Computer Sciences Commons^™

Self-Trained Deep Ordinal Regression For End-To-End Video Anomaly Detection, Guansong Pang, Cheng Yan, Chunhua Shen, Anton Van Den Hengel, Xiao Bai

Research Collection School Of Computing and Information Systems

Depression is among the most prevalent mental disorders, affecting millions of people of all ages globally. Machine learning techniques have shown effective in enabling automated detection and prediction of depression for early intervention and treatment. However, they are challenged by the relative scarcity of instances of depression in the data. In this work we introduce a novel deep multi-task recurrent neural network to tackle this challenge, in which depression classification is jointly optimized with two auxiliary tasks, namely one-class metric learning and anomaly ranking. The auxiliary tasks introduce an inductive bias that improves the classification model’s generalizability on small depression …

Learning Transferable Deep Convolutional Neural Networks For The Classification Of Bacterial Virulence Factors, Dandan Zheng, Guansong Pang, Bo Liu, Lihong Chen, Jian Yang

Research Collection School Of Computing and Information Systems

Motivation: Identification of virulence factors (VFs) is critical to the elucidation of bacterial pathogenesis and prevention of related infectious diseases. Current computational methods for VF prediction focus on binary classification or involve only several class(es) of VFs with sufficient samples. However, thousands of VF classes are present in real-world scenarios, and many of them only have a very limited number of samples available.Results: We first construct a large VF dataset, covering 3446 VF classes with 160 495 sequences, and then propose deep convolutional neural network models for VF classification. We show that (i) for common VF classes with sufficient samples, …

Check Your Tech – Considering The Provenance Of Data Used To Build Digital Products And Services: Case Studies And An Ethical Checksheet, Dympna O'Sullivan, Damian Gordon

Conference papers

Digital products and services are producing unprecedented amounts of data worldwide. These products and services have broad reach and include many users and consumers in the developing world. Once data is collected it is often used to create large and valuable datasets. A lack of data protection regulation in the developing world has led to concerns about digital colonization and a lack of control of their data on the part of citizens in the developing world. The authors of this paper are developing a new digital ethics curriculum for the instruction of computer science students. In this paper we present …

Cc2vec: Distributed Representations Of Code Changes, Thong Hoang, Hong Jin Kang, Julia Lawall, David Lo

Research Collection School Of Computing and Information Systems

Existing work on software patches often use features specific to a single task. These works often rely on manually identified features, and human effort is required to identify these features for each task. In this work, we propose CC2Vec, a neural network model that learns a representation of code changes guided by their accompanying log messages, which represent the semantic intent of the code changes. CC2Vec models the hierarchical structure of a code change with the help of the attention mechanism and usesmultiple comparison functions to identify the differences between the removed and added code. To evaluate if CC2Vec can …

Goods Consumed During Transit In Split Delivery Vehicle Routing Problems: Modeling And Solution, Wenzhe Yang, Di Wang, Wei Pang, Ah-Hwee Tan, You Zhou

Research Collection School Of Computing and Information Systems

This article presents the modeling and solution of an extended type of split delivery vehicle routing problem (SDVRP). In SDVRP, the demands of customers need to be met by efficiently routing a given number of capacitated vehicles, wherein each customer may be served multiple times by more than one vehicle. Furthermore, in many real-world scenarios, consumption of vehicles en route is the same as the goods being delivered to customers, such as food, water and fuel in rescue or replenishment missions in harsh environments. Moreover, the consumption may also be in virtual forms, such as time spent in constrained tasks. …

Visual Commonsense Representation Learning Via Causal Inference, Tan Wang, Jianqiang Huang, Hanwang Zhang, Qianru Sun

Research Collection School Of Computing and Information Systems

We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA. Given a set of detected object regions in an image (e.g., using Faster R-CNN), like any other unsupervised feature learning methods (e.g., word2vec), the proxy training objective of VC R-CNN is to predict the con-textual objects of a region. However, they are fundamentally different: the prediction of VC R-CNN is by using causal intervention: P(Y|do(X)), while others are by using the conventional likelihood: P(Y|X). We extensively apply …

