Physical Sciences and Mathematics Commons^™

A Hybrid And Scalable Error Correction Algorithm For Indel And Substitution Errors Of Long Reads, Arghya Kusum Das, Sayan Goswami, Kisung Lee, Seung Jong Park

Computer Science Faculty Research & Creative Works

Background: Long-read sequencing has shown the promises to overcome the short length limitations of second-generation sequencing by providing more complete assembly. However, the computation of the long sequencing reads is challenged by their higher error rates (e.g., 13% vs. 1%) and higher cost ($0.3 vs. $0.03 per Mbp) compared to the short reads. Methods: In this paper, we present a new hybrid error correction tool, called ParLECH (Parallel Long-read Error Correction using Hybrid methodology). The error correction algorithm of ParLECH is distributed in nature and efficiently utilizes the k-mer coverage information of high throughput Illumina short-read sequences to rectify the …

Learning Nearest Neighbor Graphs From Noisy Distance Samples, Blake Mason, Ardhendu S. Tripathy, Robert Nowak

Computer Science Faculty Research & Creative Works

We consider the problem of learning the nearest neighbor graph of a dataset of n items. The metric is unknown, but we can query an oracle to obtain a noisy estimate of the distance between any pair of items. This framework applies to problem domains where one wants to learn people's preferences from responses commonly modeled as noisy distance judgments. In this paper, we propose an active algorithm to find the graph with high probability and analyze its query complexity. In contrast to existing work that forces Euclidean structure, our method is valid for general metrics, assuming only symmetry and …

Maxgap Bandit: Adaptive Algorithms For Approximate Ranking, Sumeet Katariya, Ardhendu S. Tripathy, Robert Nowak

Computer Science Faculty Research & Creative Works

This paper studies the problem of adaptively sampling from K distributions (arms) in order to identify the largest gap between any two adjacent means. We call this the MaxGap-bandit problem. This problem arises naturally in approximate ranking, noisy sorting, outlier detection, and top-arm identification in bandits. The key novelty of the MaxGap bandit problem is that it aims to adaptively determine the natural partitioning of the distributions into a subset with larger means and a subset with smaller means, where the split is determined by the largest gap rather than a pre-specified rank or threshold. Estimating an arm's gap requires …

Introduction Of A Hybrid Monitor For Cyber-Physical Systems, J. Ceasar Aguma, Bruce M. Mcmillin, Amelia Regan

Computer Science Faculty Research & Creative Works

Computing systems and mobile technologies have changed dramatically since the introduction of firewall technology in 1988. The internet has grown from a simple network of networks to a cyber and physical entity that encompasses the entire planet. Cyber-physical systems(CPS) now control most of the day to day operations of human civilization from autonomous cars to nuclear energy plants. While phenomenal, this growth has created new security threats. These are threats that cannot be blocked by a firewall for they are not only cyber but cyber-physical. In light of these cyber-physical threats, this paper proposes a security measure that promises to …

Social And Geographical Disparities In Twitter Use During Hurricane Harvey, Lei Zou, Nina S.N. Lam, Shayan Shams, Heng Cai, Michelle A. Meyer, Seungwon Yang, Kisung Lee, Seung Jong Park, Margaret A. Reams

Computer Science Faculty Research & Creative Works

Social media such as Twitter is increasingly being used as an effective platform to observe human behaviors in disastrous events. However, uneven social media use among different groups of population in different regions could lead to biased consequences and affect disaster resilience. This paper studies the Twitter use during 2017 Hurricane Harvey in 76 counties in Texas and Louisiana. We seek to answer a fundamental question: did social-geographical disparities of Twitter use exist during the three phases of emergency management (preparedness, response, recovery)? We employed a Twitter data mining framework to process the data and calculate two indexes: Ratio and …

Blended Root Finding Algorithm Outperforms Bisection And Regula Falsi Algorithms, Chaman Sabharwal

Computer Science Faculty Research & Creative Works

Finding the roots of an equation is a fundamental problem in various fields, including numerical computing, social and physical sciences. Numerical techniques are used when an analytic solution is not available. There is not a single algorithm that works best for every function. We designed and implemented a new algorithm that is a dynamic blend of the bisection and regula falsi algorithms. The implementation results validate that the new algorithm outperforms both bisection and regula falsi algorithms. It is also observed that the new algorithm outperforms the secant algorithm and the Newton-Raphson algorithm because the new algorithm requires fewer computational …

Use Cases Of Lossy Compression For Floating-Point Data In Scientific Data Sets, Franck Cappello, Sheng Di, Sihuan Li, Xin Liang, Ali Murat Gok, Dingwen Tao, For Full List Of Authors, See Publisher's Website.

