iosr-JCE   Volume-19 ~ Issue-6 ~ Nov-Dec 2017

Abstract: Using word class-based features improves the performance of natural language processing tasks based on factual observation that decline the sum of parameter magnitudes. In this paper, we explore the sequel of the word class-based features focusing on NLU tasks and indicate that the performance improvements could be attributed to the standardize effect of the class-based features. We show that class-based features extracted from different data sources using alternate word clustering methods can individually impart to the performance gain. We analyzed the actual basis of features improve the model accuracy and showed the connection with shrinkage in the model size. Since the proposed features are generated in validation of task independence on different classification and sequence tagging tasks .

Keywords: Natural Language Understanding, Standardize, Sequence Tagging Tasks, Word Class-Based Features.

[1]. P. Xu and R. Sarikaya, "Joint intent detection and slot filling with convo- lutional neural networks," Proc. IEEE ASRU, Olomouc: Czech Republic, 2013, pp. 78–83.
[2]. Asli Celikyilmaz, IEEE, Ruhi Sarikaya, IEEE, Minwoo Jeong, IEEE, and Anoop Deoras, IEEE,"An Empirical Investigation of Word Class-Based Features for Natural Language Understanding".
[3]. A. Deoras and R. Sarikaya, "Deep belief network based semantic taggers for spoken language understanding," Proc. Interspeech, Lyon: France, 2013.
[4]. R. Sarikaya, S. F. Chen, B. Ramabhadran, "Shrinkage based features for natural language call routing," Proc. Interspeech, Florence: Italy, Aug. 2011.
[5]. S. F. Chen, "Shrinking exponential language models," Proc. HLT- NAACL, Boulder: CO, USA, 2009

Abstract: In this study, a method for retrieving desired frame has been proposed in short, plain, fast and without missing part from video.The number of videos is increasing due to increased multimedia tools, social media and advancing technology.It is difficult to retrieve the request because of the increase in numbers.Video shot cut detection is focused to make this a little easier.Fast and accurate determination of video shot cut detection is an important step.As known, the videos consist of frames.Video shot cut detection was determined using the differences between the frames..............

Keywords: shot cut detection, video, block-based, statistic, feature extraction.

[1]. Liu, Fang, and Yi Wan. "Improving the video shot boundary detection using the HSV color space and image subsampling." Advanced
Computational Intelligence (ICACI), Seventh International Conference on. IEEE, 2015.
[2]. Mishra, Ravishankar, S. K. Singhai, and Mukesh Sharma. "Comparative study of block matching algorithm and dual tree complex
wavelet transform for shot detection in videos." Electronic Systems, Signal Processing and Computing Technologies (ICESC),
International Conference on. IEEE, 2014.
[3]. Sowmya, R., and R. Shettar. "Analysis and verification of video summarization using shot boundary detection." Am Int J Res
SciTechnolEng Math 3.1: 82-86, 2013.
[4]. Lu, Zhe-Ming, and Yong Shi. "Fast video shot boundary detection based on SVD and pattern matching." Image Processing, IEEE
Transactions on 22.12: 5136-5145, 2013.
[5]. Zajić, Goran J., Irini S. Reljin, and Branimir D. Reljin. "Video shot boundary detection based on multifractal analisys." Telfor Journal
3.2: 105-110, 2011..

Abstract: Many companies start using Hadoop for advanced data analytics over large datasets. While a traditional Hadoop cluster deployment assumes a homogeneous cluster, many enterprise clusters are grown incrementally over time, and might have a variety of different servers in the cluster. The nodes' heterogeneity represents an additional challenge for efficient cluster and job management. Due to resource heterogeneity, it is often unclear which resources introduce inefficiency and bottlenecks, and how such a Hadoop cluster should be configured and optimized. In this work1, we explore the efficiency and performance accuracy of the boundsbased performance model for predicting the Map Reduce job completion times in heterogeneous Hadoop clusters. We validate the accuracy of the proposed performance model using a diverse set of 13 realistic applications and two different heterogeneous.........

