Dhananjay R. Kalbande

Emotion detection from “the SMS of the internet”

Due to the sudden eruption of activity in the social networking domain, analysts, social media as well as general public are drawn to Sentiment Analysis domain to gain invaluable information. In this paper, we go beyond basic sentiment classification (positive, negative and neutral) and target deeper emotion classification of Twitter data. We have focused on emotion identification into Ekmans six basic emotions i.e. JOY, SURPRISE, ANGER, DISGUST, FEAR and SADNESS. We have employed two diverse machine learning algorithms with three varied datasets and analyzed their outcomes. We show how equal distribution of emotions in training tweets results in better learning accuracies and hence better performance in the classification task.

Voice enabled Android application for vehicular complaint system: Using GPS and GSM-SMS technology

Commuters in India face a lot of vehicular problems which usually go unreported and thus, unattended. This is because making a location aware complaint is an inconvenient affair. This paper presents the architecture of a Voice Enabled Global Positioning System (GPS) based approach for reporting vehicular complaints on an Android platform. The complaint is registered via the Short Message Service (SMS) over the Global System for Mobile Communications (GSM). GPS tracking enhances the accuracy and competence of the complaint system by mapping the location where the complaint was issued. This will aid the authorities to identify the spot and have the problems resolved responsively. Since the proposed system is voice enabled and Android based on the complainant side, it will serve as a facilitative platform for Indian road commuters to send complaints to the relevant authorities, in addition to the existing channels, so that these issues could be addressed in a timely manner.

Investigation of throughput gains by mobile data offloading from LTE to Wi-Fi

Recently, there has been a tremendous increase in mobile data usage with widespread proliferation of smartphone like devices and increasing popularity of video streaming services such as YouTube. This is already causing overloading of 3G cellular access networks. It is estimated that even the 4G LTE (Long Term Evolution) technology which has significantly higher spectral efficiency than 3G will also face overloading in near future. As a result, it has become important to find out ways and means of offloading the traffic from the LTE network. One possible solution is offloading it to Wi-Fi to gain extra capacity and improve overall network performance. In this paper we have considered an outdoor macro cell LTE Network being offloaded by a Wi-Fi network. We study the loading of LTE Network in different types of user and traffic distribution and investigate how offload to Wi-Fi APs can help in easing the congestion in LTE network and thereby lead to better per user throughputs and better quality of experience to end users using NS-3. Also, among the various scheduling algorithms that have been defined for efficient resource allocation in LTE, three schedulers have been considered: Round Robin (RR), Proportional Fair (PF) and Priority Set Scheduler (PSS) schedulers and their performance has been evaluated in the offloading scenario.

Demonstration of Signature Analysis Using Intelligent Systems

Signature is a form of self portrayal through which the author is publicly recognized. Personality traits of a person, like his emotional stability, sensitivity, creativity, thoughtfulness and his general attitude towards himself and others, can easily be estimated by analyzing his signature. This paper proposes a new technique to implement signature analysis and predict the dominant personality traits the author exhibited while signing. For implementing this technique, the image of the signature is processed and certain characteristics of the signature are measured. These quantified values are forwarded as the input to an intelligent system, which analyzes the inputs and generates the output as a group of appropriate adjectives. Thus, the current temperament of the author is described.

Integrating ERP to accelerate business process agility: A case study and critical research review in Indian pharmaceutical industry

Pharmaceutical companies are one of the fastest growing companies in the market. ERP as a business solution can help pharmaceutical companies to ease the work flow in the organization and to enhance its performance. This paper is based on the survey carried out at Leben Laboratory Pvt. Ltd., a pharmaceutical company, involved in manufacturing of various kinds of medicines. Objectives of this paper are to study the need of automation software/ERP in pharmaceutical companies, identify the problem faced in these companies while using the Software and their failures. It also aims at documenting the current software used by Leben and developing customized software as per their requirements thereby overcoming the drawbacks of current software. It reports how the developed software can fulfil needs of many SMEs and effectively provide better solutions to manage their work.

