Computer Sciences Commons^™

Cloud Computing, Drilon Beqiraj

Theses and Dissertations

Cloud computing është teknologjia e gjeneratës së ardhshme. Kjo teknologji është bërë pjesë jetike për të gjithë sektorët publik dhe privatë, si dhe sektorët qeveritarë, në mënyrë që të plotësojnë kërkesat e tyre duke përfshirë një spektër të gjerë aplikimesh. Kostoja e ulët e llogaritjes në cloud dhe shkallëzimi dinamik e bën atë një nxitës të inovacionit për kompanitë, veçanërisht botën në zhvillim. Prandaj, qëllimi kryesor i punimit është trajtimi i koncepteve të ndryshme të përfshira në cloud computing, siç janë arkitektura e cloud computing, strategjitë e vendosjes, algoritmet dhe elementet e sigurisë të cloud computing. Meqenëse, teknologjia po zhvillohet …

Periodic Tilings And Auxetic Deployments, Ciprian S. Borcea, Ileana Streinu

Computer Science: Faculty Publications

We investigate geometric characteristics of a specific planar periodic framework with three degrees of freedom. While several avatars of this structural design have been considered in materials science under the name of chiral or missing rib models, all previous studies have addressed only local properties and limited deployment scenarios. We describe the global configuration space of the framework and emphasize the geometric underpinnings of auxetic deformations. Analogous structures may be considered in arbitrary dimension.

Terrace-Based Food Counting And Segmentation, Huu-Thanh Nguyen, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

This paper represents object instance as a terrace, where the height of terrace corresponds to object attention while the evolution of layers from peak to sea level represents the complexity in drawing the finer boundary of an object. A multitask neural network is presented to learn the terrace representation. The attention of terrace is leveraged for instance counting, and the layers provide prior for easy-to-hard pathway of progressive instance segmentation. We study the model for counting and segmentation for a variety of food instances, ranging from Chinese, Japanese to Western food. This paper presents how the terrace model deals with …

Understanding Adversarial Robustness Via Critical Attacking Route, Tianlin Li, Aishan Liu, Xianglong Liu, Yitao Xu, Chongzhi Zhang, Xiaofei Xie

Research Collection School Of Computing and Information Systems

Deep neural networks (DNNs) are vulnerable to adversarial examples which are generated by inputs with imperceptible perturbations. Understanding adversarial robustness of DNNs has become an important issue, which would for certain result in better practical deep learning applications. To address this issue, we try to explain adversarial robustness for deep models from a new perspective of critical attacking route, which is computed by a gradient-based influence propagation strategy. Similar to rumor spreading in social net-works, we believe that adversarial noises are amplified and propagated through the critical attacking route. By exploiting neurons' influences layer by layer, we compose the critical …

The Role Of Steps And Game Elements In Gamified Fitness Tracker Apps: A Systematic Review, Aatish Neupane, Derek Hansen, Jerry Alan Fails, Anud Sharma

Computer Science Faculty Publications and Presentations

This article reviews 103 gamified fitness tracker apps (Android and iOS) that incorporate step count data into gameplay. Games are labeled with a set of 13 game elements as well as meta-data from the app stores (e.g., avg rating, number of reviews). Network clustering and visualizations are used to identify the relationship between game elements that occur in the same games. A taxonomy of how steps are used as rewards is provided, along with example games. An existing taxonomy of how games use currency is also mapped to step-based games. We show that many games use the triad of Social …

Olympic Games Event Recognition Via Transfer Learning With Photobombing Guided Data Augmentation, Yousef I. Mohamad, Samah S. Baraheem, Tam Van Nguyen

Computer Science Faculty Publications

Automatic event recognition in sports photos is both an interesting and valuable research topic in the field of computer vision and deep learning. With the rapid increase and the explosive spread of data, which is being captured momentarily, the need for fast and precise access to the right information has become a challenging task with considerable importance for multiple practical applications, i.e., sports image and video search, sport data analysis, healthcare monitoring applications, monitoring and surveillance systems for indoor and outdoor activities, and video captioning. In this paper, we evaluate different deep learning models in recognizing and interpreting the sport …

Covert Computation In Self-Assembled Circuits, Angel A. Cantu, Austin Luchsinger, Robert Schweller, Tim Wylie

Computer Science Faculty Publications

Traditionally, computation within self-assembly models is hard to conceal because the self-assembly process generates a crystalline assembly whose computational history is inherently part of the structure itself. With no way to remove information from the computation, this computational model offers a unique problem: how can computational input and computation be hidden while still computing and reporting the final output? Designing such systems is inherently motivated by privacy concerns in biomedical computing and applications in cryptography. In this paper we propose the problem of performing “covert computation” within tile self-assembly that seeks to design self-assembly systems that “conceal” both the input …

Lorawan Device Security And Energy Optimization, John A. Stranahan Jr.

