Skip to main content

Jalal Alowibdi

University of Illinois at Chicago, Computer Science, Graduate Student

Followers

27

Following

6

Co-author

1

Public Views

Currently, I'm pursuing my doctoral degree in computer science at College of Engineering, University of Illinois at Chicago. My research is centered primarily around Social Networks and Software Engineering. Also, I am interested in privacy in social networks, knowledge-based software system, requirements engineering and service oriented architecture. I am working with Dr. Ugo A. Buy on various problems in social networks. I worked previously with Dr. Jeffrey J.P. Tsai, Dr. Shahram Rahimi, Dr. Henry Hexmoor, Dr. Jane Cleland-Huang, Dr. Fathy Eassa and Dr. Amr Sharaf. I am very motivative and eager to learn. My concept is to read a lot specifically your interests, record every single idea comes to your mind, open your wise mind, think thoroughly in positive manner, answer a questionable question with thinkable and imaginable view, motivate and trust your ideas and yourself and Honestly, you will succeed easily.

less

University of Central Florida

Armando Marques-Guedes

UNL - New University of Lisbon

University of the Basque Country, Euskal Herriko Unibertsitatea

Thanwadee Sunetnanta

Mahidol University

Kati (Katalin) Prajda

University of Vienna

Johannes Preiser-Kapeller

Austrian Academy of Sciences

RMIT International University Vietnam

Viacheslav Kuleshov

Stockholm University

University of Trento

Gacheon University

Interests

Uploads

Papers by Jalal Alowibdi

Empirical Evaluation of Profile Characteristics for Gender Classification on Twitter

Online Social Networks (OSNs) provide reliable communication among users from different countries... more Online Social Networks (OSNs) provide reliable communication among users from different countries. The volume of texts generated by OSNs is huge and highly informative. Gender classification can serve commercial organizations for advertising, law enforcement for legal investigation, and others for social reasons. Here we explore profile characteristics for gender classification on Twitter. Unlike existing approaches to gender classification that depend heavily on posted text such as tweets, here we study the relative strengths of different characteristics extracted from Twitter profiles (e.g., first name and background color in a user's profile page). Our goal is to evaluate profile characteristics with respect to their predictive accuracy and computational complexity. In addition, we provide a novel technique to reduce the number of features of text-based profile characteristics from the order of millions to a few thousands and, in some cases, to only 40 features. We prove the validity of our approach by examining different classifiers over a large dataset of Twitter profiles.

Language independent gender classification on Twitter

Online Social Networks (OSNs) generate a huge volume of user-originated texts. Gender classificat... more Online Social Networks (OSNs) generate a huge volume of user-originated texts. Gender classification can serve multiple purposes. For example, commercial organizations can use gender classification for advertising. Law enforcement may use gender classification as part of legal investigations. Others may use gender information for social reasons. Here we explore language independent gender classification. Our approach predicts gender using five color-based features extracted from Twitter profiles (e.g., the background color in a user's profile page). Most other methods for gender prediction are typically language dependent. Those methods use high-dimensional spaces consisting of unique words extracted from such text fields as postings, user names, and profile descriptions. Our approach is independent of the user's language, efficient, and scalable, while attaining a good level of accuracy. We prove the validity of our approach by examining different classifiers over a large dataset of Twitter profiles.

Report on the Ninth International Workshop on Location and the Web (LocWeb 2019)

Sigir Forum, Dec 1, 2019

LocWeb 2019 was the ninth workshop in the LocWeb workshop series at the intersection of location-... more LocWeb 2019 was the ninth workshop in the LocWeb workshop series at the intersection of location-based services and Web architecture and was held at The Web Conference, WWW 2019, in San Francisco. It focused on Web-scale services and systems facilitating location-aware information access as well as on Spatial Social Behavior Analytics on the Web. The LocWeb 2019 workshop had contributions ranging from location data analysis over vocational trips and visualization of linked data to geolocation and browser integration. This report briefly presents the theme, contributions, and discussions of the workshop.

Report on the tenth international workshop on location and the web (LocWeb 2020)

Sigir Forum, Jun 1, 2020

LocWeb 2020 was the tenth workshop in the LocWeb workshop series at the intersection of location-... more LocWeb 2020 was the tenth workshop in the LocWeb workshop series at the intersection of location-based analytics and Web architecture and was held at The Web Conference, WWW 2020, on 21stApril 2020. The focus was on Web-scale services and systems facilitating location-aware information access as well as on Spatial Social Computing on the Web. The LocWeb 2019 workshop had contributions ranging from urban location data analysis over geospatial open data access to worldwide media consumption patterns.The workshop and conference was intended to be held in Taipei, Taiwan, but was instead held as a virtual workshop since also The Web Conference itself moved to be an online-only event, due to the current pandemic. That also gave rise to a number of discussions around spatial models, online work modes, and current mitigation efforts.This report presents an overview of these discussions, after an introduction to the workshop theme and the individual contributions.

