OS and Networks Commons^™

Improving The Efficacy Of Context-Aware Applications, Jon C. Hammer

Graduate Theses and Dissertations

In this dissertation, we explore methods for enhancing the context-awareness capabilities of modern computers, including mobile devices, tablets, wearables, and traditional computers. Advancements include proposed methods for fusing information from multiple logical sensors, localizing nearby objects using depth sensors, and building models to better understand the content of 2D images.

First, we propose a system called Unagi, designed to incorporate multiple logical sensors into a single framework that allows context-aware application developers to easily test new ideas and create novel experiences. Unagi is responsible for collecting data, extracting features, and building personalized models for each individual user. We demonstrate the …

An Industry-Based Study On The Efficiency Benefits Of Utilising Public Cloud Infrastructure And Infrastructure As Code Tools In The It Environment Creation Process, Shane Callanan

Masters

The traditional approaches to IT infrastructure management typically involve the procuring, housing and running of company-owned and maintained physical servers. In recent years, alternative solutions to IT infrastructure management based on public cloud technologies have emerged. Infrastructure as a Service (IaaS), also known as public cloud infrastructure, allows for the on-demand provisioning of IT infrastructure resources via the Internet. Cloud Service Providers (CSP) such as Amazon Web Services (AWS) offer integration of their cloud-based infrastructure with Infrastructure as Code (IaC) tools. These tools allow for the entire configuration of public cloud based infrastructure to be scripted out and defined as …

Empirical Risk Landscape Analysis For Understanding Deep Neural Networks, Pan Zhou, Jiashi Feng

Research Collection School Of Computing and Information Systems

This work aims to provide comprehensive landscape analysis of empirical risk in deep neural networks (DNNs), including the convergence behavior of its gradient, its stationary points and the empirical risk itself to their corresponding population counterparts, which reveals how various network parameters determine the convergence performance. In particular, for an l-layer linear neural network consisting of di neurons in the i-th layer, we prove the gradient of its empirical risk uniformly converges to the one of its population risk, at the rate of O(r 2l p l √ maxi dis log(d/l)/n). Here d is the total weight dimension, s is …

Learning Latent Characteristics Of Locations Using Location-Based Social Networking Data, Thanh Nam Doan

Dissertations and Theses Collection (Open Access)

This dissertation addresses the modeling of latent characteristics of locations to describe the mobility of users of location-based social networking platforms. With many users signing up location-based social networking platforms to share their daily activities, these platforms become a gold mine for researchers to study human visitation behavior and location characteristics. Modeling such visitation behavior and location characteristics can benefit many use- ful applications such as urban planning and location-aware recommender sys- tems. In this dissertation, we focus on modeling two latent characteristics of locations, namely area attraction and neighborhood competition effects using location-based social network data. Our literature survey …

Bayesian Network Modeling And Inference Of Gwas Catalog, Qiuping Pan

Graduate Theses and Dissertations

Genome-wide association studies (GWASs) have received an increasing attention to understand genotype-phenotype relationships. The Bayesian network has been proposed as a powerful tool for modeling single-nucleotide polymorphism (SNP)-trait associations due to its advantage in addressing the high computational complex and high dimensional problems. Most current works learn the interactions among genotypes and phenotypes from the raw genotype data. However, due to the privacy issue, genotype information is sensitive and should be handled by complying with specific restrictions. In this work, we aim to build Bayesian networks from publicly released GWAS statistics to explicitly reveal the conditional dependency between SNPs and …

Breathing-Based Authentication On Resource-Constrained Iot Devices Using Recurrent Neural Networks, Jagmohan Chauhan, Suranga Seneviratne, Yining Hu, Archan Misra, Aruna Seneviratne, Youngki Lee

Research Collection School Of Computing and Information Systems

Recurrent neural networks (RNNs) have shown promising resultsin audio and speech-processing applications. The increasingpopularity of Internet of Things (IoT) devices makes a strongcase for implementing RNN-based inferences for applicationssuch as acoustics-based authentication and voice commandsfor smart homes. However, the feasibility and performance ofthese inferences on resource-constrained devices remain largelyunexplored. The authors compare traditional machine-learningmodels with deep-learning RNN models for an end-to-endauthentication system based on breathing acoustics.

