data, Pattern mining on event log data. But some problems are persisting in each method. The paper proposes the method to overcome the existing problems and the improved method "Privacy preserving decision tree learning using unrealized data sets" is proposed in this paper.

Keywords: Data mining, multiple keys, Encrypted data, Distributed system


[2]. Mohammed Z. Omer, Hui Gao "Distributed SVM data mining" International Conference on Soft Computing & Machine Intelligence, 2016.
[3]. Jerry Chun, WenshengGan "Privacy preserving utility mining" Science Direct, 2016.
[4]. Xuan Wang, Ye Li, Zoe L. Jiang "ID3 mining over encrypted data" IEEE International Conference on Embedded and Ubiquitous Computing, 2017.
[5]. Alessandro Marrella, Anna Monreale "Pattern mining on event log data" IEEE International Conference on Cloud Computing Technology and Science, 2016.

Paper Type :: Research Paper
Title :: Design of an Efficient and Robust Secret Sharing Method for Big Data Analysis
Country :: India
Authors :: Miss. Purva D. Thakare || Dr.Mrs.S.N.Kale || Dr.V.M.Thakare
Page No. :: 16-20

Big data is a phrase used to mean data sets that are too large or complex. It contains both structured and unstructured data. It becomes difficult to process data using traditional database and software techniques. Big- data can obtain large amount of individual users' sensitive data by sorting, analyzing, and mining the data. Secure sharing is a major issue. Big data demands a strong infrastructure for secure sharing. This paper is focused on five different techniques such as secure social multimedia big data sharing using a scalable JFE in TSHWT domain, Secret(N,N) threshold QR sharing approach, Verifiable secret sharing scheme using AMBTC, aggregation scheme based on secret sharing with fault tolerance and Fast secure computation based on XOR scheme. The method proposed is" secret sharing method for big data analysis using a third party auditor on hadoop storage."

Keywords: Privacy-preserving, data-confidentiality, security, encryption, cipher-text, decryption.

[1]. Conghuan Ye, Hefei ling, ZenggangXiong, Fuhao Zou Cong Liu, Fang Xu "Secure Social Multimedia Big Data Sharing Using Scalable JFE in the TSHWT Domain",ACM Trans. Multimedia Computing Communication, Vol. 12, No. 4s,61.1-61.23, Vol. 12, No. 4s,61.1-61.23.
[2]. Pei-Yu Lin" Distributed Secret Sharing Approach with Cheater Prevention based on QR Code", IEEE Transactions on Industrial Informatics , VOL. 129, 955-966, February 2011.
[3]. Kun-You Cai, Shin-Shian Wang, Pei-Feng Shiu, Chia-Chen Lin," A Verifiable Secret Sharing Scheme based on AMBTC", ACM Access , VOL. 129, 955- 966 , February 2011
[4]. Zhitao Guan, Guanlin Si, Xiaojiang Du, Peng Liu, Zijian Zhang, Zhenyu Zhou"Protecting User Privacy Based on Secret Sharing with Fault Tolerance for Big Data in Smart Grid",IEEE ICC 2017 SAC Symposium Big Data Networking Track , Vol. 12, No. 4s,61.1-61.23, 2017.
[5]. KyoheiTokita, Keiichi Iwamura "Fast Secure Computation Based on a Secret Sharing Scheme for n < 2k–1",ACM Trans. Multimedia Computing
Communication , Vol. 12, No. 4s,61.1-61.23, June 2018.

Paper Type :: Research Paper
Title :: Designing the Authentication System for DDoS Attack Detection and Prevention on Cloud Platform
Country :: India
Authors :: Abhijeetsingh S. Thakur || Dr. Mrs. S. S. Sherekar || Dr. V. M. Thakare
Page No. :: 21-24

Cloud Computing provides easy access to the end users i.e. users can access the services easily from wherever they want to without the concern about the storage, management, and cost and so on. As the numbers of users per day are increasing, threats for protecting the data residing in the Cloud is also increasing. This paper is focused on analysis of five different techniques and systems such as SD-IoT Framework, Low Rate Strategy, Three Tier Network Architecture, Network Simulation Strategy and Survey of Defense Mechanisms etc. But there are some problems that are present in each method. The problems to overcome are given in analysis and discussion. To overcome these problems, this paper proposes a new DDoS attack detection system model, so as to reduce the rate of DDoS attacks and prevent them.

Keywords: Cloud Computing, Distributed Denial of Service attack, Security, Defense, SDN.

