Computer Sciences Commons^™

Prediction Of Laser Ablation In Brain: Sensitivity, Calibration, And Validation, Samuel J. Fahrenholtz

Dissertations and Theses (Open Access)

The surgical planning of MR-guided laser induced thermal therapy (MRgLITT) stands to benefit from predictive computational modeling. The dearth of physical model parameter data leads to modeling uncertainty. This work implements a well-accepted framework with three key steps for model-building: model-parameter sensitivity analysis, model calibration, and model validation.

The sensitivity study is via generalized polynomial chaos (gPC) paired with a transient finite element (FEM) model. Uniform probability distribution functions (PDFs) capture the plausible range of values suggested by the literature for five model parameters. The five PDFs are input separately into the FEM model to gain a probabilistic sensitivity response …

Virtual Humans And Photorealism: The Effect Of Photorealism Of Interactive Virtual Humans In Clinical Virtual Environment On Affective Responses, Himanshu Chaturvedi

All Theses

The ability of realistic vs stylized representations of virtual characters to elicit emotions in users has been an open question for researchers and artists alike. We designed and performed a between subjects experiment using a medical virtual reality simulation to study the differences in the emotions aroused in participants while interacting with realistic and stylized virtual characters. The experiment included three conditions each of which presented a different representation of the virtual character namely; photo-realistic, non-photorealistic cartoon-shaded and non-photorealistic charcoal-sketch. The simulation used for the experiment, called the Rapid Response Training System was developed to train nurses to identify symptoms …

Using A Personalized Machine Learning Approach To Detect Stolen Phones, Huizhong Hu

Theses and Dissertations

With the increasing number of smartphone penetration, mining smartphone data that make smartphone smarter became a top research area, there are a lot of event data which we can use to predict behavior or detect anomalies. The privacy disclosure caused by stolen or lost phones becomes an increasingly difficult problem that cannot be ignored. So we design an anomaly detection system by mining patterns to detect stolen phones. We use a pattern mining algorithm to abstract patterns from user past behavior, then construct a personalized model and use a scoring function and threshold setting strategy to detect stolen events. Moreover, …

Iterative Design And Testing Of A Mobile Application To Support Food Consumption Monitoring And Decision Making, Melva James

All Dissertations

Food overconsumption is a major contributor to weight gain leading to obesity. Constant exposure to larger amounts of food and beverage has caused many individuals to experience “portion distortion,” the perception that bigger portion sizes are appropriate for consumption at a single sitting. Independently and accurately changing this perception can be very difficult even if one has a desire to do so. In response to these observations, we developed and tested Picture-Perfect Portions, a mobile application designed to combat overconsumption, at the individual level, by leveraging the power of simple visualizations to help adults understand and adjust their food consumption …

Downstream Bandwidth Management For Emerging Docsis-Based Networks, Gongbing Hong

All Dissertations

In this dissertation, we consider the downstream bandwidth management in the context of emerging DOCSIS-based cable networks. The latest DOCSIS 3.1 standard for cable access networks represents a significant change to cable networks. For downstream, the current 6 MHz channel size is replaced by a much larger 192 MHz channel which potentially can provide data rates up to 10 Gbps. Further, the current standard requires equipment to support a relatively new form of active queue management (AQM) referred to as delay-based AQM. Given that more than 50 million households (and climbing) use cable for Internet access, a clear understanding of …

Preface To Wi-Iat 2015 Workshops And Demo/Posters, Ah-Hwee Tan, Yuefeng Li

Research Collection School Of Computing and Information Systems

This volume contains the papers selected for presentation at the workshops and demonstration/poster track as part of the 2015 IEEE/WIC/ACM International Conference on Web Intelligence (WI’15) and 2015 IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT’15) held from 6 to 9 December 2015 in Singapore.