Theses and Dissertations

Resource-constrained devices are commonly connected to a network and become "things" that make up the Internet of Things (IoT). Many industries are interested in cost-effective, reliable, and cyber secure sensor networks due to the ever-increasing connectivity and benefits of IoT devices. The full advantages of IoT devices are seen in a long-range and remote context. However, current IoT platforms show many obstacles to achieve a balance between power efficiency and cybersecurity. Battery-powered sensor nodes can reliably send data over long distances with minimal power draw by adopting Long-Range (LoRa) wireless radio frequency technology. With LoRa, these devices can stay active …

Speech Enhancement Using Speech Synthesis Techniques, Soumi Maiti

Dissertations, Theses, and Capstone Projects

Traditional speech enhancement systems reduce noise by modifying the noisy signal to make it more like a clean signal, which suffers from two problems: under-suppression of noise and over-suppression of speech. These problems create distortions in enhanced speech and hurt the quality of the enhanced signal. We propose to utilize speech synthesis techniques for a higher quality speech enhancement system. Synthesizing clean speech based on the noisy signal could produce outputs that are both noise-free and high quality. We first show that we can replace the noisy speech with its clean resynthesis from a previously recorded clean speech dictionary from …

3d Object Detection, Instance Segmentation And Classification From 3d Range And 2d Color Images, Xiaoke Shen

Dissertations, Theses, and Capstone Projects

We address the problem of 3D object detection and instance segmentation by proposing a novel object segmentation and detection system. First, we detect 2D objects based on RGB, Depth only, or RGB-D images. A 3D convolutional-based system, named Frustum VoxNet, is proposed. This system 1) generates frustums from 2D detection results, 2) proposes 3D candidate voxelized images for each frustum, and uses a 3D convolutional neural network (CNN) based on these candidates voxelized images to perform the 3D instance segmentation and object detection. Although the volumetric data representation is widely used for 3D object classification, there are fewer works on …

A New Feature Selection Method Based On Class Association Rule, Sami A. Al-Dhaheri

Dissertations, Theses, and Capstone Projects

Feature selection is a key process for supervised learning algorithms. It involves discarding irrelevant attributes from the training dataset from which the models are derived. One of the vital feature selection approaches is Filtering, which often uses mathematical models to compute the relevance for each feature in the training dataset and then sorts the features into descending order based on their computed scores. However, most Filtering methods face several challenges including, but not limited to, merely considering feature-class correlation when defining a feature’s relevance; additionally, not recommending which subset of features to retain. Leaving this decision to the end-user may …

Modeling And Analysis Of Affiliation Networks With Subsumption, Alexey Nikolaev

Dissertations, Theses, and Capstone Projects

An affiliation (or two-mode) network is an abstraction commonly used for representing systems with group interactions. It consists of a set of nodes and a set of their groupings called affiliations. We introduce the notion of affiliation network with subsumption, in which no affiliation can be a subset of another. A network with this property can be modeled by an abstract simplicial complex whose facets are the affiliations of the network.

We introduce a new model for generating affiliation networks with and without subsumption (represented as simplicial complexes and hypergraphs, respectively). In this model, at each iteration, a constant number …

Role Of Artificial Intelligence In The Internet Of Things (Iot) Cybersecurity, Murat Kuzlu, Corinne Fair, Ozgur Guler

Engineering Technology Faculty Publications

In recent years, the use of the Internet of Things (IoT) has increased exponentially, and cybersecurity concerns have increased along with it. On the cutting edge of cybersecurity is Artificial Intelligence (AI), which is used for the development of complex algorithms to protect networks and systems, including IoT systems. However, cyber-attackers have figured out how to exploit AI and have even begun to use adversarial AI in order to carry out cybersecurity attacks. This review paper compiles information from several other surveys and research papers regarding IoT, AI, and attacks with and against AI and explores the relationship between these …