Keywords:Map Reduce, heterogeneous clusters, performance modeling, efficiency

[1]. F. Ahmad et al. Tarazu: Optimizing MapReduce on heterogeneous clusters. In Proc. of ASPLOS, 2012.
[2]. Apache. Capacity Scheduler Guide, 2010.
[3]. J. Dean and S. Ghemawat. MapReduce: Simplified Data Processing on Large Clusters. Communications of the ACM, 51(1), 2008.
[4]. H. Herodotou, F. Dong, and S. Babu. No one (cluster) size fits all: Automatic cluster sizing for data-intensive analytics. In Proc. of
ACM Symposium on Cloud Computing, 2011.
[5]. H. Herodotou, H. Lim, G. Luo, N. Borisov, L. Dong, F. Cetin, and S. Babu. Starfish: A Self-tuning System for Big Data Analytics.
In Proc. of 5th Conf. on Innovative Data Systems Research (CIDR), 2011..

Abstract: Search engines like Google and Yahoo! that allow the users to search for documents on the World Wide Web. In Search engines the user has to check each and every document to get useful answer to the question and it is a time consuming process. The Question Answering (QA) system reduces the search time to get exact answer to the question. Question Answering system is an important research area in information retrieval. Research on the area of Question Answering system started in the year 1960 and present lot of Question Answering systems have been developed. Question Answering system combines the research from different domains like Natural Language Processing, Artificial Intelligence, Information Retrieval and Information extraction. The objective of question answering........

Keywords: Information Retrieval, Natural Language Processing, Question Answering System.

[1]. Waheeb Ahmed, Babu Anto P, Arabic Question Answering System Based On Data Mining, International Journal Of Scientific & Technology, 6, 2, February 2017,237-239.
[2]. Nabeel Neamah, Saidah Saad, Question Answering System Using Similarity And Classification Techniques, International Journal of Computer Systems, 03,07, July, 2016,542-548
[3]. Amit Mishra, Sanjay Kumar Jain, A survey on question answering systems with classification, Journal of King Saud University – Computer and Information Sciences , 28, 2016 , 345–361.
[4]. Gursharan Singh Dhanjal, Sukhwinder Sharma, Advancements In Question Answering Systems Towards Indic Languages, International Journal of Research in Computer Science, 5, 1,2015,15-26
[5]. Ajith Kumar, Khillare, Namrata Mahender, Question Answering System, Approaches and Techniques: A Review, International Journal of Computer Applications, 141, 3, May 2016, 34-39.

Abstract: Energy minimization in Bio-molecular system is an intensive application in Protein Structure Prediction (PSP). Traditional methods for reducing energy such as The Conjugate gradient method and Steepest descent method converge only local energy minima which ara highly reliant on set the parameter for calculation in initial stage. In this paper we put forward a modified PSO (DIWPSO) with control parameter D which choose best Inertia Weight strategies for energy minimization in homologous protein structure, among four best Inertia weight strategies. The proposed approach (DIWPSO) significantly improvement to search deeper energy minima and find out global energy minimum. It is found that in result analysis, proposed algorithm gives better result with regard to rate of.........

Keywords: Particle swarm optimization, Inertia weight strategies, Protein Structure, Energy Minimization, Hybridization, Convergence

[1]. R. Eberhart and J. Kennedy. A new optimizer using particle swarm theory. In Micro Machine and Human Science, 1995. MHS'95.,Proceedings of the Sixth International Symposium on, pages 39–43. Ieee, 1995.
[2]. Y. Shi and R. Eberhart. A modified particle swarm optimizer. In Evolutionary Computation Proceedings, 1998. IEEE World Congress on Computational Intelligence., The 1998 IEEE International Conference on, pages 69–73. IEEE, 1998.
[3]. JC Bansal, PK Singh, Mukesh Saraswat, Abhishek Verma, Shimpi Singh Jadon, and Ajith Abraham. Inertia weight strategies in particle swarm optimization. In Nature and Biologically Inspired Computing (NaBIC), 2011 Third World Congress on, pages 633–640. IEEE, 2011.
[4]. M. H. Hao and H. A. Scheraga. How optimization of potential functions affects protein folding. Proceedings of the National Academy of Sciences, National Academy of Sciences Publication, 93(10):4984– 4989, 1996.
[5]. K. Koretke, Z. Luthey, and P. G. Wolynes. Self-consistently optimized energy functions for protein structure prediction by molecular dynamics. Proceedings of the National Academy of Sciences, National Academy of Sciences Publication, 95(6):2932–2937, 1998...