Predicting Intraday Financial Market Dynamics Using Takens' Vectors; Incorporating Causality Testing And Machine Learning Techniques, Abubakar-Sadiq Bouda Abdulai

Electronic Theses and Dissertations

Traditional approaches to predicting financial market dynamics tend to be linear and stationary, whereas financial time series data is increasingly nonlinear and non-stationary. Lately, advances in dynamical systems theory have enabled the extraction of complex dynamics from time series data. These developments include theory of time delay embedding and phase space reconstruction of dynamical systems from a scalar time series. In this thesis, a time delay embedding approach for predicting intraday stock or stock index movement is developed. The approach combines methods of nonlinear time series analysis with those of causality testing, theory of dynamical systems and machine learning (artificial …

An Open Virtual Multi-Services Networking Architecture For The Future Internet, May El Barachi, Nadjia Kara, Sleiman Rabah, Mathieu Forgues

All Works

© 2015, El Barachi et al.; licensee Springer. Network virtualization is considered as a promising way to overcome the limitations and fight the gradual ossification of the current Internet infrastructure. The network virtualization concept consists in the dynamic creation of several co-existing logical network instances (or virtual networks) over a shared physical network infrastructure. We have previously proposed a service-oriented hierarchical business model for virtual networking environments. This model promotes the idea of network as a service, by considering the functionalities offered by different types of network resources as services of different levels – services that can be dynamically discovered, …

Fall Detection By Using Video, Robert J. Gripentog

UNLV Theses, Dissertations, Professional Papers, and Capstones

Cameras have become common in our society and as a result there is more video available today than ever before. While the video can be used for entertainment or possibly as storage it can also be used as a sensor capturing crucial information, The information captured can be put to all types of uses, but one particular use is to identify a fall. The importance of identifying a fall can be seen especially in the older population that is affected by falls every year. The falls experienced by the elderly are devastating as they can cause apprehension to normal life …

Facilitating Corpus Annotation By Improving Annotation Aggregation, Paul L. Felt

Theses and Dissertations

Annotated text corpora facilitate the linguistic investigation of language as well as the automation of natural language processing (NLP) tasks. NLP tasks include problems such as spam email detection, grammatical analysis, and identifying mentions of people, places, and events in text. However, constructing high quality annotated corpora can be expensive. Cost can be reduced by employing low-cost internet workers in a practice known as crowdsourcing, but the resulting annotations are often inaccurate, decreasing the usefulness of a corpus. This inaccuracy is typically mitigated by collecting multiple redundant judgments and aggregating them (e.g., via majority vote) to produce high quality consensus …

The Bounded Edge Coloring Problem And Offline Crossbar Scheduling, Jonathan Turner

All Computer Science and Engineering Research

This paper introduces a variant of the classical edge coloring problem in graphs that can be applied to an offline scheduling problem for crossbar switches. We show that the problem is NP-complete, develop three lower bounds bounds on the optimal solution value and evaluate the performance of several approximation algorithms, both analytically and experimentally. We show how to approximate an optimal solution with a worst-case performance ratio of 3/2 and our experimental results demonstrate that the best algorithms produce results that very closely track a lower bound.

Coordinated Persuasion With Dynamic Group Formation For Collaborative Elderly Care, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Ageing in place demands a new paradigm of inhouse caregiving allowing many aspects of daily lives to be tackled by smart appliances and technologies. The important challenges include the effective provision of recommendations by multiple parties of caregiver constituting changes of the user's behavior. In this multiagent environment, interdependencies between agents become major issues to tackle. This paper presents an approach of dynamic group formation for autonomous caregiving agents to collaborate in recommending different aspects of well-being. The approach supports the agents to regulate the timing of their recommendations, prevent conflicting messages, and cooperate to make more effective persuasions. A …

A Bayesian Recommender Model For User Rating And Review Profiling, Mingming Jiang, Dandan Song, Lejian Liao, Feida Zhu

Research Collection School Of Computing and Information Systems

Intuitively, not only do ratings include abundant information for learning user preferences, but also reviews accompanied by ratings. However, most existing recommender systems take rating scores for granted and discard the wealth of information in accompanying reviews. In this paper, in order to exploit user profiles' information embedded in both ratings and reviews exhaustively, we propose a Bayesian model that links a traditional Collaborative Filtering (CF) technique with a topic model seamlessly. By employing a topic model with the review text and aligning user review topics with "user attitudes" (i.e., abstract rating patterns) over the same distribution, our method achieves …

