Physical Sciences and Mathematics Commons^™

E-Customer Relationship Management In Insurance Industry In Albania, Evelina Bazini

UBT International Conference

E- Customer relationship management is an issue that every company, large or small must take in some way. Handled well, a CRM strategy can deliver significant benefits for companies and customers. Interaction with customers, in particular, has been enhanced and organizations who wish to remain competitive have started to implement CRM programmes and techniques in order to develop closer relations with their customers and to develop a better understanding of their needs. At the same time, the use of e-commerce techniques in CRM allows insurance organizations to identify customers, monitor their habits and use of information, and deliver them improved …

Effect Of Retiring Custom Web Applications On Business And Information Technology Alignment, Shubhashree Thekahally

Shubhashree Thekahally 7340504

Web applications provide the information technology (IT) implementation of business and align IT with business. Retirement of IT applications should ensure stability of business and IT alignment. The current study investigated the alignment gaps created between business and IT resulting from retiring IT software applications. The purpose of this study was to identify IT integration points with business and provide a process-based solution that sustained IT alignment with business after retiring IT applications. The theoretical framework strategic alignment model aided in identifying 3 IT domains as the IT integration points with business: enterprise architecture, configuration management database, and service-level agreement. …

Using Digital Genomics To Create An Intelligent Enterprise, Mario Domingo

Asian Management Insights

Every business knows that it needs to leverage customer data, but few know the potential it has to transform business processes, decisions and performance.

Intelligshop: Enabling Intelligent Shopping In Malls Through Location-Based Augmented Reality, Aditi Adhikari, Vincent W. Zheng, Hong Cao, Miao Lin, Yuan Fang, Kevin Chen-Chuan Chang

Research Collection School Of Computing and Information Systems

Shopping experience is important for both citizens and tourists. We present IntelligShop, a novel location-based augmented reality application that supports intelligent shopping experience in malls. As the key functionality, IntelligShop provides an augmented reality interface-people can simply use ubiquitous smartphones to face mall retailers, then IntelligShop will automatically recognize the retailers and fetch their online reviews from various sources (including blogs, forums and publicly accessible social media) to display on the phones. Technically, IntelligShop addresses two challenging data mining problems, including robust feature learning to support heterogeneous smartphones in localization and learning to query for automatically gathering the retailer content …

Lesinn: Detecting Anomalies By Identifying Least Similar Nearest Neighbours, Guansong Pang, Kai Ming Ting, David Albrecht

Research Collection School Of Computing and Information Systems

We introduce the concept of Least Similar Nearest Neighbours (LeSiNN) and use LeSiNN to detect anomalies directly. Although there is an existing method which is a special case of LeSiNN, this paper is the first to clearly articulate the underlying concept, as far as we know. LeSiNN is the first ensemble method which works well with models trained using samples of one instance. LeSiNN has linear time complexity with respect to data size and the number of dimensions, and it is one of the few anomaly detectors which can apply directly to both numeric and categorical data sets. Our extensive …

Cnl: Collective Network Linkage Across Heterogeneous Social Platforms, Ming Gao, Ee-Peng Lim, David Lo, Feida Zhu, Philips Kokoh Prasetyo, Aoying Zhou

Research Collection School Of Computing and Information Systems

The popularity of social media has led many users to create accounts with different online social networks. Identifying these multiple accounts belonging to same user is of critical importance to user profiling, community detection, user behavior understanding and product recommendation. Nevertheless, linking users across heterogeneous social networks is challenging due to large network sizes, heterogeneous user attributes and behaviors in different networks, and noises in user generated data. In this paper, we propose an unsupervised method, Collective Network Linkage (CNL), to link users across heterogeneous social networks. CNL incorporates heterogeneous attributes and social features unique to social network users, handles …

Cost-Sensitive Online Classification With Adaptive Regularization And Its Applications, Peilin Zhao, Furen Zhuang, Min Wu, Xiao-Li Li, Hoi, Steven C. H.

Research Collection School Of Computing and Information Systems

Cost-Sensitive Online Classification is recently proposed to directly online optimize two well-known cost-sensitive measures: (i) maximization of weighted sum of sensitivity and specificity, and (ii) minimization of weighted misclassification cost. However, the previous existing learning algorithms only utilized the first order information of the data stream. This is insufficient, as recent studies have proved that incorporating second order information could yield significant improvements on the prediction model. Hence, we propose a novel cost-sensitive online classification algorithm with adaptive regularization. We theoretically analyzed the proposed algorithm and empirically validated its effectiveness with extensive experiments. We also demonstrate the application of the …