Maximum A Posteriori Estimation For Information Source Detection, Biao Chang, Enhong Chen, Feida Zhu, Qi Liu, Tong Xu

Research Collection School Of Computing and Information Systems

Information source detection is to identify nodes initiating the diffusion process in a network, which has a wide range of applications including epidemic outbreak prevention, Internet virus source identification, and rumor source tracing in social networks. Although it has attracted ever-increasing attention from research community in recent years, existing solutions still suffer from high time complexity and inadequate effectiveness, due to high dynamics of information diffusion and observing just a snapshot of the whole process. To this end, we present a comprehensive study for single information source detection in weighted graphs. Specifically, we first propose a maximum a posteriori (MAP) …

Cookgan: Causality Based Text-To-Image Synthesis, Bin Zhu, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

This paper addresses the problem of text-to-image synthesis from a new perspective, i.e., the cause-and-effect chain in image generation. Causality is a common phenomenon in cooking. The dish appearance changes depending on the cooking actions and ingredients. The challenge of synthesis is that a generated image should depict the visual result of action-on-object. This paper presents a new network architecture, CookGAN, that mimics visual effect in causality chain, preserves fine-grained details and progressively upsamples image. Particularly, a cooking simulator sub-network is proposed to incrementally make changes to food images based on the interaction between ingredients and cooking methods over a …

Talk Like Somebody Is Watching: Understanding And Supporting Novice Live Streamers, Terrance Mok, Colin Matthew Au Yueng, Anthony Tang, Lora Oehlberg

Research Collection School Of Computing and Information Systems

We built a chatbot system–Audience Bot–that simulates an audience for novice live streamers to engage with while streaming. New live streamers on platforms like Twitch are expected to perform and talk to themselves, even while no one is watching. We ran an observational lab study on how Audience Bot assists novice live streamers as they acclimate to multitasking–simultaneously playing a video game while performing for a (simulated) audience.

Greenwatch-Shing: Using Ai To Detect Greenwashing, Theodor Florian Cojoianu, Andreas G. F. Hoepner, Georgiana Ifrim, Yanan Lin

Research Collection College of Integrative Studies

The rise of fake news has resulted in a wide discrepancy between the attention given to the scientific understanding of an issue versus misinformed and sometimes purposefully disinformed claims (false information that is purposely spread to deceive people) coming from outside the scientific community. One such example relates to climate change, where a nature study shows that climate change contrarians are featured in 49% more media articles than scientists, despite the overwhelming consensus in the scientific community over the significance of anthropogenic climate change. In addition, many companies worldwide make inaccurate and often misleading claims about their environmental and social …

Integrated In Silico Techniques For Mechanism Studies Of Antiviral And Antidiabetic Compounds, Mohd Isa Diyana

Student Works (2020-2029)

Discovery and development of drug is an iterative process that involves identification of target and leads discovery, lead optimization and pre-clinical of biological profile and is continued until the drugs are eligible to be tested in the clinical phase. Computer-aided drug design (CADD) is an efficient way to overcome the demands of cost, time consumption and drug validation. CADD utilizes in silico technique approaches such as molecular docking to understand their binding pattern and affinity with the target protein and molecular dynamic (MD) simulations to provide an atomic view of the dynamic behavior and stability of bioactive compound inside the …

Integrating Finance Dictionary In Lexicon-Based Approach With Machine Learning Algorithm To Analyse The Impact Of Opec News Sentiment On Financial Market, Ling Wu

Student Works (2020-2029)

Since last few decades, machine learning algorithm which trains computers to learn from experience, is one of the most rapidly developing techniques which settles in the intersection research field of statistics and computer science. This research aims to build a properly trained machine learning classifier to study the impact of Organization of Petroleum Exporting Countries (OPEC) news sentiment on stock prices of six Malaysian public listed companies (energy sector) in the main board of Bursa Malaysia. The data used in this research are collected during the period 2012-2017. To carry out the research, firstly, lexicon-based approach is used to analyze …

Optimal Control Of A Rumor Propagation Model With Different Propagation Degrees In Social Network, Yingfeng Tang

Student Works (2020-2029)