Computer Science Faculty Research & Creative Works

Architectural and technological trends of systems used for scientific computing call for a significant reduction of scientific data sets that are composed mainly of floating-point data. This article surveys and presents experimental results of currently identified use cases of generic lossy compression to address the different limitations of scientific computing systems. The article shows from a collection of experiments run on parallel systems of a leadership facility that lossy data compression not only can reduce the footprint of scientific data sets on storage but also can reduce I/O and checkpoint/restart times, accelerate computation, and even allow significantly larger problems to …

Collective Representation Learning On Spatiotemporal Heterogeneous Information Networks, Dakshak Keerthi Chandra, Pengyang Wang, Jennifer Leopold, Yanjie Fu

Computer Science Faculty Research & Creative Works

Representation learning is a technique that is used to capture the underlying latent features of complex data. Representation learning on networks has been widely implemented for learning network structure and embedding it in a low dimensional vector space. In recent years, network embedding using representation learning has attracted increasing attention, and many deep architectures have been widely proposed. However, existing network embedding techniques ignore the multi-class spatial and temporal relationships that crucially reflect the complex nature among vertices and links in spatiotemporal heterogeneous information networks(SHINs).

To address this problem, in this paper, we present two types of collective representation learning …

A Deep Learning Approach For Tweet Classification And Rescue Scheduling For Effective Disaster Management, Md. Yasin Kabir, Sanjay Kumar Madria

Computer Science Faculty Research & Creative Works

Every activity in disaster management demands accurate and up-todate information to allow a quick, easy, and cost-efective response to reduce the possible loss of lives and properties. It is a challenging and complex task to acquire information from diferent regions of a disaster-afected area in a timely fashion. The extensive spread and reach of social media and networks such as Twitter allow people to share information in real-time. However, gathering of valuable information requires a series of operations such as (1) processing each tweet for the text classiication, (2) possible location determination of people needing help based on tweets, and …

Tracking The 6-Dof Flight Trajectory Of Windborne Debris Using Stereophotogrammetry, Chaman Sabharwal, Yanlin Guo

Computer Science Faculty Research & Creative Works

Numerous post-windstorm investigations have reported that windborne debris can cause costly damage to the envelope of buildings in urban areas under strong winds (e.g., during hurricanes or tornados). Thus, understanding the physics of debris flight is of critical importance. Previously developed numerical models describing debris flight physics have not been validated for the complex urban flow environment; such a validation requires experimentally measuring the debris flight trajectory in wind tunnel tests. In this context, this paper proposes a debris measurement algorithm using stereophotogrammetry. This algorithm aims to determine the six-degree-of-freedom (6-DOF) trajectory and velocity of flying debris, addressing the research …

The 2nd 3d Face Alignment In The Wild Challenge (3dfaw-Video): Dense Reconstruction From Video, Rohith Krishnan Pillai, Laszlo Attila Jeni, Huiyuan Yang, Zheng Zhang, Lijun Yin, Jeffrey F. Cohn

Computer Science Faculty Research & Creative Works

3D face alignment approaches have strong advantages over 2D with respect to representational power and robustness to illumination and pose. Over the past few years, a number of research groups have made rapid advances in dense 3D alignment from 2D video and obtained impressive results. How these various methods compare is relatively unknown. Previous benchmarks addressed sparse 3D alignment and single image 3D reconstruction. No commonly accepted evaluation protocol exists for dense 3D face reconstruction from video with which to compare them. The 2nd 3D Face Alignment in the Wild from Videos (3DFAW-Video) Challenge extends the previous 3DFAW 2016 competition …

Edgesense: Edge-Mediated Spatial-Temporal Crowdsensing, Sijia Yang, Jiang Bian, Licheng Wang, Haojin Zhu, Yanjie Fu, Haoyi Xiong

