Computer Engineering Commons^™

Interpretable Multimodal Retrieval For Fashion Products, Lizi Liao, Xiangnan He, Bo Zhao, Chong-Wah Ngo, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Deep learning methods have been successfully applied to fashion retrieval. However, the latent meaning of learned feature vectors hinders the explanation of retrieval results and integration of user feedback. Fortunately, there are many online shopping websites organizing fashion items into hierarchical structures based on product taxonomy and domain knowledge. Such structures help to reveal how human perceive the relatedness among fashion products. Nevertheless, incorporating structural knowledge for deep learning remains a challenging problem. This paper presents techniques for organizing and utilizing the fashion hierarchies in deep learning to facilitate the reasoning of search results and user intent. The novelty of …

Minutes & Seconds: The Scientists, Patrick Aievoli

Zea E-Books Collection

Minutes & Seconds, is a captivating intelligible read for those who strive to understand where the “what if” moment has gone. Succeeding his other captivating books, Aievoli’s deep introspective lens dials his readers in to awaken the proverbial sleeping giant inside of our consciousness. He designs an insightful exciting romp through the surreal landscape of our society and illustrates how various pioneers have lead us to a crossroads. I’m truly impressed with Aievoli’s perspicacious comprehension of where digital has taken us through the hands of these select individuals. --Sequoyah Wharton

In creating Minutes & Seconds, Aievoli has assembled an interesting …

Tourism Review Sentiment Classification Using A Bidirectional Recurrent Neural Network With An Attention Mechanism And Topic-Enriched Word Vectors, Qin Li, Shaobo Li, Jie Hu, Sen Zhang, Jianjun Hu

Faculty Publications

Sentiment analysis of online tourist reviews is playing an increasingly important role in tourism. Accurately capturing the attitudes of tourists regarding different aspects of the scenic sites or the overall polarity of their online reviews is key to tourism analysis and application. However, the performances of current document sentiment analysis methods are not satisfactory as they either neglect the topics of the document or do not consider that not all words contribute equally to the meaning of the text. In this work, we propose a bidirectional gated recurrent unit neural network model (BiGRULA) for sentiment analysis by combining a topic …

Cultivating Third Party Development In Platform-Centric Software Ecosystems: Extended Boundary Resources Model, Brown C. Msiska

The African Journal of Information Systems

Software ecosystems provide an effective way through which software solutions can be constructed by composing software components, typically applications, developed by internal and external developers on top of a software platform. Third party development increases the potential of a software ecosystem to effectively and quickly respond to context-specific software requirements. The boundary resources model gives a theoretical account for cultivation of third party development premised on the role of platform boundary resources such as application programming interfaces (API). However, from a longitudinal case study of the DHIS2 software ecosystem, this paper observes that no matter how good the boundary resources …

End-To-End Convolutional Neural Network Model For Gear Fault Diagnosis Based On Sound Signals, Yong Yao, Honglei Wang, Shaobo Li, Zhongnhao Liu, Gui Gui, Yabo Dan, Jianjun Hu

Faculty Publications

Currently gear fault diagnosis is mainly based on vibration signals with a few studies on acoustic signal analysis. However, vibration signal acquisition is limited by its contact measuring while traditional acoustic-based gear fault diagnosis relies heavily on prior knowledge of signal processing techniques and diagnostic expertise. In this paper, a novel deep learning-based gear fault diagnosis method is proposed based on sound signal analysis. By establishing an end-to-end convolutional neural network (CNN), the time and frequency domain signals can be fed into the model as raw signals without feature engineering. Moreover, multi-channel information from different microphones can also be fused …

Pfix: Fixing Concurrency Bugs Based On Memory Access Patterns, Huarui Lin, Zan Wang, Shuang Liu, Jun Sun, Dongdi Zhang, Guangning Wei

Research Collection School Of Computing and Information Systems

Concurrency bugs of a multi-threaded program may only manifest with certain scheduling, i.e., they are heisenbugs which are observed only from time to time if we execute the same program with the same input multiple times. They are notoriously hard to fix. In this work, we propose an approach to automatically fix concurrency bugs. Compared to previous approaches, our key idea is to systematically fix concurrency bugs by inferring locking policies from failure inducing memory-access patterns. That is, we automatically identify memory-access patterns which are correlated with the manifestation of the bug, and then conjecture what is the intended locking …

Higher-Level Consistencies: Where, When, And How Much, Robert J. Woodward

School of Computing: Dissertations, Theses, and Student Research

Determining whether or not a Constraint Satisfaction Problem (CSP) has a solution is NP-complete. CSPs are solved by inference (i.e., enforcing consistency), conditioning (i.e., doing search), or, more commonly, by interleaving the two mechanisms. The most common consistency property enforced during search is Generalized Arc Consistency (GAC). In recent years, new algorithms that enforce consistency properties stronger than GAC have been proposed and shown to be necessary to solve difficult problem instances.

