Physical Sciences and Mathematics Commons^™

Finding All ∈-Good Arms In Stochastic Bandits, Blake Mason, Lalit Jain, Ardhendu S. Tripathy, Robert Nowak

Computer Science Faculty Research & Creative Works

The pure-exploration problem in stochastic multi-armed bandits aims to find one or more arms with the largest (or near largest) means. Examples include finding an ∈-good arm, best-arm identification, top-k arm identification, and finding all arms with means above a specified threshold. However, the problem of finding all ∈-good arms has been overlooked in past work, although arguably this may be the most natural objective in many applications. For example, a virologist may conduct preliminary laboratory experiments on a large candidate set of treatments and move all ∈-good treatments into more expensive clinical trials. Since the ultimate clinical efficacy is …

Distributed De Novo Assembler For Large-Scale Long-Read Datasets, Sayan Goswami, Kisung Lee, Seung Jong Park

Computer Science Faculty Research & Creative Works

Third-generation DNA sequencing technologies such as single-molecule real-time sequencing (SMRT) and nanopore sequencing have the potential to fill the gaps in the existing genome databases since the raw sequences produced by these machines are much longer than those of previous generations and therefore result in more contiguous assemblies. However, these long reads have a high error rate, which makes the assembly process computationally challenging. Moreover, since existing long-read assemblers are designed to run on a single machine, they either take days to complete or run out of memory on even moderate-sized datasets. In this paper, we present a distributed long-read …

An Eeg-Based Multi-Modal Emotion Database With Both Posed And Authentic Facial Actions For Emotion Analysis, Xiaotian Li, Xiang Zhang, Huiyuan Yang, Wenna Duan, Weiying Dai, Lijun Yin

Computer Science Faculty Research & Creative Works

Emotion is an experience associated with a particular pattern of physiological activity along with different physiological, behavioral and cognitive changes. One behavioral change is facial expression, which has been studied extensively over the past few decades. Facial behavior varies with a person's emotion according to differences in terms of culture, personality, age, context, and environment. In recent years, physiological activities have been used to study emotional responses. A typical signal is the electroencephalogram (EEG), which measures brain activity. Most of existing EEG-based emotion analysis has overlooked the role of facial expression changes. There exits little research on the relationship between …

Set Operation Aided Network For Action Units Detection, Huiyuan Yang, Taoyue Wang, Lijun Yin

Computer Science Faculty Research & Creative Works

As a large number of parameters exist in deep model-based methods, training such models usually requires many fully AU-annotated facial images. This is true with regard to the number of frames in two widely used datasets: BP4D [31] and DISFA [18], while those frames were captured from a small number of subjects (41, 27 respectively). This is problematic, as subjects produce highly consistent facial muscle movements, adding more frames per subject would only adds more close points in the feature space, and thus the classifier does not benefit from those extra frames. Data augmentation methods can be applied to alleviate …

Communicating Uncertain Information From Deep Learning Models In Human Machine Teams, Harishankar V. Subramanian, Casey I. Canfield, Daniel Burton Shank, Luke Andrews, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

The role of human-machine teams in society is increasing, as big data and computing power explode. One popular approach to AI is deep learning, which is useful for classification, feature identification, and predictive modeling. However, deep learning models often suffer from inadequate transparency and poor explainability. One aspect of human systems integration is the design of interfaces that support human decision-making. AI models have multiple types of uncertainty embedded, which may be difficult for users to understand. Humans that use these tools need to understand how much they should trust the AI. This study evaluates one simple approach for communicating …

Adaptive Multimodal Fusion For Facial Action Units Recognition, Huiyuan Yang, Taoyue Wang, Lijun Yin

Computer Science Faculty Research & Creative Works

Multimodal facial action units (AU) recognition aims to build models that are capable of processing, correlating, and integrating information from multiple modalities (i.e., 2D images from a visual sensor, 3D geometry from 3D imaging, and thermal images from an infrared sensor). Although the multimodal data can provide rich information, there are two challenges that have to be addressed when learning from multimodal data: 1) the model must capture the complex cross-modal interactions in order to utilize the additional and mutual information effectively; 2) the model must be robust enough in the circumstance of unexpected data corruptions during testing, in case …

Cusz: An Efficient Gpu-Based Error-Bounded Lossy Compression Framework For Scientific Data, Jiannan Tian, Sheng Di, Kai Zhao, Cody Rivera, Megan Hickman Fulp, Robert Underwood, Sian Jin, Xin Liang, For Full List Of Authors, See Publisher's Website.