Network Security Analyzer: Detection and Prevention of Web Attacks

In today’s technology world one may have been attacked or witnessed cyber-attacks on their applications. Currently there are many systems that help you detect as well as prevent various kinds of attacks that your application may be vulnerable to. There is dire necessity to protect your Projects from these kinds of attacks. Using NSA tool, security can be implemented, one can detect and analyze if there is any attack taking place or there has been an attack. NSA helps in detecting all sorts of attacks ranging from databases to network. Cross-Site Scripting, SQL injection, URL rewriting, Buffer Overflow and Cross-Site Request Forgery are amongst the few that are found by NSA. Studies have also showed rapid rise in these attacks, it has become necessary to provide solution to protect the web applications against them. Use of firewalls along with NSA is one of the solutions to mitigate these attacks along with others.

Twitilyzer: Designing an approach for ad-hoc search engine

There are many micro blogging sites which provides rich source of information about personality, products, sports, politics, technology etc. As of February 2014, about 241 million tweets are being generated per day. In this paper Twitilyzer, Twitter, a micro blogging site has been used to gather the information on different topics. The information will be in the form of tweets. These tweets are extracted from the Twitter through Twitter API. These tweets are then preprocessed to remove mistakes. The Naive Bayes machine learning algorithm is developed to classify the tweets into positive and negative sentiments. The Ranking algorithm is developed which will display top positive and top negative sentiments about the particular topic. The experimental result shows statistics of positive and negative sentiments. Thus it can contribute to organization for analysis of current market trends.

ANFIS based Spam Filtering Model for Social Networking Websites

Spam is flooding the Internet with many copies of the same message, in an attempt to force the message on people who would not otherwise choose to receive it. There are various types of spam such as email spam, forum spam, online classified ads spam, attachment spam, social networking spam etc. For the purpose of this paper, we would like to concentrate more on social networking spam (SNS). SNS is when unwanted messages or posts are sent to people in bulk, or when a single click of a seemingly harmless link reposts the link on other profiles, thus spreading the spam like a virus. We plan to use an adaptive neuro fuzzy inference system (ANFIS) that incorporates the advantages of both the neural networking concepts and fuzzy logic to identify the spam messages on such websites. General Terms Design, algorithm, documentation, experimentation, performance

e-procurement for increasing business process agility

Today the business is changing rapidly over the period. Every enterprise need to develop new service offerings and new technologies has to be adopted or reconfigured. Most of the service companies are tied with traditional project techniques, which include a staged approach. These stages need to be compressed and changed to meet time-to-market demands. Today every enterprise must be agile enough to respond with changing requirements of their customers. Agility has becomes the basic key attribute today as business faces uncertain and volatile environments. E-Procurement makes it possible to automate buying and selling over the internet. Typically an e-Procurement-enabled website will have product comparisons across vendors and various processes like tendering, auctioning, vendor management, and catalogue and contract management. High-end e-procurement solutions allow organizations to define their own processes in the form of workflows - thus utilizing concepts of business process modeling. In this paper we present the findings from a recent survey on e-procurement in India and explain how an e-procurement can be used in such fast growing organization to speed up the business activity at the suitable agility level and its impact on centralization and firms efficiency in the procurement process.

Screen sharing application for mobile phones

With the advent of smart phones, mobile phones underwent metamorphosis and became the mother of all inventions. Transforming into devices capable of handling high end applications, mobile phones have introduced the features of mobility and portability in almost all applications and software that were designed for a personal computer. They also serve as dynamic gateways to the internet through which real time exchange of information and resources can take place. Technology that allows applications to share local resources through a remote service is one of the latest breakthroughs in the world of communication. We aim to develop an environment through which mobile phone users can experience the use of such technology. All smart phones with Android OS incorporate touch screens. Such phones utilize their screens to display and manipulate information conveniently. By making the screen of one mobile user available to other mobile users, the interaction between two mobile users can be taken to a whole new level. This is what we want to achieve through our application.