Deception detection in Twitter

Social Network Analysis and Mining, Jun 30, 2015

Online Social Networks (OSNs) play a significant role in the daily life of hundreds of millions o... more Online Social Networks (OSNs) play a significant role in the daily life of hundreds of millions of people. However, many user profiles in OSNs contain deceptive information. Existing studies have shown that lying in OSNs is quite widespread, often for protecting a user's privacy. In this paper, we propose a novel approach for detecting deceptive profiles in OSNs. We specifically define a set of analysis methods for detecting deceptive information about user genders and locations in Twitter. First, we collected a large dataset of Twitter profiles and tweets. Next, we defined methods for gender guessing from Twitter profile colors and names. Subsequently, we apply Bayesian classification and K-means clustering algorithms to Twitter profile characteristics (e.g., profile layout colors, first names, user names, spatiotemporal information) and geolocations to analyze the user behavior. We establish the overall accuracy of each indicator through extensive experimentation with our crawled dataset. Based on the outcomes of our approach, we are able to detect deceptive profiles about gender and location with a reasonable accuracy.

An empirical study of data race detector tools

The industry of software applications has been increased significantly because of the high demand... more The industry of software applications has been increased significantly because of the high demand of using the software applications. This revolution leads on developing many concurrent software systems. Noticeably, some of these concurrent software systems have falsely report data race condition to one or more of their shared variables. Debugging such concurrent software systems to find the race condition is a challenge, especially for large and complex software systems. Since the race condition concerned mostly ignored in the concurrent software systems, adopting it could help to ensure the efficiency of these software systems. There are few detector tools that have been known in the industry focusing on data race detectors. This paper aims to study those tools. We are going to conduct empirical study of data race using well known tools in order to measure the correctness, performances and effectiveness of those tools in practical by using some benchmarks. Those benchmarks will be tested on each tool and compare it with others to see the similarity and differentiate.

Data analysis to uncover intruder attacks using data mining techniques

Radicalism is becoming an increasingly potential concern. Intruder groups are using handful tacti... more Radicalism is becoming an increasingly potential concern. Intruder groups are using handful tactics and radicalism has disparaging effects, particularly in Gulf and Pakistan region. Forecasting the pattern of attacks is a complex task. This research paper presents new insights on intruder groups and targets using data mining algorithms. We propose a framework, which uses historical data to train machine-learning classifiers and can predict intruder groups and attack types based on selected features. We analyzed that the major victims of intruder groups would be citizen and property, government, police, and military sectors. We figured out that J48 and IBK learning algorithms perform consistently well under various experimental settings.

Coronavirus Pandemic (COVID-19)

IGI Global eBooks, Jun 10, 2022

People are afraid about COVID-19 and are actively talking about it on social media platforms such... more People are afraid about COVID-19 and are actively talking about it on social media platforms such as Twitter. People are showing their emotions openly in their tweets on Twitter. It's very important to perform sentiment analysis on these tweets for finding COVID-19's impact on people's lives. Natural language processing, textual processing, computational linguists, and biometrics are applied to perform sentiment analysis to identify and extract the emotions. In this work, sentiment analysis is carried out on a large Twitter dataset of English tweets. Ten emotional themes are investigated. Experimental results show that COVID-19 has spread fear/anxiety, gratitude, happiness and hope, and other mixed emotions among people for different reasons. Specifically, it is observed that positive news from top officials like Trump of chloroquine as cure to COVID-19 has suddenly lowered fear in sentiment, and happiness, gratitude, and hope started to rise. But, once FDA said, chloroquine is not effective cure, fear again started to rise.

Machine learning based classification of normal, slow and fast walking by extracting multimodal features from stride interval time series

Mathematical Biosciences and Engineering, 2021

The gait speed affects the gait patterns (biomechanical and spatiotemporal parameters) of distinc... more The gait speed affects the gait patterns (biomechanical and spatiotemporal parameters) of distinct age populations. Classification of normal, slow and fast walking is fundamental for understanding the effects of gait speed on the gait patterns and for proper evaluation of alternations associated with it. In this study, we extracted multimodal features such as time domain and entropy-based complexity measures from stride interval signals of healthy subjects moving with normal, slow and fast speeds. The classification between different gait speeds was performed using machine learning classifiers such as classification and regression tree (CART), support vector machine linear (SVM-L), Naïve Bayes, neural network, and ensemble classifiers (random forest (RF), XG boost, averaged neural network (AVNET)). The performance was evaluated in term of accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), p-value, area under the receiver operating characteristic curve (AUC). To distinguish the slow and normal gait walking, the highest performance was yielded in terms of accuracy (100%), p-value (0.004), and AUC (1.00) using RF, XGB-L followed by XGB-Tree with accuracy (88%), p-value (0.04) and AUC (1.00). To classify the fast and normal walking, the highest performance was obtained with accuracy (88%), p-value (0.04) using XGB-L, XGB-Tree and AVNET. The highest AUC (0.94) was obtained using NB. To discriminate the fast and slow gait walking, the highest performance was obtained using SVM-R, NNET, RF, AVNET with accuracy (88%), p-value (0.04) and AUC (0.94) using RF and AUC (0.96) using XGB-L.

