Open Access. Powered by Scholars. Published by Universities.®

Computer Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

11624 Full-Text Articles 13321 Authors 3038814 Downloads 163 Institutions

All Articles in Computer Engineering

Faceted Search

11624 full-text articles. Page 1 of 345.

Fast On-Line Kernel Density Estimation For Active Object Localization, Anthony D. Rhodes, Max H. Quinn, Melanie Mitchell 2017 Portland State University

Fast On-Line Kernel Density Estimation For Active Object Localization, Anthony D. Rhodes, Max H. Quinn, Melanie Mitchell

Computer Science Faculty Publications and Presentations

A major goal of computer vision is to enable computers to interpret visual situations—abstract concepts (e.g., “a person walking a dog,” “a crowd waiting for a bus,” “a picnic”) whose image instantiations are linked more by their common spatial and semantic structure than by low-level visual similarity. In this paper, we propose a novel method for prior learning and active object localization for this kind of knowledge-driven search in static images. In our system, prior situation knowledge is captured by a set of flexible, kernel-based density estimations— a situation model—that represent the expected spatial structure of the ...


Developing Grounded Goals Through Instant Replay Learning, Lisa Meeden, Douglas S. Blank 2017 Swarthmore College

Developing Grounded Goals Through Instant Replay Learning, Lisa Meeden, Douglas S. Blank

Computer Science Faculty Research and Scholarship

This paper describes and tests a developmental architecture that enables a robot to explore its world, to find and remember interesting states, to associate these states with grounded goal representations, and to generate action sequences so that it can re-visit these states of interest. The model is composed of feed-forward neural networks that learn to make predictions at two levels through a dual mechanism of motor babbling for discovering the interesting goal states and instant replay learning for developing the grounded goal representations. We compare the performance of the model with grounded goal representations versus random goal representations, and find ...


Natural Language Processing Based Generator Of Testing Instruments, Qianqian Wang 2017 California State University, San Bernardino

Natural Language Processing Based Generator Of Testing Instruments, Qianqian Wang

Electronic Theses, Projects, and Dissertations

Natural Language Processing (NLP) is the field of study that focuses on the interactions between human language and computers. By “natural language” we mean a language that is used for everyday communication by humans. Different from programming languages, natural languages are hard to be defined with accurate rules. NLP is developing rapidly and it has been widely used in different industries. Technologies based on NLP are becoming increasingly widespread, for example, Siri or Alexa are intelligent personal assistants using NLP build in an algorithm to communicate with people. “Natural Language Processing Based Generator of Testing Instruments” is a stand-alone program ...


Comparing And Improving Facial Recognition Method, Brandon Luis Sierra 2017 California State University – San Bernardino

Comparing And Improving Facial Recognition Method, Brandon Luis Sierra

Electronic Theses, Projects, and Dissertations

Facial recognition is the process in which a sample face can be correctly identified by a machine amongst a group of different faces. With the never-ending need for improvement in the fields of security, surveillance, and identification, facial recognition is becoming increasingly important. Considering this importance, it is imperative that the correct faces are recognized and the error rate is as minimal as possible. Despite the wide variety of current methods for facial recognition, there is no clear cut best method. This project reviews and examines three different methods for facial recognition: Eigenfaces, Fisherfaces, and Local Binary Patterns to determine ...


Parallel Computation Using Mems Oscillator-Based Computing System, Xinrui Wang, Ilias Bilionis, Salar Safarkhani 2017 Purdue University

Parallel Computation Using Mems Oscillator-Based Computing System, Xinrui Wang, Ilias Bilionis, Salar Safarkhani

The Summer Undergraduate Research Fellowship (SURF) Symposium

In recent years, parallel computing systems such as artificial neural networks (ANNs) have been of great interest. In these systems which emulate the behavior of human brains, the processing is carried out simultaneously. However, it is still a challenging engineering problem to design highly efficient hardware for parallel computing systems. We will study the properties of networks of Microelectromechanical System (MEMS) oscillators to explore their capabilities as parallel computing infrastructure. Furthermore, we simulate the time-variant states of MEMS oscillators network under various initial conditions and performance of certain tasks. Recent theoretical results show that networks of MEMS oscillators have some ...


