Computer Sciences Commons^™

How Are Deep Learning Models Similar? An Empirical Study On Clone Analysis Of Deep Learning Software, Xiongfei Wu, Liangyu Qin, Bing Yu, Xiaofei Xie, Lei Ma, Yinxing Xue, Yang Liu, Jianjun Zhao

Research Collection School Of Computing and Information Systems

Deep learning (DL) has been successfully applied to many cutting-edge applications, e.g., image processing, speech recognition, and natural language processing. As more and more DL software is made open-sourced, publicly available, and organized in model repositories and stores (Model Zoo, ModelDepot), there comes a need to understand the relationships of these DL models regarding their maintenance and evolution tasks. Although clone analysis has been extensively studied for traditional software, up to the present, clone analysis has not been investigated for DL software. Since DL software adopts the data-driven development paradigm, it is still not clear whether and to what extent …

Identification Of Microscopy Cell Images By Using Convolutional Neural Network Application, Ajis Norfatin Farisya

Student Works (2020-2029)

Breast cancer has been the major factor of cancer death and the second main cause of women’s deaths in the world. The false positive results of this cancer cell detection during the screening test leads to false treatment and emotional disturbance of the patients. Thus, breast cancer cell lines (MCF7) is used as the microscopy image samples together with the Human Bone Osteosarcoma Epithelial Cells (U2OS), and Human Hepatocyte as control to study the effectiveness of convolutional neural network (CNN) as a method of image recognition. The objectives of this study are to determine the ability of convolutional neural network …

The Critical Success Factors Of Cloud Based Application Implementation In Construction Management, Sukiman Mohd Asfahani

Student Works (2020-2029)

Design and construction are information intensive activities, involving a great number of people collaborating to produce complex, one-off developments. Whilst historically, information may have been managed and communicated using paper-based systems and verbal instructions, the integration of the supply chain, the introduction of computer aided design (CAD) and building information modelling (BIM) and the development of cloud computing application means that information communications technology (ICT) is becoming a fundamental part, not just of the design office, but also of the construction site. Cloud computing is a relatively new phenomenon in the construction industry. It allows the delivery over the 'cloud' …

Improving Client-Consultant-Contractor Communication In Construction Industry Through Whatsapp Application, Muhammad Hafizul Taib

Student Works (2020-2029)

A Smooth and effective communication is very important in construction industry to prevent iteration and rework which will cause money. Since there are a lot of parties involve in construction,it is important to have a good communication platform. In the current world, people are using the technology advancement to enhance the effectiveness of communication amongst people who work in construction industry. Though there are a lot of mobile application designed for construction purpose, WhatsApp is the most commonly used by all. However, there are no studies done to identify the effectiveness of it. This thesis will gather respond from client, …

Cyberspace Odyssey: A Competitive Team-Oriented Serious Game In Computer Networking, Kendra Graham, James Anderson, Conrad Rife, Bryce Heitmeyer, Pranav R. Patel, Scott L. Nykl, Alan C. Lin, Laurence D. Merkle

Faculty Publications

Cyber Space Odyssey (CSO) is a novel serious game supporting computer networking education by engaging students in a race to successfully perform various cybersecurity tasks in order to collect clues and solve a puzzle in virtual near-Earth 3D space. Each team interacts with the game server through a dedicated client presenting a multimodal interface, using a game controller for navigation and various desktop computer networking tools of the trade for cybersecurity tasks on the game's physical network. Specifically, teams connect to wireless access points, use packet monitors to intercept network traffic, decrypt and reverse engineer that traffic, craft well-formed and …

Hybrid Stochastic-Deterministic Minibatch Proximal Gradient: Less-Than-Single-Pass Optimization With Nearly Optimal Generalization, Pan Zhou, Xiaotong Yuan

Research Collection School Of Computing and Information Systems

Stochastic variance-reduced gradient (SVRG) algorithms have been shown to work favorably in solving large-scale learning problems. Despite the remarkable success, the stochastic gradient complexity of SVRG-type algorithms usually scales linearly with data size and thus could still be expensive for huge data. To address this deficiency, we propose a hybrid stochastic-deterministic minibatch proximal gradient (HSDMPG) algorithm for strongly-convex problems that enjoys provably improved data-size-independent complexity guarantees.