CommuniMents

IGI Global eBooks, 2021

Social media has revolutionized human communication and styles of interaction. Due to its effecti... more Social media has revolutionized human communication and styles of interaction. Due to its effectiveness and ease, people have started using it increasingly to share and exchange information, carry out discussions on various events, and express their opinions. Various communities may have diverse sentiments about events and it is an interesting research problem to understand the sentiments of a particular community for a specific event. In this article, the authors propose a framework CommuniMents which enables us to identify the members of a community and measure the sentiments of the community for a particular event. CommuniMents uses automated snowball sampling to identify the members of a community, then fetches their published contents (specifically tweets), pre-processes the contents and measures the sentiments of the community. The authors perform qualitative and quantitative evaluation for a variety of real world events to validate the effectiveness of the proposed framework.

IoT-IaaS: A New Public Cloud Service to Unleash Innovation in the IoT Space

Springer proceedings in complexity, 2019

IoT solution developers today are hampered by the regulatory permit burdens and high up-front dep... more IoT solution developers today are hampered by the regulatory permit burdens and high up-front deployment and maintenance costs, particularly in the public domain. Essentially, it keeps the development of IoT solutions requiring large deployments in the purview of deep-pocketed players, to the exclusion of millions of small developers who may have figured out novel solutions to problems, but lack the resources to pilot them. This is akin to the situation of cellphones before the release of SDKs for Apple iOS and Android smartphones; phones with relatively capable hardware were often restricted to running the dozen-or-so apps they shipped with. Together, smartphone SDKs and public cloud services, which were becoming available at around the same time, less well-resourced developers were able to bring their ideas for apps to the public, thus launching the smartphone revolution. In this paper we conducted a survey of studies that describe various pieces of the technology puzzle that could contribute towards democratizing access to public IoT resources.

Latent Dirichlet Allocation and POS Tags Based Method for External Plagiarism Detection

IGI Global eBooks, 2019

Inthisarticlewepresentanewsemanticandsyntactic-basedmethodforexternalplagiarismdetection. Inthepr... more Inthisarticlewepresentanewsemanticandsyntactic-basedmethodforexternalplagiarismdetection. Intheproposedapproach,latentdirichletallocation(LDA)andpartsofspeech(POS)tagsareused together to detect plagiarism between the sample and a number of source documents. The basic hypothesisisthatconsideringsemanticandsyntacticinformationbetweentwotextdocumentsmay improvetheperformanceoftheplagiarismdetectiontask.Ourmethodisbasedontwosteps,naming, whichisapre-processingwherewedetectthetopicsfromthesentencesindocumentsusingtheLDA andconverteachsentenceinPOStagsarray;thenapostprocessingstepwherethesuspiciouscases areverifiedpurelyonthebasisofsemanticrules.Fortwotypesofexternalplagiarism(copyand randomobfuscation),weempiricallycompareourapproachtothestate-of-the-artN-grambasedand stop-wordN-grambasedmethodsandobservesignificantimprovements.

Probability weighted moments regularization based blind image De-blurring

Multimedia Tools and Applications, Apr 4, 2019

The main objective of blind image de-blurring is to recover a sharp image from a given blurry ima... more The main objective of blind image de-blurring is to recover a sharp image from a given blurry image. A good estimation of the kernel plays an important role in recovering a sharp image. However, if the local object textures are neglected when the kernel is being estimated, this can lead to over-smoothing or can produce a strong ringing effect. In this paper, a new image regularization term based on the Probability Weighted Moments (PWM) for kernel estimation is proposed named as Probability Weighted Moments Regularization (PWMR). PWMR has the ability to preserve the small local texture structure in an image while minimizing the artifacts. Further, it can preserve the better contrast information between neighboring pixels and their corresponding central pixels in a current sliding window; moreover, it has the ability to resist outliers even in a small sample size. The kernel estimated by PWMR is subsequently used to recover the sharp latent image. An extensive comparison of synthetic and real standard benchmark images indicates the effectiveness of PWMR compared to current state-of-the-art blind image de-blurring methods.