Computer Science Faculty Research & Creative Works

Error-bounded lossy compression is a state-of-the-art data reduction technique for HPC applications because it not only significantly reduces storage overhead but also can retain high fidelityfor postanalysis. Because supercomputers and HPC applicationsare becoming heterogeneous using accelerator-based architectures,in particular GPUs, several development teams have recently released GPU versions of their lossy compressors. However, existingstate-of-the-art GPU-based lossy compressors suffer from eitherlow compression and decompression throughput or low compression quality. In this paper, we present an optimized GPU version,cuSZ, for one of the best error-bounded lossy compressors-SZ.To the best of our knowledge, cuSZ is the first error-boundedlossy compressor on GPUs for scientific data. …

An Explainable And Statistically Validated Ensemble Clustering Model Applied To The Identification Of Traumatic Brain Injury Subgroups, Dacosta Yeboah, Louis Steinmeister, Daniel B. Hier, Bassam Hadi, Donald C. Wunsch, Gayla R. Olbricht, Tayo Obafemi-Ajayi

Electrical and Computer Engineering Faculty Research & Creative Works

We present a framework for an explainable and statistically validated ensemble clustering model applied to Traumatic Brain Injury (TBI). The objective of our analysis is to identify patient injury severity subgroups and key phenotypes that delineate these subgroups using varied clinical and computed tomography data. Explainable and statistically-validated models are essential because a data-driven identification of subgroups is an inherently multidisciplinary undertaking. In our case, this procedure yielded six distinct patient subgroups with respect to mechanism of injury, severity of presentation, anatomy, psychometric, and functional outcome. This framework for ensemble cluster analysis fully integrates statistical methods at several stages of …

Analysis Of Distributed And Autonomous Scheduling Functions For 6tisch Networks, Francesca Righetti, Carlo Vallati, Sajal K. Das, Giuseppe Anastasi

Computer Science Faculty Research & Creative Works

The 6TiSCH architecture is expected to play a significant role to enable the Internet of Things paradigm also in industrial environments, where reliability and timeliness are of paramount importance to support critical applications. Many research activities have focused on the Scheduling Function (SF) used for managing the allocation of communication resources in order to guarantee the application requirements. Two different approaches have mainly attracted the interest of researchers, namely distributed and autonomous scheduling. Although many different (both distributed and autonomous) SFs have been proposed and analyzed, a direct comparison of these two approaches is still missing. In this work, we …

Big Data Energy Management, Analytics And Visualization For Residential Areas, Ragini Gupta, A. R. Al-Ali, Imran A. Zualkernan, Sajal K. Das

Computer Science Faculty Research & Creative Works

With the rapid development of IoT based home appliances, it has become a possibility that home owners share with Utilities in the management of home appliances energy consumption. Thus, the proposed work empowers home owners to manage their home appliances energy consumption and allow them to compare their consumption with respect to their local community total consumption. This serves as a nudge in consumer's behavior to schedule their home appliances operation according to their local community consumption profile and trend. Utilizing the same common communication infrastructure, it also allows the utilities on different consumption levels (community, state, country) to monitor …

Evaluation Of Standard And Semantically-Augmented Distance Metrics For Neurology Patients, Daniel B. Hier, Jonathan Kopel, Steven U. Brint, Donald C. Wunsch, Gayla R. Olbricht, Sima Azizi, Blaine Allen

Electrical and Computer Engineering Faculty Research & Creative Works

Background: Patient distances can be calculated based on signs and symptoms derived from an ontological hierarchy. There is controversy as to whether patient distance metrics that consider the semantic similarity between concepts can outperform standard patient distance metrics that are agnostic to concept similarity. The choice of distance metric can dominate the performance of classification or clustering algorithms. Our objective was to determine if semantically augmented distance metrics would outperform standard metrics on machine learning tasks.