Rumor is a social interaction of information, and its development is of great significance to human beings. In this paper, by studying the D K model and a rumor model spreading with rumor latent period, deduces the rumor model with differe nt propagation degrees of the spreaders. The two equilibrium points in the system are found through derivation. In real life, enterprises often ignore the reasonable planning of the cost of rumor control. By means of public education and media technology u sing by the authorities to debunk rumors, an optimal control problem i s established. The Pontryagin’s maximum principle …

The Accumulation Of It Capability And Its Long-Term Effect On Financial Performance, Jin Ho Kim

Theses and Dissertations in Business Administration

Many scholars have been studying information technology (IT) capability and its impact on business performance. However, it has been debated whether the IT capability influences firm performance because prior literature shows mixed results. To understand this phenomenon, I performed two studies in this research, placed in two parts. First, by deploying the new concept of accumulation of IT capability, I attempted to reinvestigate the relationship between IT capability and business performance. Next, I examined what factors influence the accumulation of IT capability. In the first part, I suggested two novel constructs that measure the extent of the accumulation of IT …

Battlespace Next™: Developing A Serious Game To Explore Multi-Domain Operations, Nathaniel Flack, Alan C. Lin, Gilbert L. Peterson, Mark G. Reith

Faculty Publications

Changes in the geopolitical landscape and increasing technological complexity have prompted the U.S. Military to coin the terms Multi-Domain Operations (MDO) and Joint All-Domain Command and Control (JADC2) as over-arching strategy to frame the complexity of warfare across both traditional and emerging warfighting domains. Teaching new concepts associated with these terms requires both innovation as well as distinct education and training tools in order to realize the cultural change advocated by senior military leaders. Battlespace Next™ (BSN) is a serious game designed to teach concepts integral to MDO and initiate discussion on military strategy while conserving time, money, and manpower. …

A Machine Learning Approach For Vulnerability Curation, Yang Chen, Andrew E. Santosa, Ming Yi Ang, Abhishek Sharma, Asankhaya Sharma, David Lo

Research Collection School Of Computing and Information Systems

Software composition analysis depends on database of open-source library vulerabilities, curated by security researchers using various sources, such as bug tracking systems, commits, and mailing lists. We report the design and implementation of a machine learning system to help the curation by by automatically predicting the vulnerability-relatedness of each data item. It supports a complete pipeline from data collection, model training and prediction, to the validation of new models before deployment. It is executed iteratively to generate better models as new input data become available. We use self-training to significantly and automatically increase the size of the training dataset, opportunistically …

Homo Ludens Moralis: Designing And Developing A Board Game To Teach Ethics For Ict Education, Damian Gordon, Dympna O'Sullivan, Ioannis Stavrakakis, Andrea Curley

Conference papers

The ICT ethical landscape is changing at an astonishing rate, as technologies become more complex, and people choose to interact with them in new and distinct ways, the resultant interactions are more novel and less easy to categorise using traditional ethical frameworks. It is vitally important that the developers of these technologies do not live in an ethical vacuum; that they think about the uses and abuses of their creations, and take some measures to prevent others being harmed by their work.

To equip these developers to rise to this challenge and to create a positive future for the use …

Disparity-Aware Domain Adaptation In Stereo Image Restoration, Bo Yan, Chenxi Ma, Bahetiyaer Bare, Weimin Tan, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Under stereo settings, the problems of disparity estimation, stereo magnification and stereo-view synthesis have gathered wide attention. However, the limited image quality brings non-negligible difficulties in developing related applications and becomes the main bottleneck of stereo images. To the best of our knowledge, stereo image restoration is rarely studied. Towards this end, this paper analyses how to effectively explore disparity information, and proposes a unified stereo image restoration framework. The proposed framework explicitly learn the inherent pixel correspondence between stereo views and restores stereo image with the cross-view information at image and feature level. A Feature Modulation Dense Block (FMDB) …