Factors Influencing Small Construction Businesses From Implementing Information Security: A Case Study, Carl Andrew Mayes

Doctoral Dissertations and Projects

This qualitative study described the influence of small businesses’ failure to properly implement information security technologies resulting in the loss of sensitive and proprietary business information. A collective case study approach was used to determine the most effective way to gain a holistic picture of how small construction businesses make security technology implementation decisions to support their workforce. The theory guiding this study was the Unified Theory of Acceptance and Use of Technology (UTAUT) model which is related to the Theory of Planned Behavior and the Technology Acceptance Model which helped explain the intentions of individuals to use information systems. …

Divide And Capture: An Improved Cryptanalysis Of The Encryption Standard Algorithm Rsa, Willy Susilo, Joseph Tonien, Guomin Yang

Research Collection School Of Computing and Information Systems

RSA is a well known standard algorithm used by modern computers to encrypt and decrypt messages. In some applications, to save the decryption time, it is desirable to have a short secret key d compared to the modulus N. The first significant attack that breaks RSA with short secret key given by Wiener in 1990 is based on the continued fraction technique and it works with d < 1/4 root 18 N-.(25). A decade later, in 2000, Boneh and Durfee presented an improved attack based on lattice technique which works with d < N-.(292). Until this day, Boneh-Durfee attack remain as the best attack on RSA with short secret key. In this paper, we revisit the continued fraction technique and propose a new attack on RSA. Our main result shows that when d < root t (2 root 2 + 8/3) N-.(75)/root e, where e is the public exponent and t is a chosen parameter, our attack can break the RSA with the running time of O(tlog (N)). Our attack is especially well suited for the case where e is much smaller than N. When e approximate to N, the Boneh-Durfee attack outperforms ours. As a result, we could simultaneously run both attacks, our new attack and the classical Boneh-Durfee attack as a backup.

Scalable Verification Of Quantized Neural Networks, Thomas A. Henzinger, Mathias Lechner, Dorde Zikelic

Research Collection School Of Computing and Information Systems

Formal verification of neural networks is an active topic of research, and recent advances have significantly increased the size of the networks that verification tools can handle. However, most methods are designed for verification of an idealized model of the actual network which works over real arithmetic and ignores rounding imprecisions. This idealization is in stark contrast to network quantization, which is a technique that trades numerical precision for computational efficiency and is, therefore, often applied in practice. Neglecting rounding errors of such low-bit quantized neural networks has been shown to lead to wrong conclusions about the network’s correctness. Thus, …

Adversarial Meta Sampling For Multilingual Low-Resource Speech Recognition, Yubei Xiao, Ke Gong, Pan Zhou, Guolin Zheng, Xiaodan Liang, Liang Lin

Research Collection School Of Computing and Information Systems

Human doctors with well-structured medical knowledge can diagnose a disease merely via a few conversations with patients about symptoms. In contrast, existing knowledgegrounded dialogue systems often require a large number of dialogue instances to learn as they fail to capture the correlations between different diseases and neglect the diagnostic experience shared among them. To address this issue, we propose a more natural and practical paradigm, i.e., low-resource medical dialogue generation, which can transfer the diagnostic experience from source diseases to target ones with a handful of data for adaptation. It is capitalized on a commonsense knowledge graph to characterize the …

Graph-Evolving Meta-Learning For Low-Resource Medical Dialogue Generation, Shuai Lin, Pan Zhou, Xiaodan Liang, Jianheng Tang, Ruihui Zhao, Ziliang Chen, Liang Lin

Research Collection School Of Computing and Information Systems

Human doctors with well-structured medical knowledge can diagnose a disease merely via a few conversations with patients about symptoms. In contrast, existing knowledge-grounded dialogue systems often require a large number of dialogue instances to learn as they fail to capture the correlations between different diseases and neglect the diagnostic experience shared among them. To address this issue, we propose a more natural and practical paradigm, i.e., low-resource medical dialogue generation, which can transfer the diagnostic experience from source diseases to target ones with a handful of data for adaptation. It is capitalized on a commonsense knowledge graph to characterize the …

To Thine Own Self Be True? Incentive Problems In Personalized Law, Jordan M. Barry, John William Hatfield, Scott Duke Kominers

William & Mary Law Review

Recent years have seen an explosion of scholarship on “personalized law.” Commentators foresee a world in which regulators armed with big data and machine learning techniques determine the optimal legal rule for every regulated party, then instantaneously disseminate their decisions via smartphones and other “smart” devices. They envision a legal utopia in which every fact pattern is assigned society’s preferred legal treatment in real time.