We frame the question of balancing the cost and the pruning effectiveness of consistency algorithms as the question of determining where, when, and how much of a higher-level …

Enhancing 3d Visual Odometry With Single-Camera Stereo Omnidirectional Systems, Carlos A. Jaramillo

Dissertations, Theses, and Capstone Projects

We explore low-cost solutions for efficiently improving the 3D pose estimation problem of a single camera moving in an unfamiliar environment. The visual odometry (VO) task -- as it is called when using computer vision to estimate egomotion -- is of particular interest to mobile robots as well as humans with visual impairments. The payload capacity of small robots like micro-aerial vehicles (drones) requires the use of portable perception equipment, which is constrained by size, weight, energy consumption, and processing power. Using a single camera as the passive sensor for the VO task satisfies these requirements, and it motivates the …

Blockchain Based Efficient And Robust Fair Payment For Outsourcing Services In Cloud Computing, Yinghui Zhang, Robert H. Deng, Ximeng Liu, Dong Zheng

Research Collection School Of Computing and Information Systems

As an attractive business model of cloud computing, outsourcing services usually involve online payment and security issues. The mutual distrust between users and outsourcing service providers may severely impede the wide adoption of cloud computing. Nevertheless, most existing payment solutions only consider a specific type of outsourcing service and rely on a trusted third-party to realize fairness. In this paper, in order to realize secure and fair payment of outsourcing services in general without relying on any third-party, trusted or not, we introduce BCPay, a blockchain based fair payment framework for outsourcing services in cloud computing. We first present the …

Androparse - An Android Feature Extraction Framework & Dataset, Robert Schmicker, Frank Breitinger, Ibrahim Baggili

Electrical & Computer Engineering and Computer Science Faculty Publications

Android malware has become a major challenge. As a consequence, practitioners and researchers spend a significant time analyzing Android applications (APK). A common procedure (especially for data scientists) is to extract features such as permissions, APIs or strings which can then be analyzed. Current state of the art tools have three major issues: (1) a single tool cannot extract all the significant features used by scientists and practitioners (2) Current tools are not designed to be extensible and (3) Existing parsers do not have runtime efficiency. Therefore, this work presents AndroParse which is an open-source Android parser written in Golang …

Digital Forensics In The Next Five Years, Laoise Luciano, Ibrahim Baggili, Mateusz Topor, Peter Casey, Frank Breitinger

Electrical & Computer Engineering and Computer Science Faculty Publications

Cyber forensics has encountered major obstacles over the last decade and is at a crossroads. This paper presents data that was obtained during the National Workshop on Redefining Cyber Forensics (NWRCF) on May 23-24, 2017 supported by the National Science Foundation and organized by the University of New Haven. Qualitative and quantitative data were analyzed from twenty-four cyber forensics expert panel members. This work identified important themes that need to be addressed by the community, focusing on (1) where the domain currently is; (2) where it needs to go and; (3) steps needed to improve it. Furthermore, based on the …

I Know What You Did Last Summer: Your Smart Home Internet Of Things And Your Iphone Forensically Ratting You Out, Gokila Dorai, Shiva Houshmand, Ibrahim Baggili

Electrical & Computer Engineering and Computer Science Faculty Publications

The adoption of smart home Internet of Things (IoT) devices continues to grow. What if your devices can snitch on you and let us know where you are at any given point in time? In this work we examined the forensic artifacts produced by Nest devices, and in specific, we examined the logical backup structure of an iPhone used to control a Nest thermostat, Nest Indoor Camera and a Nest Outdoor Camera. We also integrated the Google Home Mini as another method of controlling the studied Smart Home devices. Our work is the primary account for the examination of Nest …