Computer Science Faculty Research & Creative Works

Edge computing recently is increasingly popular due to the growth of data size and the need of sensing with the reduced center. Based on Edge computing architecture, we propose a novel crowdsensing framework called Edge-Mediated Spatial-Temporal Crowdsensing. This algorithm targets on receiving the environment information such as air pollution, temperature, and traffic flow in some parts of the goal area, and does not aggregate sensor data with its location information. Specifically, EdgeSense works on top of a secured peer-To-peer network consisted of participants and propose a novel Decentralized Spatial-Temporal Crowdsensing framework based on Parallelized Stochastic Gradient Descent. To approximate the …

Action Recognition In Manufacturing Assembly Using Multimodal Sensor Fusion, Md. Al-Amin, Wenjin Tao, David Doell, Ravon Lingard, Zhaozheng Yin, Ming-Chuan Leu, Ruwen Qin

Computer Science Faculty Research & Creative Works

Production innovations are occurring faster than ever. Manufacturing workers thus need to frequently learn new methods and skills. In fast changing, largely uncertain production systems, manufacturers with the ability to comprehend workers' behavior and assess their operation performance in near real-time will achieve better performance than peers. Action recognition can serve this purpose. Despite that human action recognition has been an active field of study in machine learning, limited work has been done for recognizing worker actions in performing manufacturing tasks that involve complex, intricate operations. Using data captured by one sensor or a single type of sensor to recognize …

A Region-Based Deep Learning Algorithm For Detecting And Tracking Objects In Manufacturing Plants, Muhammad Monjurul Karim, David Doell, Ravon Lingard, Zhaozheng Yin, Ming-Chuan Leu, Ruwen Qin

Computer Science Faculty Research & Creative Works

In today's competitive production era, the ability to identify and track important objects in a near real-time manner is greatly desired among manufacturers who are moving towards the streamline production. Manually keeping track of every object in a complex manufacturing plant is infeasible; therefore, an automatic system of that functionality is greatly in need. This study was motivated to develop a Mask Region-based Convolutional Neural Network (Mask RCNN) model to semantically segment objects and important zones in manufacturing plants. The Mask RCNN was trained through transfer learning that used a neural network (NN) pre-trained with the MS-COCO dataset as the …

Data-Driven Privacy-Preserving Communication, Ye Wang, Prakash Ishwar, Ardhendu S. Tripathy

Computer Science Faculty Research & Creative Works

A communication system including a receiver to receive training data. An input interface to receive input data coupled to a hardware processor and a memory. The hardware processor is configured to initialize the privacy module using the training data. Generate a trained privacy module, by iteratively optimizing an objective function. Wherein for each iteration the objective function is computed by a combination of a distortion of the useful attributes in the transformed data and of a mutual information between the sensitive attributes and the transformed data. Such that the mutual information is estimated by the auxiliary module that maximizes a …

Deepsz: A Novel Framework To Compress Deep Neural Networks By Using Error-Bounded Lossy Compression, Sian Jin, Sheng Di, Xin Liang, Jiannan Tian, Dingwen Tao, Franck Cappello

Computer Science Faculty Research & Creative Works

Today's deep neural networks (DNNs) are becoming deeper and wider because of increasing demand on the analysis quality and more and more complex applications to resolve. The wide and deep DNNs, however, require large amounts of resources (such as memory, storage, and I/O), significantly restricting their utilization on resource-constrained platforms. Although some DNN simplification methods (such as weight quantization) have been proposed to address this issue, they suffer from either low compression ratios or high compression errors, which may introduce an expensive fine-tuning overhead (i.e., a costly retraining process for the target inference accuracy). In this paper, we propose DeepSZ: …

Sensor System And Method For Cognitive Health Assessment, Debraj De, Sajal K. Das, Mignon Makos

Computer Science Faculty Research & Creative Works

Sensors arranged on a chair on which a subject is seated detect a physical characteristic of the subject during administration of a cognitive health assessment. An assessment processor coupled to the sensors executes computer-executable instructions causing the processor to determine a contemporaneous reaction corresponding to each of the questions as a function of the detected physical characteristic. And the subject is assigned a cognitive health assessment score based on the subject's answers and determined reactions.

