IU Indianapolis ScholarWorks :: Browsing by Author "Raje, Rajeev R."

Browsing by Author "Raje, Rajeev R."

Now showing 1 - 10 of 28

CDASH: Community Data Analytics for Social Harm Prevention
(IEEE, 2018-09) Pandey, Saurabh; Chowdhury, Nahida; Patil, Milan; Raje, Rajeev R.; Shreyas, C. S.; Mohler, George; Carter, Jeremy; Computer and Information Science, School of Science
Communities are adversely affected by heterogeneous social harm events (e.g., crime, traffic crashes, medical emergencies, drug use) and police, fire, health and social service departments are tasked with mitigating social harm through various types of interventions. Smart cities of the future will need to leverage IoT, data analytics, and government and community human resources to most effectively reduce social harm. Currently, methods for collection, analysis, and modeling of heterogeneous social harm data to identify government actions to improve quality of life are needed. In this paper we propose a system, CDASH, for synthesizing heterogeneous social harm data from multiples sources, identifying social harm risks in space and time, and communicating the risk to the relevant community resources best equipped to intervene. We discuss the design, architecture, and performance of CDASH. CDASH allows users to report live social harm events using mobile hand-held devices and web browsers and flags high risk areas for law enforcement and first responders. To validate the methodology, we run simulations on historical social harm event data in Indianapolis illustrating the advantages of CDASH over recently introduced social harm indices and existing point process methods used for predictive policing.
Computer Program Instrumentation Using Reservoir Sampling & Pin++
(2019-08) Upp, Brandon E.; Hill, James H.; Tuceryan, Mihran; Raje, Rajeev R.
This thesis investigates techniques for improving real-time software instrumentation techniques of software systems. In particular, this thesis investigates two aspects of this real-time software instrumentation. First, this thesis investigates techniques for achieving different levels of visibility (i.e., ensuring all parts of a system are represented, or visible, in final results) into a software system without compromising software system performance. Secondly, this thesis investigates how using multi-core computing can be used to further reduce instrumentation overhead. The results of this research show that reservoir sampling can be used to reduce instrumentation overhead. Reservoir sampling at a rate of 20%, combined with parallelized disk I/O, added 34.1% additional overhead on a four-core machine, and only 9.9% additional overhead on a sixty-four core machine while also providing the desired system visibility. Additionally, this work can be used to further improve the performance of real-time distributed software instrumentation.
A Conceptual Framework for Distributed Software Quality Network
(2019-08) Patil, Anushka H.; Hill, James H.; Raje, Rajeev R.; Tuceryan, Mihran
The advancement in technology has revolutionized the role of software in recent years. Software usage is practically found in all areas of the industry and has become a prime factor in the overall working of the companies. Simultaneously with an increase in the utilization of software, the software quality assurance parameters have become more crucial and complex. Currently the quality measurement approaches, standards, and models that are applied in the software industry are extremely divergent. Many a time the correct approach will wind up to be a combination of di erent concepts and techniques from di erent software assurance approaches [1]. Thus, having a platform that provides a single workspace for incorporating multiple software quality assurance approaches will ease the overall software quality process. In this thesis we have proposed a theoretical framework for distributed software quality assurance, which will be able to continuously monitor a source code repository; create a snapshot of the system for a given commit (both past and present); the snapshot can be used to create a multi-granular blockchain of the system and its metrics (i.e.,metadata) which we believe will let the tool developers and vendors participate continuously in assuring quality and security of systems and in the process be accessible when required while being rewarded for their services.
COVID CV: A System for Creating Holistic Academic CVs during a Global Pandemic
(IEEE, 2021-05) Raja, Umesh; Chowdhury, Nahida Sultana; Raje, Rajeev R.; Wheeler, Rachel; Williams, Jane; Ganci, Aaron; Computer and Information Science, School of Science