Computational Thinking And Literacy, Sharin Rawhiya Jacob, Mark Warschauer

Journal of Computer Science Integration

Today’s students will enter a workforce that is powerfully shaped by computing. To be successful in a changing economy, students must learn to think algorithmically and computationally, to solve problems with varying levels of abstraction. These computational thinking skills have become so integrated into social function as to represent fundamental literacies. However, computer science has not been widely taught in K-12 schools. Efforts to create computer science standards and frameworks have yet to make their way into mandated course requirements. Despite a plethora of research on digital literacies, research on the role of computational thinking in the literature is sparse. …

Chaos Firefly Algorithm With Self-Adaptation Mutation Mechanism For Solving Large-Scale Economic Dispatch With Valve-Point Effects And Multiple Fuel Options, Yude Yang, Bori Wei, Hui Liu, Yiyi Zhang, Junhui Zhao, Emad Manla

Electrical & Computer Engineering and Computer Science Faculty Publications

This paper presents a new metaheuristic optimization algorithm, the firefly algorithm (FA), and an enhanced version of it, called chaos mutation FA (CMFA), for solving power economic dispatch problems while considering various power constraints, such as valve-point effects, ramp rate limits, prohibited operating zones, and multiple generator fuel options. The algorithm is enhanced by adding a new mutation strategy using self-adaptation parameter selection while replacing the parameters with fixed values. The proposed algorithm is also enhanced by a self-adaptation mechanism that avoids challenges associated with tuning the algorithm parameters directed against characteristics of the optimization problem to be solved. The …

Self-Powered Time-Keeping And Time-Of-Occurrence Sensing, Liang Zhou

McKelvey School of Engineering Graduate Student Theses & Dissertations

Self-powered and passive Internet-of-Things (IoT) devices (e.g. RFID tags, financial assets, wireless sensors and surface-mount devices) have been widely deployed in our everyday and industrial applications. While diverse functionalities have been implemented in passive systems, the lack of a reference clock limits the design space of such devices used for applications such as time-stamping sensing, recording and dynamic authentication. Self-powered time-keeping in passive systems has been challenging because they do not have access to continuous power sources. While energy transducers can harvest power from ambient environment, the intermittent power cannot support continuous operation for reference clocks. The thesis of this …

Forensic Analysis Of Immersive Virtual Reality Social Applications: A Primary Account, Ananya Yarramreddy, Peter Gromkowski, Ibrahim Baggili

Electrical & Computer Engineering and Computer Science Faculty Publications

Our work presents the primary account for exploring the forensics of immersive Virtual Reality (VR) systems and their social applications. The Social VR applications studied in this work include Bigscreen, Altspace VR, Rec Room and Facebook Spaces. We explored the two most widely adopted consumer VR systems: the HTC Vive and the Oculus Rift. Our tests examined the efficacy of reconstructing evidence from network traffic as well as the systems themselves. The results showed that a significant amount of forensically relevant data such as user names, user profile pictures, events, and system details may be recovered. We anticipate that this …

Remote Sensing Using I-Band And S-Band Signals Of Opportunity, Kadir Efecik, Benjamin R. Nold, James L. Garrison

The Summer Undergraduate Research Fellowship (SURF) Symposium

Measurement of soil moisture, especially the root zone soil moisture, is important in agriculture, meteorology, and hydrology. Root zone soil moisture is concerned with the first meter down the soil. Active and passive remote sensing methods used today utilizing L-band(1-2GHz) are physically limited to a sensing depth of about 5 cm or less. To remotely sense the soil moisture in the deeper parts of the soil, the frequency should be lowered. Lower frequencies cannot be used in active spaceborne instruments because of their need for larger antennas, radio frequency interference (RFI), and frequency spectrum allocations. Ground-based passive remote sensing using …

Investigating Dataset Distinctiveness, Andrew Ulmer, Kent W. Gauen, Yung-Hsiang Lu, Zohar R. Kapach, Daniel P. Merrick

The Summer Undergraduate Research Fellowship (SURF) Symposium

Just as a human might struggle to interpret another human’s handwriting, a computer vision program might fail when asked to perform one task in two different domains. To be more specific, visualize a self-driving car as a human driver who had only ever driven on clear, sunny days, during daylight hours. This driver – the self-driving car – would inevitably face a significant challenge when asked to drive when it is violently raining or foggy during the night, putting the safety of its passengers in danger. An extensive understanding of the data we use to teach computer vision models – …