Preface: Wi 2015, Ah-Hwee Tan, Yuefeng Li, Ee-Peng Lim, Jie Zhang, Dell Zhang, Julita Vassileva

Research Collection School Of Computing and Information Systems

This volume contains the papers selected for presentation at the 2015 IEEE/WIC/ACM International Conference on Web Intelligence (WI’15), which was held from 6 to 9 December 2015 in Singapore, a city which welcomes people from different parts of the world to work and play. Following the tradition of WI conference in previous years, WI’15 was collocated with 2015 IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT’15). Both WI’15 and IAT’15 were sponsored by the IEEE Computer Society, Web Intelligence Consortium (WIC), Association for Computing Machinery (ACM), and the Memetic Computing Society. The two collocated conferences were hosted by the Joint …

Preface Iat 2015, Ah-Hwee Tan, Yuefeng Li, Ee-Peng Lim, An Bo, Anita Raja, Sarvapali Ramchurn

Research Collection School Of Computing and Information Systems

This volume contains the papers selected for presentation at the 2015 IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT’15), which was held from 6 to 9 December 2015 in Singapore, a city which welcomes people from different parts of the world to work and play. Following the tradition of IAT conference in previous years, IAT’15 was collocated with 2015 IEEE/WIC/ACM International Conference on Web Intelligence (WI’15). Both WI’15 and IAT’15 were sponsored by the IEEE Computer Society, Web Intelligence Consortium (WIC), Association for Computing Machinery (ACM), and the Memetic Computing Society. The two collocated conferences were hosted by the Joint …

Progressive Sequence Matching For Adl Plan Recommendation, Shan Gao, Di Wang, Ah-Hwee Tan, Chunyan Miao

Research Collection School Of Computing and Information Systems

Activities of Daily Living (ADLs) are indicatives of a person’s lifestyle. In particular, daily ADL routines closely relate to a person’s well-being. With the objective of promoting active lifestyles, this paper presents an agent system that provides recommendations of suitable ADL plans (i.e., selected ADL sequences) to individual users based on the more active lifestyles of the others. Specifically, we develop a set of quantitative measures, named wellness scores, spanning the evaluation across the physical, cognitive, emotion, and social aspects based on his or her ADL routines. Then we propose an ADL sequence learning model, named Recommendation ADL ART, or …

Silver Assistants For Aging-In-Place, Di Wang, Budhitama Subagdja, Yilin Kang, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

In this demo, we present an assembly of silver assistants for supporting Aging-In-Place (AIP). The virtual agents are designed to serve around the clock to complement human care within the intelligent home environment. Residing in different platforms with ubiquitous access, the agents collaboratively provide holistic care to the elderly users. The demonstration is shown in a 3-D virtual home replicating a typical 5-room apartment in Singapore. Sensory inputs are stored in a knowledge base named Situation Awareness Model (SAM). Therefore, the capabilities of the agents can always be extended by expanding the knowledge defined in SAM. Using the simulation system, …

Non-Intrusive Robust Human Activity Recognition For Diverse Age Groups, Di Wang, Ah-Hwee Tan, Daqing Zhang

Research Collection School Of Computing and Information Systems

—Many elderly prefer to live independently at their own homes. However, how to use modern technologies to ensure their safety presents vast challenges and opportunities. Being able to non-intrusively sense the activities performed by the elderly definitely has great advantages in various circumstances. Non-intrusive activity recognition can be performed using the embedded sensors in modern smartphones. However, not many activity recognition models are robust enough that allow the subjects to carry the smartphones in different pockets with unrestricted orientations and varying deviations. Moreover, to the best of our knowledge, no existing literature studied the difference between the youth and the …

Aesthetic Experience And Acceptance Of Human Computation Games, Xiaohui Wang, Dion Hoe-Lian Goh, Ee-Peng Lim, Adrian Wei Liang Vu

Research Collection School Of Computing and Information Systems

Human computation games (HCGs) are applications that leverage games to solve computational problems that are out reach of the capacity of computers. Game aesthetics are critical for HCG acceptance, and the game elements should motivate users to contribute time and effort. In this paper, we examine the effect of aesthetic experience on intention to use HCGs. A between-subjects experiment was conducted to compare a HCG and a human computation system (HCS). Results demonstrated that HCGs provided a greater sense of aesthetic experience and attracted more intentional usage than HCSs. Implications of this study are discussed.