Optimal Control Of Linear Continuous-Time Systems In The Presence Of State And Input Delays With Application To A Chemical Reactor, Rohollah Moghadam, Sarangapani Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, the optimal regulation of linear continuous-time systems with state and input delays is introduced by utilizing a quadratic cost function and state feedback. The Lyapunov-Krakovskii functional incorporating state and input delays is defined as a value function. Next, the Bellman type equation is formulated, and a delay Algebraic Riccati equation (DARE) over infinite time horizon is derived. By using the stationarity condition for the Bellman type equation, the optimal control input is obtained. It is demonstrated that the proposed optimal control input makes the closed-loop system asymptotically stable. Finally, simulation results confirm the theoretical claims by applying …

Distributed Adaptive State Estimation And Tracking Scheme For Nonlinear Systems Using Active Passive Sensor Networks, Akhilesh Raj, S. Jagannathan, Tansel Yucelen

Electrical and Computer Engineering Faculty Research & Creative Works

This paper proposes a novel adaptive neural network (NN) based distributed state estimation scheme for a heterogeneous sensor network (HSN), to estimate the state vector of an unknown nonlinear process/target by using sensed output when the target input remains unknown. The active nodes in the HSN can sense the target output based on the detection range. By using a connected graph, the active nodes will communicate their estimated state vector from their adaptive NN observer to other passive nodes in the neighborhood that cannot sense the target, so that they can estimate the target state vector. Next, a subset of …

Online Optimal Adaptive Control Of A Class Of Uncertain Nonlinear Discrete-Time Systems, Rohollah Moghadam, Pappa Natarajan, Krishnan Raghavan, Sarangapani Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, a multi-layer neural network (MNN) based online optimal adaptive regulation of a class of nonlinear discrete-time systems in affine form with uncertain internal dynamics is introduced. The multi-layer neural networks (MNN)-based actor-critic framework is utilized to estimate the optimal control input and cost function. The temporal difference (TD) error is derived from the difference between actual and estimated cost function. The MNN weights of both critic and actor are tuned at every sampling instant as a function of the instantaneous temporal difference and control policy errors. The proposed approach does not require the selection of any basis …

Deep Learning Of Facial Embeddings And Facial Landmark Points For The Detection Of Academic Emotions, Hua Leong Fwa

Research Collection School Of Computing and Information Systems

Automatic emotion recognition is an actively researched area as emotion plays a pivotal role in effective human communications. Equipping a computer to understand and respond to human emotions has potential applications in many fields including education, medicine, transport and hospitality. In a classroom or online learning context, the basic emotions do not occur frequently and do not influence the learning process itself. The academic emotions such as engagement, frustration, confusion and boredom are the ones which are pivotal to sustaining the motivation of learners. In this study, we evaluated the use of deep learning on FaceNet embeddings and facial landmark …

A Review On Eye-Tracking Metrics For Sleepiness, Debasis Roy, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Sleepiness that can arise from sleep deprivation can increase human errors in task performance and create workplace hazards and accidents. Hence, it is critical to detect sleepiness to minimize hazards and human errors. This paper provides a review of the literature on eye tracking metrics that can be used to detect sleepiness. These metrics include blink duration, blink frequency, saccade latency, saccade peak velocity, saccade accuracy, smooth pursuit velocity gain, fixation rate, pupil size, and latency to pupil constriction.

Search Me In The Dark: Privacy-Preserving Boolean Range Query Over Encrypted Spatial Data, Xiangyu Wang, Jianfeng Ma, Ximeng Liu, Robert H. Deng, Yinbin Miao, Dan Zhu, Zhuoran Ma

Research Collection School Of Computing and Information Systems

With the increasing popularity of geo-positioning technologies and mobile Internet, spatial keyword data services have attracted growing interest from both the industrial and academic communities in recent years. Meanwhile, a massive amount of data is increasingly being outsourced to cloud in the encrypted form for enjoying the advantages of cloud computing while without compromising data privacy. Most existing works primarily focus on the privacy-preserving schemes for either spatial or keyword queries, and they cannot be directly applied to solve the spatial keyword query problem over encrypted data. In this paper, we study the challenging problem of Privacy-preserving Boolean Range Query …