But regulation is a dynamic process; regulated parties react to law. They change their behavior to pursue their preferred outcomes— which often diverge from society’s—and they will continue to do so under personalized law: They …

Statistical Analysis And Comparison Of Optical Classification Of Atmospheric Aerosol Lidar Data, Mohammed Alqawba, Norou Diawara, Kwasi G. Afrifa, Mohamed I. Elbakary, Mecit Cetin, Khan Iftekharuddin

Mathematics & Statistics Faculty Publications

In this article, we present a new study for the analysis and classification of atmospheric aerosols in remote sensing LIDAR data. Information on particle size and associated properties are extracted from these remote sensing atmospheric data which are collected by a ground-based LIDAR system. This study first considers optical LIDAR parameter-based classification methods for clustering and classification of different types of harmful aerosol particles in the atmosphere. Since accurate methods for aerosol prediction behaviors are based upon observed data, computational approaches must overcome design limitations, and consider appropriate calibration and estimation accuracy. Consequently, two statistical methods based on generalized linear …

Fault Analysis And Debugging Of Microservice Systems: Industrial Survey, Benchmark System, And Empirical Study, Xiang Zhou, Xin Peng, Tao Xie, Jun Sun, Chao Ji, Wenhai Li, Dan Ding

Research Collection School Of Computing and Information Systems

The complexity and dynamism of microservice systems pose unique challenges to a variety of software engineering tasks such as fault analysis and debugging. In spite of the prevalence and importance of microservices in industry, there is limited research on the fault analysis and debugging of microservice systems. To fill this gap, we conduct an industrial survey to learn typical faults of microservice systems, current practice of debugging, and the challenges faced by developers in practice. We then develop a medium-size benchmark microservice system (being the largest and most complex open source microservice system within our knowledge) and replicate 22 industrial …

Multi-Decoder Attention Model With Embedding Glimpse For Solving Vehicle Routing Problems, Liang Xin, Wen Song, Zhiguang Cao, Jie Zhang

Research Collection School Of Computing and Information Systems

We present a novel deep reinforcement learning method to learn construction heuristics for vehicle routing problems. In specific, we propose a Multi-Decoder Attention Model (MDAM) to train multiple diverse policies, which effectively increases the chance of finding good solutions compared with existing methods that train only one policy. A customized beam search strategy is designed to fully exploit the diversity of MDAM. In addition, we propose an Embedding Glimpse layer in MDAM based on the recursive nature of construction, which can improve the quality of each policy by providing more informative embeddings. Extensive experiments on six different routing problems show …

Learning To Pre-Train Graph Neural Networks, Yuanfu Lu, Xunqiang Jiang, Yuan Fang, Chuan Shi

Research Collection School Of Computing and Information Systems

Graph neural networks (GNNs) have become the de facto standard for representation learning on graphs, which derive effective node representations by recursively aggregating information from graph neighborhoods. While GNNs can be trained from scratch, pre-training GNNs to learn transferable knowledge for downstream tasks has recently been demonstrated to improve the state of the art. However, conventional GNN pre-training methods follow a two-step paradigm: 1) pre-training on abundant unlabeled data and 2) fine-tuning on downstream labeled data, between which there exists a significant gap due to the divergence of optimization objectives in the two steps. In this paper, we conduct an …

Neural Architecture Search As Sparse Supernet, Y. Wu, A. Liu, Zhiwu Huang, S. Zhang, Gool L. Van

Research Collection School Of Computing and Information Systems

This paper aims at enlarging the problem of Neural Architecture Search (NAS) from Single-Path and Multi-Path Search to automated Mixed-Path Search. In particular, we model the NAS problem as a sparse supernet using a new continuous architecture representation with a mixture of sparsity constraints. The sparse supernet enables us to automatically achieve sparsely-mixed paths upon a compact set of nodes. To optimize the proposed sparse supernet, we exploit a hierarchical accelerated proximal gradient algorithm within a bi-level optimization framework. Extensive experiments on Convolutional Neural Network and Recurrent Neural Network search demonstrate that the proposed method is capable of searching for …