[1]. Da Min, Lianming Zhang, Kun Yang, "A DDoS Attack Detection and Mitigation With Software-Defined Internet of Things Framework", IEEE Access, April 2018.
[2]. Massimo Ficco and FrancescoPalmieri, "Introducing Fraudulent Energy Consumption in Cloud Infrastructures: A New Generation of Denial-of-Service Attacks", IEEE, June 2017.
[3]. Akashdeep Bhardwaj, GVB Subrahmanyam, Vinay Avasthi, Hanumat Sastry, "Three Tier Network Architecture to Mitigate DDoS Attacks on Hybrid Cloud Environments", ACM, March, 2016.
[4]. Zahid Anwar and Asad Waqar Malik, "Can a DDoS Attack Meltdown My Data Center? A Simulation Study July 2014.
[5]. Saman Taghavi Zargar, James Joshi, David Tipper, "A Survey of Defense Mechanisms Against Distributed Denial of Service (DDoS) Flooding Attacks", IEEE COMMUNICATIONS SURVEYS & TUTORIALS 2013.

Paper Type :: Research Paper
Title :: Comparative Analysis of Various Issues and Challenges for Position Based Routing Protocols in Manet and Designing Efficient Protocol
Country :: India
Authors :: Miss. Dipa P. Bodkhe || Dr. Mr. R. N. Khobragade || Dr. V. M. Thakare
Page No. :: 25-29

Mobility of MANET have been still research area in mobile computing and in wireless network with lots of mobility algorithms to design the efficient mobility model. This paper is focused on analysis of five different techniques such as Minimizing Communication Interference for Stable Position-Based Routing in Mobile Ad Hoc Networks, Location Based Transmission using a Neighbour Aware with optimized Extended Inter-Frame Spacing (EIFS) for Ad Hoc Networks MAC ,Energy Efficient Multipath Routing Protocol for Mobile Ad-Hoc Network Using the Fitness Function , A review of forest fire surveillance technologies: Mobile ad-hoc network routing protocols perspective............

Keywords-Mobile ad hoc network, interference, overhead, throughput, transmission power, routing protocols and energy efficient.

[1]. AbedalmotalebZadina, Thomas Fevens,"Minimizing Communication Interference for Stable Position-Based Routing in Mobile Ad Hoc Networks",Procedia Computer Science 52,460 – 467,2015.
[2]. Jims Marchang, Bogdan Ghita, David Lancaster," Location based transmission using a neighbour aware with optimized EIFS MAC for ad hoc networks", IEEE,VOL. 4, 8053-8064, 2017.
[3]. AqeelTaha, RaedAlsaqour, Mueen Uddin, MahaAbdelhaq,TanzilaSaba,"Energy Efficient Multipath Routing Protocol For Mobile Ad-Hoc Network Using The Fitness Function",IEEE VOL 5, 10370-10381,2017.
[4]. Fahad Taha AL-Dhief , NaseerSabri , S. Fouad , N.M. Abdul Latiff , Musatafa Abbas AbboodAlbader,"A Review Of Forest Fire Surveillance Technologies: Mobile Ad-Hoc Network Routing Protocols Perspective", IEEE,VOL. 4, 8053-8064,2016.
[5]. Kazy Noor E AlamSiddiquee, FariaFarjana Khan, Karl Andersson , Mohammad Shahadat hossain,"Optimal Dynamic Routing Protocols For Argo-Sensor Communication In MANETs" ,IEEEVOL. 4, 8053-8064, 2017.

Paper Type :: Research Paper
Title :: Dynamic IoT Multiple Data Streamlining using Croston's Intermittent Demand Forecasting Method
Country :: India
Authors :: Miss. ReshmaNargis Mohammad Siddique || Dr.V.M.Thakare
Page No. :: 30-33

The objective of providing a never ending delightful experience to the customer is broadly characterized by the company and focus on increasing the reach, setting industry benchmarks & ensuring low cost of ownership. This paper is focused on analysis of five different techniques such as, an effective handling of secure data stream, three hierarchical levels of big-data market model over multiple data sources, ubiquitous transmission of multimedia sensor, adaptive clustering for dynamic IoT data streams, secure data sharing and searching at the edge of cloud-assisted. But some problems exist in streams of data. So to overcome these problems, paper proposes aCroston's method. Croston's method is mostly used to predict inventory demand when it is intermittent. Accurate demand forecasting is vital importance in inventory management.