Mutation Testing Of Smart Contracts At Scale, Pieter Hartel, Richard Schumi

Research Collection School Of Computing and Information Systems

It is crucial that smart contracts are tested thoroughly due to their immutable nature. Even small bugs in smart contracts can lead to huge monetary losses. However, testing is not enough; it is also important to ensure the quality and completeness of the tests. There are already several approaches that tackle this challenge with mutation testing, but their effectiveness is questionable since they only considered small contract samples. Hence, we evaluate the quality of smart contract mutation testing at scale. We choose the most promising of the existing (smart contract specific) mutation operators, analyse their effectiveness in terms of killability …

Empirical Evaluation Of Three Common Assumptions In Building Political Media Bias Datasets, Soumen Ganguly, Juhi Kulshrestha, Jisun An, Haewoon Kwak

Research Collection School Of Computing and Information Systems

In this work, we empirically validate three common assumptions in building political media bias datasets, which are (i) labelers' political leanings do not affect labeling tasks, (ii) news articles follow their source outlet's political leaning, and (iii) political leaning of a news outlet is stable across different topics. We build a ground-truth dataset of manually annotated article-level political leaning and validate the three assumptions. Our findings warn that the three assumptions could be invalid even for a small dataset. We hope that our work calls attention to the (in)validity of common assumptions in building political media bias datasets.

Context-Aware And Scale-Insensitive Temporal Repetition Counting, Huaidong Zhang, Xuemiao Xu, Guoqiang Han, Shengfeng He

Research Collection School Of Computing and Information Systems

Temporal repetition counting aims to estimate the number of cycles of a given repetitive action. Existing deep learning methods assume repetitive actions are performed in a fixed time-scale, which is invalid for the complex repetitive actions in real life. In this paper, we tailor a context-aware and scale-insensitive framework, to tackle the challenges in repetition counting caused by the unknown and diverse cycle-lengths. Our approach combines two key insights: (1) Cycle lengths from different actions are unpredictable that require large-scale searching, but, once a coarse cycle length is determined, the variety between repetitions can be overcome by regression. (2) Determining …

Don't Hit Me! Glass Detection In Real-World Scenes, Haiyang Mei, Xin Yang, Yang Wang, Yuanyuan Liu, Shengfeng He, Qiang Zhang, Xiaopeng Wei, Rynson W.H. Lau

Research Collection School Of Computing and Information Systems

Glass is very common in our daily life. Existing computer vision systems neglect it and thus may have severe consequences, e.g., a robot may crash into a glass wall. However, sensing the presence of glass is not straightforward. The key challenge is that arbitrary objects/scenes can appear behind the glass, and the content within the glass region is typically similar to those behind it. In this paper, we propose an important problem of detecting glass from a single RGB image. To address this problem, we construct a large-scale glass detection dataset (GDD) and design a glass detection network, called GDNet, …

Adaptive Loss-Aware Quantization For Multi-Bit Networks, Zhongnan Qu, Zimu Zhou, Yun Cheng, Lothar Thiele

Research Collection School Of Computing and Information Systems

We investigate the compression of deep neural networks by quantizing their weights and activations into multiple binary bases, known as multi-bit networks (MBNs), which accelerate the inference and reduce the storage for the deployment on low-resource mobile and embedded platforms. We propose Adaptive Loss-aware Quantization (ALQ), a new MBN quantization pipeline that is able to achieve an average bitwidth below one-bit without notable loss in inference accuracy. Unlike previous MBN quantization solutions that train a quantizer by minimizing the error to reconstruct full precision weights, ALQ directly minimizes the quantizationinduced error on the loss function involving neither gradient approximation nor …

A New Framework For Privacy-Preserving Biometric-Based Remote User Authentication, Yangguang Tian, Yingjiu Li, Robert H. Deng, Nan Li, Pengfei Wu, Anyi Liu

Research Collection School Of Computing and Information Systems

In this paper, we introduce the first general framework for strong privacy-preserving biometric-based remote user authentication based on oblivious RAM (ORAM) protocol and computational fuzzy extractors. We define formal security models for the general framework, and we prove that it can achieve user authenticity and strong privacy. In particular, the general framework ensures that: (1) a strong privacy and a log-linear time-complexity are achieved by using a new tree-based ORAM protocol; (2) a constant bandwidth cost is achieved by exploiting computational fuzzy extractors in the challenge-response phase of remote user authentications.

