Department of Computer Information and Graphics Technology

Permanent URI for this community

https://hdl.handle.net/1805/6256

Browse

Now showing 1 - 10 of 76

A Computationally Effective Pedestrian Detection using Constrained Fusion with Body Parts for Autonomous Driving
(IEEE, 2021) Islam, Muhammad Mobaidul; Newaz, Abdullah Al Redwan; Tian, Renran; Homaifar, Abdollah; Karimoddini, Ali; Computer Information and Graphics Technology, School of Engineering and Technology
This paper addresses the problem of detecting pedestrians using an enhanced object detection method. In particular, the paper considers the occluded pedestrian detection problem in autonomous driving scenarios where the balance of performance between accuracy and speed is crucial. Existing works focus on learning representations of unique persons independent of body parts semantics. To achieve a real-time performance along with robust detection, we introduce a body parts based pedestrian detection architecture where body parts are fused through a computationally effective constraint optimization technique. We demonstrate that our method significantly improves detection accuracy while adding negligible runtime overhead. We evaluate our method using a real-world dataset. Experimental results show that the proposed method outperforms existing pedestrian detection methods.
Accelerating complex modeling workflows in CyberWater using on-demand HPC/Cloud resources
(IEEE, 2021-09) Li, Feng; Chen, Ranran; Fu, Yuankun; Song, Fengguang; Liang, Yao; Ranawaka, Isuru; Pamidighantam, Sudhakar; Luna, Daniel; Liang, Xu; Computer Information and Graphics Technology, School of Engineering and Technology
Workflow management systems (WMSs) are commonly used to organize/automate sequences of tasks as workflows to accelerate scientific discoveries. During complex workflow modeling, a local interactive workflow environment is desirable, as users usually rely on their rich, local environments for fast prototyping and refinements before they consider using more powerful computing resources. However, existing WMSs do not simultaneously support local interactive workflow environments and HPC resources. In this paper, we present an on-demand access mechanism to remote HPC resources from desktop/laptop-based workflow management software to compose, monitor and analyze scientific workflows in the CyberWater project. Cyber-Water is an open-data and open-modeling software framework for environmental and water communities. In this work, we extend the open-model, open-data design of CyberWater with on-demand HPC accessing capacity. In particular, we design and implement the LaunchAgent library, which can be integrated into the local desktop environment to allow on-demand usage of remote resources for hydrology-related workflows. LaunchAgent manages authentication to remote resources, prepares the computationally-intensive or data-intensive tasks as batch jobs, submits jobs to remote resources, and monitors the quality of services for the users. LaunchAgent interacts seamlessly with other existing components in CyberWater, which is now able to provide advantages of both feature-rich desktop software experience and increased computation power through on-demand HPC/Cloud usage. In our evaluations, we demonstrate how a hydrology workflow that consists of both local and remote tasks can be constructed and show that the added on-demand HPC/Cloud usage helps speeding up hydrology workflows while allowing intuitive workflow configurations and execution using a desktop graphical user interface.
ACTS: Extracting Android App Topological Signature through Graphlet Sampling
(IEEE, 2016-10) Peng, Wei; Gao, Tianchong; Sisodia, Devkishen; Saha, Tanay Kumar; Li, Feng; Al Hasan, Mohammad; Computer Information and Graphics Technology, School of Engineering and Technology
Android systems are widely used in mobile & wireless distributed systems. In the near future, Android is believed to dominate the mobile distributed environment. However, with the popularity of Android-based smartphones/tablets comes the rampancy of Android-based malware. In this paper, we propose a novel topological signature of Android apps based on the function call graphs (FCGs) extracted from their Android App Packages (APKs). Specifically, by leveraging recent advances in graphlet sampling, the proposed method fully captures the invocator-invocatee relationship at local neighborhoods in an FCG without exponentially inflating the state space. Using real benign app and malware samples, we demonstrate that our method, ACTS (App topologiCal signature through graphleT Sampling), can detect malware and identify malware families robustly and efficiently. More importantly, we demonstrate that, without augmenting the FCG with any semantic features such as bytecode-based vertex typing, local topological information captured by ACTS alone can achieve a high malware detection accuracy. Since ACTS only uses structural features, which are orthogonal to semantic features, it is expected that combining them would give a greater improvement in malware detection accuracy than combining non-orthogonal semantic features.
Analyzing the Correlations between the Uninsured and Diabetes Prevalence Rates in Geographic Regions in the United States