The Practicality Of Cloud Computing, Xiaohua (Cindy) Li 2017 Sacred Heart University

The Practicality Of Cloud Computing, Xiaohua (Cindy) Li

Cindy Li

Since its inception, cloud computing has become the current paradigm. Organizations of different size and type have embraced the concept because of its both technological and economic advantages. Sacred Heart University Library has recently published its newly designed website on the cloud. For a small academic library, what does it mean to put their online data on the cloud? This paper will analyze and discuss the advantages of cloud computing, and some potential obstacles created by it through the author’s observations. This paper hopes the uniqueness of the case will contribute to the improvement of cloud computing experience of ...


Effects Of Anthropomorphism On Trust In Human-Robot Interaction, Keith R. MacArthur, William T. Shugars, Tracy L. Sanders, Peter A. Hancock 2017 University of Central Florida

Effects Of Anthropomorphism On Trust In Human-Robot Interaction, Keith R. Macarthur, William T. Shugars, Tracy L. Sanders, Peter A. Hancock

Keith Reid MacArthur

Robots are being integrated into everyday use, making the evaluation of trust in human-robot interactions (HRI) important to ensure their acceptance and correct usage (Lee & See, 2004; Parasuraman & Riley, 1997). Goetz, Kiesler, and Powers (2003) found that participants preferred robots with an anthropomorphic appearance appropriate for the social context of the task. This preference for robots with human-like appearance may be indicative of increased levels of trust and therefore, the present research evaluates the effects of anthropomorphism on trust.
Eighteen participants (Mage = 34.22, SDage = 10.55, n = 8 male, n =10 female) with subject matter expertise in ...


Development Of A Water Quality Status And Trend Detection Tool*, Ruchir Aggarwal, Valeria Mijares, Margaret W. Gitau 2017 Purdue University

Development Of A Water Quality Status And Trend Detection Tool*, Ruchir Aggarwal, Valeria Mijares, Margaret W. Gitau

The Summer Undergraduate Research Fellowship (SURF) Symposium

Water Quality Index (WQI) models have been developed since the early 1970s. They present a means by which water quality status and trends can be compared across time and space on the basis of a composite value computed using existing water quality data. There is a need for a tool that can bring the different water quality parameters together and calculate the WQIs so as to facilitate data use in predictive modeling and water quality management. We are developing a software tool that can be used by water quality managers and others with different technical backgrounds to calculate WQI of ...


Optimal Placement Of Intrusion Detection Systems To Identify Multi-Stage Attacks In Software Defined Networks, Rebecca S. Salo, Subramaniyam Kannan, Paul C. Wood 2017 Purdue University

Optimal Placement Of Intrusion Detection Systems To Identify Multi-Stage Attacks In Software Defined Networks, Rebecca S. Salo, Subramaniyam Kannan, Paul C. Wood

The Summer Undergraduate Research Fellowship (SURF) Symposium

A major threat to network security is the multi-stage attack, where an attacker compromises an outer edge server from which he penetrates an inner server, and so on, until he gains access to protected information deep in the network. Intrusion detection systems (IDS) can detect such attacks, but limited resources constrain the number of IDS deployed. Software defined networking (SDN) provides network flexibility, and combined with network function virtualization (NFV), it enables IDS placement optimizations that can relieve cost constraint pressures. In this work, we develop a novel algorithm for placing IDS to maximize network protection benefits and minimize costs ...


Ani-Bot: A Mixed-Reality Ready Modular Robotics System, Zhuangying Xu, Yuanzhi Cao 2017 Purdue University

Ani-Bot: A Mixed-Reality Ready Modular Robotics System, Zhuangying Xu, Yuanzhi Cao

The Summer Undergraduate Research Fellowship (SURF) Symposium

DIY modular robotics has always had a strong appeal to makers and designers; being able to quickly design, build, and animate their own robots opens the possibility of bringing imaginations to life. However, current interfaces to control and program the DIY robot either lacks connection and consistency between the users and target (Graphical User Interface) or suffers from limited control capabilities due to the lack of versatility and functionality (Tangible User interface). We present Ani-Bot, a modular robotics system that allows users to construct Do-It-Yourself (DIY) robots and use mixed-reality approach to interact with them instantly. Ani-Bot enables novel user ...