Dictionary Pair Learning On Grassmann Manifolds For Image Denoising, Xianhua Zeng, Wei Bian, Wei Liu, Jialie Shen, Dacheng Tao

Research Collection School Of Computing and Information Systems

Image denoising is a fundamental problem in computer vision and image processing that holds considerable practical importance for real-world applications. The traditional patch-based and sparse coding-driven image denoising methods convert 2D image patches into 1D vectors for further processing. Thus, these methods inevitably break down the inherent 2D geometric structure of natural images. To overcome this limitation pertaining to the previous image denoising methods, we propose a 2D image denoising model, namely, the dictionary pair learning (DPL) model, and we design a corresponding algorithm called the DPL on the Grassmann-manifold (DPLG) algorithm. The DPLG algorithm first learns an initial dictionary …

Where Are The Passengers? A Grid-Based Gaussian Mixture Model For Taxi Bookings, Meng-Fen Chiang, Tuan Anh Hoang, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Taxi bookings are events where requests for taxis are made by passengers either over voice calls or mobile apps. As the demand for taxis changes with space and time, it is important to model both the space and temporal dimensions in dynamic booking data. Several applications can benefit from a good taxi booking model. These include the prediction of number of bookings at certain location and time of the day, and the detection of anomalous booking events. In this paper, we propose a Grid-based Gaussian Mixture Model (GGMM) with spatio-temporal dimensions that groups booking data into a number of spatio-temporal …

Not All Trips Are Equal: Analyzing Foursquare Check-Ins Of Trips And City Visitors, Wen Haw Chong, Bingtian Dai, Ee Peng Lim

Research Collection School Of Computing and Information Systems

Location-Based Social Networks (LBSN) such as Foursquare allow users to indicate venue visits via check-ins. This results in much fine grained context-rich data, useful for studying user mobility. In this work, we use check-ins to characterize trips and visitors to two cities, where visitors are defined as having their home cities elsewhere. First, we divide trips into two duration types: long and short. We then show that trip types differ in check-in distributions over venue categories, time slots, as well as check-in intensity. Based on the trip types, we then divide visitors into long-term and short-term visitors. We compare visitor …

Modelling Cascades Over Time In Microblogs, Xie Wei, Feida Zhu, Siyuan Liu, Ke Wang

Research Collection School Of Computing and Information Systems

One of the most important features of microblogging services such as Twitter is how easy it is to re-share a piece of information across the network through various user connections, forming what we call a "cascade". Business applications such as viral marketing have driven a tremendous amount of research effort predicting whether a certain cascade will go viral. Yet the rarity of viral cascades in real data poses a challenge to all existing prediction methods. One solution is to simulate cascades that well fit the real viral ones, which requires our ability to tell how a certain cascade grows over …

Analysis Of Aspects And Star Ratings In Consumer Reviews, Maruthi Prithivirajan, Vivian Lai, Kyong Jin Shim

Research Collection School Of Computing and Information Systems

This paper presents an analysis of star ratings in consumer reviews in Yelp, an online social platform for sharing consumer reviews about local businesses. In particular, we analyze consumer reviews about food businesses. We analyze how well or poorly the star ratings (on a scale of one star to five stars) associated with these reviews tally with the sentiment derived from the textual portion of the consumer review.

Evaporite Geo-Hazard In The Sauris Area (Friuli Venezia Giulia Region - Ne Italy), Chiara Calligaris, Stefano Devoto, Luca Zini, Franco Cucchi

Sinkhole Conference 2015

Evaporite sinkholes represent a severe threat to many European countries, including Italy. Among the Italian regions, of the area most affected is the northern sector of Friuli Venezia Giulia Region (NE Italy). Here chalks had two main depositional periods first in the Late Permian and then during the Late Carnian (Late Triassic). Evaporites outcrop mainly in the Alpine valleys or are partially mantled by Quaternary deposits, as occur along the Tagliamento River Valley. Furthermore, evaporites make up some portions of mountains and Alpine slopes, generating hundreds of karst depressions. This paper presents the preliminary results of the research activities carried …

Implicit Information Extraction From Clinical Notes, Sujan Perera

Kno.e.sis Publications

We address the problem of extracting implicit information from the unstructured clinical notes. Here we introduce the problem of 'implicit entity recognition in clinical notes', propose a knowledge driven approach to address this problem and demonstrate the results of our initial experiments.