Emerging Computer Vision Based Machine Learning Issues for Smart Cities

Machine learning algorithms boast remarkable predictive capabilities and deep learning, a branch ... more Machine learning algorithms boast remarkable predictive capabilities and deep learning, a branch of machine learning, has already provided the much required breakthroughs for recognition and authentication. This has enabled the deployment of a face recognition based biometric identification system by the Department of Homeland Security at U.S. airports. Deep learning algorithms require huge amounts of data for training. However, this shall not be an issue in smart cities. Instead, the ability to use the same deep learning technology for ulterior motives raise some issues. Machine learning algorithms have already been developed which can generate fake images and videos and rendering humans incapable of differentiating between real and generated content. Such content can be used for spreading disinformation regarding individuals and may lead to legal issues. Any system, relying on face recognition may be mislead using such technology. Similarly, researchers were able to create master ...

Empirical Evaluation of Profile Characteristics for Gender Classification on Twitter

2013 12th International Conference on Machine Learning and Applications, 2013

Online Social Networks (OSNs) provide reliable communication among users from different countries... more Online Social Networks (OSNs) provide reliable communication among users from different countries. The volume of texts generated by OSNs is huge and highly informative. Gender classification can serve commercial organizations for advertising, law enforcement for legal investigation, and others for social reasons. Here we explore profile characteristics for gender classification on Twitter. Unlike existing approaches to gender classification that depend heavily on posted text such as tweets, here we study the relative strengths of different characteristics extracted from Twitter profiles (e.g., first name and background color in a user's profile page). Our goal is to evaluate profile characteristics with respect to their predictive accuracy and computational complexity. In addition, we provide a novel technique to reduce the number of features of text-based profile characteristics from the order of millions to a few thousands and, in some cases, to only 40 features. We prove the validity of our approach by examining different classifiers over a large dataset of Twitter profiles.

An empirical study of data race detector tools

2013 25th Chinese Control and Decision Conference (CCDC), 2013

The industry of software applications has been increased significantly because of the high demand... more The industry of software applications has been increased significantly because of the high demand of using the software applications. This revolution leads on developing many concurrent software systems. Noticeably, some of these concurrent software systems have falsely report data race condition to one or more of their shared variables. Debugging such concurrent software systems to find the race condition is a challenge, especially for large and complex software systems. Since the race condition concerned mostly ignored in the concurrent software systems, adopting it could help to ensure the efficiency of these software systems. There are few detector tools that have been known in the industry focusing on data race detectors. This paper aims to study those tools. We are going to conduct empirical study of data race using well known tools in order to measure the correctness, performances and effectiveness of those tools in practical by using some benchmarks. Those benchmarks will be tested on each tool and compare it with others to see the similarity and differentiate.

Managing Online Requirements Elicitation in Ultra-Large Software System

Detecting deception in Online Social Networks

2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2014), 2014

Over the past decade Online Social Networks (OSNs) have been helping hundreds of millions of peop... more Over the past decade Online Social Networks (OSNs) have been helping hundreds of millions of people develop reliable computer-mediated relations. However, many user profiles in OSNs contain misleading, inconsistent or false information. Existing studies have shown that lying in OSNs is quite widespread, often for protecting a user's privacy. In order for OSNs to continue expanding their role as a communication medium in our society, it is crucial for information posted on OSNs to be trusted. Here we define a set of analysis methods for detecting deceptive information about user genders in Twitter. In addition, we report empirical results with our stratified data set consisting of 174,600 Twitter profiles with a 50-50 breakdown between male and female users. Our automated approach compares gender indicators obtained from different profile characteristics including first name, user name, and layout colors. We establish the overall accuracy of each indicator and the strength of all possible values for each indicator through extensive experimentations with our data set. We define male trending users and female trending users based on two factors, namely the overall accuracy of each characteristic and the relative strength of the value of each characteristic for a given user. We apply a Bayesian classifier to the weighted average of characteristics for each user. We flag for possible deception profiles that we classify as male or female in contrast with a selfdeclared gender that we obtain independently of Twitter profiles. Finally, we use manual inspections on a subset of profiles that we identify as potentially deceptive in order to verify the correctness of our predictions.

Reducing Travel Time by Incident Reporting via CrowdSourcing

— The contribution of this work is the creation of a novel system that enables motorists who witn... more — The contribution of this work is the creation of a novel system that enables motorists who witness incidents to submit reports to our system via the web. These reports are aggregated, validated and verified automatically. Then, they are used to update the road network graph. In this work, we designed and implemented an incident reporting system whereby users can report an incident such as an accident or construction on a road network. We extended the FreeSim simulator to accommodate our incident reporting system. Experimental results showed that our system is capable of reducing the travel time of users. We also presented our verification algorithms that are used to verify that reports are fact. Current approaches to congestion detection such as loop detectors probe vehicles, and video image detection may not be available on arterial streets. These technologies may not be available in countries whose transportation budget is low. Our model is less expensive, easy to implement and ...

