2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)最新文献

{"title":"Image processing based degraded camera captured document enhancement for improved OCR accuracy","authors":"Pooja Sharma, Shanu Sharma","doi":"10.1109/CONFLUENCE.2016.7508160","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508160","url":null,"abstract":"Over the past decade the document analysis and processing related to camera based document images has gained the interest of research community. Nowadays, cameras are easily available in the smart phones that can be carried in the small space of our pockets while being lightweight, portable and relieving us from the burden of walking down to a scanner for a digital copy of a document. But even though capturing a document image through a phone camera appears simple, the chances of obtaining a perfect picture are scanty. As when the picture is captured in an unconstrained environment, there are chances of degradation to creep in that will hamper the visual quality of the document image which further effect the readability(in terms of OCR accuracy). Low quality documents give poor results. Document images contain various degradations such as blur, uneven illumination, perspective distortion, low resolution, smear etc. Quality enhancement is helpful to recognize a camera captured document more accurately and if not completely removing the degradations, it can be used for suppressing them and making the text more readable. This paper evaluates the performance of various deblurring techniques for noisy and blurred camera captured documents.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115959073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dynamic Cluster based Privacy-Preserving Multi-Keyword Search over encrypted cloud data","authors":"Gagan, Dr. C. Rama Krishna, R. Handa","doi":"10.1109/CONFLUENCE.2016.7508104","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508104","url":null,"abstract":"Cloud computing enables the data stored on the cloud to be accessed anytime and anywhere. The data stored online must be encrypted using either symmetric key encryption or public key encryption to prevent it from unauthorized access. The end user may desire to perform dynamic updates i.e. insertion, deletion and modification of data along with the search operation on the encrypted cloud data to improve the search efficiency. The search operation is performed to access its current up-to-date version from anywhere and at anytime. In earlier search schemes the generated index was static in nature which used to support only searching. To handle the dynamic updates along with searching, the generated index is made dynamic instead of static. The proposed search scheme posses all the security requirements as proposed in the existing approaches in literature but provides searching and dynamic updates results efficiently. Experimental results demonstrate the effectiveness of the proposed dynamic search scheme as it efficiently retrieves the documents with the updated version. Also the cost of index generation is reduced as compared to existing available searching schemes which support tree-based index.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124832455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Graph-based concept discovery in multi relational data","authors":"Y. Kavurucu, Alev Mutlu, T. Ensari","doi":"10.1109/CONFLUENCE.2016.7508128","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508128","url":null,"abstract":"Developments in technology, especially in computer science created the need of storing data in variety of areas. This need created the term database where the data is stored in a useful form. In the database, data is logically integrated in file/files according to relations among them. One of the important issues is to extract knowledge from these databases that hold data in a useful and complete form. This process is called as data mining. The main objective of data mining is to extract implicit and useful knowledge from huge and at first glance meaningless mass of data that is stored in database(s). Multi-Relational databases are the ones in which the data is stored in multiple tables (relations). The relationships between those tables are also stored as tables (relations) in the database. The more effective and commonly known approaches for Multi-Relational Data Mining (MRDM) are based on Inductive Logic Programming (ILP). ILP contains concepts from Inductive Learning and Logic Programming. From this point, the main purpose of MRDM is extracting implicit and trivial knowledge from relational database(s) using ILP approaches and techniques. In this approach, data is represented in graph structures and graph mining techniques are used for knowledge discovery. Concept discovery in multi-relational data mining aims to find relational rules that best describe a relation, called target relation, in terms of other relations in the database, called background knowledge. In this study, a graph-based concept discovery method for concept discovery is presented. The proposed method, namely G-CDS (Graph-based Concept Discovery System), utilizes methods both from substructure-based and path-finding based approaches, hence it can be considered as a hybrid method. G-CDS generates disconnected graph structures for each target relation and its related background knowledge, which are initially stored in a relational database, and utilizes them to guide generation of a summary graph. The summary graph is traversed to find concept descriptors. A set of experiments is conducted on datasets that belong to different learning problems. The experimental results show that G-CDS is capable of learning definitions of target relations that belong to different learning problems.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125411865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A comprehensive study on Facial Expressions Recognition Techniques","authors":"Roshan Jameel, Abhishek Singhal, Abhay Bansal","doi":"10.1109/CONFLUENCE.2016.7508167","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508167","url":null,"abstract":"Motion of one or more than one muscles underneath the skin is Facial Expression. These movements plays very important role in conveying the emotional states of individual to the observer. Human face-to-face communication is important in human interaction. In recent years, different approaches have been put forward for developing methods for fully automated facial expressions analysis that is important for human computer interaction. In Facial Expression Recognition System the image is processed to extract such information from it, which can help in recognizing six universal expressions that are neutral, happy, sad, angry, disgust and surprise. This processing is done in several phases including image acquisition, features extraction and finally expressions classification. This paper surveys some of the techniques that are used for the purpose of facial expression recognition; a summary of some of the papers from 2001 to 2012 is given in tabular form. A list of few challenges in this field is given at the end along with the possible future advancements.