Sentiment analysis is one of the key challenges for mining online and offline user generated content. This paper focuses the reviews of college which are an important form of opinionated contents. The objective of this work is to classify every sentence's semantic orientation (e.g. positive, negative and neutral) of the reviews. This paper presents a weakly-supervised embedding model to learn the weak labels for college reviews sentiment analysis. This paper introduce the max entropy method to investigate the problem of incorporating sentiment prior knowledge to learn weak label meaningful word embeddings for sentiment analysis using R tool.

[1]. M. Mäntylä, D. Graziotin and M. Kuutila, "The Evolution of Sentiment Analysis - A Review of Research Topics, Venues, and Top Cited Papers," Oulu, Finland.

[2]. B. Liu, "Sentiment Analysis and Subjectivity," University of Illinois at Chicago, Chicago, 2010.

[3]. R. Collobert, J. Weston, L. Bottou, M. Karlen, K. Kavukcuoglu, and P. Kuksa, "Natural language processing (almost) from scratch," J. Mach. Learn. Res., vol. 12, pp. 2493–2537, 2011.

[4]. L. Qu, R. Gemulla, and G. Weikum, "A weakly supervised model for sentence-level semantic orientation analysis with multiple experts," in Proc. Joint Conf. Empirical Methods Natural Language Process. Comput. Natural Language Learn., pp. 149–159, 2012.

[5]. R. Socher, et al., "Recursive deep models for semantic compositionality over a sentiment treebank," in Proc. Conf. Empirical Methods Natural Language Process, vol. 1631, Art. no. 1642, 2013.

Computerized images are broadly utilized as a part of PC applications. Uncompressed computerized images require impressive capacity limit also, transmission data transmission. Productive image compression arrangements are ending up more basic with the ongoing development of information serious, and mixed media based web applications. The data compression has an objective to decrease the volume of vital information to speak to a specific level of data. Change coding is a well-known what's more, broadly utilized procedure in image compression. The reason of the change serves to create decor related coefficients what's more, expel repetition. Pathology laboratories produce a huge amount of computerized image sequences. The
main aim of this paper is to propose a compression algorithm which helps pathology labs to save the memory space in huge manner in very less time. This..............

Keywords: compression, image, medical, sequence.

[1]. Haddas, Coatrieus, Cozic, Bouslimi, (2017), "Joint Watermarking and Lossless JPEG- LS Compression for Medical Image
Security.", Innovation and Research in BioMedical engineering, Volume 38, Issue 4, pp. 198-206.
[2]. Manpreet Kaur, Vikas Wasson, ROI Based Medical Image Compression for Telemedicine Application, Procedia Computer Science,
Volume 70, 2015, Pages 579-585.
[3]. N. Sriraam, R. Shyamsunder, 3-D medical image compression using 3-D wavelet coders, Digital Signal Processing, Volume 21,
Issue 1, 2011, Pages 100-109.
[4]. Nader Karimi, Shadrokh Samavi, S.M.Reza Soroushmehr, Shahram Shirani, Kayvan Najarian, Toward practical guideline for
design of image compression algorithms for biomedical applications, Expert Systems with Applications, Volume 56, 2016, Pages
360-367.
[5]. Narmatha, Manimegalai, Manimurugan, (2017), "A Lossless Compression Scheme for Grayscale Medical Images Using a P2-Bit
Short Technique", Journal of Medical Imaging and Health Informatics, Volume 7, Issue 6, pp. 1196-1204.

Speech processing is an interesting area for understanding different way of communication in signal processing. Even though various features have reported in the literature of stuttering speech signal analysis, Histogram Oriented Gradient (HOG) and Spectral Histogram Oriented Gradient (SHOG) methods plays vital role in detection of stuttered word. These features are fed to classifier to segregate normal words from abnormal word. This research paper explain the process of these two enhanced features briefly

Keywords: HOG, SHOG

[1]. Anuradha R. Fukane, Shashikant L. Sahare, "Noise estimation Algorithms for Speech Enhancement in highly non-stationary
Environments", IJCSI International Journal of Computer Science Issues, Vol. 8, Issue 2, March 2011. ISSN (Online): 1694-0814.
[2]. Navneet Dalal and Bill Triggs, "Histogram of Oriented Gradient for Human Detection", Computer Vision and Pattern Recognition,
IEEE, Computer Socienty conference, Volume-1, Page 886-893, 2005..