Disruptive Bussiness Model For Higher Education, Aya Rizik Abushawish

Theses

A business model is a plan for the successful operation of a business, identifying the source of revenue, the intended customers, value proposition, key resources, activities, and financing. It describes how organizations create, deliver and capture value. The recent developments in information and communications technology (ICT) disrupted most business models in different industries. The higher education industry is no exception, where it witnessed enormous integration of information and communications technologies. E-learning in higher education has made a tremendous shift in students’ life and raised the expectations of higher education service quality. The main objective of this thesis to develop a …

Cybersecurity, Digital Forensics, And Mobile Computing: Building The Pipeline Of Next-Generation University Graduates Through Focused High School Summer Camps, Mahmoud K. Quweider, Fitratullah Khan, Liyu Zhang, Lei Xu, Yessica Rodriguez, Yessenia Rodriguez

Computer Science Faculty Publications

To prepare the next generation of skilled university graduates that would help in filling the national need for cybersecurity, digital forensics, and mobile computing professionals, a team of minority/under-represented graduate students, the University Upward Bound Program (a federally funded program and part of the U.S. Department of Education; one of 967 programs nationwide) staff, and faculty from the Computer Science (CS) department got together and proposed a focused 10-week long funded summer camp for two local high schools with the following objectives:

1. Provide graduate students to instruct in the areas of` mobile application development, forensics and cyber Security.

2. …

Proof-Of-Activity Consensus Protocol Based On A Network's Active Nodes, Roman Belfer, Antonina Kashtalian, Andrii Nicheporuk, George Markowsky, Anatoliy Sachenko

Computer Science Faculty Research & Creative Works

The paper proposes a new socially oriented protocol that avoids pseudo-decentralization and monopolization of the network, increases the availability of the system, provides a fair selection of potential validator nodes, and provides a fair reward for creating new blocks and adding them to the blockchain. Our proposed protocol provides for the creation and addition of new blocks to a blockchain. Defines a node validator, which will create the next block according to its useful activity in the network according to predefined conditions, which can be formed according to the requirements of the system and will satisfy the individual needs of …

Transfer Learning: Bridging The Gap Between Deep Learning And Domain-Specific Text Mining, Chaoran Cheng

Dissertations

Inspired by the success of deep learning techniques in Natural Language Processing (NLP), this dissertation tackles the domain-specific text mining problems for which the generic deep learning approaches would fail. More specifically, the domain-specific problems are: (1) success prediction in crowdfunding, (2) variants identification in biomedical literature, and (3) text data augmentation for domains with low-resources.

In the first part, transfer learning in a multimodal perspective is utilized to facilitate solving the project success prediction on the crowdfunding application. Even though the information in a project profile can be of different modalities such as text, images, and metadata, most existing …

Efficient Hardware Implementations Of Bio-Inspired Networks, Anakha Vasanthakumaribabu

Dissertations

The human brain, with its massive computational capability and power efficiency in small form factor, continues to inspire the ultimate goal of building machines that can perform tasks without being explicitly programmed. In an effort to mimic the natural information processing paradigms observed in the brain, several neural network generations have been proposed over the years. Among the neural networks inspired by biology, second-generation Artificial or Deep Neural Networks (ANNs/DNNs) use memoryless neuron models and have shown unprecedented success surpassing humans in a wide variety of tasks. Unlike ANNs, third-generation Spiking Neural Networks (SNNs) closely mimic biological neurons by operating …

Memory Constraints In Cued-Recall-Dependent Learning And Performance Tasks: Why Do Humans Struggle With Simple Yet Memory-Intensive Tasks?, Jack L. Burgess

Dartmouth College Undergraduate Theses

This study explores how various constraints on a computer agent's memory and recall capacities affect how it performs a simple reinforcement learning task: the card-matching memory game "Concentration". Existing computer agents can solve this task easily, but humans struggle with it, even though its rules and objectives are simple. Why is this the case? We identify specific human memory limitations that may be at play: decaying of memories over time and remembering broad characteristics of card locations and faces while forgetting card specifics. Through building and testing a reinforcement learning agent with these human-like memory constraints, we find that they …