Feedback-Driven Radiology Exam Report Retrieval With Semantics, Sarasi Lalithsena, Luis Tari, Anna Von Reden, Benjamin Wilson, Brian J. Kolowitz, John Kalafut, Steven Gustafson, Amit P. Sheth

Kno.e.sis Publications

Clinical documents are vital resources for radiologists to have a better understanding of patient history. The use of clinical documents can complement the often brief reasons for exams that are provided by physicians in order to perform more informed diagnoses. With the large number of study exams that radiologists have to perform on a daily basis, it becomes too time-consuming for radiologists to sift through each patient's clinical documents. It is therefore important to provide a capability that can present contextually relevant clinical documents, and at the same time satisfy the diverse information needs among radiologists from different specialties. In …

Social Health Signals, Ashutosh Sopan Jadhav, Swapnil Soni, Amit P. Sheth

Kno.e.sis Publications

Recently Twitter, has emerged as one of the primary medium for sharing and seeking of the latest information related to variety of the topics including health information. Recently, Twitter has emerged as one of the primary mediums for sharing and seeking the latest information related to a variety of topics, including health information. Although Twitter is an excellent information source, identification of useful information from the deluge of tweets is one of the major challenge. Twitter search is limited to keyword based techniques to retrieve information for a given query and sometimes the results do not contain real-time information. Moreover, …

Smart Inventory Management System, Ajay Akarapu, Chandrakanth Reddy Dasari, Nagaraju Deshini, Sushmita Mamidi

All Capstone Projects

Smart Inventory Management System is an online software application which fulfills the requirement of a typical Stock Analysis in various godowns. It provides the interface to users in a graphical way to manage the daily transactions as well as historical data. Also provides the management reports like monthly inwards, monthly deliveries and monthly returns. This application maintains the centralized database so that any changes done at a location reflects immediately. This is an online tool so more than one user can login into system and use the tool simultaneously. The aim of this application is to reduce the manual effort …

Graph Database, George Dovgin

All Capstone Projects

This project will review the new technology of graph databases. Graph databases, which model data using nodes and relationships, utilize a different paradigm than the rows and columns of relational databases.

The main goals of this project are to provide the basic background information on graph database technology and then use this knowledge to convert an RDBMS into a GDBMS. The RDBMS used will be the sample Accounts Payable (AP) relational database used in the Murach SQL 2012 book. The following will be accomplished:

• Explore graph database versus relational for querying and updating the Accounts Payable database. Review Cypher (Neo4j …

Big Data Insights Using Analytics, Naga Krishna Reddy Muppidi, Sai Kiran Merugu, Khambhampati Pramod

All Capstone Projects

The main objective of this project is to find the data insights from the huge amount of data that is evolving around us day by day. In order to analyze the data we need an architecture that is suitable for all kinds of data that we see in 21st century. We are using SPLUNK architecture for analyzing the data and getting the insights that we need for taking better decisions. SPLUNK is google for datacenters. By using SPLUNK we can generate all kinds of DASHBOARDS, ALERTS, SCHEDULING, PIVOTS and a lot more important things that is very usable for managers …

Data Framework Management System, Firasat Ali Mohammed, Ahmad Munir Rizwi Syed

All Capstone Projects

The goal of this project is to design a system for managing multiple data source through networks. The end user is concerned about the computations that depend on information from several data sources. The access will be from a portal. The system should use grid computing standards to fetch information from the different information sources, consolidates them, presented them as required.

Ezdi's Semantics-Enhanced Linguistic, Nlp, And Ml Approach For Health Informatics, Raxit Goswami, Neil Shah, Amit P. Sheth

Kno.e.sis Publications

ezDI uses large and extensive knowledge graph to enhance linguistics, NLP and ML techniques to improve structured data extraction from millions of EMR records. It then normalizes it, and maps it with various computer-processable nomenclature such as SNOMED-CT, RxNorm, ICD-9, ICD-10, CPT, and LOINC. Furthermore, it applies advanced reasoning that exploited domain-specific and hierarchical relationships among entities in the knowledge graph to make the data actionable. These capabilities are part of its highly scalable AWS deployed heath intelligence platform that support healthcare informatics applications, including Computer Assisted Coding (CAC), Computerized Document Improvement (CDI), compliance and audit, and core measures and …

Web Crawler, Michael Schmidt

All Capstone Projects

A web crawler is a piece of code that travels the Internet and collects data from various web pages, also known as web scraping. Some web crawlers are autonomous and require no instructions once started. This project will focus on a user driven web crawler where user input will direct where the crawler goes and how the collected data is analyzed. Web scraping replaces the need for manual data entry and more easily reveals trends among data collected. It can also aggregate information from multiple sources into one central location. While this application provides three specific examples of web crawling/scraping, …

Telecom Data Analysis, Sai Roopak Sarva, Anudeep Masetty, Vinay Reddy Kondam

All Capstone Projects

The telecommunications industry regularly uses data analytics in fields such as customer analysis and network optimization. For financial analysis such as identifying risks, which could negatively impact an entity’s financial performance, communications service providers have traditionally used statistical sampling techniques that cover only short time periods and a limited subset of data.