Keywords-Internet of Things, Croston's method, Adaptive clustering, stream processing, data collection, big data.

[1]. Jaejin Jang, Im.Y Jung, Jong Hyuk Park, "An effective handling of secure data stream in IoT",ScienceDirect, VOL. 68, 811-820, MAY 2017.
[2]. Busik Jang, Sangdon Park, Joohyung Lee, Sang-Geun Hahn, "Three hierarchical levels of big-data market model over multiple data sources for internet of things", IEEE Access,VOL No. 6, 31269 - 31280, June 2018.
[3]. Gang Xu, Edith C.H. Ngai and Jiangchuan Liu, "Ubiquitous Transmission of Multimedia Sensor Data in Internet-of-Things", IEEE Internet of Things Journal, VOL 5, NO. 1, 403-414, FEBRUARY 2018.
[4]. Daniel Puschmann, PayamBarnaghi and Rahim Tafazolli,"Adaptive Clustering for Dynamic IoT Data Streams", IEEE INTERNET OF THINGS JOURNAL, VOL 5, NO. 1, 403-414, October 2016.
[5]. Muhammad BaqerMollah and Md. AbulKalam Azad, Athanasios Vasilakos, "Secure data sharing and searching at the edge of cloud-assisted internet of things", IEEE Cloud Computing,VOL. 04, NO. 01, 34-42, February 2017.

Paper Type :: Research Paper
Title :: Data Security Model in Cloud Computing for Privacy and Risk Management
Country :: India
Authors :: Mr. H. D. Kale || Dr. V. M. Thakare
Page No. :: 34-39

Cloud storage technology has been paid additional and additional attention as an rising network storage technology that is extended and developed by cloud computing concepts. Cloud computing setting depends on user services like high-speed storage and retrieval provided by cloud ADP system. Meanwhile, knowledge security is a crucial drawback to resolve desperately for cloud storage technology. knowledge security is taken into account because the constant issue leading towards a hitch within the adoption of cloud computing. knowledge privacy, Integrity and trust problems area unit few severe security considerations resulting in wide adoption of cloud computing.............

Keywords-Cloud Computing, Cloud storage technology, Data security, Security Assessment Model.

[1]. Bernd Grobauer, Tobias Walloschek, and ElmarStöcker, "Understanding Cloud Computing Vulnerabilities," Copublished By The Ieee Computer And Reliability Societies ,MARCH/APRIL 2011.
[2]. Yuan Zhang ,Chunxiang Xu ,Shui Yu, Hongwei Li, "SCLPV: Secure Certificateless Public Verification for Cloud-Based Cyber- Physical-Social Systems Against Malicious Auditors," IEEE Transactions On Computational Social Systems, VOL. 2, NO. 4, DECEMBER 2015.
[3]. LIN Guoyuan, WANG Danrul, BIE Yuyul, LEI Min," MTBAC: A Mutual Trust Based Access Control Model in Cloud Computing",China Communications· April 2014.
[4]. Dan Gonzales,Jeremy M. Kaplan, Evan Saltzman, Zev Winkelman, and Dulani Woods "Cloud-Trust—a Security Assessment Model for Infrastructure as a Service (IaaS) Clouds",IEEE Transactions On Cloud Computing, VOL. 5, NO. 3, July-September 2017.
[5]. Jianan Hong, KaipingXue,"DAC-MACS: Effective Data Access Control for Multiauthority Cloud Storage Systems"/Security Analysis of Attribute Revocation in Multiauthority Data Access Control for Cloud Storage Systems," IEEE Transactions On Information Forensics And Security, Vol. 10, No. 6, June 2015.

Paper Type :: Research Paper
Title :: Big Data Analytics of SVM and Naïve Bayes Algorithm for Multiple Datasets
Country :: India
Authors :: Madhura A. Chinchmalatpure || Dr. Mahendra Dhore
Page No. :: 40-43

Big data is a collection of large datasets. Big data is structured, unstructured, semi-structured or heterogeneous in nature. For analyzing data, we used regression and machine learning as a statistical Technique. It shows the statistical relationship between two or more variables. The statistical technique can be evaluated for the predictive model based on the requirement of the data. This paper deals with two machine learning techniques Support vector machine and Neive Bayes applied on two databases, we create model using machine learning techniques which are compared using the training dataset in order to see correct model for better prediction and accuracy applied on database.