Geoprune: Efficiently Matching Trips In Ride-Sharing Through Geometric Properties, Yixin Xu, Jianzhong Qi, Renata Borovica-Gajic

Research Collection School Of Computing and Information Systems

On-demand ride-sharing is rapidly growing. Matching trip requests to vehicles efficiently is critical for the service quality of ride-sharing. To match trip requests with vehicles, a prune-And-select scheme is commonly used. The pruning stage identifies feasible vehicles that can satisfy the trip constraints (e.g., trip time). The selection stage selects the optimal one(s) from the feasible vehicles. The pruning stage is crucial to lowering the complexity of the selection stage and to achieve efficient matching. We propose an effective and efficient pruning algorithm called GeoPrune. GeoPrune represents the time constraints of trip requests using circles and ellipses, which can be …

Privacy-Enhanced Remote Data Integrity Checking With Updatable Timestamp, Tong Wu, Guomin Yang, Yi Mu, Rongmao Chen, Shengmin Xu

Research Collection School Of Computing and Information Systems

Remote data integrity checking (RDIC) enables clients to verify whether the outsourced data is intact without keeping a copy locally or downloading it. Nevertheless, the existing RDIC schemes do not support the pay-as-you-go (PAYG) payment model, where the payment is decided by the volume and duration of the outsourced data. Specifically, none of the existing works have considered the client’s control over changes in storage duration. In this paper, we propose an RDIC scheme to simultaneously check the data content and storage duration represented by an updatable timestamp via the third-party auditor (TPA). Also, our proposed scheme achieves indistinguishable privacy …

Probabilistic Value Selection For Space Efficient Model, Gunarto Sindoro Njoo, Baihua Zheng, Kuo-Wei Hsu, Wen-Chih Peng

Research Collection School Of Computing and Information Systems

An alternative to current mainstream preprocessing methods is proposed: Value Selection (VS). Unlike the existing methods such as feature selection that removes features and instance selection that eliminates instances, value selection eliminates the values (with respect to each feature) in the dataset with two purposes: reducing the model size and preserving its accuracy. Two probabilistic methods based on information theory's metric are proposed: PVS and P + VS. Extensive experiments on the benchmark datasets with various sizes are elaborated. Those results are compared with the existing preprocessing methods such as feature selection, feature transformation, and instance selection methods. Experiment results …

Adaptive Large Neighborhood Search For Vehicle Routing Problem With Cross-Docking, Aldy Gunawan, Audrey Tedja Widjaja, Pieter Vansteenwegen, Vincent F. Yu

Research Collection School Of Computing and Information Systems

Cross-docking is considered as a method to manage and control the inventory flow, which is essential in the context of supply chain management. This paper studies the integration of the vehicle routing problem with cross-docking, namely VRPCD which has been extensively studied due to its ability to reducethe overall costs occurring in a supply chain network. Given a fleet of homogeneous vehicles for delivering a single type of product from suppliers to customers through a cross-dock facility, the objective of VRPCD is to determine the number of vehicles used and the corresponding vehicle routes, such that the vehicleoperational and transportation …

Next-Term Grade Prediction: A Machine Learning Approach, Audrey Tedja Widjaja, Lei Wang, Nghia Truong Trong, Aldy Gunawan, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

As students progress in their university programs, they have to face many course choices. It is important for them to receive guidance based on not only their interest, but also the "predicted" course performance so as to improve learning experience and optimise academic performance. In this paper, we propose the next-term grade prediction task as a useful course selection guidance. We propose a machine learning framework to predict course grades in a specific program term using the historical student-course data. In this framework, we develop the prediction model using Factorization Machine (FM) and Long Short Term Memory combined with FM …

Biane: Bipartite Attributed Network Embedding, Wentao Huang, Yuchen Li, Yuan Fang, Ju Fan, Hongxia Yang

