Computer Engineering Commons^™

Sensor-Based Human Activity Recognition Using Bidirectional Lstm For Closely Related Activities, Arumugam Thendramil Pavai

Electronic Theses, Projects, and Dissertations

Recognizing human activities using deep learning methods has significance in many fields such as sports, motion tracking, surveillance, healthcare and robotics. Inertial sensors comprising of accelerometers and gyroscopes are commonly used for sensor based HAR. In this study, a Bidirectional Long Short-Term Memory (BLSTM) approach is explored for human activity recognition and classification for closely related activities on a body worn inertial sensor data that is provided by the UTD-MHAD dataset. The BLSTM model of this study could achieve an overall accuracy of 98.05% for 15 different activities and 90.87% for 27 different activities performed by 8 persons with 4 …

Feature-Based Transfer Learning In Natural Language Processing, Jianfei Yu

Dissertations and Theses Collection (Open Access)

In the past few decades, supervised machine learning approach is one of the most important methodologies in the Natural Language Processing (NLP) community. Although various kinds of supervised learning methods have been proposed to obtain the state-of-the-art performance across most NLP tasks, the bottleneck of them lies in the heavy reliance on the large amount of manually annotated data, which is not always available in our desired target domain/task. To alleviate the data sparsity issue in the target domain/task, an attractive solution is to find sufficient labeled data from a related source domain/task. However, for most NLP applications, due to …

Modeling Movement Decisions In Networks: A Discrete Choice Model Approach, Larry Lin Junjie

Dissertations and Theses Collection (Open Access)

In this dissertation, we address the subject of modeling and simulation of agents and their movement decision in a network environment. We emphasize the development of high quality agent-based simulation models as a prerequisite before utilization of the model as an evaluation tool for various recommender systems and policies. To achieve this, we propose a methodological framework for development of agent-based models, combining approaches such as discrete choice models and data-driven modeling.

The discrete choice model is widely used in the field of transportation, with a distinct utility function (e.g., demand or revenue-driven). Through discrete choice models, the movement decision …

Automatically `Verifying’ Discrete-Time Complex Systems Through Learning, Abstraction And Refinement, Jingyi Wang, Jun Sun, Shengchao Qin, Cyrille Jegourel

Research Collection School Of Computing and Information Systems

Precisely modeling complex systems like cyber-physical systems is challenging, which often render model-based system verification techniques like model checking infeasible. To overcome this challenge, we propose a method called LAR to automatically ‘verify’ such complex systems through a combination of learning, abstraction and refinement from a set of system log traces. We assume that log traces and sampling frequency are adequate to capture ‘enough’ behaviour of the system. Given a safety property and the concrete system log traces as input, LAR automatically learns and refines system models, and produces two kinds of outputs. One is a counterexample with a bounded …

Co-Location Resistant Virtual Machine Placement In Cloud Data Centers, Amit Agarwal, Nguyen Binh Duong Ta

Research Collection School Of Computing and Information Systems

Due to increasing number of avenues for conducting cross-virtual machine (VM) side-channel attacks, the security of public IaaS cloud data centers is a growing concern. These attacks allow an adversary to steal private information from a target user whose VM instance is co-located with that of the adversary. To reduce the probability of malicious co-location, we propose a novel VM placement algorithm called “Previously Co-Located Users First”. We perform a theoretical and empirical analysis of our proposed algorithm to evaluate its resource efficiency and security. Our results, obtained using real-world cloud traces containing millions of VM requests and thousands of …

Early Prediction Of Merged Code Changes To Prioritize Reviewing Tasks, Yuanrui Fan, Xin Xia, David Lo, Shanping Li

Research Collection School Of Computing and Information Systems

Modern Code Review (MCR) has been widely used by open source and proprietary software projects. Inspecting code changes consumes reviewers much time and effort since they need to comprehend patches, and many reviewers are often assigned to review many code changes. Note that a code change might be eventually abandoned, which causes waste of time and effort. Thus, a tool that predicts early on whether a code change will be merged can help developers prioritize changes to inspect, accomplish more things given tight schedule, and not waste reviewing effort on low quality changes. In this paper, motivated by the above …