Sort Vs. Hash Join On Knights Landing Architecture, Victor L. Pan, Felix Lin

The Summer Undergraduate Research Fellowship (SURF) Symposium

With the increasing amount of information stored, there is a need for efficient database algorithms. One of the most important database operations is “join”. This involves combining columns from two tables and grouping common values in the same row in order to minimize redundant data. The two main algorithms used are hash join and sort merge join. Hash join builds a hash table to allow for faster searching. Sort merge join first sorts the two tables to make it more efficient when comparing values. There has been a lot of debate over which approach is superior. At first, hash join …

Deep Neural Network Architectures For Modulation Classification Using Principal Component Analysis, Sharan Ramjee, Shengtai Ju, Diyu Yang, Aly El Gamal

The Summer Undergraduate Research Fellowship (SURF) Symposium

In this work, we investigate the application of Principal Component Analysis to the task of wireless signal modulation recognition using deep neural network architectures. Sampling signals at the Nyquist rate, which is often very high, requires a large amount of energy and space to collect and store the samples. Moreover, the time taken to train neural networks for the task of modulation classification is large due to the large number of samples. These problems can be drastically reduced using Principal Component Analysis, which is a technique that allows us to reduce the dimensionality or number of features of the samples …

Security Services Using Blockchains: A State Of The Art Survey, Maeda Zolanvari, Aiman Erbad, Raj Jain, Mohammed Samaka

All Computer Science and Engineering Research

This article surveys blockchain-based approaches for several security services. These services include authentication, confidentiality, privacy and access control list (ACL), data and resource provenance, and integrity assurance. All these services are critical for the current distributed applications, especially due to the large amount of data being processed over the networks and the use of cloud computing. Authentication ensures that the user is who he/she claims to be. Confidentiality guarantees that data cannot be read by unauthorized users. Privacy provides the users the ability to control who can access their data. Provenance allows an efficient tracking of the data and resources …

Scaling Up An Infrastructure For Controlled Experimentation With Testing Techniques, Wayne D. Motycka

School of Computing: Dissertations, Theses, and Student Research

Software testing research often involves reproducing previous experimental results. Previous work created a repository infrastructure for containment and dissemination of testable research subjects using a private centralized storage mechanism for hosting these test subject archives. While this is a good way to store these subjects it can be inefficient when the size of subjects increases or the number of versions of the subject’s source code is large. The delivery of these large subjects from a centralized repository can be quite large and on occasion may not succeed requiring the user to repeat the download request. Coupled with the limited resources …

Customer Segmentation Using Online Platforms: Isolating Behavioral And Demographic Segments For Persona Creation Via Aggregated User Data, Jisun An, Haewoon Kwak, Soon‑Gyo Jung, Joni Salminen, Bernard J. Jansen

Research Collection School Of Computing and Information Systems

We propose a novel approach for isolating customer segments using online customer data for products that are distributed via online social media platforms. We use non-negative matrix factorization to first identify behavioral customer segments and then to identify demographic customer segments. We employ a methodology for linking the two segments to present integrated and holistic customer segments, also known as personas. Behavioral segments are generated from customer interactions with online content. Demographic segments are generated using the gender, age, and location of these customers. In addition to evaluating our approach, we demonstrate its practicality via a system leveraging these customer …

Exact Processing Of Uncertain Top-K Queries In Multi-Criteria Settings, Kyriakos Mouratidis, Bo Tang

Research Collection School Of Computing and Information Systems

Traditional rank-aware processing assumes a dataset that contains available options to cover a specific need (e.g., restaurants, hotels, etc) and users who browse that dataset via top-k queries with linear scoring functions, i.e., by ranking the options according to the weighted sum of their attributes, for a set of given weights. In practice, however, user preferences (weights) may only be estimated with bounded accuracy, or may be inherently uncertain due to the inability of a human user to specify exact weight values with absolute accuracy. Motivated by this, we introduce the uncertain top-k query (UTK). Given uncertain preferences, that is, …

Code Smells For Model-View-Controller Architectures, Maurício Aniche, Gabriele Bavota, Christoph Treude, Marco Aurélio Gerosa, Arie Van Deursen