Research Collection School Of Computing and Information Systems

Network embedding effectively transforms complex network data into a low-dimensional vector space and has shown great performance in many real-world scenarios, such as link prediction, node classification, and similarity search. A plethora of methods have been proposed to learn node representations and achieve encouraging results. Nevertheless, little attention has been paid on the embedding technique for bipartite attributed networks, which is a typical data structure for modeling nodes from two distinct partitions. In this paper, we propose a novel model called BiANE, short for Bipartite Attributed Network Embedding. In particular, BiANE not only models the inter-partition proximity but also models …

Designing Leakage-Resilient Password Entry On Head-Mounted Smart Wearable Glass Devices, Yan Li, Yao Cheng, Wenzhi Meng, Yingjiu Li, Robert H. Deng

Research Collection School Of Computing and Information Systems

With the boom of Augmented Reality (AR) and Virtual Reality (VR) applications, head-mounted smart wearable glass devices are becoming popular to help users access various services like E-mail freely. However, most existing password entry schemes on smart glasses rely on additional computers or mobile devices connected to smart glasses, which require users to switch between different systems and devices. This may greatly lower the practicability and usability of smart glasses. In this paper, we focus on this challenge and design three practical anti-eavesdropping password entry schemes on stand-alone smart glasses, named gTapper, gRotator and gTalker. The main idea is to …

Simulated Experince Evaluation In Developing Multi-Agent Coordination Graphs, Andrew J. Watson

Theses and Dissertations

Cognitive science has proposed that a way people learn is through self-critiquing by generating 'what-if' strategies for events (simulation). It is theorized that people use this method to learn something new as well as to learn more quickly. This research adds this concept to a graph-based genetic program. Memories are recorded during fitness assessment and retained in a global memory bank based on the magnitude of change in the agent’s energy and age of the memory. Between generations, candidate agents perform in simulations of the stored memories. Candidates that perform similarly to good memories and differently from bad memories are …

The Meaning Of Red And Green In User Interfaces For The Color Deficient, Bassel Hamieh

University Honors Theses

Around 108 million web users are color blind which is a problem when the way we communicate over the web or interfaces is through the use of color. Red and green are two colors that are especially heavily used in interface design because of their strong symbolic associations; red being a sign to warn or stop and green being the opposite. This has a large effect on red-green color blind people who are not able to perceive either of those colors correctly. Many solutions exist that aim to help through color differentiation but none take into account color symbolism. With …

Empirical Analysis Of Cbow And Skip Gram Nlp Models, Tejas Menon

University Honors Theses

CBOW and Skip Gram are two NLP techniques to produce word embedding models that are accurate and performant. They were invented in the seminal paper by T. Mikolov et al. and have since observed optimizations such as negative sampling and subsampling. This paper implements a fully-optimized version of these models using Py-Torch and runs them through a toy sentiment/subject analysis. It is weakly observed that different corpus types affect the skew of word embeddings such that fictional corpus are better suited for sentiment analysis and non-fictional for subject analysis.

Automatic Keyphrase Extraction From Russian-Language Scholarly Papers In Computational Linguistics, Yves Wienecke

University Honors Theses

The automatic extraction of keyphrases from scholarly papers is a necessary step for many Natural Language Processing (NLP) tasks, including text retrieval, machine translation, and text summarization. However, due to the different grammatical and semantic intricacies of languages, this is a highly language-dependent task. Many free and open source implementations of state-of-the-art keyphrase extraction techniques exist, but they are not adapted for processing Russian text. Furthermore, the multi-linguistic character of scholarly papers in the field of Russian computational linguistics and NLP introduces additional complexity to keyphrase extraction. This paper describes a free and open source program as a proof of …

Functional Programming For Systems Software: Implementing Baremetal Programs In Habit, Donovan Ellison

University Honors Theses

Programming in a baremetal environment, directly on top of hardware with very little to help manage memory or ensure safety, can be dangerous even for experienced programmers. Programming languages can ease the burden on developers and sometimes take care of entire sets of errors. This is not the case for a language like C that will do almost anything you want, for better or worse. To operate in a baremetal environment often requires direct control over memory, but it would be nice to have that capability without sacrificing safety guarantees. Rust is a new language that aims to fit this …