Deploying, Improving And Evaluating Edge Bundling Methods For Visualizing Large Graphs, Jieting Wu

School of Computing: Dissertations, Theses, and Student Research

A tremendous increase in the scale of graphs has been witnessed in a wide range of fields, which demands efficient and effective visualization techniques to assist users in better understandings of large graphs. Conventional node-link diagrams are often used to visualize graphs, whereas excessive edge crossings can easily incur severe visual clutter in the node-link diagram of a large graph. Edge bundling can effectively remedy visual clutter and reveal high-level graph structures. Although significant efforts have been devoted to developing edge bundling, three challenging problems remain. First, edge bundling techniques are often computationally expensive and are not easy to deploy …

Evoalloy: An Evolutionary Approach For Analyzing Alloy Specifications, Jianghao Wang

School of Computing: Dissertations, Theses, and Student Research

Using mathematical notations and logical reasoning, formal methods precisely define a program’s specifications, from which we can instantiate valid instances of a system. With these techniques, we can perform a variety of analysis tasks to verify system dependability and rigorously prove the correctness of system properties. While there exist well-designed automated verification tools including ones considered lightweight, they still lack a strong adoption in practice. The essence of the problem is that when applied to large real world applications, they are not scalable and applicable due to the expense of thorough verification process. In this thesis, I present a new …

Controller Evolution And Divergence: A Software Perspective, Balaji Balasubramaniam

School of Computing: Dissertations, Theses, and Student Research

Successful controllers evolve as they are refined, extended, and adapted to new systems and contexts. This evolution occurs in the controller design and also in its software implementation. Model-based design and controller synthesis can help to synchronize this evolution of design and software, but such synchronization is rarely complete as software tends to also evolve in response to elements rarely present in a control model, leading to mismatches between the control design and the software.

In this thesis, we perform a first-of-its-kind study on the evolution of two popular open-source safety-critical autopilot control software -- ArduPilot, and Paparazzi, to better …

Automatic Identification Of Animals In The Wild: A Comparative Study Between C-Capsule Networks And Deep Convolutional Neural Networks., Joel Kamdem Teto, Ying Xie

Master of Science in Computer Science Theses

The evolution of machine learning and computer vision in technology has driven a lot of

improvements and innovation into several domains. We see it being applied for credit decisions, insurance quotes, malware detection, fraud detection, email composition, and any other area having enough information to allow the machine to learn patterns. Over the years the number of sensors, cameras, and cognitive pieces of equipment placed in the wilderness has been growing exponentially. However, the resources (human) to leverage these data into something meaningful are not improving at the same rate. For instance, a team of scientist volunteers took 8.4 years, …

Criticality Assessments For Improving Algorithmic Robustness, Thomas B. Jones

Computer Science ETDs

Though computational models typically assume all program steps execute flawlessly, that does not imply all steps are equally important if a failure should occur. In the "Constrained Reliability Allocation" problem, sufficient resources are guaranteed for operations that prompt eventual program termination on failure, but those operations that only cause output errors are given a limited budget of some vital resource, insufficient to ensure correct operation for each of them.

In this dissertation, I present a novel representation of failures based on a combination of their timing and location combined with criticality assessments---a method used to predict the behavior of systems …

Exploring The Role Of Sentiments In Identification Of Active And Influential Bloggers, Mohammad Alghobiri, Umer Ishfaq, Hikmat Ullah Khan, Tahir Afzal Malik

International Journal of Business and Technology

The social Web provides opportunities for the public to have social interactions and online discussions. A large number of online users using the social web sites create a high volume of data. This leads to the emergence of Big Data, which focuses on computational analysis of data to reveal patterns, and associations relating to human interactions. Such analyses have vast applications in various fields such as understanding human behaviors, studying culture influence, and promoting online marketing. The blogs are one of the social web channels that offer a way to discuss various topics. Finding the top bloggers has been a …