(IEEE, 2017-07) Luo, Xiao; Computer Information and Graphics Technology, School of Engineering and Technology
The increasing prevalence of diagnosed diabetes has drawn attentions of researchers in recently years. Research has been done in finding the correlations between diabetes prevalence with socioeconomic factors, obesity, social behaviors and so on. Since 2010, diabetes preventive services have been covered under health insurance plans in order to reduce diabetes burden and control the increasing of diabetes prevalence. In this study, a hierarchical clustering model is proposed by using Expectation-Maximization algorithm to investigate the correlations between the uninsured and diabetes prevalence rates in 3142 counties in United States for years from 2009 to 2013. The results identified geographic disparities in the uninsured and diabetes prevalence rates of individual years and over consecutive years.
Analyzing the symptoms in colorectal and breast cancer patients with or without type 2 diabetes using EHR data
(Sage, 2021) Luo, Xiao; Storey, Susan; Gandhi, Priyanka; Zhang, Zuoyi; Metzger, Megan; Huang, Kun; Computer Information and Graphics Technology, School of Engineering and Technology
This research extracted patient-reported symptoms from free-text EHR notes of colorectal and breast cancer patients and studied the correlation of the symptoms with comorbid type 2 diabetes, race, and smoking status. An NLP framework was developed first to use UMLS MetaMap to extract all symptom terms from the 366,398 EHR clinical notes of 1694 colorectal cancer (CRC) patients and 3458 breast cancer (BC) patients. Semantic analysis and clustering algorithms were then developed to categorize all the relevant symptoms into eight symptom clusters defined by seed terms. After all the relevant symptoms were extracted from the EHR clinical notes, the frequency of the symptoms reported from colorectal cancer (CRC) and breast cancer (BC) patients over three time-periods post-chemotherapy was calculated. Logistic regression (LR) was performed with each symptom cluster as the response variable while controlling for diabetes, race, and smoking status. The results show that the CRC and BC patients with Type 2 Diabetes (T2D) were more likely to report symptoms than CRC and BC without T2D over three time-periods in the cancer trajectory. We also found that current smokers were more likely to report anxiety (CRC, BC), neuropathic symptoms (CRC, BC), anxiety (BC), and depression (BC) than non-smokers.
Android Malware Detection via Graphlet Sampling
(IEEE, 2018-11) Gao, Tianchong; Peng, Wei; Sisodia, Devkishen; Saha, Tanay Kumar; Li, Feng; Al Hasan, Mohammad; Computer Information and Graphics Technology, School of Engineering and Technology
Android systems are widely used in mobile & wireless distributed systems. In the near future, Android is believed to dominate the mobile distributed environment. However, with the popularity of Android-based smartphones/tablets comes the rampancy of Android-based malware. In this paper, we propose a novel topological signature of Android apps based on the function call graphs (FCGs) extracted from their Android App PacKages (APKs). Specifically, by leveraging recent advances on graphlet mining, the proposed method fully captures the invocator-invocatee relationship at local neighborhoods in an FCG without exponentially inflating the state space. Using real benign app and malware samples, we demonstrate that our method, ACTS (App topologiCal signature through graphleT Sampling), can detect malware and identify malware families robustly and efficiently. More importantly, we demonstrate that, without augmenting the FCG with any semantic features such as bytecode-based vertex typing, local topological information captured by ACTS alone can achieve a high malware detection accuracy. Since ACTS only uses structural features, which are orthogonal to semantic features, it is expected that combining them would give a greater improvement in malware detection accuracy than combining non-orthogonal semantic features.
Applying Rating Systems to Challenge Based Cybersecurity Education
(IEEE, 2017-01) Samuels, Andrew; Li, Feng; Justice, Connie; Computer Information and Graphics Technology, School of Engineering and Technology
As technology becomes a larger part of everyday life, it becomes increasingly more important for CS and CIT students to learn about cyber security during their education. While many cyber security oriented courses exist, it is also necessary that students must be able to work and learn in an environment that resembles a real world context. To address this problem it has become common to adapt cyber security challenges into the classroom as a method for students to put their knowledge into practice. One problem is that these challenges can vary considerably in levels of difficulty, which makes it problematic for students to be able to select a challenge that is an appropriate difficulty for their skill level. A potential solution to this problem could be to adapt a rating system to rank both the students and the challenges. This would then allow the students to easily select challenges that are appropriate for them to engage with by comparing their own rating with the rating of available challenges. In this project we propose methods that could be used to adapt a rating system to an existing cyber security education program. Finally we propose a method to survey students that interact with the program so that the effect of the rating system can be measured.