With the advancement of web technology there is a tremendous volume of information present in the web for internet users. Nowadays millions of people are utilizing social network sites like Facebook, Twitter, Google Plus, etc. to express their emotions, opinion, share their perspectives and to interface with different sources. Social media generating a large volume of sentiment rich data in the form of tweets, status updates, comments, reviews, etc. Sentiment Analysis is significant in all fields especially in business to understand the conversations and discussions to identify the negative sentiments and turn poor experiences into good ones. This analysis classifies the type of users by analysis of their posted data on the social web sites. In some
cases,peoples express opinions in............

Keywords:Sentiment Analysis, Tweets comments, Preprocessing, Feature Extraction and Convolutional Neural Network.

[1]. Liang, P.W. and Dai, B.R., 2013, June. Opinion mining on social media data. In Mobile Data Management (MDM), 2013 IEEE
14th International Conference on (Vol. 2, pp. 91-96). IEEE.
[2]. Go, A., Bhayani, R. and Huang, L., 2009. Twitter sentiment classification using distant supervision. CS224N Project Report,
Stanford, 1(12).
[3]. Xia, R., Zong, C. and Li, S., 2011. Ensemble of feature sets and classification algorithms for sentiment classification. Information
Sciences, 181(6), pp.1138-1152.
[4]. Davidov, D., Tsur, O. and Rappoport, A., 2010, August. Enhanced sentiment learning using twitter hashtags and smileys. In
Proceedings of the 23rd international conference on computational linguistics: posters (pp. 241-249). Association for Computational
Linguistics.
[5]. Wang, H. and Castanon, J.A., 2015. Sentiment expression via emoticons on social media. arXiv preprint arXiv:1511.02556.

In the past few years, there has been a significant development in Machine Learning that can be used in various industries and research areas. Machine learning is a limb of Artificial Intelligence where its concepts introduce the core idea of teaching a computer to learn the concepts using data without being explicitly programmed. This paper focuses on elucidation of the concept and progression of Machine Learning, Machine Learning algorithms and its application in various research areas. It is fairly expected that this development of Machine Learning will grow considerably in coming years.

Keywords : Machine Learning, Artificial Intelligence, Algorithms

[1]. S. S. Shwartz, Y. Singer, N. Srebro, "Pegasos: Primal Estimated sub - Gradient Solver for SVM", Proceedings of the 24th
International Conference on Machine Learning, Corvallis, OR, 2007.
[2]. https://towardsdatascience.com/introduction-to-markov-chains-50da3645a50d
[3]. Yogesh Singh, Pradeep Kumar Bhatia & Omprakash Sangwan "A REVIEW OF STUDIES ON MACHINE LEARNING
TECHNIQUES ", International Journal of Computer Science and Security, Volume (1) : Issue (1), (2015).
[4]. Z. H. Zhou, "Ensemble Learning", National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China
[5]. V. Sharma, S. Rai, A. Dev, "A Comprehensive Study of Artificial Neural Networks", International Journal of Advanced Research
in Computer Science and Software Engineering, ISSN 2277128X, Volume 2, Issue 10, October 2012.

Internet of Things (IOT) makes changes in the world in recent days. IOT is now well developing and reduces a human effort a IOT. Nowadays, People don't care about their health due their busy schedule lifestyle. In that case of situation, IOT plays a major role to provide an effective solution through monitoring the health of the patient in hospital as well as from home. Sensors are used here to acquire the data from various health parameters and these data's are sent into the Raspberry Pi for further analysis and it is to be stored into the cloud. Stored data can be viewed through website from anywhere. This proposed system having alarm system to provide the prescribed medicine in time. It having additional features like sent an SMS or Email to the take care of the patient In order to avoid a critical situation and it also creates an optimum surroundings depending upon the patients' health. In this paper, we have discussed the monitoring of heart rate, blood pressure, respiration rate, body temperature, IR sensors..

Keywords: IOT, Raspberry Pi, Sensors, Alarm, Cloud

[1]. Ananda Mohon Ghosh; Debashish Halder; S K Alamgir Hossain,Remote health monitoring system through IoT, 5th International
Conference on Informatics, Electronics and Vision (ICIEV).
[2]. R. Kumar; M. Pallikonda Rajasekaran, An IoT based patient monitoring system using raspberry Pi, 2016 International Conference on
Computing Technologies and Intelligent Data Engineering (ICCTIDE'16)
[3]. Sarfraz Fayaz Khan, Health care monitoring system in Internet of Things (IoT) by using RFID, 2017 6th International Conference on
Industrial Technology and Management (ICITM)
[4]. Freddy Jimenez, Romina Torres; Building an IoT – aware healthcare monitoring system, 2015 34th International Conference of the
Chilean Computer Science Society (SCCC)
[5]. S. Siva1, P. Suresh, S. Seeba Merlin and R. Punidha; A Smart heart rate sensing system in the internet of Internet of Things, IJCTA, 9(9),
2016, pp. 3659-3663.