Perfect Metamaterial Absorber Based Energy Harvesting Application In Ism Band, Furkan Dincer, Mehmet Bakir, Muharrem Karaaslan, Kemal Delihacioglu, Cumali Sabah

International Journal of Business and Technology

An electromagnetic (EM) energy harvesting application based on metamaterial absorber (MA) is introduced and discussed in this paper. This application is operating at ISM band (2.40 GHz) which is especially chosen due to its wide usage area. Square ring resonator (SRR) which has two gaps and resistors across the gaps on it is used. Chips resistors are used to deliver power to any active component. Transmission and reflection characteristics of metamaterial absorber (MA) for energy harvesting application are investigated. 83.6% efficient for energy harvesting application is realized in this study.

The Analytic Hierarchic Process: A Model To Evaluate The Risk Of Getting Cancer, Daniela (Halidini) Qendraj, Markela Muça

International Journal of Business and Technology

The aim of this study is to classify the risk factors of being with a type of cancer by applying the AHP (analytic hierarchy process) scale. The Saaty’s analytic hierarchy process is applied for computing weights for the factors, is a modeling for classification. A case study of QSUT Tirana hospital data base is presented to rank four cancer types. By the data collect from the hospital during the years 2011-2015, the results show that lung cancer is mostly spread in humans, and the prostate cancer is lower spread in humans.

Internet Of Things: From Applications, Challenges And Standardization To Industry Implementations, Xhafer Krasniqi

International Journal of Business and Technology

The Internet of Things that is defined as anything that can be accessible anytime and anywhere provides connectivity to different objects and sensors around us and which will enable the transfer of different data between these objects and devices. A thing in the Internet of Things can be any natural or man-made object that can be assigned an IP address with a capability to exchange date over a network. There is a huge number of applications of IoT to benefit users, such as health monitors, smart homes, connected cars etc.

If everything around us is connected and information about these …

Hybrid Modelling In System Simulation, Andreas Körner

International Journal of Business and Technology

In times of increasing power and capacity in computer, simulation mathematical models are getting more and more important. For different technical applications and in natural science but also in economic systems and management processes appropriate mathematical model descriptions are necessary. Hybrid modelling is a special technique for more complex model descriptions in order to reduce the degree of complexity. In different fields of interest, the behavior of a model is dependent on the active state. When the model description is changing from one state to another, a so-called state event takes place. State event modelling is the overall term to …

E-Learning Systems In Higher Education Institutions: An Outlook Of Their Use In The Western Balkan Region, Blerta Abazi Chaushi, Agron Chaushi, Florije Ismaili

International Journal of Business and Technology

This study provides a review of the literature on e-learning systems evolution and environments. The argument is that e-learning systems should be embedded in the core strategy of the institution. To support this premise, studies for e-learning are analyzed and six recommendations are drawn for universities to follow in order to have successful e-learning environments. The main contribution of this study, however, is the identification of the trends and statistics regarding the e-learning usage in the Balkan region. These stats are identified through a survey conducted in 40 universities in 10 countries from this region. The results show that more …

Definition, Validation And Comparison Of Two Population Models For Austria, Martin Bicher, Barbara Glock, Florian Miksch, Niki Popper, Günter Schneckenreither

International Journal of Business and Technology

In this work we present two structurally different mathematical models for the prognostic simulation of Austria’s population: A time-continuous, macroscopic system dynamics approach and a time-discrete, microscopic agent-based approach. Both models were developed as case studies of a series of population concepts in order to support models for decision-support in Austria’s health care system. In the present work we want to focus on the definition, the parametrisation as well as especially the validation process of both population-models. The latter was of special interest as it included a cross-model validation with Statistics Austria’s own prognostic model SIKURS.