Automated transportation transfer detection using GPS enabled smartphones

— Understanding the mobility of a traveller from mobile sensor data is an important area of work ... more — Understanding the mobility of a traveller from mobile sensor data is an important area of work in context aware and ubiquitous computing. Given a multimodal GPS trace, we will identify where in the GPS trace the traveller changed transportation modes. For example, where in the GPS trace the traveller alight a bus and boards a train, or where did the client stop running and start walking. Using data mining schemes to understand mobility data, in conjunction with real world observations, we propose an algorithm to identify mobility transfer points automatically. We compared the proposed algorithm against the state of the art that is used in the previously proposed work. Evaluation on real world data collected from GPS enabled mobile phones indicate that the proposed algorithm is accurate, has a good coverage, and a good asymptotic run time complexity. I.

Empirical Evaluation of Profile Characteristics for Gender Classification on Twitter

Online Social Networks (OSNs) provide reliable communication among users from different countries... more Online Social Networks (OSNs) provide reliable communication among users from different countries. The volume of texts generated by OSNs is huge and highly informative. Gender classification can serve commercial organizations for advertising, law enforcement for legal investigation, and others for social reasons. Here we explore profile characteristics for gender classification on Twitter. Unlike existing approaches to gender classification that depend heavily on posted text such as tweets, here we study the relative strengths of different characteristics extracted from Twitter profiles (e.g., first name and background color in a user's profile page). Our goal is to evaluate profile characteristics with respect to their predictive accuracy and computational complexity. In addition, we provide a novel technique to reduce the number of features of text-based profile characteristics from the order of millions to a few thousands and, in some cases, to only 40 features. We prove the validity of our approach by examining different classifiers over a large dataset of Twitter profiles.

Language independent gender classification on Twitter

Online Social Networks (OSNs) generate a huge volume of user-originated texts. Gender classificat... more Online Social Networks (OSNs) generate a huge volume of user-originated texts. Gender classification can serve multiple purposes. For example, commercial organizations can use gender classification for advertising. Law enforcement may use gender classification as part of legal investigations. Others may use gender information for social reasons. Here we explore language independent gender classification. Our approach predicts gender using five color-based features extracted from Twitter profiles (e.g., the background color in a user's profile page). Most other methods for gender prediction are typically language dependent. Those methods use high-dimensional spaces consisting of unique words extracted from such text fields as postings, user names, and profile descriptions. Our approach is independent of the user's language, efficient, and scalable, while attaining a good level of accuracy. We prove the validity of our approach by examining different classifiers over a large dataset of Twitter profiles.

Report on the Ninth International Workshop on Location and the Web (LocWeb 2019)

Sigir Forum, Dec 1, 2019

LocWeb 2019 was the ninth workshop in the LocWeb workshop series at the intersection of location-... more LocWeb 2019 was the ninth workshop in the LocWeb workshop series at the intersection of location-based services and Web architecture and was held at The Web Conference, WWW 2019, in San Francisco. It focused on Web-scale services and systems facilitating location-aware information access as well as on Spatial Social Behavior Analytics on the Web. The LocWeb 2019 workshop had contributions ranging from location data analysis over vocational trips and visualization of linked data to geolocation and browser integration. This report briefly presents the theme, contributions, and discussions of the workshop.

Report on the tenth international workshop on location and the web (LocWeb 2020)

Sigir Forum, Jun 1, 2020

LocWeb 2020 was the tenth workshop in the LocWeb workshop series at the intersection of location-... more LocWeb 2020 was the tenth workshop in the LocWeb workshop series at the intersection of location-based analytics and Web architecture and was held at The Web Conference, WWW 2020, on 21stApril 2020. The focus was on Web-scale services and systems facilitating location-aware information access as well as on Spatial Social Computing on the Web. The LocWeb 2019 workshop had contributions ranging from urban location data analysis over geospatial open data access to worldwide media consumption patterns.The workshop and conference was intended to be held in Taipei, Taiwan, but was instead held as a virtual workshop since also The Web Conference itself moved to be an online-only event, due to the current pandemic. That also gave rise to a number of discussions around spatial models, online work modes, and current mitigation efforts.This report presents an overview of these discussions, after an introduction to the workshop theme and the individual contributions.

Deception detection in Twitter

Social Network Analysis and Mining, Jun 30, 2015

Online Social Networks (OSNs) play a significant role in the daily life of hundreds of millions o... more Online Social Networks (OSNs) play a significant role in the daily life of hundreds of millions of people. However, many user profiles in OSNs contain deceptive information. Existing studies have shown that lying in OSNs is quite widespread, often for protecting a user's privacy. In this paper, we propose a novel approach for detecting deceptive profiles in OSNs. We specifically define a set of analysis methods for detecting deceptive information about user genders and locations in Twitter. First, we collected a large dataset of Twitter profiles and tweets. Next, we defined methods for gender guessing from Twitter profile colors and names. Subsequently, we apply Bayesian classification and K-means clustering algorithms to Twitter profile characteristics (e.g., profile layout colors, first names, user names, spatiotemporal information) and geolocations to analyze the user behavior. We establish the overall accuracy of each indicator through extensive experimentation with our crawled dataset. Based on the outcomes of our approach, we are able to detect deceptive profiles about gender and location with a reasonable accuracy.

