Volume-7 Issue-5
| Version | |
| Download | 20 |
| Total Views | 259 |
| Stock | ∞ |
| File Size | 4.00 KB |
| File Type |  |
| Create Date | January 6, 2018 |
| Last Updated | November 23, 2018 |
Download Abstract Book
|
S. No |
Volume-7 Issue-5, February 2018, ISSN: 2278-3075 (Online) Published By: Blue Eyes Intelligence Engineering & Sciences Publication Pvt. Ltd. |
Page No. |
|
|
1. |
Authors: |
Abhinav Pandey, Harendra Singh | |
|
Paper Title: |
A Survey on Live Video Stream using Distributed Technologies | ||
|
Abstract: As data is growing in multiple dimensions with lots of verities and gradually becoming humungous so there is high demand of frameworks for processing Big Data. There were frameworks available for processing structured and semi-structured data but for processing un-structured data with real time analysis, very few options were availabe which can process only limited amount of data and high volume of data was a bottleneck for IT industries. It was not a big deal to work with ‘data in rest’ and only few frameworks available for analyzing data in motion like Apache Storm, got lots of motivation. Recently, for live streaming analysis and instant decision making Spark Streaming got introduced by Data Bricks and this is gaining lots of limelight due to its easy configuration and setup with loads of machine learning techniques and reliability at distributed platform. Using Storm prediction and face recognition were implemented. Through this study we will implement Real time video streaming analysis using Spark Streaming. Keywords: Distributed system, Hadoop, Spark, Spark Streaming, Opne CV References:
|
|
||
|
2. |
Authors: |
Abhinav Pandey, Harendra Singh | |
|
Paper Title: |
Face Recognition of Pedestrians from Live Video Stream using Apache Spark Streaming and Kafka | ||
|
Abstract: Face recognition of pedestrians by analyzing live video streaming, aims to identify movements and faces by performing image matching with existing images using Apache Spark Streaming, Kafka and OpenCV, on distributed platform and derive decisions. Since video processing and analysis from multiple resources become slow when using Cloud or even any single highly configured machine, hence for making quick decisions and actions, Apache Spark Streaming and Kafka have been used as real time analysis frameworks, which deliver event based decisions making on Hadoop distributed environment. If continuous live events analysis is possible then the decision can make there-after or at the same time. And large amount videos in parallel processing are also not a bottleneck after getting the involvement of Hadoop because base of all real time analysis distributed tools is Hadoop. This event based analysis can be applied at any place where an immediate action is required like monitoring border areas of countries by cameras and drones, road traffic monitoring, life science domain, airlines, logo recognition and where-ever continuous monitoring and decision making involved in large scale data set. Keywords: Distributed System, Hadoop, Spark, Spark Streaming, Kafka, Open CV. References:
|
|
||
|
3. |
Authors: |
J. H. Patil, S. N. Patankar |
|
|
Paper Title: |
|||
|
Abstract: Nowadays, the need of advanced free text filtering is increasing. Therefore, when searching for specific keywords, it is desirable to eliminate occurrences where the word or words are used in an inappropriate sense. This task could be exploited in internet browsers, and resource discovery systems, relational databases containing free text fields, electronic document management systems, data warehouse and data mining systems, etc. In order to resolve this problem in this work, we present joint approach to Word Sense Disambiguation (WSD). Our method exploits IndoWordNet, is a linked lexical knowledge base of word nets of 18 scheduled languages of India, a very large knowledge base, to perform graph based WSD across different languages in India, and brings together empirical evidence from these languages using ensemble methods. Therefore the results show that, by complementing the wide-coverage lexical knowledge with robust graph-based algorithms and combination methods, we can achieve the state of the art in WSD settings. However, it does not require any sort of training process, no hand-coding of lexical entries, nor the hand-tagging of texts.