Next Generation Tcp/Ip Side Channels, Xu Zhang

Computer Science ETDs

Side channel techniques have been developed in recent years to fulfill various tasks in modern computer network measurements. However, due to their nature, these techniques are typically limited in terms of both fidelity and their ability to be used on the real Internet without raising ethical concerns because of packet rates. I propose the next generation of TCP/IP side channel techniques that exploit information flow in modern systems’ network stacks to overcome weaknesses in previous techniques. The proposed work is novel, non-intrusive, and can carry out measurements with high fidelity. I achieved this by deeply understanding the behaviors of modern …

Virtualization In Wireless Sensor Networks: Fault Tolerant Embedding For Internet Of Things, Omprakash Kaiwartya, Abdul Hanan Abdullah, Yue Cao, Jaime Lloret, Sushil Kumar, Rajiv Ratn Shah, Mukesh Prasad, Shiv Prakash

Research Collection School Of Computing and Information Systems

Recently, virtualization in wireless sensor networks (WSNs) has witnessed significant attention due to the growing service domain for IoT. Related literature on virtualization in WSNs explored resource optimization without considering communication failure in WSNs environments. The failure of a communication link in WSNs impacts many virtual networks running IoT services. In this context, this paper proposes a framework for optimizing fault tolerance in virtualization in WSNs, focusing on heterogeneous networks for service-oriented IoT applications. An optimization problem is formulated considering fault tolerance and communication delay as two conflicting objectives. An adapted non-dominated sorting based genetic algorithm (A-NSGA) is developed to …

Automated Man-In-The-Middle Attack Against Wi‑Fi Networks, Martin Vondráček, Jan Pluskal, Ondřej Ryšavý

Journal of Digital Forensics, Security and Law

Currently used wireless communication technologies suffer security weaknesses that can be exploited allowing to eavesdrop or to spoof network communication. In this paper, we present a practical tool that can automate the attack on wireless security. The developed package called wifimitm provides functionality for the automation of MitM attacks in the wireless environment. The package combines several existing tools and attack strategies to bypass the wireless security mechanisms, such as WEP, WPA, and WPS. The presented tool can be integrated into a solution for automated penetration testing. Also, a popularization of the fact that such attacks can be easily automated …

Pattern-Of-Life Modeling Using Data Leakage In Smart Homes, Steven M. Beyer

Theses and Dissertations

This work investigates data leakage in smart homes by providing a Smart Home Automation Architecture (SHAA) and a device classifier and pattern-of-life analysis tool, CITIoT (Classify, Identify, and Track Internet of things). CITIoT was able to capture traffic from SHAA and classify 17 of 18 devices, identify 95% of the events that occurred, and track when users were home or away with near 100% accuracy. Additionally, a mitigation tool, MIoTL (Mitigation of IoT Leakage) is provided to defend against smart home data leakage. With mitigation, CITIoT was unable to identify motion and camera devices and was inundated with an average …

Towards Practical Privacy-Preserving Analytics For Iot And Cloud Based Healthcare Systems, Sagar Sharma, Keke Chen, Amit P. Sheth

Kno.e.sis Publications

Modern healthcare systems now rely on advanced computing methods and technologies, such as IoT devices and clouds, to collect and analyze personal health data at unprecedented scale and depth. Patients, doctors, healthcare providers, and researchers depend on analytical models derived from such data sources to remotely monitor patients, early-diagnose diseases, and find personalized treatments and medications. However, without appropriate privacy protection, conducting data analytics becomes a source of privacy nightmare. In this paper, we present the research challenges in developing practical privacy-preserving analytics in healthcare information systems. The study is based on kHealth - a personalized digital healthcare information system …

Scaling Human Activity Recognition Via Deep Learning-Based Domain Adaptation, Md Abdullah Hafiz Khan, Nirmalya Roy, Archan Misra