An empirical study of data race detector tools

The industry of software applications has been increased significantly because of the high demand... more The industry of software applications has been increased significantly because of the high demand of using the software applications. This revolution leads on developing many concurrent software systems. Noticeably, some of these concurrent software systems have falsely report data race condition to one or more of their shared variables. Debugging such concurrent software systems to find the race condition is a challenge, especially for large and complex software systems. Since the race condition concerned mostly ignored in the concurrent software systems, adopting it could help to ensure the efficiency of these software systems. There are few detector tools that have been known in the industry focusing on data race detectors. This paper aims to study those tools. We are going to conduct empirical study of data race using well known tools in order to measure the correctness, performances and effectiveness of those tools in practical by using some benchmarks. Those benchmarks will be tested on each tool and compare it with others to see the similarity and differentiate.

Data analysis to uncover intruder attacks using data mining techniques

Radicalism is becoming an increasingly potential concern. Intruder groups are using handful tacti... more Radicalism is becoming an increasingly potential concern. Intruder groups are using handful tactics and radicalism has disparaging effects, particularly in Gulf and Pakistan region. Forecasting the pattern of attacks is a complex task. This research paper presents new insights on intruder groups and targets using data mining algorithms. We propose a framework, which uses historical data to train machine-learning classifiers and can predict intruder groups and attack types based on selected features. We analyzed that the major victims of intruder groups would be citizen and property, government, police, and military sectors. We figured out that J48 and IBK learning algorithms perform consistently well under various experimental settings.

Coronavirus Pandemic (COVID-19)

IGI Global eBooks, Jun 10, 2022

People are afraid about COVID-19 and are actively talking about it on social media platforms such... more People are afraid about COVID-19 and are actively talking about it on social media platforms such as Twitter. People are showing their emotions openly in their tweets on Twitter. It's very important to perform sentiment analysis on these tweets for finding COVID-19's impact on people's lives. Natural language processing, textual processing, computational linguists, and biometrics are applied to perform sentiment analysis to identify and extract the emotions. In this work, sentiment analysis is carried out on a large Twitter dataset of English tweets. Ten emotional themes are investigated. Experimental results show that COVID-19 has spread fear/anxiety, gratitude, happiness and hope, and other mixed emotions among people for different reasons. Specifically, it is observed that positive news from top officials like Trump of chloroquine as cure to COVID-19 has suddenly lowered fear in sentiment, and happiness, gratitude, and hope started to rise. But, once FDA said, chloroquine is not effective cure, fear again started to rise.

Machine learning based classification of normal, slow and fast walking by extracting multimodal features from stride interval time series

Mathematical Biosciences and Engineering, 2021

The gait speed affects the gait patterns (biomechanical and spatiotemporal parameters) of distinc... more The gait speed affects the gait patterns (biomechanical and spatiotemporal parameters) of distinct age populations. Classification of normal, slow and fast walking is fundamental for understanding the effects of gait speed on the gait patterns and for proper evaluation of alternations associated with it. In this study, we extracted multimodal features such as time domain and entropy-based complexity measures from stride interval signals of healthy subjects moving with normal, slow and fast speeds. The classification between different gait speeds was performed using machine learning classifiers such as classification and regression tree (CART), support vector machine linear (SVM-L), Naïve Bayes, neural network, and ensemble classifiers (random forest (RF), XG boost, averaged neural network (AVNET)). The performance was evaluated in term of accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), p-value, area under the receiver operating characteristic curve (AUC). To distinguish the slow and normal gait walking, the highest performance was yielded in terms of accuracy (100%), p-value (0.004), and AUC (1.00) using RF, XGB-L followed by XGB-Tree with accuracy (88%), p-value (0.04) and AUC (1.00). To classify the fast and normal walking, the highest performance was obtained with accuracy (88%), p-value (0.04) using XGB-L, XGB-Tree and AVNET. The highest AUC (0.94) was obtained using NB. To discriminate the fast and slow gait walking, the highest performance was obtained using SVM-R, NNET, RF, AVNET with accuracy (88%), p-value (0.04) and AUC (0.94) using RF and AUC (0.96) using XGB-L.

