Numerical Analysis and Scientific Computing Commons^™

Creating Top Ranking Options In The Continuous Option And Preference Space, Bo Tang, Kyriakos Mouratidis, Man Lung Yiu, Zhenyu Chen

Research Collection School Of Computing and Information Systems

Top-k queries are extensively used to retrieve the k most relevantoptions (e.g., products, services, accommodation alternatives, etc)based on a weighted scoring function that captures user preferences. In this paper, we take the viewpoint of a business owner whoplans to introduce a new option to the market, with a certain type ofclientele in mind. Given a target region in the consumer spectrum,we determine what attribute values the new option should have,so that it ranks among the top-k for any user in that region. Ourmethodology can also be used to improve an existing option, at theminimum modification cost, so that it ranks …

Krylov Subspace Spectral Methods With Non-Homogenous Boundary Conditions, Abbie Hendley

Master's Theses

For this thesis, Krylov Subspace Spectral (KSS) methods, developed by Dr. James Lambers, will be used to solve a one-dimensional, heat equation with non-homogenous boundary conditions. While current methods such as Finite Difference are able to carry out these computations efficiently, their accuracy and scalability can be improved. We will solve the heat equation in one-dimension with two cases to observe the behaviors of the errors using KSS methods. The first case will implement KSS methods with trigonometric initial conditions, then another case where the initial conditions are polynomial functions. We will also look at both the time-independent and time-dependent …

State-Of-The-Art Solution Techniques For Optw And Toptw, Pieter Vansteenwegen, Aldy Gunawan

Research Collection School Of Computing and Information Systems

In Chaps. 2 and 3, different orienteering problems (or routing problems with profits) were introduced. The single vehicle problems were discussed in Chap. 2: the profitable tour problem (PTP), the prize-collecting traveling salesperson problem (PCTSP), and the orienteering problem (OP). The multi vehicle problems were discussed in Chap. 3: the team orienteering problem (TOP) and the team orienteering problem with time windows (TOPTW). For discussing the state-of-the-art solution techniques for these different orienteering problems in Chaps. 4, 5, and 6, the problems will be classified differently, based on the similarities between the solution techniques. Therefore, the PTP and PCTSP are …

Adversarial Learning On Heterogeneous Information Networks, Binbin Hu, Yuan Fang, Chuan Shi

Research Collection School Of Computing and Information Systems

Network embedding, which aims to represent network data in alow-dimensional space, has been commonly adopted for analyzingheterogeneous information networks (HIN). Although exiting HINembedding methods have achieved performance improvement tosome extent, they still face a few major weaknesses. Most importantly, they usually adopt negative sampling to randomly selectnodes from the network, and they do not learn the underlying distribution for more robust embedding. Inspired by generative adversarial networks (GAN), we develop a novel framework HeGAN forHIN embedding, which trains both a discriminator and a generatorin a minimax game. Compared to existing HIN embedding methods,our generator would learn the node distribution to …

Fintech Empowerment: Data Science, Ai, And Machine Learning, Keng Siau, Michael Hilgers, Langtao Chen, Steve Liu, Fiona Fui-Hoon Nah, Richard Hall, Barry Flachsbart

Research Collection School Of Computing and Information Systems

The article discusses how data science, artificial intelligence and machine learning are affecting the evolution of “fintech,” the technologies used to deliver financial services. After presenting fintech’s competitive advantages in combination with these other advanced technologies, the article posits that financial institutions that don’t move forward with the innovations will be eliminated from the marketplace.

Adapting Bert For Target-Oriented Multimodal Sentiment Classification, Jianfei Yu, Jing Jiang

Research Collection School Of Computing and Information Systems

As an important task in Sentiment Analysis, Target-oriented Sentiment Classification (TSC) aims to identify sentiment polarities over each opinion target in a sentence. However, existing approaches to this task primarily rely on the textual content, but ignoring the other increasingly popular multimodal data sources (e.g., images), which can enhance the robustness of these text-based models. Motivated by this observation and inspired by the recently proposed BERT architecture, we study Target-oriented Multimodal Sentiment Classification (TMSC) and propose a multimodal BERT architecture. To model intra-modality dynamics, we first apply BERT to obtain target-sensitive textual representations. We then borrow the idea from self-attention …

Learning Multiple Maps From Conditional Ordinal Triplets, Duy Dung Le, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Ordinal embedding seeks a low-dimensional representation of objects based on relative comparisons of their similarities. This low-dimensional representation lends itself to visualization on a Euclidean map. Classical assumptions admit only one valid aspect of similarity. However, there are increasing scenarios involving ordinal comparisons that inherently reflect multiple aspects of similarity, which would be better represented by multiple maps. We formulate this problem as conditional ordinal embedding, which learns a distinct low-dimensional representation conditioned on each aspect, yet allows collaboration across aspects via a shared representation. Our geometric approach is novel in its use of a shared spherical representation and multiple …