The effects of the Covid pandemic have been, similar to the population at-large, unequal on academicians - some groups have been more susceptible than others. Traditional CVs are inadequate to highlight these imbalances. CovidCV is a framework for academicians that allows them to document their life in a holistic way during the pandemic. It creates a color-coded CV from the user's data entries documenting the work and home life and categorizing corresponding events as good or bad. It, thus, provides a visual representation of an academician's life during the current pandemic. The user can mark any event as major or minor indicating the impact of the event on their life. The CovidCV prototypical system is developed using a three tier architecture. The first tier, the front-end, is a user interface layer that is a web application. This prototype has a back-end layer consisting of two tiers which are responsible for handling the business logic and the data management respectively. The CovidCV system design is described in this paper. A preliminary experimentation with the prototype highlights the usefulness of CovidCV.
Cyberbullying Detection System with Multiple Server Configurations
(IEEE, 2018-05) Pawar, Rohit; Agrawal, Yash; Joshi, Akshay; Gorrepati, Ranadheer; Raje, Rajeev R.; Computer and Information Science, School of Science
Due to the proliferation of online networking, friendships and relationships - social communications have reached a whole new level. As a result of this scenario, there is an increasing evidence that social applications are frequently used for bullying. State-of-the-art studies in cyberbullying detection have mainly focused on the content of the conversations while largely ignoring the users involved in cyberbullying. To encounter this problem, we have designed a distributed cyberbullying detection system that will detect bullying messages and drop them before they are sent to the intended receiver. A prototype has been created using the principles of NLP, Machine Learning and Distributed Systems. Preliminary studies conducted with it, indicate a strong promise of our approach.
Disparity between the Programmatic Views and the User Perceptions of Mobile Apps
(IEEE, 2017-12) Chowdhury, Nahida Sultana; Raje, Rajeev R.; Computer and Information Science, School of Science
User perception in any mobile-app ecosystem, is represented as user ratings of apps. Unfortunately, the user ratings are often biased and do not reflect the actual usability of an app. To address the challenges associated with selection and ranking of apps, we need to use a comprehensive and holistic view about the behavior of an app. In this paper, we present and evaluate Trust based Rating and Ranking (TRR) approach. It relies solely on an apps' internal view that uses programmatic artifacts. We compute a trust tuple (Belief, Disbelief, Uncertainty - B, D, U) for each app based on the internal view and use it to rank the order apps offering similar functionality. Apps used for empirically evaluating the TRR approach are collected from the Google Play Store. Our experiments compare the TRR ranking with the user review-based ranking present in the Google Play Store. Although, there are disparities between the two rankings, a slightly deeper investigation indicates an underlying similarity between the two alternatives.
Enhancing Trust-based Data Analytics for Forecasting Social Harm
(IEEE, 2020-09) Chowdhury, Nahida Sultana; Raje, Rajeev R.; Pandey, Saurabh; Mohler, George; Carter, Jeremy; School of Public and Environmental Affairs
First responders deal with a variety of “social harm” events (e.g. crime, traffic crashes, medical emergencies) that result in physical, emotional, and/or financial hardships. Through data analytics, resources can be efficiently allocated to increase the impact of interventions aimed at reducing social harm -T-CDASH (Trusted Community Data Analytics for Social Harm) is an ongoing joint effort between the Indiana University Purdue University Indianapolis (IUPUI), the Indianapolis Metropolitan Police Department (IMPD), and the Indianapolis Emergency Medical Services (IEMS) with this goal of using data analytics to efficiently allocate resources to respond to and reduce social harm. In this paper, we make several enhancements to our previously introduced trust estimation framework T-CDASH. These enhancements include additional metrics for measuring the effectiveness of forecasts, evaluation on new datasets, and an incorporation of collaborative trust models. To empirically validate our current work, we ran simulations on newly collected 2019 and 2020 (Jan-April) social harm data from the Indianapolis metro area. We describe the behavior and significance of the collaboration and their comparison with previously introduced stand-alone models.
Heuristic Based Sensor Ranking Algorithm for Indoor Tracking Applications