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124129891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Score based financial forecasting method by incorporating different sources of information flow into integrative river model","authors":"K. Singh, Priti Dimri","doi":"10.1109/CONFLUENCE.2016.7508205","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508205","url":null,"abstract":"Nature and behavior of data required for the financial market forecasting specially in the stock market is not only restricted to the stock prices. Data scientists had studied market behavior by applying behavior study tools like Google-Profile of Mood States (GPOMS) and OpinionFinder on information available through news and social media platforms like twitter. But behavior finance is still at a novice state and growing with a substantial pace. Data required for the market is big, heterogeneous and mammoth. It consists of prices of stock exchanges as well as socio - political - economic data from all over the globe. Green database design will help to increase the efficiency of the database towards green drive but restricted to the prices of the stock. In continuation of our previous work on green computing in financial market, we are proposing a model as score based financial forecasting method by incorporating different sources of integrated information flow into integrative river model.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129339114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Wi-Fi Fingerprint localisation using Density-based Clustering for public spaces: A case study in a shopping mall","authors":"Sian Lun Lau, Cornelius Toh, Y. Saleem","doi":"10.1109/CONFLUENCE.2016.7508143","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508143","url":null,"abstract":"Indoor localisation is to-date still an active research area. This paper presents a case study on a localisation technique using Wi-Fi fingerprints built from radio information collected using commercially-off-the-shelf smartphones. The Wi-Fi fingerprints are built using density-based clustering-based algorithms. The investigation is carried out on normal operation scenarios, where a normal crowd was present during the experiments. A simplified version of the clustering algorithm, the Simplified Fingerprint Density-based Clustering Algorithm (SFDCA), is proposed, implemented as well as evaluated with a comparison to an existing indoor localisation algorithm called Density-based Cluster Combined Algorithm (DCCLA). Furthermore, a few changes are proposed and evaluated for the recognition algorithm. This paper discusses the obtained results, observations and issues faced in the case study.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130583737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of IoT based smart security and monitoring devices for agriculture","authors":"Tanmay Baranwal, Nitika, Pushpendra Kumar Pateriya","doi":"10.1109/CONFLUENCE.2016.7508189","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508189","url":null,"abstract":"Agriculture sector being the backbone of the Indian economy deserves security. Security not in terms of resources only but also agricultural products needs security and protection at very initial stage, like protection from attacks of rodents or insects, in fields or grain stores. Such challenges should also be taken into consideration. Security systems which are being used now a days are not smart enough to provide real time notification after sensing the problem. The integration of traditional methodology with latest technologies as Internet of Things and Wireless Sensor Networks can lead to agricultural modernization. Keeping this scenario in our mind we have designed, tested and analyzed an 'Internet of Things' based device which is capable of analyzing the sensed information and then transmitting it to the user. This device can be controlled and monitored from remote location and it can be implemented in agricultural fields, grain stores and cold stores for security purpose. This paper is oriented to accentuate the methods to solve such problems like identification of rodents, threats to crops and delivering real time notification based on information analysis and processing without human intervention. In this device, mentioned sensors and electronic devices are integrated using Python scripts. Based on attempted test cases, we were able to achieve success in 84.8% test cases.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121979959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Big Data capabilities and readiness of South African retail organisations","authors":"Joan Mneney, J. Van Belle","doi":"10.1109/CONFLUENCE.2016.7508129","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508129","url":null,"abstract":"Big Data enables organisations to use the large volumes of data generated through different devices and people to increase efficiency and generate more profits. South African retail organisations are already using data to their advantage using loyalty cards, but their capabilities and readiness in using Big Data is not very clear. This paper presents a qualitative approach to understand the current capabilities and readiness of Big Data in South African retail organisations. Two theoretical models; Technology Organisation Environment (TOE) together with Task Technology Fit (TTF) were used to understand the factors that enable adoption and implementation of Big Data in retail organisations. Semi structured interviews were conducted with individuals from retail organisations, Big Data vendors and IT professional service providers to get an understanding of the current status of Big Data in the South African context. The study reveals that South African retail organisations are capable and ready to adopt and implement Big Data, however, more efforts need to be placed from the organisational perspective and Big Data technology vendors need to provide more support to enable realisation of more benefits of Big Data in South African retail organisations.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114247312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Heuristic model to improve Feature Selection based on Machine Learning in Data Mining","authors":"Jahin Majumdar, Anwesha Mal, Shruti Gupta","doi":"10.1109/CONFLUENCE.2016.7508050","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508050","url":null,"abstract":"Data Mining and Machine Learning is one of the most popular research areas in computer science that is relevant in today's world of unfathomable data. To keep up with the rising size of data, there arises a need to quickly extract knowledge from data sources to aid data analysis research and improve industry and market needs. Primary Data Mining algorithms like k-means, Apriori, PageRank etc. are used today, but Machine Learning techniques can enhance the same by learning from the complex patterns. This paper focuses on the various existing approaches where Machine Learning algorithms have been used to improve data classification and pattern recognition in Data Mining especially for Feature Selection. It compares and contrasts the existing techniques and finds out the best one among them. Further, the paper proposes a heuristic approach to theoretically overcome most of the limitations in existing algorithms.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114647470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application and scope analysis of Augmented Reality in marketing using image processing technique","authors":"S. Rajappa, G. Raj","doi":"10.1109/CONFLUENCE.2016.7508159","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508159","url":null,"abstract":"The main aim of the research paper is to understand the concept and applications of Augmented Reality (AR). It involves understanding the process of creation of an AR image, the hardware and software requirements for the process of making such an image. The paper also focuses on the ways in which the technology is used by firms and advertisers to give customers a better user experience. AR is a growing field with a lot of scope in the future, the paper also gives an insight on what is in store for AR in the near future.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133554673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}