Sajimon Abraham

Trajectory similarity of network constrained moving objects and applications to traffic security

Spatio-Temporal data analysis plays a central role in many security-related applications including those relevant to transportation infrastructure, border and inland security. In several applications, data objects move on pre-defined spatial networks such as road segments, railways, and invisible air routes, which provides the possibility of representing the data in reduced dimension. This dimensionality reduction gives additional advantages in spatio-temporal data management like indexing, query processing, similarity and clustering of trajectory data etc. There are many proposals concerning trajectory similarity problem which includes Euclidian, network, time based measures and concepts known as Position of Interest(POI), Time of Interest(TOI) etc. This paper demonstrates how these POI and TOI methods could be advantages in security informatics domain suitable to work with road network constrained moving object data, stored using a binary encoding scheme proposed in a previous PAISI paper.

Trigger Based Security Alarming Scheme for Moving Objects on Road Networks

The advent of modern monitoring applications such as location based services, presents several new challenges when dealing with continuously evolving spatio-temporal information. Spatio-Temporal data analysis plays a central role in many security-related applications including those relevant to transportation infrastructure, border and inland security. This paper reviews a novel binary encoding scheme to store location information and proposes a trigger based security alarming scheme when an object enters into a sensitive area with proper messages to the security people.

Spatio-temporal similarity of web user session trajectories and applications in dark web research

Trajectory similarity of moving objects resembles path similarity of user click-streams in web usage mining. By analyzing the URL path of each user, we are able to determine paths that are very similar and therefore effective caching strategies can be applied. In recent years, World Wide Web has been increasingly used by terrorists to spread their ideologies and web mining techniques have been used in cyber crime and terrorism research. Analysis of space and time of click stream data to establish web session similarity from historical web access log of dark web will give insights into access pattern of terrorism sites. This paper deals with the variations in applying spatio-temporal similarity measure of moving objects proposed by the authors in PAISI 2010, to web user session trajectories treating spatial similarity as a combination of structural and sequence similarity of web pages. A similarity set formation tool is proposed for web user session trajectories which has applications in mining click stream data for security related matters in dark web environment. The validity of the findings is illustrated by experimental evaluation using a web access log publically available.

Exploring the merits of nosql: A study based on mongodb

Introduction of structural, semi-structural and unstructured data has tested and challenged the scalability, flexibility and processing ability of the conventional relational database management systems (RDBMS). The new eras of frameworks demand horizontal scaling of the databases. Data with various formats including unstructured data has to be stored and processed in the databases. NoSQL methodologies are answers to these issues. The conventional approaches used in relational and object oriented DBMS cannot adopt the flexible scaling required for todays systems. Likewise, Big Databases have come into existence. But systems with advanced facilities have not emerged, which can support such databases. These enormous databases could not be stored in one physical system. It is recommended to have a distributed framework for this. With a specific goal to enhance the unstructured data processing, a NoSQL framework can be utilized. A document based NoSQL database MongoDB which commonly uses JSON data is discussed to explore the merits of NoSQL databases.

Semantic trajectory analysis for identifying locations of interest of moving objects

The upsurge in the use of Context Aware Devices in various gadgets has led to the generation of massive mobility data. These gadgets tracks and records particulars of moving objects such as location, time, waypoints etc. in to various geographical databases. The data are recorded in the form of trajectories. Identification of the moving pattern is very much useful for setting up of the architectural platform of transportation systems, design of supply chain networks, preparation of travel itinerary of tourists and the like. In order to understand the characteristic features of the journey made by objects, appropriate mining techniques are essential. Many of the existing trajectory mining applications use geographic features precisely location and time for the pattern identification. Mining of data by considering more parameters will identify divergent locations of interest in the trajectory. The concept of semantic trajectory analysis is gaining acceptance in the domain of trajectory analysis. In this paper we are introducing a conceptual model for the identification of interesting locations on the basis of spatio temporal attributes of moving objects and its semantic features. This model considers direction of the movement of the object as semantic mean for the identification of interesting locations.