Resource Estimation For Large Scale, Real-Time Image Analysis On Live Video Cameras Worldwide, Caleb Tung, Yung-Hsiang Lu, Anup Mohan 2017 Purdue University

Resource Estimation For Large Scale, Real-Time Image Analysis On Live Video Cameras Worldwide, Caleb Tung, Yung-Hsiang Lu, Anup Mohan

The Summer Undergraduate Research Fellowship (SURF) Symposium

Thousands of public cameras live-stream an abundance of data to the Internet every day. If analyzed in real-time by computer programs, these cameras could provide unprecedented utility as a global sensory tool. For example, if cameras capture the scene of a fire, a system running image analysis software on their footage in real-time could be programmed to react appropriately (perhaps call firefighters). No such technology has been deployed at large scale because the sheer computing resources needed have yet to be determined. In order to help us build computer systems powerful enough to achieve such lifesaving feats, we developed a ...


Web-Based Interactive Social Media Visual Analytics, Diego Rodríguez-Baquero, Jiawei Zhang, David S. Ebert, Sorin A. Matei 2017 Universidad de Los Andes - Colombia

Web-Based Interactive Social Media Visual Analytics, Diego Rodríguez-Baquero, Jiawei Zhang, David S. Ebert, Sorin A. Matei

The Summer Undergraduate Research Fellowship (SURF) Symposium

Real-time social media platforms enable quick information broadcasting and response during disasters and emergencies. Analyzing the massive amount of generated data to understand the human behavior requires data collection and acquisition, parsing, filtering, augmentation, processing, and representation. Visual analytics approaches allow decision makers to observe trends and abnormalities, correlate them with other variables and gain invaluable insight into these situations. In this paper, we propose a set of visual analytic tools for analyzing and understanding real-time social media data in times of crisis and emergency situations. First, we model the degree of risk of individuals’ movement based on evacuation zones ...


Compiler And Runtime Optimization Techniques For Implementation Scalable Parallel Applications, Zahra Khatami 2017 Louisiana State University and Agricultural and Mechanical College

Compiler And Runtime Optimization Techniques For Implementation Scalable Parallel Applications, Zahra Khatami

LSU Doctoral Dissertations

The compiler is able to detect the data dependencies in an application and is able to analyze the specific sections of code for parallelization potential. However, all of these techniques provided by a compiler are usually applied at compile time, so they rely on static analysis, which is insufficient for achieving maximum parallelism and desired application scalability. These compiler techniques should consider both the static information gathered at compile time and dynamic analysis captured at runtime about the system to generate a safe parallel application. On the other hand, runtime information is often speculative. Solely relying on it doesn't ...


Smooth Operator: Control Using The Smooth Robustness Of Temporal Logic, Yash Vardhan Pant, Houssam Abbas, Rahul Mangharam 2017 University of Pennsylvania

Smooth Operator: Control Using The Smooth Robustness Of Temporal Logic, Yash Vardhan Pant, Houssam Abbas, Rahul Mangharam

Real-Time and Embedded Systems Lab (mLAB)

Modern control systems, like controllers for swarms of quadrotors, must satisfy complex control objectives while withstanding a wide range of disturbances, from bugs in their software to attacks on their sensors and changes in their environments. These requirements go beyond stability and tracking, and involve temporal and sequencing constraints on system response to various events. This work formalizes the requirements as formulas in Metric Temporal Logic (MTL), and designs a controller that maximizes the robustness of the MTL formula. Formally, if the system satisfies the formula with robustness r, then any disturbance of size less than r cannot cause it ...


Study Of Comparison Of Ocs And Hybrid Switching In Fso Data Centers, Suraj Yadav 2017 University of Nebraska-Lincoln

Study Of Comparison Of Ocs And Hybrid Switching In Fso Data Centers, Suraj Yadav

Computer Science and Engineering: Theses, Dissertations, and Student Research

With the increase in big data applications, it has become the need of the hour to handle data efficiently to handle the growing traffic in the data centers. The popular mechanism is parallel processing using commodity hardware hence it is becoming an interesting research topic to explore new architectures which have high performance, but with an increase in data sizes the architecture has to expand which increases the cabling complexity. Hence the study of Free Space Optical (FSO) communication for the data centers is gaining more importance now than ever. We proposed square OWCELL topology which is a new free ...