Case Studies For A Markov Chain Approach To Analyze Agent-Based Models, Florian Kitzler, Martin Bicher

International Journal of Business and Technology

Agent-Based Models have become a widely used tool in social sciences, health care management and other disciplines to describe complex systems from a bottom-up perspective. Some reasons for that are the easy understanding of Agent-Based Models, the high flexibility and the possibility to describe heterogeneous structures. Nevertheless problems occur when it comes to analyzing Agent-Based Models. This paper shows how to describe Agent-Based Models in a macroscopic way as Markov Chains, using the random map representation. The focus is on the implementation of this method for chosen examples of a Random Walk and Opinion Dynamic Models. It is also shown …

Microsimulation Models For Simulating Pathways Of Patients With Mental Diseases, Andreas Bauer, Felix Breitenecker, Christoph Urach

International Journal of Business and Technology

Predicting demand for care is necessary to provide sufficient capacities in hospitals and enable better planning to cope with challenges like changes in the structure of the population. Emphasis in this work is put on the analysis of the data and on the parametrization of a simulation model for the paths of patients with mental diseases through the health care system. Survival analysis and model selection methods are used for this purpose. Data on patients and their treatments is analyzed with methods of survival analysis. Different methods for modelling the survival and hazard function are presented and compared. Hereby, the …

Implementation Of The Aodv Routing In An Energy-Constrained Mesh Network, Altin Zejnullahu, Zhilbert Tafa

International Journal of Business and Technology

Wireless sensor networks (WSNs) compose the fundamental platform for a number of Internet of Things (IoT) applications, especially those related to the environmental, health, and military surveillance. While being autonomous in power supply, the main challenge in node’s processing and communication architecture design remains the energy efficiency. However, this goal should not limit the main functionality of the system which is often related to the network coverage and connectivity.

This paper shows the implementation of the Ad-hoc On-demand Distance Vector (AODV) routing algorithm in an XBee based platform. As shown, the network can achieve low power consumption per node primarily …

Security Concerns Of New Alternative Telecommunication Services, Arbnora Hyseni, Krenare Pireva, Miranda Kajtazi

International Journal of Business and Technology

With the advancing new era of communication, the so-called era of ‘being always online’ many providers offer their services for free. In that sense a small company or a virtual company becomes a huge competitor for different traditional telecommunication providers. Using the same services such as: voice calls, video calls, chat and similar services, the internet technology has made huge changes how users make use of such services . Instead of using these services, users shall install applications that are specialized for offering these services via applications, such as: Viber, WhatsApp, Facebook, Google Talk etc.. During the installation and update …

Labeled-Image Captcha: Concept Of A Secured And Universally Useful Captcha, Mokter Hossain, Ken Nguyen, Muhammad Asadur Rahman

International Journal of Business and Technology

Captcha (Completely Automated Public Turing test to tell Computers and Humans Apart) is a widely used online security tool that ensures that a computer program is not posing as a human user. While smart programs with advanced image processing capability have already cracked picture based captcha systems there is a need for making the test harder. This paper presents a design prototype of a simplified type of labeled-image captcha where a picture of a common animal or household item is marked with a number of different labels and the users will be asked to provide the correct label for specific …

A Policeless Traffic Ticketing System With Autonomous Vehicles, Mükremin Özkul, Ilir Çapuni

International Journal of Business and Technology

Besides being expensive, traffic violation monitoring systems rely heavily on a huge infrastructure that incurs installation, operational, and maintenance costs.

Developing countries — where people do exhibit less traffic safety aware- ness — deployment of such systems becomes a daunting task. A police- men cannot be everywhere, and a policeman can also be bribed.

