Arushi Jain

Concoction of Ambient Intelligence and Big Data for Better Patient Ministration Services

The term Ambient Intelligence (AmI) encompasses other technologies such as ubiquitous communication, pervasive computing and ubiquitous computing. Hospitals can improve their workingbymonitoringthehealthofthepatientsandperformingautomaticanalysisofvariousand healthparameters inside the room.Securitymechanismscanalsobeenhancedbyonlyallowing authorizedhospitalstaffandattendantsintheward.WiththeadventofAmbientIntelligenceand thecongenialpoliticalenvironment,thefocusisnowshiftingtoprovidingbetterhealthcareathomes thanattraditionalmedicalcenters.Inthispaper,weimplementedanalgorithminwhichweconsider aspecificroomofahospitalastheenvironment,withapatientmonitoredforhealthandsecurity reasons.Ifanythingisnotallowedfortheparticularpatientortherearesomeunwantedvariations inthehealthparametersofthepatient,thealarmwasrangandthepatient’sassistantswerenotified. KeywoRDS Ambient Intelligence, Big Data, Sensors, Ubiquitous Computing

Movie Analytics for Effective Recommendation System using Pig with Hadoop

Movies have been a great source of entertainment for the people ever since their inception in the late 18th century. The term movie is very broad and its definition contains language and genres such as drama, comedy, science fiction and action. The data about movies over the years is very vast and to analyze it, there is a need to break away from the traditional analytics techniques and adopt big data analytics. In this paper the authors have taken the data set on movies and analyzed it against various queries to uncover real nuggets from the dataset for effective recommendation system and ratings for the upcoming movies.

Olympics Big Data Prognostications

Data is continuously snowballing over the years, gradually a huge growth is seen in data to store and tame to yield meticulous result. It gives rise to a concept nowadays, reckoned as big data analytics. With the summer Olympics at Rio de Janeiro, Brazil in the year 2016 round the corner, we, the authors have implemented a mathematical model by implementing efficient map reduce program to predict the number of medals each country might bag at the games. Based on a number of factors such as historical performance of the country in terms of medals won, the performance of athletes, financial scenario in the country, fitness levels and nutrition of athletes along with familiarity to the playing conditions can be used to come up with a reliable estimate.

Hashtag# Perspicacity of India Region Using Scalable Big Data Infrastructure Using Hadoop Environment

Social media is rapidly providing new standards of interaction between individuals in the recent era. It is known as a computer-intermediated tool that tolerates people to share, or create information, medical notes/reports, ideas, and pictures/videos through virtual communities. The online citizens (netizens) are able to create a colossal network of people to communicate with. Social media such as Facebook, Twitter, Youtube, Instagram and Tinder have prevalent uses that produce copious amount of data which is beyond the ability of normal software tools to process in the given elapsed time. Apache Hadoop project is the most famous open sourced frameworks for large scale computation on the commodity hardware. Hadoop has become kernel for distributed operating system for big data. There are two core components associated with Hadoop–Hadoop Distributed File System (HDFS) and MapReduce. MapReduce distributed the tasks on multiple nodes in the cluster, the developer only have to write code rest is taken care by MapReduce. The generated data from these social sources is real time and includes information about author’s daily activities, feelings and emotions. The messages often include images, geo-locations and many other annotations. This vast data repository provides researchers with opportunities to study the individuals’ behavior/emotions that subject to different conditions. In this chapter we will find the trending tweets from January 2017 to September 2017 depending upon the eight prominent themes that emerged from the data set and trending tweets depending upon the geolocation. For this we divide India depending upon the region that is North India, West India, South India, East India, Central India, Northeast India

Approach for an Opinion Wrapping System–Using Focused Web Crawler

Most of the search engine depends on web crawler to go through a large number of Webpages. Web crawler (i.e. web spider or scutter or bot) is used to fetch content and URL from the Webpages. It also indexes them so that browser can easily and quickly fetch pages related to the searched word. Tons of data is produced every day, 90% of data has been created in the last 2 years. This data contains opinions and thoughts of the people in unstructured form. Opinion Scutter goes through the content and fetch reviews and comments so that they can be grilled and processed to find useful information. While shopping online or searching any game to buy we are largely dependent on the reviews provided by people. If we can keep track of such reviews and opinion, it will be easy to track a good product and increase efficiency and efficacy of the search engine. The proposed system is a generic crawler which fetches all the reviews from a given site.

Hadoop Map Only Job for Enciphering Patient-Generated Health Data

Today, Big Data is being leveraged in many industries from criminal justice to health care to real estate with powerful outcomes. Organizations are using Big Data to predict the future in turn making them smarter and efficient. All the health care data such as discharge and transfer patient data maintained in Computer based Patient Records CPR, Personal Health Information PHI, and Electronic Health Records EHR. The use of Big Data analytics is becoming increasingly popular at health care centres, in clinical research, and consumer based medical product development. The biggest challenge with implementation of big data is that the nature of information of public health sector is of very sensitive nature and needs to be protected from unauthorized access and release of contents. Therefore, to provide solution to the deidentifying personal health big data in this paper we author make use of only mapper job framework for data encryption.