CommuniMents

IGI Global eBooks, 2021

Social media has revolutionized human communication and styles of interaction. Due to its effecti... more Social media has revolutionized human communication and styles of interaction. Due to its effectiveness and ease, people have started using it increasingly to share and exchange information, carry out discussions on various events, and express their opinions. Various communities may have diverse sentiments about events and it is an interesting research problem to understand the sentiments of a particular community for a specific event. In this article, the authors propose a framework CommuniMents which enables us to identify the members of a community and measure the sentiments of the community for a particular event. CommuniMents uses automated snowball sampling to identify the members of a community, then fetches their published contents (specifically tweets), pre-processes the contents and measures the sentiments of the community. The authors perform qualitative and quantitative evaluation for a variety of real world events to validate the effectiveness of the proposed framework.

IoT-IaaS: A New Public Cloud Service to Unleash Innovation in the IoT Space

Springer proceedings in complexity, 2019

IoT solution developers today are hampered by the regulatory permit burdens and high up-front dep... more IoT solution developers today are hampered by the regulatory permit burdens and high up-front deployment and maintenance costs, particularly in the public domain. Essentially, it keeps the development of IoT solutions requiring large deployments in the purview of deep-pocketed players, to the exclusion of millions of small developers who may have figured out novel solutions to problems, but lack the resources to pilot them. This is akin to the situation of cellphones before the release of SDKs for Apple iOS and Android smartphones; phones with relatively capable hardware were often restricted to running the dozen-or-so apps they shipped with. Together, smartphone SDKs and public cloud services, which were becoming available at around the same time, less well-resourced developers were able to bring their ideas for apps to the public, thus launching the smartphone revolution. In this paper we conducted a survey of studies that describe various pieces of the technology puzzle that could contribute towards democratizing access to public IoT resources.

Latent Dirichlet Allocation and POS Tags Based Method for External Plagiarism Detection

IGI Global eBooks, 2019

Inthisarticlewepresentanewsemanticandsyntactic-basedmethodforexternalplagiarismdetection. Inthepr... more Inthisarticlewepresentanewsemanticandsyntactic-basedmethodforexternalplagiarismdetection. Intheproposedapproach,latentdirichletallocation(LDA)andpartsofspeech(POS)tagsareused together to detect plagiarism between the sample and a number of source documents. The basic hypothesisisthatconsideringsemanticandsyntacticinformationbetweentwotextdocumentsmay improvetheperformanceoftheplagiarismdetectiontask.Ourmethodisbasedontwosteps,naming, whichisapre-processingwherewedetectthetopicsfromthesentencesindocumentsusingtheLDA andconverteachsentenceinPOStagsarray;thenapostprocessingstepwherethesuspiciouscases areverifiedpurelyonthebasisofsemanticrules.Fortwotypesofexternalplagiarism(copyand randomobfuscation),weempiricallycompareourapproachtothestate-of-the-artN-grambasedand stop-wordN-grambasedmethodsandobservesignificantimprovements.

Probability weighted moments regularization based blind image De-blurring

Multimedia Tools and Applications, Apr 4, 2019

The main objective of blind image de-blurring is to recover a sharp image from a given blurry ima... more The main objective of blind image de-blurring is to recover a sharp image from a given blurry image. A good estimation of the kernel plays an important role in recovering a sharp image. However, if the local object textures are neglected when the kernel is being estimated, this can lead to over-smoothing or can produce a strong ringing effect. In this paper, a new image regularization term based on the Probability Weighted Moments (PWM) for kernel estimation is proposed named as Probability Weighted Moments Regularization (PWMR). PWMR has the ability to preserve the small local texture structure in an image while minimizing the artifacts. Further, it can preserve the better contrast information between neighboring pixels and their corresponding central pixels in a current sliding window; moreover, it has the ability to resist outliers even in a small sample size. The kernel estimated by PWMR is subsequently used to recover the sharp latent image. An extensive comparison of synthetic and real standard benchmark images indicates the effectiveness of PWMR compared to current state-of-the-art blind image de-blurring methods.

Emerging Computer Vision Based Machine Learning Issues for Smart Cities

Machine learning algorithms boast remarkable predictive capabilities and deep learning, a branch ... more Machine learning algorithms boast remarkable predictive capabilities and deep learning, a branch of machine learning, has already provided the much required breakthroughs for recognition and authentication. This has enabled the deployment of a face recognition based biometric identification system by the Department of Homeland Security at U.S. airports. Deep learning algorithms require huge amounts of data for training. However, this shall not be an issue in smart cities. Instead, the ability to use the same deep learning technology for ulterior motives raise some issues. Machine learning algorithms have already been developed which can generate fake images and videos and rendering humans incapable of differentiating between real and generated content. Such content can be used for spreading disinformation regarding individuals and may lead to legal issues. Any system, relying on face recognition may be mislead using such technology. Similarly, researchers were able to create master ...