Keywords: Big Data Analysis, regression technique, machine learning technique

[1]. Gemson Andrew Ebenezer J.1 and Durga S.2,‖ BIG DATA ANALYTICS IN HEALTHCARE: A SURVEY‖ ARPN Journal of Engineering and Applied Sciences ©2006-2015 Asian Research Publishing Network (ARPN). All rights reserved. VOL. 10, NO. 8, MAY 2015, ISSN 1819-6608
[2]. Alexandra L'Heureux, Katarina Grolinger, Hany F. ElYamany, Miriam A. M. Capretz,―Machine Learning with Big Data: Challenges and Approaches‖, DOI 10.1109/ACCESS.2017.2696365, IEEE Access
[3]. Guoqiang Peter Zhang, ―Neural Networks for Classification: A Survey‖, IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART C: APPLICATIONS AND REVIEWS, VOL. 30, NO. 4, NOVEMBER 2000
[4]. Wilbert Sibanda, Philip Pretorius,‖Artificial Neural Networks- A Review of Applications of Neural Networks in the Modeling of HIV Epidemic‖, International Journal of Computer Applications (0975 – 8887) Volume 44– No16, April 2012
[5]. Shrwan Ram Dr. N.C. Barwar,‖A Comparative Study of Multilayer Perceptron, Radial Basis Function Networks and logistic Regression for Healthcare Data Classification‖, Volume 3, Issue 3, March -2016

Paper Type :: Research Paper
Title :: A Review of Block chain Technology in Cryptography
Country :: India
Authors :: Dr. (Mrs) RadhaPimpale
Page No. :: 44-49

The blockchain technology has great prospective in cryptography. It is facing a number of technical challenges such as authentication or authorization and security in cryptography. In this paper, review has been taken on Blockchain technology, which offers new tools for authentication and authorization in the digital world, it create new digital relationships. Blockchain is a technology to create and maintain a cryptographically secure, shared, and distributed ledger (a database) for transactions. Blockchain brings trust, accountability, and transparency to digital transactions. When we used block chain technology, A block contains a timestamp with reference to the previous block, the transactions and the computational problem that had to be solved before the block went on the Blockchain. Rigorous encryption and data distribution protocols on a network, can ensure that the information will remain safely and out of the reach of hackers.

Keywords: Block chain technology, digital transaction, Private Key, Public Key, Block

[1]. https://www.coindesk.com/information/how-does-blockchain-technology-work
[2]. https://www.pluralsight.com/guides/blockchain-architecture
[3]. https://spectrum.ieee.org/computing/networks/do-you-need-a-blockchain
[4]. Zibin Zheng1, Shaoan Xie1, Hongning Dai2, Xiangping Chen4, and Huaimin Wang3, "An Overview of Blockchain Technology: Architecture, Consensus, and Future Trends", 2017 IEEE 6th International Congress on Big Data, 978-1-5386-1996-4/17 $31.00 © 2017 IEEE, DOI 10.1109/BigDataCongress.2017.85
[5]. https://jaxenter.com/cryptographic-hashing-secure-blockchain-149464.html

Paper Type :: Research Paper
Title :: Analysis of various fault prediction models for software and evaluation of its performance, validation
Country :: India
Authors :: Miss. S. V. Athawale || Dr. V. M. Thakare
Page No. :: 50-54

Software systems are being utilized to solve or model increasingly sophisticated and complex problems in a variety of application domains. Software fault prediction has been one of the active parts of software engineering, but to date, there are few test cases prioritization technique using fault prediction. There are many models are developed for fault prediction in software development lifecycle. In this paper the analysis of various fault prediction models is proposed. It analyses various software faults prediction models and does the evaluation of its performance, validation.

Keywords:Software fault prediction, feature selection, classification, software metric selection

[1]. Lei Xiao, Huaikou Miao, Weiwei Zhuang, Shaojun Chen, "An Empirical Study On Clustering Approach Combining Fault Prediction For Test Case Prioritization", IEEE Computer Society,5090-5507, Pg No. 815 - 820, MAY 2017.
[2]. Yan Gao, Chunhui Yang, Lixin Liang, "Software Defect Prediction based on Geometric Mean for Subspace Learning",IEEE, 4673- 8979, Pg No. 225-229, AUGUST 2017.
[3]. Lin Chen, Bin Fang, Zhaowei Shang, "Software Fault Prediction Based On One-Class SVM", International Conference on Machine Learning and Cybernetics, 5090-0390, Pg No.1003-1008, JULY, 2016.
[4]. Shou-Yu Lee, Dong Li, Yihao Li, "An Investigation of Essential Topics on Software Fault-Proneness Prediction", International Symposium on System and Software Reliability (ISSSR), 5090-5563, Pg No. 113-119, AUGUST, 2016.
[5]. C. Jin, S.-W. Jin, J.-M. Ye, "Artificial neural network-based metric selection for software fault-prone prediction model", IET Software,Vol. 6, Iss. 6, Pg No. 479–487, MAY 2012