Incremental Dcop Search Algorithms For Solving Dynamic Dcop Problems, William Yeoh, Pradeep Varakantham, Xiaoxun Sun, Sven Koenig

Research Collection School Of Computing and Information Systems

Distributed constraint optimization (DCOP) problems are well-suited for modeling multi-agent coordination problems. However, it only models static problems, which do not change over time. Consequently, researchers have introduced the Dynamic DCOP (DDCOP) model to model dynamic problems. In this paper, we make two key contributions: (a) a procedure to reason with the incremental changes in DDCOPs and (b) an incremental pseudo-tree construction algorithm that can be used by DCOP algorithms such as any-space ADOPT and any-space BnB-ADOPT to solve DDCOPs. Due to the incremental reasoning employed, our experimental results show that any-space ADOPT and any-space BnB-ADOPT are up to 42% …

Active Crowdsourcing For Annotation, Shuji Hao, Chunyan Miao, Steven C. H. Hoi, Peilin Zhao

Research Collection School Of Computing and Information Systems

Crowdsourcing has shown great potential in obtaining large-scale and cheap labels for different tasks. However, obtaining reliable labels is challenging due to several reasons, such as noisy annotators, limited budget and so on. The state-of-the-art approaches, either suffer in some noisy scenarios, or rely on unlimited resources to acquire reliable labels. In this article, we adopt the learning with expert~(AKA worker in crowdsourcing) advice framework to robustly infer accurate labels by considering the reliability of each worker. However, in order to accurately predict the reliability of each worker, traditional learning with expert advice will consult with external oracles~(AKA domain experts) …

Incorporating Analytics Into A Business Process Modelling Course, Gottipati Swapna, Shankararaman, Venky

Research Collection School Of Computing and Information Systems

Embedding analytics is about integrating data analytics into operational systems that are part of an organization’s business processes. Currently, most organizations focus on automation business processes and enhancing productivity. However, going forward, in order to stay competitive, organizations have to go beyond automating their processes, by making them more intelligent, by embedding analytics into their processes and business applications. Therefore, there is need for enhancing the knowledge and skills of BPM professionals with know-how on improving a business process by embedding analytics into the workflow. In this paper contribution, the authors share their experience on how an existing process modelling, …

Lossy Projective Hashing And Its Applications, Haiyang Xue, Yamin Liu, Xianhui Lu, Bao Li

Research Collection School Of Computing and Information Systems

In this paper, we introduce a primitive called lossy projective hashing. It is unknown before whether smooth projective hashing (Cramer-Shoup, Eurocrypt’02) can be constructed from dual projective hashing (Wee, Eurocrypt’12). The lossy projective hashing builds a bridge between dual projective hashing and smooth projective hashing. We give instantiations of lossy projective hashing from DDH, DCR, QR and general subgroup membership assumptions (including 2k-th residue, p-subgroup and higher residue assumptions). We also show how to construct lossy encryption and fully IND secure deterministic public key encryption from lossy projective hashing. – We give a construction of lossy projective hashing via dual …

Social Learning Systems: The Design Of Evolutionary, Highly Scalable, Socially Curated Knowledge Systems, Nolan Hemmatazad

Student Work

In recent times, great strides have been made towards the advancement of automated reasoning and knowledge management applications, along with their associated methodologies. The introduction of the World Wide Web peaked academicians’ interest in harnessing the power of linked, online documents for the purpose of developing machine learning corpora, providing dynamical knowledge bases for question answering systems, fueling automated entity extraction applications, and performing graph analytic evaluations, such as uncovering the inherent structural semantics of linked pages. Even more recently, substantial attention in the wider computer science and information systems disciplines has been focused on the evolving study of social …

A Benchmark And Comparative Study Of Video-Based Face Recognition On Cox Face Database, Zhiwu Huang, S. Shan, R. Wang, H. Zhang, S. Lao, A. Kuerban, X. Chen

