Nasseh Tabrizi

A Survey on Real-Time Big Data Analytics: Applications and Tools

Large and complex amounts of data are being generated where traditional data processing applications are inadequate to deal with them. On the other hand, there is a growing need for extracting information from operational data in real time, which is crucial in fast changing situation. The faster one can harness insights from data, the greater the benefit in driving value, taking, reducing costs, and increasing efficiency. This paper surveys different approaches in real-time analytics of Big Data or near real-time in the specific fields of application, as well as tools and techniques being used. The survey results indicate what technologies have been used in each of the fields of application and what the reason for the choice was.

Using Synchronized Audio Mapping to Track and Predict Velar and Pharyngeal Wall Locations during Dynamic MRI Sequences

Purpose : The purpose of this study is to demonstrate a novel innovative computational modeling technique to 1) track velar and pharyngeal wall movement from dynamic MRI data and to 2) examine the utility of using recorded participant audio signals to estimate velar and pharyngeal wall movement during a speech task. A series of dynamic MRI data and audio acoustic features were used to develop and inform a Hidden Markov Model (HMM) and Mel-Frequency Cepstral Coefficients (MFCC) model. Methods : One adult male subject was imaged using a fast-gradient echo Fast Low Angle Shot (FLASH) multi-shot spiral technique to acquire 15.8 frames per second (fps) of the midsagittal image plane during the production of “ansa.” The nasal surface of the velum and the posterior pharyngeal wall was identified and marked using a novel pixel selection method. The error rate was measured by calculating the accumulation error and through visual inspection. Results : The proposed model traced and animated dynamic articulators during the speech process in real-time with an overall accuracy of 81% considering one pixel threshold. The predicted markers (pixels) segmented the structures of interest in the velopharyngeal area and were able to successfully predict the velar and pharyngeal configurations when provided with the audio signal. Conclusion : This study demonstrates a novel and innovative approach to tracking dynamic velopharyngeal movements. Discussion of the potential application of a predictive model that relies on audio signals to detect the presence of a velopharyngeal gap is discussed.

A Taxonomy and Survey of Green Data Centers

An issue of great concern as it relates to global warming is power consumption and efficient use of computers especially in large data centers. Green computing is emerging as a solution to this problem as evidenced by a recent boom in publications in this area including those articles published between 2009 and 2014. Here we classify these recent publications by subject, fields of application, and recommended techniques and further categorize them according to environmental, timing, algorithms, and other aspects. We compare and analyze proposed green computing solutions in terms of features like server system power management, green cloud computing employing various types of energy efficient algorithms, data center cooling systems, and processor architecture. We explore future directions in the field and present a guideline for those interested in green computing.

Migrating Existing Applications to the Cloud

Although not a new technology, the combination of parallel computing and cloud environments can offer a number of benefits for many types of applications if the cost of application modifications combined with the costs of configuration and maintenance of the environment can be justified. This case study explores the use of cloud computing to provide a flexible deployment environment in which to run a migrated existing application using one of the popular parallel computing frameworks, Hadoop. To this end, we have documented the migration of a text-mining application, acting as a proxy for any existing application, through a number of stages progressing towards deployment in a cloud environment.

Developing an agent based Feed Analyzer system in the cloud

This paper presents an experience report documenting the design and development of an agent-based distributed software system called the “Feed Analyzer” a system deployed to Microsofts Windows Azure Cloud Service. Cloud services are emerging as an increasingly attractive deployment option given that system developers can leverage the power of a scalable infrastructure without the need to purchase or directly manage hardware or IT resources themselves; all at relatively reduced costs. But as this trend towards the cloud continues, reliable software engineering methodologies that readily lend themselves to the development of cloud applications will become increasingly important. The goal of this experience report is not to evaluate the results of the Feed Analyzer project, either quantitatively or qualitatively, from the perspective of a working software system. The goal of the project itself was to evaluate the applicability of agent-based software engineering methodologies to the relatively new realm of cloud services. Consequently, the overarching purpose of this experience report is to contribute to the body of knowledge relative to the process of deploying agent-based systems to cloud platforms.

Developing a Real-Time Data Analytics Framework for Twitter Streaming Data

Twitter is an online social networking service with more than 300 million users, generating a huge amount of information every day. Twitters most important characteristic is its ability for users to tweet about events, situations, feelings, opinions, or even something totally new, in real time. Currently there are different workflows offering real-time data analysis for Twitter, presenting general processing over streaming data. This study will attempt to develop an analytical framework with the ability of in-memory processing to extract and analyze structured and unstructured Twitter data. The proposed framework includes data ingestion, stream processing, and data visualization components with the Apache Kafka messaging system that is used to perform data ingestion task. Furthermore, Spark makes it possible to perform sophisticated data processing and machine learning algorithms in real time. We have conducted a case study on tweets about the earthquake in Japan and the reactions of people around the world with analysis on the time and origin of the tweets.

A Desktop Usability Evaluation of the Facebook Mobile Interface using the JAWS Screen Reader with Blind Users

Social networking sites (SNSs) like Facebook are widely used and have been broadly studied but despite years of investigation, accessibility complaints from individuals with visual impairments continue to persist. To investigate this issue we have conducted a quasi-ethnographic usability evaluation of Facebook involving blind participants, the mobile interface (m.facebook.com) and the JAWS screen reader on a desktop computer; a configuration that has been suggested in the related literature but insufficiently investigated. Six participants attempted 18 tasks designed to be representative of common SNS user activities. Of the features evaluated participants were most severely challenged by the process of creating a user profile and identifying other users with whom to establish relationships; two of the three core activities commonly viewed as characterizing SNSs. These findings suggest that despite recent progress additional research may be needed to make Facebook truly accessible for individuals with visual impairments.

A Pilot Study Examining the Online Behavior of Web Users with Visual Impairments

This report presents the results of a pilot study on the online behavioral habits of 46 internet users; 26 of whom self-identified as having a visual impairment (either blind or low vision). While significant research exists which documents the degree of difficulty that users with visual impairments have in interacting with the Web relative to the sighted, few have addressed the degree to which this usability disparity impacts online behavior; information seeking and online exploratory behaviors especially. Fewer still have addressed this usability disparity within the context of distinct website types; i.e. are usability issues more pronounced with certain categories of websites as opposed to others? This pilot study was effective both in exploring these issues and in identifying the accessibility of online social networks as a primary topic of investigation with respect to the formal study that is to follow.

Adversarial Machine Learning: A Literature Review

Machine learning is becoming more and more utilized as a tool for businesses and governments to aid in decision making and automation processes. These systems are also susceptible to attacks by an adversary, who may try evading or corrupting the system. In this paper, we survey the current landscape of research in this field, and provide analysis of the overall results and of the trends in research. We also identify several topics which can better define the categorization.

Tracking Happiness of Different US Cities from Tweets

Research into the possibilities of Twitter data has grown greatly over the past few years. Studies have shown its potential in identifying and managing disasters, predicting flu trends, predicting the success of movies at the box office, and analyzing people’s emotions. In this study, tweets from Twitter were collected and analyzed from nine different cities across America. East Carolina University’s Hadoop cluster was used to run our application and the Stanford CoreNLP was then used to give the sentiment of each statement in the tweets. Although our research reviled small distinction between nine individual cities in the percentage of positive, negative, and neutral statements, but however, there were significant differences in overall statements, where up 47.88% of all the statements were neutral, positive statements only 14.95%, while 37.16% of the statements were negative.