Research Collection School Of Computing and Information Systems

We investigate the problem of making human activityrecognition (AR) scalable–i.e., allowing AR classifiers trainedin one context to be readily adapted to a different contextualdomain. This is important because AR technologies can achievehigh accuracy if the classifiers are trained for a specific individualor device, but show significant degradation when the sameclassifier is applied context–e.g., to a different device located ata different on-body position. To allow such adaptation withoutrequiring the onerous step of collecting large volumes of labeledtraining data in the target domain, we proposed a transductivetransfer learning model that is specifically tuned to the propertiesof convolutional neural networks (CNNs). Our model, …

Back Matter, Adfsl

Annual ADFSL Conference on Digital Forensics, Security and Law

No abstract provided.

Front Matter, Adfsl

Annual ADFSL Conference on Digital Forensics, Security and Law

No abstract provided.

Contents, Adfsl

Annual ADFSL Conference on Digital Forensics, Security and Law

No abstract provided.

Sequential Recommendation With User Memory Networks, Xu Chen, Hongteng Xu, Yongfeng Zhang, Jiaxi Tang, Yixin Cao, Zheng Qin, Hongyuan Zha

Research Collection School Of Computing and Information Systems

User preferences are usually dynamic in real-world recommender systems, and a user»s historical behavior records may not be equally important when predicting his/her future interests. Existing recommendation algorithms -- including both shallow and deep approaches -- usually embed a user»s historical records into a single latent vector/representation, which may have lost the per item- or feature-level correlations between a user»s historical records and future interests. In this paper, we aim to express, store, and manipulate users» historical records in a more explicit, dynamic, and effective manner. To do so, we introduce the memory mechanism to recommender systems. Specifically, we design …

Building Deep Networks On Grassmann Manifolds, Zhiwu Huang, J. Wu, Gool L. Van

Research Collection School Of Computing and Information Systems

Learning representations on Grassmann manifolds is popular in quite a few visual recognition tasks. In order to enable deep learning on Grassmann manifolds, this paper proposes a deep network architecture by generalizing the Euclidean network paradigm to Grassmann manifolds. In particular, we design full rank mapping layers to transform input Grassmannian data to more desirable ones, exploit re-orthonormalization layers to normalize the resulting matrices, study projection pooling layers to reduce the model complexity in the Grassmannian context, and devise projection mapping layers to respect Grassmannian geometry and meanwhile achieve Euclidean forms for regular output layers. To train the Grassmann networks, …

Iot-Enhanced Human Experience, Amit P. Sheth, Biplav Srivastava, Florian Michahelles

Kno.e.sis Publications

The two articles in this special section represent ongoing Internet of Things applications in the context of Europe trying to make solutions usable to people in daily times.

Knowledge-Enabled Personalized Dashboard For Asthma Management In Children, Vaikunth Sridharan, Revathy Venkataramanan, Dipesh Kadariya, Krishnaprasad Thirunarayan, Amit Sheth, Maninder Kalra

Kno.e.sis Publications

Introduction: Childhood Asthma is a significant public health concern worldwide. Effective management of childhood asthma requires close monitoring of disease triggers, medication compliance and symptom control. The recent growth of the Internet of Things (IoT) based devices has enabled continuous monitoring of patients. kHealth-Asthma is a knowledge-enabled semantic framework consisting of IoT enabled sensors to record patient symptoms, medication usage and their environment. For each patient, 29 diverse parameters with 1852 data points are collected daily. kHealthDash platform enables real-time visual analysis at an individual and cohort level over such high volume, high variety data.

Methods: The kHealth kit was …

Khealth: A Personalized Healthcare Approach For Pediatric Asthma, Utkarshani Jaimini, Hong Y. Yip, Revathy Venkataramanan, Dipesh Kadariya, Vaikunth Sridharan, Tanvi Banerjee, Krishnaprasad Thirunarayan, Maninder Kalra, Amit Sheth

Kno.e.sis Publications

Can we assess the asthma control level, determine vulnerability, and medication compliance for a patient? Can we understand the causal relationship between the asthma symptom and possible factors responsible for it? Can we reduce the number of asthma attacks through continuous monitoring of the patient’s health condition?