Learning Temporal Information From A Single Image For Au Detection, Huiyuan Yang, Lijun Yin

Computer Science Faculty Research & Creative Works

Automatic Facial Action Units (AUs) detection is the recognition of the facial appearance changes caused by the contraction or relaxation of one or more related facial muscles. Compared to the sequence-based methods, a decreased performance is observed for the static image-based AU detection, due to the loss of temporal information. To solve this problem, we propose a novel method that implicitly learns temporal information from a single image for AU detection by adding a hidden optical-flow layer to concatenate two Convolutional Neural Networks (CNNs) models: optical-flow net (OF-Net) and AU detection net (AU-Net). The OF-Net is designed to estimate the …

Multi-Modality Empowered Network For Facial Action Unit Detection, Peng Liu, Zheng Zhang, Huiyuan Yang, Lijun Yin

Computer Science Faculty Research & Creative Works

This paper presents a new thermal empowered multi-task network (TEMT-Net) to improve facial action unit detection. Our primary goal is to leverage the situation that the training set has multi-modality data while the application scenario only has one modality. Thermal images are robust to illumination and face color. In the proposed multi-task framework, we utilize both modality data. Action unit detection and facial landmark detection are correlated tasks. To utilize the advantage and the correlation of different modalities and different tasks, we propose a novel thermal empowered multi-task deep neural network learning approach for action unit detection, facial landmark detection …

Parlech: Parallel Long-Read Error Correction With Hadoop, Arghya Kusum Das, Kisung Lee, Seung Jong Park

Computer Science Faculty Research & Creative Works

Long-read sequencing is emerging as a promising sequencing technology because it can tackle the short length limitation of second-generation sequencing, which has dominated the sequencing market in past years. However, it has substantially higher error rates compared to short-read sequencing (e.g., 13% vs. 0.1%), and its sequencing cost per base is typically more expensive than that of short-read sequencing. To address these limitations, we present a distributed hybrid error correction framework, called ParLECH, that is scalable and cost-efficient for PacBio long reads. For correcting the errors in the long reads, ParLECH utilizes the Illumina short reads that have the low …

Applications Of Machine Learning In Nuclear Imaging And Radiation Detection, Shaikat Mahmood Galib

Doctoral Dissertations

"The main focus of this work is to use machine learning and data mining techniques to address some challenging problems that arise from nuclear data. Specifically, two problem areas are discussed: nuclear imaging and radiation detection. The techniques to approach these problems are primarily based on a variant of Artificial Neural Network (ANN) called Convolutional Neural Network (CNN), which is one of the most popular forms of 'deep learning' technique.

The first problem is about interpreting and analyzing 3D medical radiation images automatically. A method is developed to identify and quantify deformable image registration (DIR) errors from lung CT scans …

Deep Neural Network Learning-Based Classifier Design For Big-Data Analytics, Krishnan Raghavan

Doctoral Dissertations

"In this digital age, big-data sets are commonly found in the field of healthcare, manufacturing and others where sustainable analysis is necessary to create useful information. Big-data sets are often characterized by high-dimensionality and massive sample size. High dimensionality refers to the presence of unwanted dimensions in the data where challenges such as noise, spurious correlation and incidental endogeneity are observed. Massive sample size, on the other hand, introduces the problem of heterogeneity because complex and unstructured data types must analyzed. To mitigate the impact of these challenges while considering the application of classification, a two step analysis approach is …

Volumetric Error Compensation For Industrial Robots And Machine Tools, Le Ma

Doctoral Dissertations

“A more efficient and increasingly popular volumetric error compensation method for machine tools is to compute compensation tables in axis space with tool tip volumetric measurements. However, machine tools have high-order geometric errors and some workspace is not reachable by measurement devices, the compensation method suffers a curve-fitting challenge, overfitting measurements in measured space and losing accuracy around and out of the measured space. Paper I presents a novel method that aims to uniformly interpolate and extrapolate the compensation tables throughout the entire workspace. By using a uniform constraint to bound the tool tip error slopes, an optimal model with …