Abstract: In This section explains some basic concepts such as Object-oriented programming, objects, database system, and object-oriented database. Also there is some explanations of the basic object-oriented modeling .

Keywords: complex objects, object identity, classes, attributes, behaviors, encapsulation, inheritance, overriding behaviors, late binding, and naming

[1] Database Management Systems Revisited, An Updated DACS State-of-the-Art Report. Prepared by: Gregory McFarland, Andres Rudmik, and David Lange Modus Operandi, Inc, 1999.
[2] Cattell, R.G.G., Object Data Management: Object-Oriented and Extended Relational Database Systems. Massachusetts: Addison-Wesley, 1997.
[3] C. J DATE An Introduction to Database System – 7th ed, Addison Wesley, 2005.
[4] Database System Manifesto "Malcolm Atkinson" http://www.cs.cmu. edu/People/clamen/OODBMS/Manifesto/htManifesto/Manifesto.html
[5] Elisa Bertino and Lorenzo: Object Database Systems: Concepts and Architectures. Reading, Mass.: Addison-wesley (1993)..

Abstract: Automated Medical image Analysis is a most challenging interdisciplinary research field. From past decades enormous research work is ongoing in the field of Computer vision and Pattern Recognition [PR] for the development robust algorithms for computerized diagnosis. The advanced computational intelligence based algorithms has a significant potential for faster and accurate clinical diagnosis, surgical planning and have paved the way for a new digital era of Quantitative analysis. Computerized clinical diagnosis methods also has substantial implications for improved clinical care, provide diagnostic second opinions, prognosis especially for Medical Professionals practicing in rural areas. With an increasing research on better algorithms for quantitative analysis, it is important.........

Keywords: Deeplearning, Convolutional Neural Network, Active contour,Texture Analysis naming

[1]. Barbu, Tudor. "Automatic Moment-Based Texture Segmentation."Development 11848 (2013): 9996878.
[2]. C. Xu and J. L. Prince, "Snakes, shapes, and gradient vector flow".IEEE Transactions on Image Processing, vol. 7, no. 3, pp. 359–369, 1998. [Online; accessed 3-February-2011]
[3]. Dettori, Lucia, Alia Bashir, and Julie Hasemann. "Texture classification of normal tissues in computed tomography using Gabor filters." Medical Imaging. International Society for Optics and Photonics, 2007.
[4]. Drakopoulos, Kimon, and Petros Maragos. "Active contours on graphs: Multiscale morphology and graphcuts."IEEE Journal of Selected Topics in Signal Processing 6.7 (2012): 780-794.
[5]. Dvořák P, Bartušek K, Kropatsch WG, Smékal Z. Automated Multi-Contrast Brain Pathological Area Extraction from 2D MR Images. Journal of applied research and technology. 2015 Feb 28;13(1):58-69...

Abstract: This system is based on integration of web technology and wearable sensor technology that provide a web interface between the doctor and the patient for communication. This system is very helpful in diagnosing and treating the patient online and can solve the issue to a great extent for the people living in rural areas. The doctor receives an alert message once any incident is uploaded. In addition this system will help the user for searching the specialist doctor, making an appointment and follow up electronically. The patient history can be retrieved easily. A case study about incident reporting in rural areas is incorporated. User can manage and take care of sufferers related to common problems as well as age-related diseases such as diabetes, heart disease etc. in the rural areas. This will save.......

Keywords: Wearable sensor, online diagnosis, Remote areas, ASP.Net, C#, SQL Server, JQuery, CSS and Ajax.

[1]. S. Meystre, The current state of tele monitoring: a comment on the literature, Telemedicine Journal & e-Health, 11(1), 2005, pp.63–69.
[2]. H. S. Ng, M. L. Sim, C. M. Tan, and C. C. Wong, Wireless technologies for telemedicine, BT Technology Journal, 24(2), 2006, pp.130–137.
[3]. G. Asada, M. Dong, T.S. Lin, F. Newberg, G. Pottie, W.J. Kaiser, H.O. Marcy, Wireless, Integrated Network Sensors: Low Power Systems on a Chip, In Proceedings of the 1998 European , Solid State Circuits Conference.
[4]. Korhonen I., Parkka J., Van Gils M. Health Monitoring in the Home of the Future, IEEE ,Engineering in Medicine and Biology
Magazine, 22(3), 2003 pp. 66-73.
[5]. Millan J., Park S.-E., Kiefer S. and Meyer J-U. TOPCARE-Implementation of a Telematic Homecare Platform in Cooperative Health Care Provider Networks, The Second Joint EMBS/BMESConference, 2002, pp. 1869-1870.