Given the massive number of transactions processed by telecommunications companies; and the costs and complexity involved in their operations, data analytics offers a valuable opportunity for enhancing the frameworks and procedures they adopt to drive profitability and minimize unnecessary downside risk.

Online Dormitory Reservation System, Adithya Mothe, Koushik Kumar Suragoni, Ramya Vakity

All Capstone Projects

This project is Online Dorms Systems which allows users to book their room in the dorm from anywhere; this is an automated system where the user can search the availability of rooms in the dorm.

The search can be done based on the dates. The rooms that available are come with the status available, it will display all the rooms available as of that particular search date. Once the room has been booked the user can cancel the reservation within 48 hours. And there is concept of user login. As the user creates his own account with his email id, …

E-Classroom For An Underserved Institution, Bhanuprakash Madupati, Kaleem Danish Mohammed, Dilipkumar Pampana

All Capstone Projects

The E-Class Room system is a web based project. An educational institution in India is understaffed and has limited interaction among faculty, student and industry experts. The project is to provide an online platform for the students and faculty of the institution to enhance their educational needs and to share their learning with their fellow students, faculty or industrial experts. It aims to provide a platform for mutual cooperation between different kinds of learning. The new system will provide directional way for online learning between faculty, student and industrial experts.

Social Tag Relevance Estimation Via Ranking-Oriented Neighbour Voting, Chaoran Cui, Jialie Shen, Jun Ma, Tao Lian

Research Collection School Of Computing and Information Systems

User-generated tags associated with social images are frequently imprecise and incomplete. Therefore, a fundamental challenge in tag-based applications is the problem of tag relevance estimation, which concerns how to interpret and quantify the relevance of a tag with respect to the contents of an image. In this paper, we address the key problem from a new perspective of learning to rank, and develop a novel approach to facilitate tag relevance estimation to directly optimize the ranking performance of tag-based image search. A supervision step is introduced into the neighbour voting scheme, in which tag relevance is estimated by accumulating votes …

Leveraging Synergy Between Database And Programming Language Courses, Brian T. Howard

Computer Science Faculty publications

Undergraduate courses in database systems and programming languages are frequently taught without much overlap. This paper argues that there is a substantial benefit to emphasizing some areas of commonality, both old and new, between the two subjects. Examples of cross-fertilization that may be used to enhance one of both of the courses include query language design and implementation, object-relational mapping, transactional memory, and various aspects of the recent "NoSQL" movement.

Scheduled Approximation For Personalized Pagerank With Utility-Based Hub Selection, Fanwei Zhu, Yuan Fang, Kevin Chen-Chuan Chang, Jing Ying

Research Collection School Of Computing and Information Systems

As Personalized PageRank has been widely leveraged for ranking on a graph, the efficient computation of Personalized PageRank Vector (PPV) becomes a prominent issue. In this paper, we propose FastPPV, an approximate PPV computation algorithm that is incremental and accuracy-aware. Our approach hinges on a novel paradigm of scheduled approximation: the computation is partitioned and scheduled for processing in an “organized” way, such that we can gradually improve our PPV estimation in an incremental manner and quantify the accuracy of our approximation at query time. Guided by this principle, we develop an efficient hub-based realization, where we adopt the metric …

Assessing Developer Contribution With Repository Mining-Based Metrics, Jalerson Lima, Christoph Treude, Fernando Figueira Filho, Uirá Kulesza

Research Collection School Of Computing and Information Systems

Productivity as a result of individual developers' contributions is an important aspect for software companies to maintain their competitiveness in the market. However, there is no consensus in the literature on how to measure productivity or developer contribution. While some repository mining-based metrics have been proposed, they lack validation in terms of their applicability and usefulness from the individuals who will use them to assess developer contribution: team and project leaders. In this paper, we propose the design of a suite of metrics for the assessment of developer contribution, based on empirical evidence obtained from project and team leaders. In …

Structural Constraints For Multipartite Entity Resolution With Markov Logic Network, Tengyuan Ye, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Multipartite entity resolution seeks to match entity mentions across several collections. An entity mention is presumed unique within a collection, and thus could match at most one entity mention in each of the other collections. In addition to domain-specific features considered in entity resolution, there are a number of domain-invariant structural contraints that apply in this scenario, including one-to-one assignment as well as cross-collection transitivity. We propose a principled solution to the multipartite entity resolution problem, building on the foundation of Markov Logic Network (MLN) that combines probabilistic graphical model and first-order logic. We describe how the domain-invariant structural constraints …