Now a days, large number of customers, on-line services and social media's are increasing day by day, so every second generating a huge amount of data in the format of unstructured. But it is not suitable for extracting particular information. Big Data technologies can be viewed as a new generation of technologies and architectures designed to extract value economically from very large volume of data by enabling high velocity capture, discovery and analysis. It surpasses the processing capacity of conventional DB systems. B ig data might be petabytes (1024 terabytes) or Exabyte(1024 petabytes) of data consisting of billions to trillions of records from different sources such as web, sales, customer care, social media, mobile data etc., Big data refers
to relatively large amounts of structured............

Keywords - BigData, Machine Learning, Block chain etc.,

[1]. "IBM What is big data? —Bringing big data to the enterprise". www.ibm.com. Retrieved 2013-08-26.
[2]. George, Lars (September 20, 2011) ―HBase: The Definitive Guide (1st ed.)‖, O'Reilly Media. p. 556. ISBN 978-1449396107
[3]. Kon stantin Shvachko et.al. ―The Hadoop Distributed File System, Yahoo! ―Sunnyvale, California USA, 978-1-4244-7153-9, 2010.
[4]. T. White, Hadoop: The Definitive Guide. O'Reilly Media, Yahoo! Press, June 5, 2009.
[5]. http://hadoop.apache.org/releases.pdf.
[6]. Bijesh Dhyani et.al. ―Big Data Analytics using Hadoop‖, International Journal of Computer Applications (0975 – 8887), 108(12):1-
5, 2014..

Machine Learning makes changes in the world in recent days. Machine Learning is now well developing and reduces a human effort. Agriculture is the art and science of growing plant and other crops for rising economic gain. However, the diseases that affect the Plant leaf have make an impact of agriculture production. The Plant leaf usually gets infected by pathogens such as bacteria, fungus and virus. In order to address the above issue a novel prediction system for earlier detection of plant leaf diseases. In that case of situation, Machine Learning plays a major role to provide an effective solution through monitoring the whether the leaf is healthy or not. Deep Learning algorithm are used here to acquire the data from various plant health parameters and these data's are stored into the cloud. Stored data can be viewed through website from anywhere. In this paper our proposed.

Keywords- Machine Learning, Deep Learning, Image

[1]. Alvaro Fuentes , Sook Yoon , Sang Cheol Kim and Dong Sun Park A Robust Deep Learning-Based Detector for Real-Time Tomato
Plant Diseases and Pests Recognition, Sensors 2017, 17, 2022; doi:10.3390/s17092022.
[2]. Andreas Kamilaris, Francesc X. Prenafeta-Boldu Deep learning in agriculture: A survey, Computers and Electronics in Agriculture
147 (2018) 70–90.
[3]. Bashir Sabah, Sharma Navdeep. Remote area plant disease detection using image processing. IOSR J Electron Commun Eng
2012;2(6):31–4. ISSN: 2278-2834.
[4]. C. C. Stearns and K. Kannappan, "Method for 2-D affine transformation of images," US Patent No. 5,475,803, 1995.
[5]. D. M. Hawkins, "The problem of over-fitting," Journal of Chemical information and Computer Sciences, vol. 44, no. 1, pp. 1–12,
2004.

Cloud computing is architecture for providing computing services through the internet on demand and pay-per-use access to a pool of shared resources namely networks, storage, servers and applications without physically acquiring them. So it saves managing cost and time for organizations. Developing an application in the cloud enables users to get their product to market quickly. Many industries, such as banking, healthcare and education are moving towards the cloud due to the efficiency of services provided by the payper- use pattern based on resources such as processing power used, transactions carried out, bandwidth consumed, data transferred, storage space occupied etc. Cloud computing architecture comprises of many cloud components, which are loosely coupled.............

Keywords - Cloud architecture, components and issues.