The Building Blocks for Enhanced Technological Literacy
(Indiana Association for Career and Technical Education, 2015) McLeod, Alister; Savoy, April
Many students have experience with smart phones, internet browsing, and social networking. Although exposure to these types of technologies are pure indicators of society’s evolution towards a more integrated and pervasive computing environment, they do not serve as accurate indicators of technological literacy. With the advent and rapid expansion of knowledge and technology intensive industries, these skills do not provide a sufficient core/foundational literacy to the development of characteristics possessed by technologically literate students. Gonzales and Renshaw (2005) identified six computing competency skill areas for pre-engineering majors – 1) Computer use and file management, 2) Word processing, 3) Spreadsheets, 4)Databases, 5) Presentations, and 6) Information and Communications. These competencies, previously the focus of engineers, have now transferred to society at large with 38% of all the value created in the U.S. requiring the skills of a technologically literate workforce (National Science Board, 2010). The widespread use of technology in society and everyday life has forced the need of technological literacy amongst non-Science, Technology, Engineering and Mathematics (STEM) majors, hence the need for a comprehensive course that provides the building blocks for technological literacy. However, there is still skepticism on the value of classes that focus on the introduction of computers. These classes lay the foundation that is crucial for non-STEM majors to become technologically literate. The goal of this paper is to show that there is still a need for these types of classes and also that they provide a gateway for these students to become technologically literate before their graduation. By reviewing the performance of 130 students in an introductory level computing course at Indiana State University the need for such a class will be evidenced.
Building cohesion in distributed telemedicine teams: findings from the Department of Veterans Affairs National Telestroke Program
(BMJ, 2021) Patel, Himalaya; Damush, Teresa M.; Miech, Edward J.; Rattray, Nicholas A.; Martin, Holly A.; Savoy, April; Plue, Laurie; Anderson, Jane; Martini, Sharyl; Graham, Glenn D.; Williams, Linda S.
Background As telemedicine adoption increases, so does the importance of building cohesion among physicians in telemedicine teams. For example, in acute telestroke services, stroke specialists provide rapid remote stroke assessment and treatment to patients at hospitals without stroke specialty care. In the National Telestroke Program (NTSP) of the U.S. Department of Veterans Affairs, a virtual (distributed) hub of stroke specialists throughout the country provides 24/7 consultations nationwide. We examined how these specialists adapted to distributed teamwork, and we identified cohesion-related factors in program development and support. Methods We studied the virtual hub of stroke specialists employed by the NTSP. Semi-structured, confidential interviews with stroke specialists in the virtual hub were recorded and transcribed. We explored the extent to which these specialists had developed a sense of shared identity and team cohesion, and we identified factors in this development. Using a qualitative approach with constant comparison methods, two researchers coded each interview transcript independently using a shared codebook. We used matrix displays to identify themes, with special attention to team cohesion, communication, trust, and satisfaction. Results Of 13 specialists with at least 8 months of NTSP practice, 12 completed interviews; 7 had previously practiced in telestroke programs in other healthcare systems. Interviewees reported high levels of trust and team cohesion, sometimes even more with their virtual colleagues than with co-located colleagues. Factors facilitating perceived team cohesion included a weekly case conference call, a sense of transparency in discussing challenges, engagement in NTSP development tasks, and support from the NTSP leadership. Although lack of in-person contact was associated with lower cohesion, annual in-person NTSP meetings helped mitigate this issue. Despite technical challenges in establishing a new telehealth system within existing national infrastructure, providers reported high levels of satisfaction with the NTSP. Conclusion A virtual telestroke hub can provide a sense of team cohesion among stroke specialists at a level comparable with a standard co-located practice. Engaging in transparent discussion of challenging cases, reviewing new clinical evidence, and contributing to program improvements may promote cohesion in distributed telemedicine teams.
Can Early-Assignment Grades Predict Final Grades in IT Courses?: American Society for Engineering Education
(2017) Ramanathan, Parameswari; Fernandez, Eugenia; Computer Information and Graphics Technology, School of Engineering and Technology

Browse

Browsing Department of Computer Information and Graphics Technology by Title

Results Per Page

Sort Options