Research Collection School Of Computing and Information Systems

Previous studies have shown the negative effects that low-quality code can have on maintainability proxies, such as code change- and defect-proneness. One of the symptoms of low-quality code are code smells, defined as sub-optimal implementation choices. While this definition is quite general and seems to suggest a wide spectrum of smells that can affect software systems, the research literature mostly focuses on the set of smells defined in the catalog by Fowler and Beck, reporting design issues that can potentially affect any kind of system, regardless of their architecture (e.g., Complex Class). However, systems adopting a specific architecture (e.g., the …

Learning Representations Of Ultrahigh-Dimensional Data For Random Distance-Based Outlier Detection, Guansong Pang, Longbing Cao, Ling Chen, Defu Lian, Huan Liu

Research Collection School Of Computing and Information Systems

Learning expressive low-dimensional representations of ultrahigh-dimensional data, e.g., data with thousands/millions of features, has been a major way to enable learning methods to address the curse of dimensionality. However, existing unsupervised representation learning methods mainly focus on preserving the data regularity information and learning the representations independently of subsequent outlier detection methods, which can result in suboptimal and unstable performance of detecting irregularities (i.e., outliers).This paper introduces a ranking model-based framework, called RAMODO, to address this issue. RAMODO unifies representation learning and outlier detection to learn low-dimensional representations that are tailored for a state-of-the-art outlier detection approach - the random …

Chaotic Phase-Coded Waveforms With Space-Time Complementary Coding For Mimo Radar Applications, Sheng Hong, Fuhui Zhou, Yantao Dong, Zhixin Zhao, Yuhao Wang, Maosong Yan

Electrical and Computer Engineering Faculty Publications

A framework for designing orthogonal chaotic phase-coded waveforms with space-time complementary coding (STCC) is proposed for multiple-input multiple-output (MIMO) radar applications. The phase-coded waveform set to be transmitted is generated with an arbitrary family size and an arbitrary code length by using chaotic sequences. Due to the properties of chaos, this chaotic waveform set has many advantages in performance, such as anti-interference and low probability of intercept. However, it cannot be directly exploited due to the high range sidelobes, mutual interferences, and Doppler intolerance. In order to widely implement it in practice, we optimize the chaotic phase-coded waveform set from …

An Application Of Game Theory In Distributed Collaborative Decision Making, Angran Xiao

Publications and Research

In a distributed product realization environment, new paradigms and accompanying software systems are necessary to support the collaborative work of geographically dispersed engineering teams from different disciplines who have different knowledge, experience, tools and resources. To verify the concept of collaboration by separation, we propose a generic information communication medium to enable knowledge representation and exchange between engineering teams, a digital interface. Across digital interfaces, each engineering team maintains its own perspective towards the product realization problem, and each controls a subset of design variables and seeks to maximize its own payoff function subject to individual constraints. Hence, we postulate …

An Ensemble Stacked Convolutional Neural Network Model For Environmental Event Sound Recognition, Shaobo Li, Yong Yao, Jie Hu, Guokai Liu, Xuemei Yao, Jianjun Hu

Faculty Publications

Convolutional neural networks (CNNs) with log-mel audio representation and CNN-based end-to-end learning have both been used for environmental event sound recognition (ESC). However, log-mel features can be complemented by features learned from the raw audio waveform with an effective fusion method. In this paper, we first propose a novel stacked CNN model with multiple convolutional layers of decreasing filter sizes to improve the performance of CNN models with either log-mel feature input or raw waveform input. These two models are then combined using the Dempster–Shafer (DS) evidence theory to build the ensemble DS-CNN model for ESC. Our experiments over three …

High-Performance Testbed For Vision-Aided Autonomous Navigation For Quadrotor Uavs In Cluttered Environments, Shakeeb Ahmad

Electrical and Computer Engineering ETDs

This thesis presents the development of an aerial robotic testbed based on Robot Operating System (ROS). The purpose of this high-performance testbed is to develop a system capable of performing robust navigation tasks using vision tools such as a stereo camera. While ensuring the computation of robot odometery, the system is also capable of sensing the environment using the same stereo camera. Hence, all the navigation tasks are performed using a stereo camera and an inertial measurement unit (IMU) as the main sensor suite. ROS is used as a framework for software integration due to its capabilities to provide efficient …