Computer Sciences Commons^™

Generating Realistic Stock Market Order Streams, Junyi Li, Xintong Wang, Yaoyang Lin, Arunesh Sinha, Michael P. Wellman

Research Collection School Of Computing and Information Systems

We propose an approach to generate realistic and high-fidelity stock market data based on generative adversarial networks. We model the order stream as a stochastic process with finite history dependence, and employ a conditional Wasserstein GAN to capture history dependence of orders in a stock market. We test our approach with actual market and synthetic data on a number of different statistics, and find the generated data to be close to real data.

Multi-Level Head-Wise Match And Aggregation In Transformer For Textual Sequence Matching, Shuohang Wang, Yunshi Lan, Yi Tay, Jing Jiang, Jingjing Liu

Research Collection School Of Computing and Information Systems

Transformer has been successfully applied to many natural language processing tasks. However, for textual sequence matching, simple matching between the representation of a pair of sequences might bring in unnecessary noise. In this paper, we propose a new approach to sequence pair matching with Transformer, by learning head-wise matching representations on multiple levels. Experiments show that our proposed approach can achieve new state-of-the-art performance on multiple tasks that rely only on pre-computed sequence-vectorrepresentation, such as SNLI, MNLI-match, MNLI-mismatch, QQP, and SQuAD-binary

Distinguishing Similar Design Pattern Instances Through Temporal Behavior Analysis, Renhao Xiong, David Lo, Bixin Li

Research Collection School Of Computing and Information Systems

Design patterns (DPs) encapsulate valuable design knowledge of object-oriented systems. Detecting DP instances helps to reveal the underlying rationale, thus facilitates the maintenance of legacy code. Resulting from the internal similarity of DPs, implementation variants, and missing roles, approaches based on static analysis are unable to well identify structurally similar instances. Existing approaches further employ dynamic techniques to test the runtime behaviors of candidate instances. Automatically verifying the runtime behaviors of DP instances is a challenging task in multiple aspects. This paper presents an approach to improve the verification process of existing approaches. To exercise the runtime behaviors of DP …

Neural Approximate Dynamic Programming For On-Demand Ride-Pooling, Sanket Shah, Meghna Lowalekar, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

On-demand ride-pooling (e.g., UberPool, LyftLine, GrabShare) has recently become popular because of its ability to lower costs for passengers while simultaneously increasing revenue for drivers and aggregation companies (e.g., Uber). Unlike in Taxi on Demand (ToD) services – where a vehicle is assigned one passenger at a time – in on-demand ride-pooling, each vehicle must simultaneously serve multiple passengers with heterogeneous origin and destination pairs without violating any quality constraints. To ensure near real-time response, existing solutions to the real-time ride-pooling problem are myopic in that they optimise the objective (e.g., maximise the number of passengers served) for the current …

Saga: Efficient And Large-Scale Detection Of Near-Miss Clones With Gpu Acceleration, Guanhua Li, Yijian Wu, Chanchal K. Roy, Jun Sun, Xin Peng, Nanjie Zhan, Bin Hu, Jingyi Ma

Research Collection School Of Computing and Information Systems

Clone detection on large code repository is necessary for many big code analysis tasks. The goal is to provide rich information on identical and similar code across projects. Detecting near-miss code clones on big code is challenging since it requires intensive computing and memory resources as the scale of the source code increases. In this work, we propose SAGA, an efficient suffix-array based code clone detection tool designed with sophisticated GPU optimization. SAGA not only detects Type-l and Type-2 clones but also does so for cross-project large repositories and for the most computationally expensive Type-3 clones. Meanwhile, it also works …

Sentiment Analysis For Airline Services On Twitter Using Deep Learning With Word Embedding, Nour El Daim El Khalifa Mawada Mohamed

Student Works (2020-2029)

The use of social media platform in the airline industries have increased rapidly to allow analysis introduce the quality and performance of the services. The role of Sentiment Analysis (SA) is to classify people's opinions into different categories, such as positive and negative from text, using existing algorithms. However, existing approaches such as the Bag of Words (BOW) model is frequently used for text classification, where a document is mapped to a feature vector before the construction of the actual model, using machine learning techniques, like Logistical Regression and Support Vector algorithms. This problem has led to low accuracy in …