Controlled Switching In Kalman Filtering And Iterative Learning Controls, He Li

Masters Theses

“Switching is not an uncommon phenomenon in practical systems and processes, for examples, power switches opening and closing, transmissions lifting from low gear to high gear, and air planes crossing different layers in air. Switching can be a disaster to a system since frequent switching between two asymptotically stable subsystems may result in unstable dynamics. On the contrary, switching can be a benefit to a system since controlled switching is sometimes imposed by the designers to achieve desired performance. This encourages the study of system dynamics and performance when undesired switching occurs or controlled switching is imposed. In this research, …

Advanced Techniques For Improving Canonical Genetic Programming, Adam Tyler Harter

Masters Theses

"Genetic Programming (GP) is a type of Evolutionary Algorithm (EA) commonly employed for automated program generation and model identification. Despite this, GP, as most forms of EA's, is plagued by long evaluation times, and is thus generally reserved for highly complex problems. Two major impacting factors for the runtime are the heterogeneous evaluation time for the individuals and the choice of algorithmic primitives. The first paper in this thesis utilizes Asynchronous Parallel Evolutionary Algorithms (APEA) for reducing the runtime by eliminating the need to wait for an entire generation to be evaluated before continuing the search. APEA is applied to …

Impact Of Framing And Base Size Of Computer Security Risk Information On User Behavior, Xinhui Zhan

Masters Theses

"This research examines the impact of framing and base size of computer security risk information on users' risk perceptions and behavior (i.e., download intention and download decision). It also examines individual differences (i.e., demographic factors, computer security awareness, Internet structural assurance, self-efficacy, and general risk-taking tendencies) associated with users' computer security risk perceptions. This research draws on Prospect Theory, which is a theory in behavioral economics that addresses risky decision-making, to generate hypotheses related to users' decision-making in the computer security context. A 2 x 3 mixed factorial experimental design (N = 178) was conducted to assess the effect of …

Evolved Parameterized Selection For Evolutionary Algorithms, Samuel Nathan Richter

Masters Theses

"Selection functions enable Evolutionary Algorithms (EAs) to apply selection pressure to a population of individuals, by regulating the probability that an individual's genes survive, typically based on fitness. Various conventional fitness based selection functions exist, each providing a unique method of selecting individuals based on their fitness, fitness ranking within the population, and/or various other factors. However, the full space of selection algorithms is only limited by max algorithm size, and each possible selection algorithm is optimal for some EA configuration applied to a particular problem class. Therefore, improved performance is likely to be obtained by tuning an EA's selection …

Predictive Modeling Of Webpage Aesthetics, Ang Chen

Masters Theses

"Aesthetics plays a key role in web design. However, most websites have been developed based on designers' inspirations or preferences. While perceptions of aesthetics are intuitive abilities of humankind, the underlying principles for assessing aesthetics are not well understood. In recent years, machine learning methods have shown promising results in image aesthetic assessment. In this research, we used machine learning methods to study and explore the underlying principles of webpage aesthetics"--Abstract, page iii.

Design And Implementation Of Applications Over Delay Tolerant Networks For Disaster And Battlefield Environment, Karthikeyan Sachidanandam

Masters Theses

"In disaster/battlefield applications, there may not be any centralized network that provides a mechanism for different nodes to connect with each other to share important data. In such cases, we can take advantage of an opportunistic network involving a substantial number of mobile devices that can communicate with each other using Bluetooth and Google Nearby Connections API(it uses Bluetooth, Bluetooth Low Energy (BLE), and Wi-Fi hotspots) when they are close to each other. These devices referred to as nodes form a Delay Tolerant Network (DTN), also known as an opportunistic network. As suggested by its name, DTN can tolerate delays …

Structure And Topology Of Transcriptional Regulatory Networks And Their Applications In Bio-Inspired Networking, Satyaki Roy

Doctoral Dissertations

"Biological networks carry out vital functions necessary for sustenance despite environmental adversities. Transcriptional Regulatory Network (TRN) is one such biological network that is formed due to the interaction between proteins, called Transcription Factors (TFs), and segments of DNA, called genes. TRNs are known to exhibit functional robustness in the face of perturbation or mutation: a property that is proven to be a result of its underlying network topology. In this thesis, we first propose a three-tier topological characterization of TRN to analyze the interplay between the significant graph-theoretic properties of TRNs such as scale-free out-degree distribution, low graph density, small …