Exploring The Telecommunications Properties Of The Human Nervous System: Analytical Modeling And Experimental Validation Of Information Flow Through The Somatosensory System, Natalie Hanisch 2017 University of Nebraska-Lincoln

Exploring The Telecommunications Properties Of The Human Nervous System: Analytical Modeling And Experimental Validation Of Information Flow Through The Somatosensory System, Natalie Hanisch

Computer Science and Engineering: Theses, Dissertations, and Student Research

The growing field of Body Area Networks (BANs) is providing solutions to the wireless connectivity of wearable and implantable devices with applications in medicine, entertainment, fitness, and military, amongst others. While electromagnetic wave propagation has been the main BANs' enabling technology, the increasingly pervasive nature of these devices encourages novel solutions with added bio-compatibility and sustainability. In this thesis, a novel communication system is proposed for BANs based on the natural propagation of tactile stimuli through the nervous system. This system is composed of a tactile stimulator coupled to an ElectroEncephaloGraphy (EEG) system, and realizes the propagation of somatosensory signals ...


Deep Learning And Transfer Learning In The Classification Of Eeg Signals, Jacob M. Williams 2017 University of Nebraska - Lincoln

Deep Learning And Transfer Learning In The Classification Of Eeg Signals, Jacob M. Williams

Computer Science and Engineering: Theses, Dissertations, and Student Research

Deep learning is seldom used in the classification of electroencephalography (EEG) signals, despite achieving state of the art classification accuracies in other spatial and time series data. Instead, most research has continued to use manual feature extraction followed by a traditional classifier, such as SVMs or logistic regression. This is largely due to the low number of samples per experiment, high-dimensional nature of the data, and the difficulty in finding appropriate deep learning architectures for classification of EEG signals. In this thesis, several deep learning architectures are compared to traditional techniques for the classification of visually evoked EEG signals. We ...


Cyber-Physical System Characterization And Co-Regulation Of A Quadrotor Uas, Seth E. Doebbeling 2017 University of Nebraska - Lincoln

Cyber-Physical System Characterization And Co-Regulation Of A Quadrotor Uas, Seth E. Doebbeling

Mechanical (and Materials) Engineering -- Dissertations, Theses, and Student Research

An Unmanned Aircraft System (UAS) is a Cyber-Physical System (CPS) in which a host of real-time computational tasks contending for shared resources must be cooperatively managed to obtain mission objectives. Traditionally, control of the UAS is designed assuming a fixed, high sampling rate in order to maintain reliable performance and margins of stability. But emerging methods challenge this design by dynamically allocating resources to computational tasks, thereby affecting control and mission performance. To apply these emerging strategies, a characterization and understanding of the effects of timing on control and trajectory following performance is required. Going beyond traditional control evaluation techniques ...


Decoupling Information And Connectivity In Information-Centric Networking, Hila Ben Abraham, Jyoti Parwatikar, John Dehart, Adam Drescher, Patrick Crowley 2017 Washington University in St Louis

Decoupling Information And Connectivity In Information-Centric Networking, Hila Ben Abraham, Jyoti Parwatikar, John Dehart, Adam Drescher, Patrick Crowley

All Computer Science and Engineering Research

This paper introduces and demonstrates the concept of Information-Centric Transport as a mechanism for cleanly decoupling the information plane from the connectivity plane in Information-Centric Networking (ICN) architectures, such as NDN and CICN. These are coupled in today's incarnations of NDN and CICN through the use of forwarding strategy, which is the architectural component for deciding how to forward packets in the presence of either multiple next-hop options or dynamic feedback. As presently designed, forwarding strategy is not sustainable: application developers can only confidently specify strategy if they understand connectivity details, while network node operators can only confidently assign ...


基于 Opencv 的道路视频分析系统, 2017 Selected Works

基于 Opencv 的道路视频分析系统

JIN LIU

 The vehicle detection system in current use widely uses host to centrally process images passed back to the server, and it thus has shortcomings, such as large output data, long processing time and so on. This paper proposes a constructing plan using embedded hardware platform according to the composition of ITS system. The video image is emphatically analyzed, and the tracking algorithm is also optimized. The basic image processing tool OpenCV is used to select the preferable edge algorithm by comparing the canny operator and sobel operator. Considering smearing, the background is extracted with the improved averaging method (take interval ...


Digital Commons powered by bepress