Methods: We converted the neurological findings from 382 published neurology cases into sets of concepts with corresponding machine-readable codes. We calculated patient distances by …

Hierarchical Syntactic Models For Human Activity Recognition Through Mobility Traces, Enrico Casella, Marco Ortolani, Simone Silvestri, Sajal K. Das

Computer Science Faculty Research & Creative Works

Recognizing users’ daily life activities without disrupting their lifestyle is a key functionality to enable a broad variety of advanced services for a Smart City, from energy-efficient management of urban spaces to mobility optimization. In this paper, we propose a novel method for human activity recognition from a collection of outdoor mobility traces acquired through wearable devices. Our method exploits the regularities naturally present in human mobility patterns to construct syntactic models in the form of finite state automata, thanks to an approach known as grammatical inference. We also introduce a measure of similarity that accounts for the intrinsic hierarchical …

Motifs Enable Communication Efficiency And Fault-Tolerance In Transcriptional Networks, Satyaki Roy, Preetam Ghosh, Dipak Barua, Sajal K. Das

Computer Science Faculty Research & Creative Works

Analysis of the topology of transcriptional regulatory networks (TRNs) is an effective way to study the regulatory interactions between the transcription factors (TFs) and the target genes. TRNs are characterized by the abundance of motifs such as feed forward loops (FFLs), which contribute to their structural and functional properties. In this paper, we focus on the role of motifs (specifically, FFLs) in signal propagation in TRNs and the organization of the TRN topology with FFLs as building blocks. To this end, we classify nodes participating in FFLs (termed motif central nodes) into three distinct roles (namely, roles A, B …

Proof-Of-Activity Consensus Protocol Based On A Network's Active Nodes, Roman Belfer, Antonina Kashtalian, Andrii Nicheporuk, George Markowsky, Anatoliy Sachenko

Computer Science Faculty Research & Creative Works

The paper proposes a new socially oriented protocol that avoids pseudo-decentralization and monopolization of the network, increases the availability of the system, provides a fair selection of potential validator nodes, and provides a fair reward for creating new blocks and adding them to the blockchain. Our proposed protocol provides for the creation and addition of new blocks to a blockchain. Defines a node validator, which will create the next block according to its useful activity in the network according to predefined conditions, which can be formed according to the requirements of the system and will satisfy the individual needs of …

Efficiently Discovering Users Connectivity With Local Information In Online Social Networks, Na Li, Sajal K. Das

Computer Science Faculty Research & Creative Works

People's activities in Online Social Networks (OSNs) have generated a massive volume of data to which tremendous attention has been paid in academia and industry. With such data, researchers and third-parties can analyze human beings’ behaviors in social communities and develop more user-friendly services and applications to meet people's needs. However, often times, they face a big challenge of acquiring the data, as the access to such data is restricted by their collectors (e.g., Facebook and Twitter), due to various reasons, such as their user's privacy. In this paper, we intend to shed light on leveraging limited local social network …

A Collusion-Resistant Revocable Attribute-Based Encryption Scheme For Secure Data Sharing In Cloud, Azharul Islam, Sanjay Kumar Madria

Computer Science Faculty Research & Creative Works

Attribute-based encryption (ABE) is a prominent cryptographic tool for secure data sharing in the cloud because it can be used to enforce very expressive and fine-grained access control on outsourced data. The revocation in ABE remains a challenging problem as most of the revocation techniques available today, suffer from the collusion attack. The revocable ABE schemes which are collusion resistant require the aid of a semi-trusted manager to achieve revocation. More specifically, the semi-trusted manager needs to update the secret keys of nonrevoked users followed by a revocation. This introduces computation and communication overhead, and also increases the overall security …

System Efficient Esd Design Concept For Soft Failures, Giorgi Maghlakelidze

Doctoral Dissertations

"This research covers the topic of developing a systematic methodology of studying electrostatic discharge (ESD)-induced soft failures. ESD-induced soft failures (SF) are non-destructive disruptions of the functionality of an electronic system. The soft failure robustness of a USB3 Gen 1 interface is investigated, modeled, and improved. The injection is performed directly using transmission line pulser (TLP) with varying: pulse width, amplitude, polarity. Characterization provides data for failure thresholds and a SPICE circuit model that describes the transient voltage and current at the victim. Using the injected current, the likelihood of a SF is predicted. ESD protection by transient voltage suppressor …

