MIT-World Peace University (MIT-WPU) is a top educational institute located in Pune, India. It is recognized within&nbsp;UGC under Government of Maharashtra Act No. XXXV 2017.&nbsp;

It is part of the MIT group of institutions (established in 1983) which covers 10+ campuses across India and has more than 50,000+ students enrolled across various disciplines at a given point of time. The institute houses 15 schools ranging from Engineering &amp; Technology, Design, Pharmacy, Commerce, Governance among others. It offers undergraduate, postgraduate and PhD programs among different disciplines.&nbsp;

&nbsp;

MIT World Peace University

Engineering and Technology

E-Commerce has already entered into the Indian market for online shopping. People are more inclined towards online shopping which has changed the complete market scenario. There are several online shopping portals offered by organizations such as, Amazon, Flipkart, Snapdeal, Junglee, Jabong, and others, which are enjoying their online market share. As the number of online buyers and traders are increasing, effective business techniques need to be adopted to handle the large amount of data generated every day. Recommendation Systems play an important role in filtering this data and providing adequate information to the users. Various techniques like Collaborative Filtering, Content-based, and Demographic have been adopted for recommendation but there are several drawbacks causing these techniques to fail in providing effective recommendations. Therefore, it is necessary to identify more distinguishing features for optimizing these techniques. This can be achieved through utilizing the strengths of various techniques in a hybrid manner. This paper describes an effective hybrid technique for book recommendation with the use of Ontology for user profiling to increase system efficiency. © 2015 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license.

World University root node

School of Computer Engineering & Technology

Fulltext

Procedia Computer Science

Introducing hybrid technique for optimization of book recommender system

The requirement to perform complicated statistic analysis of big data by institutions of engineering, scientific research, health care, commerce, banking and computer research is immense. However, the limitations of the widely used current desktop software like R, excel, minitab and spss gives a researcher limitation to deal with big data. The big data analytic tools like IBM Big Insight, Revolution Analytics, and tableau software are commercial and heavily license. Still, to deal with big data, client has to invest in infrastructure, installation and maintenance of hadoop cluster to deploy these analytical tools. Apache Hadoop is an open source distributed computing framework that uses commodity hardware. With this project, I intend to collaborate Apache Hadoop and R software over the on the Cloud. Objective is to build a SaaS (Software-as-a-Service) analytic platform that stores & analyzes big data using open source Apache Hadoop and open source R software. The benefits of this cloud based big data analytical service are user friendliness & cost as it is developed using open-source software. The system is cloud based so users have their own space in cloud where user can store there data. User can browse data, files, folders using browser and arrange datasets. User can select dataset and analyze required dataset and store result back to cloud storage. Enterprise with a cloud environment can save cost of hardware, upgrading software, maintenance or network configuration, thus it making it more economical. © 2015 IEEE.

Proceedings - 1st International Conference on Computing, Communication, Control and Automation, ICCUBEA 2015

CBA: Cloud-based bigdata analytics

Outsourcing of data is increasing with the rapid growth of internet. There is every possibility that data reaches illegal hands. As a result, there is increase in illegal copying of data, piracy, illegal redistribution, forgery and theft. Watermarking technology is a solution for these challenges. It addresses the ownership problem. It deters illegal copying and protects copyright of data. Watermarking technology mainly involves the process of watermark insertion and watermark extraction. Watermark insertion means embedding an imperceptible watermark in the relational database. In watermark extraction we extract the embedded watermark without the help of original database. In this paper we propose a new watermarking technique, which will watermark both textual and numerical data. Our proposed method also does watermark verification where, the watermark extracted from the database is compared with the original watermark that is known only to the owner of the database. This is accomplished through Levenshtein distance algorithm. © 2015 IEEE.

Proceedings - 2015 International Conference on Communication, Information and Computing Technology, ICCICT 2015

A robust technique for relational database watermarking and verification

A remote reference audio-magnetotelluric (AMT) study has been carried out in Bakreswar Geothermal Province to map the possible geothermal reservoir of the area. The heat flow of BGP is two and half times of average global heat flow and is nearly equal to that of young oceanic ridge. A NS (∼16 km) profile delineated a geothermal reservoir of resistivity less than 10 ohm-m at a depth of about 3 km of large horizontal extent(>2 km). The sensitivity analysis suggests that the delineated reservoir is less sensitive. BGP belongs to high temperature volcanic region which is dominated by meteoric fluid. These fluids are heated at greater depth and rises by convection to near-surface depths, where it is entrained into the overall pattern of groundwater flow. BGP thus supports the conceptual model of magmatic geothermal plays volcanic field rather than hydrothermal alteration.

School of Petroleum Engineering

77th EAGE Conference and Exhibition 2015: Earth Science for Energy and Environment

Bakreswar Geothermal reservoir revealed from audio magnetotelluric (AMT) results

Automatic extraction of chemical names has a great importance in biomedical and life science research field. In the proposed system, accuracy in training data generation is improved by generating large amount of regular expressions. Regular expressions are generated from systematic chemical names collected from PubChem Database. Due to large amount of regular expressions, accuracy in chemical name extraction is also improved. In the work carried out, an efficient chemical name extraction system is designed. It is deployed by processing the algorithm in following steps. First stop words are removed. After removal of stop words trivial name extraction is performed by dictionary matching approach. Then CAS/Registry numbers are extracted by regular expression. For systematic name extraction, sample systematic names from various categories are given as an input for training. Normalization type 1 and type 2 is performed on these sample systematic names which is followed by tokenization. Finally regular expressions are generated from training data. Input document is then matched with the regular expressions to extract systematic chemical names.