Abstract: As the world is moving towards automation, in order to fit on the same page, UTLP based automatic toll tax collection system using RFID technology have been developed. The problems faced in the current scenario are, the total work is being carried out manually, the amount of time spent in the toll by a traveller is comparatively more, the digital payments are not involved in the system. To tackle these issues, we have developed a system which makes everything simpler by incorporating the RFID technology in ULK kit. The proposed system can be operated without a man power and makes the system to work faster and in an efficient manner. The main challenge in this system is that, every vehicle should be fitted with a RFID tag which is quite complex to implement in a large scale.

Keywords: Automation, RFID, ULK,UTLP.

[1]. B.Ponmalathi, P.Rajeswari, M.Shenbagapriya,R.Shanmugasundaram ,"Health Monitoring System for Soldiers using UTLP Kit" International Journal of Innovative Research in Science Engineering and Technology Vol. 4, Special Issue 6, May 2015.
[2]. Satyasrikanth P, Mahaveer Penna, Dileep Reddy Bolla "Automatic Toll Collection System Using Rfid" International Journal of Computer Science and Mobile Computing, Vol.5 Issue.8, August- 2016, 247-253
[3]. Alberto Carini and Silvia Malatini., "Automated Toll Plaza System using RFID", IEEE Transactions on signal Processing,Vol.16,pp.1558-1563,2008. Bram Cornelis, Simon Doclo, Tim Van dan Bogaert Marc Moonen, Fellow and Jan Wouters., "RFID Based Toll Deduction System", IEEE Transactions on Signal Processing, Vol.18, pp.1452-1458, 2010.
[4]. Das D.P, Panda,G. and Kuo,S.M., "Research Trends in RFID Technology", IEEE Transactions on Signal Processing, Vol.15 No.8, pp.1434- 1446, 2007..

Abstract: In tree based topology each and every nodes are participating on communication with other nodes. So
it is major challenge to secure the data transmission between the nodes in the network as many types of attacks
are generated in between the communication. Byzantine attack is one of the most important security thread as it
interrupt the communication of nodes in the network and behave like a innocent nodes while participating
normally. In Byzantine attack compromisation of nodes takes place in that condition it is very difficult to detect
the innocent and malicious nodes, with the byzantine nodes many other attacks are deployed as Blackhole
attack, wormhole attack, gray-hole attack, flood rushing attack, sinkhole attack etc. Routing protocols helps to
provide the way through which......

Keywords: Byzantine Attack, Distribution Detection, Tree Topology, AODV, Polynomial Time Algorithm.

[1]. Xiang He, Aylin Yener." Strong Secrecy and Reliable Byzantine Detection in the Presence of an Untrusted Relay," IEEE
transaction on information theory, vol. 59, no. 1, January2013.
[2]. Bhavya Kailkhura, Swastik Brahma, Pramod K.Varshney, "Optimal Byzantine Attacks on Distributed Detection in Tree based
Topology," International Conference on Computing, Networking and Communication, Workshop Cyber Physical system,2013.
[3]. Mai Abdelhakim, Leonard E. Lightfoot, Jian Ren, and Tongtong Li," Distributed
DetectioninMobileAccessWirelessSensorNetworksunderByzantineAttacks,"
[4]. IEEE Transaction on parallel and distributed System, March 2013
[5]. Xiaofan He, Huaiyu Dai, Peng Ning," A Byzantine Attack Defender: the Conditional Frequency Check," 2012 IEEE International
Symposium on Information Theory Proceedings

Abstract: Administration of data and its analysis have been an ineludible part of the world for ages now. With
the progression of big data, myriad number of companies that dealt with a large quantum of data gained
momentum as major issues regarding management of data had found an optimistic solution. Even the field of
analytics got a boost because of the numerous techniques introduced by big data for analysis of enormous
quantity of data. Various methodologies introduced by big data for analytics that yield ground-breaking
throughputs with high efficiency rates tend to develop complexities which could lead to damage of catastrophic
scale. The major causes included......