Paper Type :: Research Paper
Title :: Machine Learning: Some Insights
Country :: India
Authors :: Prof. RupaliChikhale
Page No. :: 55-58

Machine learning is a subfield of AI (artificial Intelligence). Main aim of machine learning is to understand the structure of data and fit that data into some models that can be easily understood and utilized by people. In traditional computing, algorithms are sets of explicitly programmed instructions used by computers to calculate or problem solve. Machine learning algorithms instead allow for computers to train on data inputs and use statistical analysis in order to output values that fall within a specific range. Because of this, machine learning facilitates computers in building models from sample data in order to automate decision-making processes based on data inputs.

Keywords: Big data, supervised learning, unsupervised learning, Clustering AI.

[1]. https://www.digitalocean.com/community/tutorials/an-introduction-to-machine-learning
[2]. https://dzone.com/articles/5-predictions-about-the-future-of-machine-learning
[3]. https://towardsdatascience.com/machine-learning/home
[4]. https://www.lumagate.com/news/the-advantages-of-machine-learning
[5]. https://www.sas.com/en_in/insights/analytics/machine-learning.html

Paper Type :: Research Paper
Title :: Artificial Neural Network – An Overview
Country :: India
Authors :: Girish S. Katkar || Madhur V. Kapoor
Page No. :: 59-63

Today, we are living in the exciting time where technology is changing day by day.The purpose of paper is to study the recent trends emerging in the field of artificial neural over Digital Computer and Human Brain.Artificial Neural Networks are electronic models based on the neural structure of the brain.Neural networks are attractive since they consist of many neurons, each of the neurons processes information separately and simultaneously. Artificial neural network is most popular in the field of pattern classification or recognition, linear filtering problems, system identification, process control..........

Keywords: Artificial Neural Networks, Hybrid Neural Network, Mesh Architecture

[1]. Antognetti, P. and Milutinovic, V., "Neural Networks: Concepts, Applications, and Implementations (Eds.)", vol. I-IV, Prentice Hall, Englewood Cliffs, NJ., (1991).
[2]. Anderson, J.A. and Rosenfeld, E., (eds.), "Neurocomputing: Foundations of Research." MIT Press, Boston, MA, (1988).
[3]. Robert,H.N., "Neurocomputing", Addison – Wesley, ISBN 0-201-09255-3, (1990).
[4]. Stanely and Jeannette, "Introduction to Neural Networks", Californian Scientific Software, (1988).
[5]. Goldberg, D., "Genetic Algorithms in Search, Optimization, and Machine Learning Reading", MA: Addison-Wesley Publishing Company, Inc., (1989).

Paper Type :: Research Paper
Title :: Short-Text Sentiment Analysis by Context-Based Regularization Method
Country :: India
Authors :: Miss. Sneha P. Jagtap || Dr. V. M. Thakare
Page No. :: 64-67

Sentiment analysis is an important task in natural language processing, which has promises great value to areas of interests such as business, politics and other fields. The prevalence of the internet has caused people to prefer expressing their opinion and sentiment on the Internet via methods such as tweeting on social media and commenting on products.In this paper, we propose a context-based regularization classification method for short text sentiment analysis. Specifically, we use contextual knowledge obtained from the data to improve performance of the sentiment classification. In this paper, the contextual knowledge includes two parts: word-sentiment knowledge and word-similarity knowledge..................

Keywords: Short texts, Text mining, text analysis, sentiment analysis, regularization, contextual knowledge.