Definitions And Mathematical Models Of Single Vehicle Routing Problems With Profits, Pieter Vansteenwegen, Aldy Gunawan

Research Collection School Of Computing and Information Systems

In this chapter, single vehicle routing problems with profits are introduced anddefined. Three variants are considered: the profitable tour problem, the prizecollecting traveling salesperson problem, and the orienteering problem. The difference between these variants is the way in which the profit and the travel cost, mostlydistance or time, are modeled. Profit and travel cost can be modeled as (part of) theobjective or as a constraint. All three problems differ from the well-known travelingsalesperson problem, for which the only objective is to find the shortest route to visitall customers in a given set. In vehicle routing problems with profits, some customerswill …

Synthetic, Yet Natural: Properties Of Wordnet Random Walk Corpora And The Impact Of Rare Words On Embedding Performance, Filip Klubicka, Alfredo Maldonado, Abhijit Mahalunkar, John D. Kelleher

Conference papers

Creating word embeddings that reflect semantic relationships encoded in lexical knowledge resources is an open challenge. One approach is to use a random walk over a knowledge graph to generate a pseudo-corpus and use this corpus to train embeddings. However, the effect of the shape of the knowledge graph on the generated pseudo-corpora, and on the resulting word embeddings, has not been studied. To explore this, we use English WordNet, constrained to the taxonomic (tree-like) portion of the graph, as a case study. We investigate the properties of the generated pseudo-corpora, and their impact on the resulting embeddings. We find …

Predicting Switch-Like Behavior In Proteins Using Logistic Regression On Sequence-Based Descriptors, Benjamin Strauss

Master's Projects

Ligands can bind at specific protein locations, inducing conformational changes such as those involving secondary structure. Identifying these possible switches from sequence, including homology, is an important ongoing area of research. We attempt to predict possible secondary structure switches from sequence in proteins using machine learning, specifically a logistic regression approach with 48 N-acetyltransferases as our learning set and 5 sirtuins as our test set. Validated residue binary assignments of 0 (no change in secondary structure) and 1 (change in secondary structure) were determined (DSSP) from 3D X-ray structures for sets of virtually identical chains crystallized under different conditions. Our …

Mathematical And Computer Simulation Of The Processes Of Two-Phase Joint Gas Filtration And Water In A Porous Environment, Elmira Nazirova

Bulletin of TUIT: Management and Communication Technologies

A mathematical model, methods and algorithms for the numerical solution of problems of joint gas-water filtration in porous media are considered. The mathematical model of the process of non-stationary joint gas-water filtration in a porous medium is described by a system of nonlinear differential equations of parabolic type. In the numerical solution of the boundary value problem of gas displacement by water in a porous medium, the differential sweeping method is used for systems of differential-difference equations. The system of differential-difference equations with respect to the gas pressure function is nonlinear, therefore, an iterative method is used for it, based …

Mathematics And Programming Exercises For Educational Robot Navigation, Ronald I. Greenberg

Computer Science: Faculty Publications and Other Works

This paper points students towards ideas they can use towards developing a convenient library for robot navigation, with examples based on Botball primitives, and points educators towards mathematics and programming exercises they can suggest to students, especially advanced high school students.

Identifying Depression In The National Health And Nutrition Examination Survey Data Using A Deep Learning Algorithm, Jihoon Oh, Kyongsik Yun, Uri Maoz, Tae-Suk Kim, Jeong-Ho Chae

Psychology Faculty Articles and Research

Background

As depression is the leading cause of disability worldwide, large-scale surveys have been conducted to establish the occurrence and risk factors of depression. However, accurately estimating epidemiological factors leading up to depression has remained challenging. Deep-learning algorithms can be applied to assess the factors leading up to prevalence and clinical manifestations of depression.

Methods

Customized deep-neural-network and machine-learning classifiers were assessed using survey data from 19,725 participants from the NHANES database (from 1999 through 2014) and 4949 from the South Korea NHANES (K-NHANES) database in 2014.