Keywords: Big data, big data analytics, Blockchain analgesia.

[1]. N. Elgendy, A. Elragal, Big Data Analytics: A Literature Review Paper, In the Proceedings of the 14th Industrial Conference,
ICDM , 2014,Russia, pp.214-227
[2]. X. Wu, X. Zhu, G. Wu, W. Ding, Data mining with big data, IEEE Transactions on Knowledge and Data Engineering, 26(1), pp.97-
107, 2014
[3]. Z.M. Bi, D.S. Cochran, Big data analytics with applications, Journal of Management analytics, 1(4), pp.249-265, 2014
[4]. H.J. Watson, Harnessing Customer Information for Strategic Advantage: Technical Challenges and Business Solutions, The Data
Warehousing Institute, USA, 2014.
[5]. Chen, H., Chiang, R. H. L., & Storey, V. C., Business Intelligence andAnalytics: From Big Data to Big Impact, MIS
Quarterly,36(4), pp.1165–1188, 2012.

Abstract: In an effort to measure the current network for suppliers and users of internet service, a paradigm
shift is needed. This condition is stimulated by the increasing scale of internet users worldwide reaching 34.4%
of the total world population according to Internet World Stats as of June 2012. Internet network measurement
is directly impacting the end-user satisfactory level as the target factor for Quality of Experience (QoE). This
research proposes an integrated internet measurement model which is involving the Quality of Service (QoS)
parameters through active measurement system activated from passive measurement. The proposed
measurement model is capable of giving feedbacks in form of network performance recommendation at any
given time interval.

Keywords: Measurement, Internet, Integrated, QoE, QoS, Recommendation

[1]. Crovella, M., and Krishnamurthy, B., 2006, Internet Measurement, John Wiley & Sons.Ltd.
[2]. Chang, R.,K.,C., 2013, Network Measurement Research in a Complex Networked World, The Hong Kong Polytechnic University.
[3]. Jiang, Y., Tham, C., Ko., C., 2000, Challenges and Approaches in Providing QoS Monitoring, Int. J. Network Mgmt 2000, 10:323-
334. John Wiley & Sons,Ltd.
[4]. Liu, Y., 2005, Network Measurement and Traffic Engineering, ECE Dept. Polytechnic University, Teaching – LectureEL933.
[5]. Peuhkuri, M., 2002, Internet traffic measurements – aims, methodology, and discoveries, Department of Electrical and
Communications Engineering, Helsinki University of Technology...

Abstract: Association rule mining in a student performance data is an important research area. This provide
support unity to deal with the uncertainty of data. The fuzzy association rule mining can be an important method
in s tu d ent ' s a c ad e mi c data due to it's the completeness and able to handle the uncertainty. In this work, a
fuzzy association rule mining is used for s t ud e nt 's a ca d e mi c data. Our experiment shows that fuzzy
association rule mining in stu d ent ' s a c ad e mi c data a give better performance as non-fuzzy association rule
mining. It performs in less time and generate less frequent set compare as existing algorithm..

Keywords: Association Rule Mining, FuzzySet.

[1] Lekha A., Srikrishna C.V., Vinod V. ,Fuzzy Association Rule Mining, Journal of Computer Science,11(1), 2015, pp.71-74.
[2] Sushil Kumar Verma, R. S. Thakur, Fuzzy Association Rule Mining based model to predict student performance, International
Journal of Electrical and Computer Engineering, 7(4), 2017, pp.22-25.
[3] Sweta V. Parmar, L.K.Sharma, Pattern mining approach towards student performanceJournal of global research in computer
science, 9(4), 2018, pp.20-23.
[4] Yan-Rui Lei, Li Lei, Lai-Quan Liu, Application of Fuzzy Association Rules in the analysis on higher vocational college students
performance, Journal of Computers, 28(1), 2017, pp. 1-12.
[5] C. Romero, S. Ventura, Educational data mining: A review of the state of the art, Trans. Sys. Man Cyber Part C, 40 (6), 2010, pp.
601–618.