Differential Training: A Generic Framework To Reduce Label Noises For Android Malware Detection, Jiayun Xu, Yingjiu Li, Robert H. Deng

Research Collection School Of Computing and Information Systems

A common problem in machine learning-based malware detection is that training data may contain noisy labels and it is challenging to make the training data noise-free at a large scale. To address this problem, we propose a generic framework to reduce the noise level of training data for the training of any machine learning-based Android malware detection. Our framework makes use of all intermediate states of two identical deep learning classification models during their training with a given noisy training dataset and generate a noise-detection feature vector for each input sample. Our framework then applies a set of outlier detection …

Treecaps: Tree-Based Capsule Networks For Source Code Processing, Duy Quoc Nghi Bui, Yijun Yu, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Recently program learning techniques have been proposed to process source code based on syntactical structures (e.g., Abstract Syntax Trees) and/or semantic information (e.g., Dependency Graphs). While graphs may be better at capturing various viewpoints of code semantics than trees, constructing graph inputs from code need static code semantic analysis that may not be accurate and introduces noise during learning. On the other hand, syntax trees are precisely defined according to the language grammar and easier to construct and process than graphs. We propose a new tree-based learning technique, named TreeCaps, by fusing capsule networks with tree-based convolutional neural networks, to …

An Exploratory Study On The Introduction And Removal Of Different Types Of Technical Debt In Deep Learning Frameworks, Jiakun Liu, Qiao Huang, Xin Xia, Emad Shihab, David Lo, Shanping Li

Research Collection School Of Computing and Information Systems

To complete tasks faster, developers often have to sacrifice the quality of the software. Such compromised practice results in the increasing burden to developers in future development. The metaphor, technical debt, describes such practice. Prior research has illustrated the negative impact of technical debt, and many researchers investigated how developers deal with a certain type of technical debt. However, few studies focused on the removal of different types of technical debt in practice. To fill this gap, we use the introduction and removal of different types of self-admitted technical debt (i.e., SATD) in 7 deep learning frameworks as an example. …

Efficientderain: Learning Pixel-Wise Dilation Filtering For High-Efficiency Single-Image Deraining, Qing Guo, Jingyang Sun, Felix Juefei-Xu, Lei Ma, Xiaofei Xie, Wei Feng, Yang Liu, Jianjun Zhao

Research Collection School Of Computing and Information Systems

Single-image deraining is rather challenging due to the unknown rain model. Existing methods often make specific assumptions of the rain model, which can hardly cover many diverse circumstances in the real world, compelling them to employ complex optimization or progressive refinement. This, however, significantly affects these methods’ efficiency and effectiveness for many efficiency-critical applications. To fill this gap, in this paper, we regard the single-image deraining as a general image-enhancing problem and originally propose a model-free deraining method, i.e., EfficientDeRain, which is able to process a rainy image within 10 ms (i.e., around 6 ms on average), over 80 times …

Decision-Guided Weighted Automata Extraction From Recurrent Neural Networks, Xiyue Zhang, Xiaoning Du, Xiaofei Xie, Lei Ma, Yang Liu, Meng Sun

Research Collection School Of Computing and Information Systems

Recurrent Neural Networks (RNNs) have demonstrated their effectiveness in learning and processing sequential data (e.g., speech and natural language). However, due to the black-box nature of neural networks, understanding the decision logic of RNNs is quite challenging. Some recent progress has been made to approximate the behavior of an RNN by weighted automata. They provide better interpretability, but still suffer from poor scalability. In this paper, we propose a novel approach to extracting weighted automata with the guidance of a target RNN’s decision and context information. In particular, we identify the patterns of RNN’s step-wise predictive decisions to instruct the …

Norm-Based Generalisation Bounds For Deep Multi-Class Convolutional Neural Networks, Antoine Ledent, Waleed Mustafa, Yunwen Lei, Marius Kloft

Research Collection School Of Computing and Information Systems

We show generalisation error bounds for deep learning with two main improvements over the state of the art. (1) Our bounds have no explicit dependence on the number of classes except for logarithmic factors. This holds even when formulating the bounds in terms of the Frobenius-norm of the weight matrices, where previous bounds exhibit at least a squareroot dependence on the number of classes. (2) We adapt the classic Rademacher analysis of DNNs to incorporate weight sharing—a task of fundamental theoretical importance which was previously attempted only under very restrictive assumptions. In our results, each convolutional filter contributes only once …