With the above goals in mind, in this paper we present an infrastructure- less and police-less traffic violation detection system that relies solely on the broadcast messages between the vehicles and secure communication of the vehicles with the transportation authority. Each vehicle should be equipped with …

Delta Debugging Microservice Systems, Xiang Zhou, Xin Peng, Tao Xie, Jun Sun, Wenhai Li, Chao Ji, Dan Ding

Research Collection School Of Computing and Information Systems

Debugging microservice systems involves the deployment and manipulation of microservice systems on a containerized environment and faces unique challenges due to the high complexity and dynamism of microservices. To address these challenges, in this paper, we propose a debugging approach for microservice systems based on the delta debugging algorithm, which is to minimize failureinducing deltas of circumstances (e.g., deployment, environmental configurations) for effective debugging. Our approach includes novel techniques for defining, deploying/manipulating, and executing deltas following the idea of delta debugging. In particular, to construct a (failing) circumstance space for delta debugging to minimize, our approach defines a set of …

On The Feasibility Of Profiling, Forecasting And Authenticating Internet Usage Based On Privacy Preserving Netflow Logs, Soheil Sarmadi

USF Tampa Graduate Theses and Dissertations

Understanding Internet user behavior and Internet usage patterns is fundamental in developing future access networks and services that meet technical as well as Internet user needs. User behavior is routinely studied and measured, but with different methods depending on the research discipline of the investigator, and these disciplines rarely cross. We tackle this challenge by developing frameworks that the Internet usage statistics used as the main features in understanding Internet user behaviors, with the purpose of finding a complete picture of the user behavior and working towards a unified analysis methodology. In this dissertation we collected Internet usage statistics via …

Mrsh-Mem: Approximate Matching On Raw Memory Dumps, Lorenz Liebler, Frank Breitinger

Electrical & Computer Engineering and Computer Science Faculty Publications

This paper presents the fusion of two subdomains of digital forensics: (1) raw memory analysis and (2) approximate matching. Specifically, this paper describes a prototype implementation named MRSH-MEM that allows to compare hard drive images as well as memory dumps and therefore can answer the question if a particular program (installed on a hard drive) is currently running / loaded in memory. To answer this question, we only require both dumps or access to a public repository which provides the binaries to be tested. For our prototype, we modified an existing approximate matching algorithm named MRSH-NET and combined it with …

Analyzing And Modeling Users In Multiple Online Social Platforms, Roy Lee Ka Wei

Dissertations and Theses Collection (Open Access)

This dissertation addresses the empirical analysis on user-generated data from multiple online social platforms (OSPs) and modeling of latent user factors in multiple OSPs setting.

In the first part of this dissertation, we conducted cross-platform empirical studies to better understand user's social and work activities in multiple OSPs. In particular, we proposed new methodologies to analyze users' friendship maintenance and collaborative activities in multiple OSPs. We also apply the proposed methodologies on real-world OSP datasets, and the findings from our empirical studies have provided us with a better understanding on users' social and work activities which are previously not uncovered …

Supporting Diverse Customers And Prioritized Traffic In Next-Generation Passive Optical Networks, Naureen Hoque

School of Computing: Dissertations, Theses, and Student Research

The already high demand for more bandwidth usage has been growing rapidly. Access network traffic is usually bursty in nature and the present traffic trend is mostly video-dominant. This motivates the need for higher transmission rates in the system. At the same time, the deployment costs and maintenance expenditures have to be reasonable. Therefore, Passive Optical Networks (PON) are considered promising next-generation access technologies. As the existing PON standards are not suitable to support future-PON services and applications, the FSAN (Full Service Access Network) group and the ITU-T (Telecommunication Standardization Sector of the International Telecommunication Union) have worked on developing …

A Comprehensive Framework To Replicate Process-Level Concurrency Faults, Supat Rattanasuksun

School of Computing: Dissertations, Theses, and Student Research

Concurrency faults are one of the most damaging types of faults that can affect the dependability of today’s computer systems. Currently, concurrency faults such as process-level races, order violations, and atomicity violations represent the largest class of faults that has been reported to various Linux bug repositories. Clearly, existing approaches for testing such faults during software development processes are not adequate as these faults escape in-house testing efforts and are discovered during deployment and must be debugged.

The main reason concurrency faults are hard to test is because the conditions that allow these to occur can be difficult to replicate, …