|
|
||
|
4. |
Authors: |
M. Usha , N.Nagadeepa |
|
|
Paper Title: |
Hybrid Two Phase Page Ranking Algorithm for Ordering the Web Pages Based on Content and Usage Mining |
||
|
Abstract: Many existing page ranking algorithms are used in web mining to display the result in search engine result page. But these existing algorithms are either based on the inlinks and outlinks of the page or content of the page. It never consider the user interest on the page to calculate the page rank of that particular page. This leads to a need of web page ranking algorithm concerning content and usage of the pages. Proposed algorithm focuses on title, Meta, H1 and paragraph tags to find the similarity of the page.Tag Analyzer Algorithm is used to analyze these tags’ content. Besides, it considers how long the user stays in that page to compute user interest score. TPPR technique computes the score in two phases. Based on the output of TPPR algorithm, the URLs are sequenced and displayed to the user. Event Explore technique detects whether the user is idle or active on the page. The proposed algorithm produced better performance and displays the most relevant web pages in the top of the result. From the results, “Two Phase Page Ranking” (TPPR) algorithm is better than PR algorithm of taken data set. TPPR algorithm can be used in web mining to improve the ranking system of search engine. Keywords: Content Mining, Page Rank, TPPR, Usage Mining
|
|
||
|
5. |
Authors: |
Salah AL- Dubai |
|
|
Paper Title: |
|||
|
Abstract: In this study, Flood Frequency Analysis at Greater-Zab was carried out using different distribution models such as Log-Normal type 3(LN3), Log-Pearson type 3(LP3) and Generalize Extreme value(GEV). The annual peak flow series of Zab River was used for this purpose. Using Kolmogorov and Anderson Darling tests, the fitness of the models was evaluated. Log-Normal Type 3 was found as the best model for estimation of floods (magnitude and return period for Greater-Zab River.
|
|
||
|
6. |
Authors: |
Bahieh Rostam Afshar, Nune Petrosyan |
|
|
Paper Title: |
Environment and Urban Sustainability | ||
|
Abstract: Urbanization is an increase in population of cities over time.This very rapid population growth, proved harmful effect to the city's survival. In this research, a new approach is introduced for evaluating urban sustainability by relating urbanization and urban planning in Tehran. This is based on the assumption that urban planning is a dynamic profession that works to improve the welfare of people and attractive places for present and future generations. Using this definition, Sustainability Index (SI), can be calculated as [1 - (Vu)], where Vu is Urbanization velocity. When SI is equal to 1, the urban development process is considered to be sustainable. Evaluation of the results indicate that Sustainability Index (SI) presents a more rational basis for evaluation of urban sustainability. Hence, the proposed model is an effective tool to help policy makers to understand whether the urban development process is sustainable or need to be corrected..
|
|
||
|
7. |
Authors: |
Nasser Rostam Afshar, Nurainin Mirhassan |
|
|
Paper Title: |
|||
|
Abstract: Climate change is undeniably has become a worldwide issue for the past few decades for its significant impact on water resources. Continuous growing water demand has pushed the natural water resource to the brink whereby the rivers in Sarawak are not spared. For the case of Baram basin, the long term impact of climate change on that regional scale is unapparent. Therefore, a detail study is needed for future back up plan and mitigation. This paper aims at presenting the findings on the rainfall pattern of Baram basin in conformity to the climate regime. By using Classical Multiplicative time-series modeling, data for the year 2005-2014 forecasted and the trend between hydrological parameters(temperature, evaporation and rainfall ) and meteorological Parameters (evaporation, temperature, relative humidity, wind speed and cloud cover) is then discussed. From the historical time series trend of hydrological and meteorological data, it was observed that the rainfall trend has decreased within 10 years’ time period (2005-2014) due to the change in climate regime. The forecast has predicted decrease in the rainfall trend throughout the future 30 years (2015-2044) and it gives a direct effect on the water resources in terms of its quantity and quality. [1] L Dahlman. (2014, 9). Climate Change, Global Temperature. Retrieved December 12, 2014, Available: http://www.climate.gov/news-features/understanding-climate/climate-change-global-temperature. [2] United