Results

A deep-learning algorithm showed area under the receiver operating characteristic curve (AUCs) …

Exploiting Mobility For Predictive Urban Analytics & Operations, Kasthuri Jayarajah

Dissertations and Theses Collection (Open Access)

As cities worldwide invest heavily in smart city infrastructure, it invites opportunities for a next wave of urban analytics. Unlike its predecessors, urban analytics applications and services can now be real-time and proactive -- they can (a) leverage situational data from large deployments of connected sensors, (b) capture attributes of a variety of entities that make up the urban fabric (e.g., people and their social relationships, transport nodes, utilities, etc.), and (c) use predictive insights to both proactively optimize urban operations (e.g., HVAC systems in smart buildings, buses in the transportation network, crowd-workers, etc.) and promote smarter policy decisions (e.g., …

Making Sense Of Crowd-Generated Content In Domain-Specific Settings, Agus Sulistya

Dissertations and Theses Collection (Open Access)

The rapid advances of the Web have changed the ways information is distributed and exchanged among individuals and organizations. Various content from different domains are generated daily and contributed by users' daily activities, such as posting messages in a microblog platform, or collaborating in a question and answer site. To deal with such tremendous volume of user generated content, there is a need for approaches that are able to handle the mass amount of available data and to extract knowledge hidden in the user generated content. This dissertation attempts to make sense of the generated content to help in three …

An Intelligent Platform With Automatic Assessment And Engagement Features For Active Online Discussions, Michelle L. F. Cheong, Yun-Chen Chen, Bing Tian Dai

Research Collection School Of Computing and Information Systems

In a universitycontext, discussion forums are mostly available in Learning and ManagementSystems (LMS) but are often ineffective in encouraging participation due topoorly designed user interface and the lack of motivating factors toparticipate. Our integrated platform with the Telegram mobile app and aweb-based forum, is capable of automatic thoughtfulness assessment of questionsand answers posted, using text mining and Natural Language Processing (NLP)methodologies. We trained and applied the Random Forest algorithm to provideinstant thoughtfulness score prediction for the new posts contributed by thestudents, and prompted the students to improve on their posts, thereby invokingdeeper thinking resulting in better quality contributions. In addition, …

Modeling Intra-Relation In Math Word Problems With Different Functional Multi-Head Attentions, Jierui Li, Lei Wang, Jipeng Zhang, Yan Wang, Bing Tian Dai, Dongxiang Zhang

Research Collection School Of Computing and Information Systems

Several deep learning models have been proposed for solving math word problems (MWPs) automatically. Although these models have the ability to capture features without manual efforts, their approaches to capturing features are not specifically designed for MWPs. To utilize the merits of deep learning models with simultaneous consideration of MWPs’ specific features, we propose a group attention mechanism to extract global features, quantity-related features, quantity-pair features and question-related features in MWPs respectively. The experimental results show that the proposed approach performs significantly better than previous state-of-the-art methods, and boost performance from 66.9% to 69.5% on Math23K with training-test split, from …

Volumetric Optimization Of Freight Cargo Loading: Case Study Of A Smu Forwarder, Tristan Lim, Michael Ser Chong Ping, Mark Goh, Shi Ying Jacelyn Tan

Research Collection School Of Computing and Information Systems

Purpose: Freight forwarders faces a challenging environment of high market volatility and margin compression risks. Hence, strategic consideration is given to undertaking capacity management and transport asset ownership to achieve longer term cost leadership. Doing so will also help to address management issues, such as better control of potential transport disruptions, improve scheduling flexibility and efficiency, and provide service level enhancement.Design/methodology/approach: The case company currently hastruck resource which is unprofitable, and the firm’s schedulers are having difficulty optimizing the loading capacity. We apply Genetic Algorithm (GA) to undertake volumetric optimization of truckcapacity and to build an easy-to-use platform to help …

Unsupervised Deep Structured Semantic Models For Commonsense Reasoning, Shuohang Wang, Sheng Zhang, Yelong Shen, Xiaodong Liu, Jingjing Liu, Jianfeng Gao, Jing Jiang

Research Collection School Of Computing and Information Systems

Commonsense reasoning is fundamental to natural language understanding. While traditional methods rely heavily on human-crafted features and knowledge bases, we explore learning commonsense knowledge from a large amount of raw text via unsupervised learning. We propose two neural network models based on the Deep Structured Semantic Models (DSSM) framework to tackle two classic commonsense reasoning tasks, Winograd Schema challenges (WSC) and Pronoun Disambiguation (PDP). Evaluation shows that the proposed models effectively capture contextual information in the sentence and co-reference information between pronouns and nouns, and achieve significant improvement over previous state-of-the-art approaches.

Implementation Of Multivariate Artificial Neural Networks Coupled With Genetic Algorithms For The Multi-Objective Property Prediction And Optimization Of Emulsion Polymers, David Chisholm

Master's Theses

Machine learning has been gaining popularity over the past few decades as computers have become more advanced. On a fundamental level, machine learning consists of the use of computerized statistical methods to analyze data and discover trends that may not have been obvious or otherwise observable previously. These trends can then be used to make predictions on new data and explore entirely new design spaces. Methods vary from simple linear regression to highly complex neural networks, but the end goal is similar. The application of these methods to material property prediction and new material discovery has been of high interest …