[1]. T. Dillon, C. Wu, and E. Chang, "Cloud Computing: Issues and Challenges," 2010 24th IEEE International Conference on Advanced Information Networking and Applications (AINA), pp. 27-33, DOI= 20-23 April 2010.
Proceedings Papers:
[2]. http://www.ijfcc.org/papers/95-F0048.pdf
[3]. http://www.worldscientificnews.com/wp-content/uploads/2017/08/WSN-863-2017-253-264-1.pdf
[4]. https://pdfs.semanticscholar.org/ca5d/86b602c4fe2625ca80ac4da6704c18f6a279.pdf

In the modern era, abundant data have become available on hand to get voluminous information. Big data points out to datasets that are not only big, but also high in variety and velocity, which makes them difficult to handle using traditional tools and techniques. It can be structured, unstructured or semi-structured, resulting in incapability of conventional data management methods. The rate of data generation is so startling, that it has induced a pressing need to implement easy and cost-effective data storage and retrieval mechanisms. Technologies such as MapReduce & Hadoop are used to essence value from Big Data. Hadoop is wellendorse, standard-based, open source software framework..............

Keywords- Big Data, Hadoop, Hive, Hadoop vs. Hive.

[1]. http://www.ijsrp.org/research-paper-1014/ijsrp- p34125.pdf
[2]. https://pdfs.semanticscholar.org/501d/814f3f83e8ca44afbd3da13792f206a16402.pdf
[3]. http://www.ijcst.com/vol74/1/11-iqbaldeep-kaur.pdf
[4]. https://www.irjet.net/archives/V3/i1/IRJET-V3I1152.pdf
[5]. https://www.infoworld.com/article/2608271/hadoop/hadoop-review-apache-hive-brings-real-time-queries-to-hadoop.html
[6]. https://www.educba.com/hadoop-vs-hive/.

Enhancing of the images is performed via the use of image enhancement process of digitally influence stored image by means of software. The major objective of this step is to procedure an image consequently with the purpose of effect is more appropriate than input image used for precise application. These methods give a huge amount of choices designed for enhancing the quality of images. However the underwater images undergo with poor quality resulting from the reduction of the propagated light, generally appropriate in the direction of combination and scattering effects. Multi-fusion underwater dehazing algorithm is introduced recently in order to eliminate the haze of underwater images collected from a camera. But still enhancing color contrast becomes difficult task............

Keywords- Image enhancement, color contrast, Contrast Limited Adaptive Histogram Equalization (CLAHE), underwater dehazing approach, underwater images, image fusion, white-balancing.

[1]. B. L. McGlamery, "A computer model for underwater camera systems", Proc. SPIE, vol. 208, pp. 221-231, Mar. 1980.
[2]. M. D. Kocak, F. R. Dalgleish, M. F. Caimi, and Y. Y. Schechner, "A focus on recent developments and trends in underwater imaging," Marine Technol. Soc. J., vol. 42, no. 1, pp. 52–67, 2008.
[3]. G. L. Foresti, "Visual inspection of sea bottom structures by an autonomous underwater vehicle," IEEE Trans. Syst., Man, Cybern. B, Cybern., vol. 31, no. 5, pp. 691–705, Oct. 2001.
[4]. A. Ortiz, M. Simó, and G. Oliver, "A vision system for an underwater cable tracker," Mach. Vis. Appl., vol. 13, pp. 129–140, Jul. 2002.
[5]. A. Olmos and E. Trucco, "Detecting man-made objects in unconstrained subsea videos," in Proc. BMVC, Sep. 2002, pp. 1–10.

Cognitive radio technology is engaging the development of Dynamic Spectrum Access (DSA) model which is envisioned to deal with the present spectrum shortage issue by empowering the contraption of new remote organizations. Cognitive gadgets have the comparable capability of CR and the network that they frame powerfully is called Cognitive Radio Ad Hoc Networks (CRAHNs). Because of predefined characteristics of wireless channels, security became a benchmark issues in CRAHN. The intention of attacks in CRAHN is not only to threaten the data, but also to reduce the network performance. The main objective of this paper is to discuss about various recent proposals and new types of attacks in CRAHN.