(Office of the Vice Chancellor for Research, 2013-04-05) Rybarczyk, Ryan; Raje, Rajeev R.; Tuceryan, Mihran
Location awareness in an indoor setup is an important function necessary in many application domains such as asset management, critical care, and augmented reality. Location awareness, or tracking, of an object within an indoor setting requires a high degree of accuracy, as room-to-room location may be very important. With the current proliferation of smart devices, with often a multitude of built-in sensors, and inexpensive sensors it is now possible to build a network of sensors, for the purpose of tracking, within an indoor environment without the high cost of installing the needed tracking infrastructure. In an effort to increase accuracy, as well as coverage area, various different sensors may be used in the tracking of an object. In this heterogeneous tracking situation, it is important for the tracking infrastructure to quickly and accurately decide which, all or a subset, of available sensors to use. Challenges related to heterogeneous data fusion and clock synchronization, must be addressed in order to provide accurate location estimates. We have proposed a heuristic based ranking algorithm to address these challenges. In this algorithm, the individual sensors are ranked based upon their quality of service (QoS) attributes and the resulting ranking is used by a filtering service during the sensor selection process. This information is provided to the filtering service when a sensor joins the tracking infrastructure and is subsequently only updated during idle periods, thereby, there avoiding additional overhead. We have implemented this algorithm into the existing prototypical Enhanced Distributed Object Tracking System or e-DOTS. e-DOTS has been extensively experimented with and the results of these experimentation validate the hypothesis that accurate indoor tracking can be achieved using a heterogeneous ensemble of cheap and mobile sensors. Our current investigation involves the incorporation of trust associated with sensors and deploying e-DOTS in a typical healthcare setup.
A Holistic Ranking Scheme for Apps
(IEEE, 2018-12) Chowdhury, Nahida Sultana; Raje, Rajeev R.; Computer and Information Science, School of Science
App stores or application distribution platforms allow users to present their sentiments about apps in the forms of ratings and reviews. However, selecting the “best one” from available apps that offer similar functionality is difficult task - especially, if the selection process only uses the average star rating of the apps. To address this challenge, we have introduced a trust-based selection and ranking system of similar apps by combining the programmatic view (“internal view”) and the sentiments based on users reviews (“external view”). The rankings based on the average star ratings are compared with the rankings generated by our approach. We empirically evaluate our approach by using the publically available apps from the Google Play Store. For this study, we have chosen a dataset of 250 apps with total 114,480 reviews from top 5 different categories - of which we focused our experiments on 90 apps that have at least 1000 reviews. Our experiments indicate that proposed holistic ranking that encompasses both the internal and external views is a better alternative than any ranking that focuses only on the internal or external view.
Integrating recommender systems into domain specific modeling tools
(2017-03-09) Nair, Arvind; Hill, James Haswell; Ning, Xia N.; Raje, Rajeev R.; Fang, Shiaofen
This thesis investigates integrating recommender systems into model-driven engineering tools powered by domain-specific modeling languages. The objective of integrating recommender systems into such tools is overcome a shortcoming of proactive modeling where the modeler must inform the model intelligence engine how to progress when it cannot automatically determine the next modeling action to execute (e.g., add, delete, or edit). To evaluate our objective, we integrated a recommender system into the Proactive Modeling Engine, which is a add-on for the Generic Modeling Environment (GME). We then conducted experiments to both subjective and objectively evaluate the enhancements to the Proactive Modeling Engine. The results of our experiments show that integrating recommender system into the Proactive Modeling Engine results in an Average Reciprocal Hit-Rank (ARHR) of 0.871. Likewise, the integration results in System Usability Scale (SUS) rating of 77. Finally, user feedback shows that the integration of the recommender system to the Proactive Modeling Engine increases the usability and learnability of domain-speci c modeling tools.

Browsing by Author "Raje, Rajeev R."

Results Per Page

Sort Options