Relational Joins On Gpus For In-Memory Database Query Processing, Ran Rui

USF Tampa Graduate Theses and Dissertations

Relational join processing is one of the core functionalities in database management systems. Implementing join algorithms on parallel platforms, especially modern GPUs, has gain a lot of momentum in the past decade. This dissertation addresses the following issues on GPU join algorithms. First, we present empirical evaluations of a state-of-the-art work on GPU-based join processing. Since 2008, the compute capabilities of GPUs have increased following a pace faster than that of the multi-core CPUs. We run a comprehensive set of experiments to study how join operations can benefit from such rapid expansion of GPU capabilities. We also present improved GPU …

Device–To-Device Association Algorithm For Optimal Neighbour Selection And Channel Sharing In 5g Cellular Networks, Chiza Christophe, Omar Hamad, Libe Massawe, Abdi Abdalla

Tanzania Journal of Science

The integration of device-to-device (D2D) communication in 5G cellular networks has generated the possibility of multiple transmission modes in a single cell. This has motivated scholars to investigate different mode selection and D2D association algorithms that guarantee the selection of proper transmission mode. However, the complexity of algorithms and tractability of devices in the cell are still remarkably challenging. This paper, therefore, presents a utility based D2D association algorithm that ensures optimal neighbour selection by using numerical linear algebra to minimize computational complexity. Simulation results show that the minimum utility based D2D association increases the expected values of attached devices …

Simulated Annealing Algorithm For The Linear Ordering Problem: The Case Of Tanzania Input Output Tables, Allen Mushi

Tanzania Journal of Science

Linear Ordering is a problem of ordering the rows and columns of a matrix such that the sum of the upper triangle values is as large as possible. The problem has many applications including aggregation of individual preferences, weighted ancestry relationships and triangulation of input-output tables in economics. As a result, many researchers have been working on the problem which is known to be NP-hard. Consequently, heuristic algorithms have been developed and implemented on benchmark data or specific real-world applications. Simulated Annealing has seldom been used for this problem. Furthermore, only one attempt has been done on the Tanzanian input …

Comparison Of Experimental And Monte Carlo Simulation Of Angular Distributions Of Bremsstrahlung Photons From 28-Ghz Electron Cyclotron Resonance (Ecr) Ion Source, Mwingereza Kumwenda

Tanzania Journal of Science

Angular distributions of deceleration radiation or bremsstrahlung in German, both experimental and simulated from Electron Cyclotron Resonance Ion Source (ECRIS) are not well understood so far. The bremsstrahlung photons of the angular distributions from 28-GHz ECR ion source at Busan Centre of Korea Basic Science Institute (KBSI) were measured in nine azimuthal angles for the first time. Three round type NaI(Tl) detectors were used to measure the angular distributions of the bremsstrahlung photons emitted at the extraction side of the ECRIS at the same time. Another NaI(Tl) detector was placed downstream from the ECR ion source for monitoring photon intensity. …

Active Deep Learning Method To Automate Unbiased Stereology Cell Counting, Saeed Alahmari

USF Tampa Graduate Theses and Dissertations

Cell quantification in histopathology images plays a significant role in understanding and diagnosing diseases such as cancer and Alzheimers. The gold-standard for quantifying cells in tissue sections is the unbiased stereology approach. Unfortunately, in unbiased stereology current practices rely on a well-trained human to manually count hundreds of cells in microscopy images. However, this human-based manual approach is time-consuming, labor-intensive, subject to human errors, recognition bias, fatigue, variable training, poor reproducibility, and inter-observer error. Thus, the lack of high-throughput technology for automating unbiased stereology analyses remains a major obstacle to further progress in a wide range of neuroscience and cancer …

Next-Generation Self-Organizing Communications Networks: Synergistic Application Of Machine Learning And User-Centric Technologies, Chetana V. Murudkar

USF Tampa Graduate Theses and Dissertations

The telecommunications industry is going through a metamorphic journey where the 5G and 6G technologies will be deeply rooted in the society forever altering how people access and use information. In support of this transformation, this dissertation proposes a fundamental paradigm shift in the design, performance assessment, and optimization of wireless communications networks developing the next-generation self-organizing communications networks with the synergistic application of machine learning and user-centric technologies.

This dissertation gives an overview of the concept of self-organizing networks (SONs), provides insight into the “hot” technology of machine learning (ML), and offers an intuitive understanding of the user-centric (UC) …