Keywords: - ad hoc network, attack, cognitive radio networks, routing, security

[1]. Jaime Lloret Mauri, Kayhan Zrar Ghafoor, Danda B. Rawat, and Javier Manuel Aguiar Perez, Cognitive Networks: Applications and Deployments, CRC Press, 2015, pp: 203-235.
[2]. Anil Carie, Mingchu Li, Satish Anamalamudi, Prakash Reddy, Bhaskar Marapelli, Hayat Dino, Wahab Khan, and Waseef Jamal, An internet of software defined cognitive radio ad-hoc networks based on directional antenna for smart environments, Sustainable Cities and Society, Volume 39, 2018, Pages 527-536.
[3]. Jin-Hee Cho, Ing-Ray Chen, Kevin S. Chan, Trust threshold based public key management in mobile ad hoc networks, Ad Hoc Networks, Volume 44, 2016, Pages 58-75.
[4]. Mounia Bouabdellah, Naima Kaabouch, Faissal El Bouanani, and Hussain BenAzza, Network layer attacks and countermeasures in cognitive radio networks: A survey, Journal of Information Security and Applications, Volume 38, 2018, Pages 40-49.
[5]. Muhammad Rashid Ramzan, Nadia Nawaz, Ashfaq Ahmed, Muhammad Naeem, Muhammad Iqbal, and Alagan Anpalagan, Multiobjective optimization for spectrum sharing in cognitive radio networks: A review, Pervasive and Mobile Computing, Volume 41, 2017, Pages 106-131.

Mobile Adhoc Networks (MANETs) is particularlyvulnerable to security attacks due to its characteristics. Wirelesscommunication is vital during disaster, natural climates andmilitary operation. In this paper,theyproposesecured network scheme that fuzzy logic scheme is used to detectblack-hole attack based on certificate authority and trust node toimprove the performance of network and compare with existing protocols namely,Adhoc On-demand Distance Vector (AODV) and Dynamic Source Routing (DSR) protocols with fuzzy logic. Fuzzy logic is used to detectmisbehaving node by giving certificate to only trusted node. Theproposed technique is more secure and reliable to increase the network lifetime, packet delivery ratio, throughput and
routing overhead with fixed topology size by continuously monitoring the individual nodes in the network. Network Simulator 2(NS2) is used to employ and investigation our proposed system.

Keywords- MANET, fuzzy logic, Routing Protocol,network lifetime, PDR, RO.

[1]. Perkins and Royer (2000) "The Ad-hoc On-demand Distance Vector Protocol", Ad hoc Networking, pp. 173–219, Addison-Wesley.
[2]. Adams, et al (2005) "Calculating a Node's Reputation in a Mobile Ad Hoc Network," Proc. 24th IEEE International Conference, Vol. 7, No. 9, pp. 303-307.
[3]. Sen, et al (2008) "Wireless Ad Hoc Networks; In: Chapter 17-Intrusion Detection in Mobile Ad Hoc Networks", Springer.
[4]. LathaTamilselvan and Sankaranarayanan (2008) "Prevention of Co-operative black-hole Attack in MANET" JOURNAL OF NETWORKS, Vol. 3, No. 5.
[5]. Payal and Prashant (2009) "DPRAODV: ADynamic Learning System against black-hole attack in AODVbased MANET ", International Journal of Computer Science,Vol. 2.

Association rule mining is Given a number of itemsets, find frequent subsets which are common to at least a minimum number s of the itemsets. Association rule mining are used to find rare events that are suspected to represent anomalies. In this research paper, association rule mining to find and summarize anomalous flows. Experimental results on the UCI repository datasets show that the proposed provide higher performance than the existing models. To extract anomalous flows, one could build a model describing normal flow characteristics and use the model to identify deviating flows.

Keywords - Anomaly detection, Association rule mining.

[1]. F. Silveira and C. Diot, "URCA: Pulling out anomalies by their root causes," in Proc. IEEE INFOCOM, Mar. 2010, pp. 1-9.
[2]. S. Ranjan, S. Shah, A. Nucci, M. M. Munafò, R. L. Cruz, and S.M Muthukrishnan, "Dowitcher: Effective worm detection and containment in the Internet core," in Proc. IEEE INFOCOM, 2007, pp.2541-2545.
[3]. G. Dewaele, K. Fukuda, P. Borgnat, P. Abry, and K. Cho, "Extracting hidden anomalies using sketch and non Gaussian multi resolution statistical detection procedures," in Proc. LSAD, 2007, pp. 145-152.
[4]. A. Lakhina, M. Crovella, and C. Diot,"Diagnosing network-wide traffic anomalies," in Proc. ACM SIGCOMM, 2004, pp. 219-230.
[5]. X. Li, F. Bian, M. Crovella, C. Diot, R. Govindan, G. Iannaccone, and A. Lakhina, "Detection and identification of network anomalies using sketch subspaces," in Proc. 6th ACM SIGCOMM IMC, 2006, pp. 147- 152.