Prediction with partitioning: Big data analytics using regression techniques

The cumulative growth of data from various sources has led to the era of big data. Big Data analytics give rise opportunities in designing of competitive offer packages for customers to provide reliable services, but analysis must be accurate and timely for successful decision making. For testing and analyzing Big Data, various statistical methods are developed. Traditional statistical analysis focuses on sampling for generating a predictive mode. To overcome this limitation, Big Data is partition into sub data sets and statistical analysis is employed on each subsets. As the structure of data sets are to be studied initially we have to go through various steps in statistical modeling up to Exploratory Data Analysis (EDA). Dependent variable and independent variables are identified and suitable parametric modeling is suggested. Regression techniques are used to describe the relation between dependent and independent variables. Here we focused different linear regression techniques. The performance are evaluated through simulation methods in the experimental data sets from UCI machine learning repository and its seen that multivariate linear regression shows better performance in parametric modeling.

Privacy preserved approach for trajectory anonymization through zone creation for halting points

The abundance of various embedded sensors on mobile devices results in huge amount of data generation, storage requirement and also causes the encroachment into the personal privacy. But for the development of new applications or making organizational decisions, the trajectory data is to be published. Moving objects trajectory publication may result in the serious violation and a threat to the individuals privacy. The existing methods in privacy preservation approach, tries to anonymize the whole trajectories together. But this will certainly result in serious information loss and published data quality. It is realized that major halting points in the trajectories are more important than the pass-by points. So here this proposal put forward a method that will extract the vital halting points from the trajectory and anonymize these points during the trajectory publication by hiding these points in a zone. Also tries to prevent the adversary from reaching the zone by knowing the moving speed. For the experimentation of methods, real world data has been used and also provide a conceptual method to solve the problem.

Analytic thinking of patients' viewpoints pertain to spa treatment

In the increasingly digitized and connected world, advantages also bring equally important challenges that often require new thinking and approach. One of the primary challenges is data that is being generated in huge quantity at enormous pace and in variety of forms. Social medium has blow up as a sort of online discussion where people create and share the information at a substantial rate. The outlook of social media user is now noticeably used for taking the decisions. Evaluating sentiments, opinions and emotions by a group of people in the form of reviews pertaining to a certain event can carve out the niche of providing insights into the review text analytics, especially when text data is large. On one hand sentiments shows the conformity, disparity or objectivity among the masses whereas on the other hand emotions coming out from text clusters the group feedback. In this paper, the authors analyses the sentiments of patients pertaining to ayurvedic spa treatment. User reviews from the top rated websites are extracted to obtain the sentiments. The authors explore the possible ways to analysis the user sentiments using NLTK and Python programming libraries.

Instructional design for learning path identification in an e-learning environment using felder-silverman learning styles model

Developing instructional design for e-content and checking its effectiveness among a group of learners is very significant in e-learning. In the current educational system, teachers are giving instructions or delivering learning contents to learners, without understanding the learner profile parameters such as learning style, motivation, attitude, aptitude etc. In an e-learning environment, providing pre-defined learning content to all learners, without understanding their profile parameters, affect their learning process. This paper proposes a system for providing personalized e-content for learners (PEL) based on Felder-Silverman Learning Styles model (FSLSM). As a case study E-content is developed for students of graduate course in Computer Applications in the subject Computer Graphics. Effectiveness of the e-content is checked by identifying the learning path among a group of visual learners.

WEBTRACLUS: a spatio-temporal trajectory clustering tool for personalization in healthcare web portals

The use of advanced diagnostics in guiding treatment decisions that are tailored to individual risks and benefits is becoming increasingly acknowledged as the future of healthcare. People search healthcare web portals for inquiry of diseases and by analyzing the web access logs combining with their individual profiles, many patterns can be mined. Trajectory similarity of moving objects in constrained networks resembles path similarity of user click-streams in web usage mining. This paper proposes a clustering algorithm (WEBTRACLUS) for web user session trajectories using the spatio-temporal measure which can be used in personalization of users in a healthcare web portal. The validity of the findings is illustrated by experimental evaluation using the server access log of a healthcare web portal.