[1]. Zhang Xiangyu , Li Hong, Wang Lihong" A Context-Based Regularization Method for Short-Text Sentiment Analysis", IEEEInternational Conference, NOVEMBER 2015.
[2]. International Conference, "A Machine Learning Approach for Identifying Disease-Treatment Relations in Short Texts", IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,, VOL. 23, NO. 6, JUNE 2011.
[3]. Tao Jiang, Bin Yuan, Jing Jiang and Hongzhi Yu "Short Text Sentiment Entropy Optimization Based on the Fuzzy sets", 12th Web Information System and Application Conference, 2015.
[4]. Yuling Chen Zhi Zhang, "Research on text sentiment analysis based on CNNs and SVM",13th IEEE Conference on Industrial Electronics and Applications (ICIEA), 2018.
[5]. Lu Ma, Dan Zhang, "Sentiment Orientation Analysis of Short Text Based on Background and Domain Sentiment Lexicon Expansion", 5th International Conference on Computer Science and Network Technology (ICCSNT), 2016.

Paper Type :: Research Paper
Title :: A Security Aspects In Cloud Computing
Country :: India
Authors :: Dr. Girish Katkar || Ms. Punam Naphade
Page No. :: 68-71

Cloud computing is considered as one of the major shifts in contemporary computing. Cloud Computing is a paradigm that focuses on sharing data and computations over a scalable network of nodes. The three fundamental classifications are often referred to as the SPI model where SPI refers to Software, Platform And Infrastructure ( As a Service) respectively.These three major parts construct the bulk of services in cloud computing environments Although the benefits of these services are obvious, widespread adaptation of cloud computing depends on properly addressing the relevant security challenges. Many of the attacks on cloud computing are related to their distributed and shared environment............

Keywords: Cloud Computing, Security, Service, Client, Service Provider

[1]. "Security Architecture of Cloud Computing", V.KRISHNA REDDY 1, Dr. L.S.S.REDDY, International Journal of Engineering Science and Technology (!JEST), Vol. 3 No. 9 September 2011.
[2]. 'The Effective and Efficient Security Services for Cloud Computing ", Sambh ajiSarode, Deepali Giri, Khushbu.
[3]. Chopde, International lournal of Computer Applications (0975 - 8887) Volume 34- No.9, November 2011.
[4]. "Cloud Computing Security" Danish Jamil Hassan Zaki, International Journal of Engineering Science and Technology (IJEST), Vol. 3 No. 4 April 201 I
[5]. Peter Mell, and Tim Grance, "Draft NIST Working Definition of Cloud Computing," 2009

Paper Type :: Research Paper
Title :: Light CNN For Deep Face Representation Using Multilevel Residual Networks
Country :: India
Authors :: Kiran Singla || Prakash Mohod
Page No. :: 72-76

Deep convolutional neural networks have shown remarkable performance in the field of face recognition tasks in recent years. The networks are continuously growing larger to better fit large amount training data thus increasing the complexity and vanishing gradient problem. It normally takes a lot of time and more computational power to train these deeper neural networks. This paper presents a Light CNN with multilevel residual network(L-MRN) to learn a compact embedding on the large scale face dataset without fine tuning. This network is designed to obtain better performance from Light CNN without increasing the number of parameters and computational costs.

Keywords: Convolutional Neural Network, Face Recognition, Residual network, Light CNN, RoR

[1]. X. Wu, R. He, Z. Sun and T. Tan, "A Light CNN for Deep Face Representation With Noisy Labels," in IEEE Transactions on
Information Forensics and Security, Nov. 2018.
[2]. Y. Bengio, P. Simard, and P. Frasconi. "Learning long-term dependencies with gradient descent is difficult". IEEE transactions on
neural networks, 5(2):157–166, 1994.
[3]. Veit, M. J. Wilber, and S. Belongie, "Residual networks behave like ensembles of relatively shallow networks". In Advances in
Neural Information Processing Systems, pages 550–558, 2016.
[4]. Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel. "Backpropagation applied to
handwritten zip code recognition". Neural computation, 1(4):541–551, 1989

Paper Type :: Research Paper
Title :: Handwriting Recognization
Country :: India
Authors :: Najeefa Nasreen || Prof. Rupali Chikhale
Page No. :: 77-80

Handwriting recognition has been an active and challenging area of research. Handwriting
recognition system plays a very important role in today's world. Handwriting recognition is very popular and
computationally expensive work. At present time it is very difficult to find correct meaning of hand written
documents. There are many areas where we need to recognize the words, alphabets and digit. There are many
application postal addresses, bank cheque where we need to recognize handwriting. This review paper will
focus on different technique which is used on handwriting recognition. There are basically two different types of
handwriting recognition system online and offline handwriting recognition. There are many approaches are
present for offline handwriting recognition system...............

Keywords:Handwriting Recognition, Neural Network, Matlab

[1]. https://citeseerx.ist.psu.edu/viewdoc/download?doi=