Research Collection School Of Computing and Information Systems

Face recognition with still face images has been widely studied, while the research on video-based face recognition is inadequate relatively, especially in terms of benchmark datasets and comparisons. Real-world video-based face recognition applications require techniques for three distinct scenarios: 1) Videoto-Still (V2S); 2) Still-to-Video (S2V); and 3) Video-to-Video (V2V), respectively, taking video or still image as query or target. To the best of our knowledge, few datasets and evaluation protocols have benchmarked for all the three scenarios. In order to facilitate the study of this specific topic, this paper contributes a benchmarking and comparative study based on a newly collected …

Learning Query And Image Similarities With Ranking Canonical Correlation Analysis, Ting Yao, Tao Mei, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

One of the fundamental problems in image search is to learn the ranking functions, i.e., similarity between the query and image. The research on this topic has evolved through two paradigms: feature-based vector model and image ranker learning. The former relies on the image surrounding texts, while the latter learns a ranker based on human labeled query-image pairs. Each of the paradigms has its own limitation. The vector model is sensitive to the quality of text descriptions, and the learning paradigm is difficult to be scaled up as human labeling is always too expensive to obtain. We demonstrate in this …

Fast Reinforcement Learning Under Uncertainties With Self-Organizing Neural Networks, Teck-Hou Teng, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Using feedback signals from the environment, a reinforcement learning (RL) system typically discovers action policies that recommend actions effective to the states based on a Q-value function. However, uncertainties over the estimation of the Q-values can delay the convergence of RL. For fast RL convergence by accounting for such uncertainties, this paper proposes several enhancements to the estimation and learning of the Q-value using a self-organizing neural network. Specifically, a temporal difference method known as Q-learning is complemented by a Q-value Polarization procedure, which contrasts the Q-values using feedback signals on the effect of the recommended actions. The polarized Q-values …

Understanding Psychophysiological Correlates Of User Experience Using Electroencephalogram (Eeg), Fiona Fui-Hoon Nah, Keng Siau, Randall Minas, Nathan W. Twyman, Nicholas A. Rollins, Wenbo Wang, Xi Wang

Research Collection School Of Computing and Information Systems

The objective of this research is to understand psychophysiological correlates of user experience using electroencephalogram (EEG). We will conduct an experimental study to assess the psychophysiological differences across three states of user experience – flow, boredom, and anxiety – and compare them with the neutral state as a baseline. EEG measurement provides a plethora of data that can be decomposed using different analytical procedures. We will utilize one type of analysis, timefrequency decomposition, to examine changes in frequency (e.g., alpha/beta/theta band) over time. These frequency bands correlate with different cognitive states. In this study, we will use Event Related Spectral …

On Top-K Selection In Multi-Armed Bandits And Hidden Bipartite Graphs, Wei Cao, Jian Li, Yufei Tao, Zhize Li

Research Collection School Of Computing and Information Systems

This paper discusses how to efficiently choose from $n$ unknown distributions the $k$ ones whose means are the greatest by a certain metric, up to a small relative error. We study the topic under two standard settings---multi-armed bandits and hidden bipartite graphs---which differ in the nature of the input distributions. In the former setting, each distribution can be sampled (in the i.i.d. manner) an arbitrary number of times, whereas in the latter, each distribution is defined on a population of a finite size $m$ (and hence, is fully revealed after m samples). For both settings, we prove lower bounds on …

Supercnn: A Superpixelwise Convolutional Neural Network For Salient Object Detection, Shengfeng He, Rynson W.H. Lau, Wenxi Liu, Zhe Huang, Qingxiong Yang

Research Collection School Of Computing and Information Systems

Existing computational models for salient object detection primarily rely on hand-crafted features, which are only able to capture low-level contrast information. In this paper, we learn the hierarchical contrast features by formulating salient object detection as a binary labeling problem using deep learning techniques. A novel superpixelwise convolutional neural network approach, called SuperCNN, is proposed to learn the internal representations of saliency in an efficient manner. In contrast to the classical convolutional networks, SuperCNN has four main properties. First, the proposed method is able to learn the hierarchical contrast features, as it is fed by two meaningful superpixel sequences, which …