Ashima Singh

Combining naive bayes and adjective analysis for sentiment detection on Twitter

Twitter is an emerging platform to express the opinion on various issues. Plenty of approaches like machine learning, information retrieval and NLP have been exercised to figure out the sentiment of the tweets. We have used movie reviews as our data set for training as well as testing and merged the naive bayes and adjective analysis for finding the polarity of the ambiguous tweets. Experimental outputs reveal that the overall accuracy of the process is improved using this model. Firstly we have applied naive bayes on collected tweets which results in set of truly polarized and falsely polarized tweets. False polarized set is further processed with adjective analysis to determine the polarity of tweets and classify it to be positive or negative.

Securing IoT devices using JavaScript based sandbox

Internet of Things is gaining research attention as one of the important fields that will affect our daily life vastly. Today, around us this revolutionary technology is growing and evolving day by day. This technology offers certain benefits like automatic processing, improved logistics and device communication that would help us to improve our social life, health, living standards and infrastructure. However, due to their simple architecture and presence on wide variety of fields they pose serious concern to security. Due to the low end architecture there are many security issues associated with IoT network devices. In this paper, we try to address the security issue by proposing JavaScript sandbox as a method to execute IoT program. Using this sandbox we also implement the strategy to control the execution of the sandbox while the program is being executed on it.

A survey on various component repositories with detail study of different methods of storage and extraction of components

Software components have played an important role in modern software and system development. The main contribution of software components is reuse which helps reduces development cost and time and increase productivity. There must be some system or an application which can efficiently store and retrieve software assets so they can be easily reused whenever same type of functionality is desired. There are so many existing software reusable component repositories which have been introduced in this paper. Information in this paper will be very useful for the developer while developing well organized, user-friendly and efficiently browse able repositories.

Nature-Inspired Optimization Techniques in VANETs and FANETs: A Survey

In recent years, Vehicular Ad hoc Networks (VANETs) and Flying Ad hoc Networks (FANETs) are evolving rapidly. VANETs and FANETs are special types of Mobile Ad hoc Networks (MANETs). VANET uses vehicles as mobile nodes for the communication. VANET provide communication during emergency situations like accidents to avoid its possibility by sending alert messages to the drivers. FANET is a collection of unmanned aerial vehicles that communicate without any predefined infrastructure. FANET being the most searched and researched topic nowadays is finding its scope in flying objects like drones used for military applications such as border surveillance and for civil applications such as disaster management, traffic monitoring. In VANETs and FANETs, routing is challenging when Quality of Service (QoS) parameters needs to be satisfied. In this paper, VANETs and FANETs’ routing protocols implementing optimization techniques (like Ant colony optimization, bee colony optimization, and particle swarm optimization) are surveyed. The differences between VANETs and FANETs are clarified first and then routing protocols for VANETs and FANETs are discussed.

Geo-localized public perception visualization using GLOPP for social media

The increasing use of social networking websites has given a platform for people to share their opinion to a wider audience. Corporations now recognise these sites as amongst primary modes of advertisement as well as the foremost source of feedback. Several companies now focus their core marketing operations and generate insights using such websites. In this paper, we propose a tool, GLOPP, for monitoring geolocation specific public perception and brand sentiment on such social media platforms, and use it to create different visualizations highlighting various aspects of the customer response for a brand in a particular region, or in a broader sense, public perception for any entity, regionally. This can help enterprises in formulating new marketing strategies, while enabling them to understand and improve customer experience.

A review on opinionated sentiment analysis based upon machine learning approach

Sentiment analysis is a rapidly emerging field and has attracted a large community of researchers to analyze an amalgamated form of people expressions shared on the internet. There are several sources like e-commerce sites, social networking sites, micro blogging sites which help in capturing user reactions corresponding to different market products and other important issues in the form of feedback. The opinions extracted from these feedbacks are useful for both individual and organizations to predict user opinionated sentiments and customer preferences. The key emphasis is put on the employing of an accurate method in the experiments to obtain correctness in the results. The main focus of this paper is to review Sentiment Analysis domain by using machine learning approach. The study is carried out by considering different facets like granularity, algorithms, polarity, applications, and data type related to the domain, which is presented and discussed in a simple manner.

Optical character recognition using template matching and back propagation algorithm

Building an effective methodology to detect characters from images with less error rate is the great task. Our aim is to furnish such an algorithm that will be able to generate error free recognition of text from the given input image which will help in document digitizing and prevention to the hand written text recognition. OCR has been in the intensive research topic for more than 4 decades, it is probably the most time consuming and labor intensive work of inputting the data through keyboard. This paper discuss about mechanical or electronic conversion of scanned images, text which contain graphics, image captured by camera, scanned images and the recognition of images where characters may be broken or smeared. The optical character recognition is the desktop based application developed using Java IDE and mysql as a database. We have gain 91.82% accuracy when applied on different data sets, in pre-processing we used different techniques to remove noise from the image in post processing we used dictionary for the characters which are not recognized during classification, in classification we have used the back propagation algorithm for the training of neural network, feature extraction has been performed by template matching and hamming distance. All the algorithms have been developed in java technology.

Gray testing support in software repository with keyword based extraction

In the software industry, generally software manufacturers develop the component and use it only once. As a result of which there is lot of wastage in effort, cost as well as time in developing softwares. The solution to the above is to reuse the software components further in the development of other similar kind of products or the products having same functionality. So, a successful component storage structure is required to increase the availability of reusable components. Repository must be developed which supports essential features like efficient storage and retrieval. In this paper gray testing tool has been implemented with an efficient storage structure which will provide both black box and white box testing support to the reusable components and will store all the test cases generated while performing gray testing of the component for future use.

Big Data Analysis with Dataset Scaling in Yet another Resource Negotiator (YARN)

data is exceedingly large day by day. In some organizations, there is a need to analyze and process the gigantic data. This is a big data problem often faced by these organizations. It is not possible for single machine to handle that data. So we have used Apache Hadoop Distributed File System (HDFS) for storage and analysis. This paper shows experimental work done on the MapReduce Application on Health sector dataset. The result shows the behavior of the MapReduce application framework to map and reduce the big volume of the data. The main problem is to check the behavior of the MapReduce applications by increasing the size of dataset. Our analysis lies in understanding the Apache MapReduce application performance. We expect that execution time increases linearly with the dataset size but our analysis shows sometimes the execution time varies non- linearly with the increase in the dataset size. The experimental result shows that with scaling the datasets execution time distinguishes. KeywordsData, Hadoop, MapReduce, YARN, Single Node, Multi