International Research Journal of Engineering and Technology

Chemical Name Extraction and its application to Rule-based System

HFC-161 is being considered as an alternative to HCFC-22 in air conditioner. Thermo physical properties of HFC-161 are closer to HCFC-22. The flammability of HFC-161 needs to be addressed while using in air conditioner. A typical split packaged air conditioner with nominal cooling capacity of 5.2 kW that was originally designed for HCFC-22 was selected for performance evaluation in psychrometric chamber. Test conditions considered are as per IS 1391 part 1. Air conditioner performance was evaluated for capacity rating test conditions. Initially, baseline performance was established with HCFC-22. Then HFC-161 was used as drop-in for HCFC-22. Under drop-in test, the cooling capacity of HFC-161 was 10.1 % lower than that of HCFC-22 and EER was 19.7% higher compared to HCFC-22. The optimized HFC-161 charge under drop-in was 385g. This was 51% of HCFC-22. In order to achieve equivalent cooling capacity of HCFC-22, modified capillary was considered in another test. In this test, HFC-161 gave 7.1% lower cooling capacity and 17.7% higher EER than that of HCFC-22.

School of Mechanical Engineering

Refrigeration Science and Technology

Performance assessment of air conditioner using HFC-161

HC-290 has been successfully experimented as replacement for HCFC-22 air conditioners by many researchers especially in last decade. The performance data of split air conditioner using HC-290 that operated on constant speed compressor is available in the literature. An EN 378 has been applied to a few of these air conditioning systems. In this paper, the performance of split air conditioner using HC-290 that operated on DC-inverter compressor has been assessed and compared with HCFC-22. In later part of this paper, the performance of split air conditioners that operated on constant speed compressor and DC-inverter compressor is compared. A typical split packaged air conditioner with nominal cooling capacity of 3.5 kW that was originally designed for HCFC-22 was selected for experimental performance evaluation using HC-290 as a substitute to HCFC-22. The performance parameters considered are cooling capacity, EER, power input, and discharge temperature. A well-equipped psychrometric test chamber facility consisting two equal size rooms (indoor room and outdoor room) was used for this purpose. The air conditions maintained were as per Indian standards IS 1391 part 1. Initially the performance of HC-290 has been compared with HCFC-22 at Capacity Rating Test conditions as per IS 1391 standard. Further, HC-290 performance was assessed at high ambient conditions. These conditions are closer to the conditions prescribed in SASO standards. At capacity rating conditions. HC-290 gave 13.4% lower cooling capacity and 14.4 % higher EER compared to HCFC-22. At high ambient conditions HC-290 cooling capacity and EER were degraded to 61.7% and 54.6% respectively than that of baseline test with HCFC-22.

Experimental performance assessment of DC-inverter operated split packaged air conditioner using HC-290

The paper discusses two approaches for fruit skin damage detection. In the former approach, two dimensional (2D) Fast discrete curvelet transform based texture features are computed. This approach divides image at fine level and curvelet transform is applied on each sub-image. The energies of these curvelet coefficients extracted from sub images are used as the feature vector. The later approach introduces a low level feature, colour texture moments which combines colour moments and local Fourier transform as a texture representation of fruit. In this approach, Local Fourier Transform is applied on image to derive eight characteristics maps for describing co-occurrence relation of pixel in various colour space and the first and second moments of these maps resulting in 48 dimensional feature vectors are calculated. Effectiveness of both feature vectors using classifiers namely Artifical Neural Network and Support Vector Machines are tested to sort defective fruits.

School of Electronics & Communication Engineering

Journal of Food Science and Technology(Springer)

Comparative performance evaluation of fast discrete curvelet transform and colour texture moments as texture features for fruit skin damage detection

It is said that the backbone of Indian economy is agriculture. The contribution of the agriculture sector to the national GDP (Gross Domestic Products) was 14.6% in the year 2010. To attain a growth rate equivalent to that of industry (viz. about 9%), it is highly mandatory for Indian agriculture to modernize and use automation at various stages of cultivation and post harvesting techniques. The use of computers in assessing the quality of fruits is one of the major activities in post harvesting technology. As of now, this assessment is majorly done manually, except for a few fruits. Currently, the fruit quality assessment by machine vision in India is still at research level. Major research has been carried out in countries like China, Malaysia, UK, and Netherlands. To suit the Indian market and psychology of Indian farmers, it is necessary to develop indigenous technology. This paper is the first step towards evaluating the research carried out by the research community all over world for tropical fruits. For the purpose of survey, we have concentrated on the tropical fruits of the state of Maharashtra, while keeping in focus of the review image processing algorithms.

Critical Reviews in Food Science and Nutrition(Taylor and Francis)

A Comprehensive Survey of Fruit Grading Systems for Tropical Fruits of Maharashtra

It is required to give proper ratio of nutrients to the crop for their growth through the fertilizers. The fertilizers required to add in the soil should be known. Many researcher are working to determine primary soil nutrients Nitrogen (N), Phosphorous (P) and Potassium (K). This paper gives review of sensing technology and other portable methods used to determine the soil nutrients NPK.