Empirical Evaluation of Profile Characteristics for Gender Classification on Twitter

2013 12th International Conference on Machine Learning and Applications, 2013

Online Social Networks (OSNs) provide reliable communication among users from different countries... more Online Social Networks (OSNs) provide reliable communication among users from different countries. The volume of texts generated by OSNs is huge and highly informative. Gender classification can serve commercial organizations for advertising, law enforcement for legal investigation, and others for social reasons. Here we explore profile characteristics for gender classification on Twitter. Unlike existing approaches to gender classification that depend heavily on posted text such as tweets, here we study the relative strengths of different characteristics extracted from Twitter profiles (e.g., first name and background color in a user's profile page). Our goal is to evaluate profile characteristics with respect to their predictive accuracy and computational complexity. In addition, we provide a novel technique to reduce the number of features of text-based profile characteristics from the order of millions to a few thousands and, in some cases, to only 40 features. We prove the validity of our approach by examining different classifiers over a large dataset of Twitter profiles.

An empirical study of data race detector tools

2013 25th Chinese Control and Decision Conference (CCDC), 2013

The industry of software applications has been increased significantly because of the high demand... more The industry of software applications has been increased significantly because of the high demand of using the software applications. This revolution leads on developing many concurrent software systems. Noticeably, some of these concurrent software systems have falsely report data race condition to one or more of their shared variables. Debugging such concurrent software systems to find the race condition is a challenge, especially for large and complex software systems. Since the race condition concerned mostly ignored in the concurrent software systems, adopting it could help to ensure the efficiency of these software systems. There are few detector tools that have been known in the industry focusing on data race detectors. This paper aims to study those tools. We are going to conduct empirical study of data race using well known tools in order to measure the correctness, performances and effectiveness of those tools in practical by using some benchmarks. Those benchmarks will be tested on each tool and compare it with others to see the similarity and differentiate.

Managing Online Requirements Elicitation in Ultra-Large Software System

Detecting deception in Online Social Networks

2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2014), 2014

Over the past decade Online Social Networks (OSNs) have been helping hundreds of millions of peop... more Over the past decade Online Social Networks (OSNs) have been helping hundreds of millions of people develop reliable computer-mediated relations. However, many user profiles in OSNs contain misleading, inconsistent or false information. Existing studies have shown that lying in OSNs is quite widespread, often for protecting a user's privacy. In order for OSNs to continue expanding their role as a communication medium in our society, it is crucial for information posted on OSNs to be trusted. Here we define a set of analysis methods for detecting deceptive information about user genders in Twitter. In addition, we report empirical results with our stratified data set consisting of 174,600 Twitter profiles with a 50-50 breakdown between male and female users. Our automated approach compares gender indicators obtained from different profile characteristics including first name, user name, and layout colors. We establish the overall accuracy of each indicator and the strength of all possible values for each indicator through extensive experimentations with our data set. We define male trending users and female trending users based on two factors, namely the overall accuracy of each characteristic and the relative strength of the value of each characteristic for a given user. We apply a Bayesian classifier to the weighted average of characteristics for each user. We flag for possible deception profiles that we classify as male or female in contrast with a selfdeclared gender that we obtain independently of Twitter profiles. Finally, we use manual inspections on a subset of profiles that we identify as potentially deceptive in order to verify the correctness of our predictions.

Reducing Travel Time by Incident Reporting via CrowdSourcing

— The contribution of this work is the creation of a novel system that enables motorists who witn... more — The contribution of this work is the creation of a novel system that enables motorists who witness incidents to submit reports to our system via the web. These reports are aggregated, validated and verified automatically. Then, they are used to update the road network graph. In this work, we designed and implemented an incident reporting system whereby users can report an incident such as an accident or construction on a road network. We extended the FreeSim simulator to accommodate our incident reporting system. Experimental results showed that our system is capable of reducing the travel time of users. We also presented our verification algorithms that are used to verify that reports are fact. Current approaches to congestion detection such as loop detectors probe vehicles, and video image detection may not be available on arterial streets. These technologies may not be available in countries whose transportation budget is low. Our model is less expensive, easy to implement and ...

Automated transportation transfer detection using GPS enabled smartphones

— Understanding the mobility of a traveller from mobile sensor data is an important area of work ... more — Understanding the mobility of a traveller from mobile sensor data is an important area of work in context aware and ubiquitous computing. Given a multimodal GPS trace, we will identify where in the GPS trace the traveller changed transportation modes. For example, where in the GPS trace the traveller alight a bus and boards a train, or where did the client stop running and start walking. Using data mining schemes to understand mobility data, in conjunction with real world observations, we propose an algorithm to identify mobility transfer points automatically. We compared the proposed algorithm against the state of the art that is used in the previously proposed work. Evaluation on real world data collected from GPS enabled mobile phones indicate that the proposed algorithm is accurate, has a good coverage, and a good asymptotic run time complexity. I.