Nations Framework, UNFCCC. (2007,9). Convention on Climate Change Impacts, Vulnerabilities and Adaptations in Developing Country. Available: http://unfccc.int/3582.php [3] Hua, T. M. ‘Trends of Rainfall in Sarawak from 1999 to 2008”. Proceeding of the International conference on Social Science Research, ICSSR, 2013, p.261. [4] Malaysian Meteorological Department Mariana Aida Ab. Kadir , (2015, 10), Available: http://www.met.gov.my/ [5] Hsu, H. S., Guo, Y. L. Effect of Wind Speed on the Measurement of Rainfall, Meiho Institut of Technology, Neipu, Pingtung Hsien: 2005, pp.81-86. [6] Rostam Afshar, N. H. Fahmi. H. (2012, . Rainfall Forecasting Using Fourier Series. Journal of Civil Engineering & Architecture. 6(9), 1258-1262. [7] C.B. Beatrice. Nasser R. A. (2014, 11). Application of Mathematical Modelling in Rainfall Forecast A Case Study in Sungai Sarawak Basin. International Journal of Research in Engineering and Technology. 3 (11), 316-319. |
|
||
|
8. |
Authors: |
Thanh Tan Nguyen Thi, Khanh Nguyen Trong |
|
|
Paper Title: |
|||
|
Abstract: In this article, we propose a new method to effectively recognize faces from connected devices like real-time camera or webcam. The method contains two phases: Detecting and recognizing faces from the webcam frame. The face detection phase uses HOG features and SVM linear classifier. The second phase bases on FaceNet neural network model to automatically extract facial features and SVM classifiers. The experiments with UOF, FEI, JAFFE and LZW dataset is presented to show the efficiency of the proposed method. Experimental results show that the proposed method achieves high accuracy and stability on the test data sets collected from the actual environment. [1] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1–9, 2015. [2] Davis E King. Dlib-ml: A machine learning toolkit. The Journal of Machine Learning Research, 10:1755–1758, 2009. [3] Dong Yi, Zhen Lei, Shengcai Liao, and Stan Z Li. Learning face representation from scratch. arXiv preprint arXiv:1411.7923, 2014. [4] Fabian Pedregosa, Gael Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, et al. Scikit-learn: Machine learning in python. The Journal of Machine Learning Research,12:2825–2830, 2011. [5] Florian Schroff, Dmitry Kalenichenko, and James Philbin. Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 815–823, 2015. [6] Gary B Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller. Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical report, Technical Report 07-49, University of Massachusetts, Amherst, 2007. [7] Hiyam Hatem, Zou Beiji,Raed Majeed, "A Survey of Feature Base Methods for Human Face Detection", International Journal of Control and Automation Vol.8, No.5 (2015), pp.61-78. [8] Hong-Wei Ng and Stefan Winkler. A data-driven approach to cleaning large face datasets. IEEE International Conference on Image Processing (ICIP), 265(265):530, 2014. [9] Hwai-Jung Hsu and Kuan-Ta Chen. Face recognition on drones: Issues and limitations. In Proceedings of the First Workshop on Micro Aerial Vehicle Networks, Systems, and Applications for Civilian Use, DroNet ’15, pages 39–44, New York, NY, USA, 2015. ACM. [10] Lawrence Sirovich and Michael Kirby. Low-dimensional procedure for the characterization of human faces. JOSA A, 4(3):519–524, 1987. [11] N. Dalal, B. Triggs, Histograms of Oriented Gradients for Human Detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005. |
|
||
|
9. |
Authors: |
Usha Rani Pisipaty, S. Balaji |
|
|
Paper Title: |
Effect of Indian Gooseberry doping on Potassium Dihydrogen Phosphate Crystals (KDP) |
||
|
Abstract: Potassium dihydrogen phosphate (KDP) crystal is an interesting non linear optical inorganic material. In this present work, KDP crystal and Indian Gooseberry extract doped KDP crystal has been grown by slow evaporation aqueous solution growth technique. The grown crystals have been investigated through various techniques viz. Fourier Transform Infrared Spectroscopy has been used for spectral analysis of grown crystals. The grown crystal have been subjected to X-ray diffraction for structural analysis. Using Energy Dispersive X-ray Spectroscopy, presence of element with weight percentage has been calculated. Nonlinear optic measurement has been used to find the SHG efficiency. Increase in KDP crystal thermal stability by an organic additive of Indian Gooseberry extract has been determined by Thermo-Gravimetric Analysis (TGA) and Differential Thermal Analysis (DTA). Using Vicker’s micro hardness test the mechanical property of KDP crystal and Indian Gooseberry extract doped KDP has been studied.
|
|
||