Attention Mechanism In Deep Neural Networks For Computer Vision Tasks, Haohan Li

Doctoral Dissertations

“Attention mechanism, which is one of the most important algorithms in the deep Learning community, was initially designed in the natural language processing for enhancing the feature representation of key sentence fragments over the context. In recent years, the attention mechanism has been widely adopted in solving computer vision tasks by guiding deep neural networks (DNNs) to focus on specific image features for better understanding the semantic information of the image. However, the attention mechanism is not only capable of helping DNNs understand semantics, but also useful for the feature fusion, visual cue discovering, and temporal information selection, which are …

Values Of Artificial Intelligence In Marketing, Yingrui Xi

Masters Theses

“Artificial Intelligence (AI) is causing radical changes in marketing and emerging as a competent assistant supporting all areas of the marketing field. The influences and impacts AI has created in various marketing segments have aroused much interest among marketing professionals and academic scholars. Comprehensive and systematic studies on the values of AI in marketing, however, are still lacking and the existing literature fragmented. This research provides a comprehensive review of the existing literature in the relevant fields as well as a series of systematic interviews using the Value-Focused Thinking approach to understand the values of AI in marketing. This research …

On Predicting Stopping Time Of Human Sequential Decision-Making Using Discounted Satisficing Heuristic, Mounica Devaguptapu

Masters Theses

“Human sequential decision-making involves two essential questions: (i) "what to choose next?", and (ii) "when to stop?". Assuming that the human agents choose an alternative according to their preference order, our goal is to model and learn how human agents choose their stopping time while making sequential decisions. In contrary to traditional assumptions in the literature regarding how humans exhibit satisficing behavior on instantaneous utilities, we assume that humans employ a discounted satisficing heuristic to compute their stopping time, i.e., the human agent stops working if the total accumulated utility goes beyond a dynamic threshold that gets discounted with time. …

Observer-Based Event-Triggered And Set-Theoretic Neuro-Adaptive Controls For Constrained Uncertain Systems, Abdul Ghafoor

Doctoral Dissertations

"In this study, several new observer-based event-triggered and set-theoretic control schemes are presented to advance the state of the art in neuro-adaptive controls. In the first part, six new event-triggered neuro-adaptive control (ETNAC) schemes are presented for uncertain linear systems. These comprehensive designs offer flexibility to choose a design depending upon system performance requirements. Stability proofs for each scheme are presented and their performance is analyzed using benchmark examples. In the second part, the scope of the ETNAC is extended to uncertain nonlinear systems. It is applied to a case of precision formation flight of the microsatellites at the Sun-Earth/Moon …

Computational Model For Neural Architecture Search, Ram Deepak Gottapu

Doctoral Dissertations

"A long-standing goal in Deep Learning (DL) research is to design efficient architectures for a given dataset that are both accurate and computationally inexpensive. At present, designing deep learning architectures for a real-world application requires both human expertise and considerable effort as they are either handcrafted by careful experimentation or modified from a handful of existing models. This method is inefficient as the process of architecture design is highly time-consuming and computationally expensive.

The research presents an approach to automate the process of deep learning architecture design through a modeling procedure. In particular, it first introduces a framework that treats …

An Approach To System Of Systems Resiliency Using Architecture And Agent-Based Behavioral Modeling, Paulette Bootz Acheson

Doctoral Dissertations

”In today’s world it is no longer a question of whether a system will be compromised but when the system will be compromised. Consider the recent compromise of the Democratic National Committee (DNC) and Hillary Clinton emails as well as the multiple Yahoo breaches and the break into the Target customer database. The list of exploited vulnerabilities and successful cyber-attacks goes on and on. Because of the amount and frequency of the cyber-attacks, resiliency has taken on a whole new meaning. There is a new perspective within defense to consider resiliency in terms of Mission Success.

This research develops a …

Novel Approaches For Constructing Persistent Delaunay Triangulations By Applying Different Equations And Different Methods, Esraa Habeeb Khaleel Al-Juhaishi

Doctoral Dissertations

“Delaunay triangulation and data structures are an essential field of study and research in computer science, for this reason, the correct choices, and an adequate design are essential for the development of algorithms for the efficient storage and/or retrieval of information. However, most structures are usually ephemeral, which means keeping all versions, in different copies, of the same data structure is expensive. The problem arises of developing data structures that are capable of maintaining different versions of themselves, minimizing the cost of memory, and keeping the performance of operations as close as possible to the original structure. Therefore, this research …

Deep Learning For Digitized Histology Image Analysis, Sudhir Sornapudi

Doctoral Dissertations

“Cervical cancer is the fourth most frequent cancer that affects women worldwide. Assessment of cervical intraepithelial neoplasia (CIN) through histopathology remains as the standard for absolute determination of cancer. The examination of tissue samples under a microscope requires considerable time and effort from expert pathologists. There is a need to design an automated tool to assist pathologists for digitized histology slide analysis. Pre-cervical cancer is generally determined by examining the CIN which is the growth of atypical cells from the basement membrane (bottom) to the top of the epithelium. It has four grades, including: Normal, CIN1, CIN2, and CIN3. In …

Towards Efficacy And Efficiency In Sparse Delay Tolerant Networks, Douglas John Mcgeehan

Doctoral Dissertations

"The ubiquitous adoption of portable smart devices has enabled a new way of communication via Delay Tolerant Networks (DTNs), whereby messages are routed by the personal devices carried by ever-moving people. Although a DTN is a type of Mobile Ad Hoc Network (MANET), traditional MANET solutions are ill-equipped to accommodate message delivery in DTNs due to the dynamic and unpredictable nature of people's movements and their spatio-temporal sparsity. More so, such DTNs are susceptible to catastrophic congestion and are inherently chaotic and arduous. This manuscript proposes approaches to handle message delivery in notably sparse DTNs. First, the ChitChat system [69] …

Human Behavior Understanding For Worker-Centered Intelligent Manufacturing, Wenjin Tao

Doctoral Dissertations

“In a worker-centered intelligent manufacturing system, sensing and understanding of the worker’s behavior are the primary tasks, which are essential for automatic performance evaluation & optimization, intelligent training & assistance, and human-robot collaboration. In this study, a worker-centered training & assistant system is proposed for intelligent manufacturing, which is featured with self-awareness and active-guidance. To understand the hand behavior, a method is proposed for complex hand gesture recognition using Convolutional Neural Networks (CNN) with multiview augmentation and inference fusion, from depth images captured by Microsoft Kinect. To sense and understand the worker in a more comprehensive way, a multi-modal approach …

Cyber Physical Security Of Avionic Systems, Anusha Thudimilla

Doctoral Dissertations

“Cyber-physical security is a significant concern for critical infrastructures. The exponential growth of cyber-physical systems (CPSs) and the strong inter-dependency between the cyber and physical components introduces integrity issues such as vulnerability to injecting malicious data and projecting fake sensor measurements. Traditional security models partition the CPS from a security perspective into just two domains: high and low. However, this absolute partition is not adequate to address the challenges in the current CPSs as they are composed of multiple overlapping partitions. Information flow properties are one of the significant classes of cyber-physical security methods that model how inputs of a …

Secure Blockchains For Cyber-Physical Systems, Matthew Edward Wagner

Doctoral Dissertations

“Blockchains are a data structure used to perform state agreement in a distributed system across an entire network. One unique trait of blockchains is the lack of a centralized trusted third-party to control the system. This prevents a corrupted trusted third party from being able to control the entire blockchain. All nodes can reach agreement in an untrusted network where nodes do not need to trust one another to believe the accuracy of the information stored. Two main issues occur when trying to apply this technology to other applications: verifiability and scalability. In previous blockchain architectures, there is no way …

Development Of A Modeling Algorithm To Predict Lean Implementation Success, Richard Charles Barclay

Doctoral Dissertations

”Lean has become a common term and goal in organizations throughout the world. The approach of eliminating waste and continuous improvement may seem simple on the surface but can be more complex when it comes to implementation. Some firms implement lean with great success, getting complete organizational buy-in and realizing the efficiencies foundational to lean. Other organizations struggle to implement lean. Never able to get the buy-in or traction needed to really institute the sort of cultural change that is often needed to implement change. It would be beneficial to have a tool that organizations could use to assess their …