Stochastically Robust Personalized Ranking For Lsh Recommendation Retrieval, Dung D. Le, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Locality Sensitive Hashing (LSH) has become one of the most commonly used approximate nearest neighbor search techniques to avoid the prohibitive cost of scanning through all data points. For recommender systems, LSH achieves efficient recommendation retrieval by encoding user and item vectors into binary hash codes, reducing the cost of exhaustively examining all the item vectors to identify the topk items. However, conventional matrix factorization models may suffer from performance degeneration caused by randomly-drawn LSH hash functions, directly affecting the ultimate quality of the recommendations. In this paper, we propose a framework named SRPR, which factors in the stochasticity of …

Deepmicrobes: Taxonomic Classification For Metagenomics With Deep Learning, Paul W. Bible, Qiaoxing Liang, Yu Liu, Bin Zou, Lai Wei

Computer Science Faculty publications

Large-scale metagenomic assemblies have uncovered thousands of new species greatly expanding the known diversity of microbiomes in specific habitats. To investigate the roles of these uncultured species in human health or the environment, researchers need to incorporate their genome assemblies into a reference database for taxonomic classification. However, this procedure is hindered by the lack of a well-curated taxonomic tree for newly discovered species, which is required by current metagenomics tools. Here we report DeepMicrobes, a deep learning-based computational framework for taxonomic classification that allows researchers to bypass this limitation. We show the advantage of DeepMicrobes over state-of-the-art tools in …

Crowdprivacy: Publish More Useful Data With Less Privacy Exposure In Crowdsourced Location-Based Services, Fang Jing Wu, Tie Luo

Computer Science Faculty Research & Creative Works

Location-based services (LBSs) typically crowdsource geo-tagged data from mobile users. Collecting more data will generally improve the utility for LBS providers; however, it also leads to more privacy exposure of users' mobility patterns. Although the tension between data utility and user privacy has been recognized, there lacks a solution that determines how much data to collect-in both spatial and temporal domains-is the "best" for both mobile users and the service provider. This article proposes a strategy toward making an optimal tradeoff such that a user submits data only if her mobility privacy will not be compromised and the data utility …

Short-Term Electricity Price Forecasting In Deregulated Electricity Market Based On Enhanced Artificial Intelligence Techniques, Pourdaryaei Alireza

Student Works (2020-2029)

Electricity price forecasting is considered as one of prime factors for operation, planning and scheduling of price-setter market participants. However, possessing time variant, non-linear and non-stationary behaviors make the electricity price a complex signal. The main challenge in this area is providing highly accurate and efficient day-ahead price forecasting. A suitable feature selection technique, which is able to model the interacting features and nonlinearities of the forecast processes, is still required although researches have been performed for day-ahead forecasting. In this research, a hybrid electricity price forecasting methodology is proposed using two-stage feature selection method and optimization using adaptive neuro-fuzzy …

Spanning Properties Of Theta-Theta-6, Mirela Damian, John Iacono, Andrew Winslow

Computer Science Faculty Publications

We show that, unlike the Yao–Yao graph YY6, the Theta–Theta graph ΘΘ6 defined by six cones is a spanner for sets of points in convex position. We also show that, for sets of points in non-convex position, the spanning ratio of ΘΘ6 is unbounded.

Supporting Blockchain-Based Cryptocurrency Mobile Payment With Smart Devices, Lei Xu, Lin Chen, Zhimin Gao, Larry Carranco, Xinxin Fan, Nolah Shah

Computer Science Faculty Publications

The smart device owning rate such as smart phone and smart watch is higher than ever before and mobile payment has become one of the major payment methods in many different areas. At the same time, blockchain-based cryptocurrency is becoming a nonnegligible type of currency and the total value of all types of cryptocurrency has reached USD 200 billion. Therefore, it is a natural demand to support cryptocurrency payment on mobile devices. Considering the poor infrastructure and low penetration of financial service in developing countries, this combination is especially attractive. The high storage cost and payment processing latency are the …

Example-Based Colourization Via Dense Encoding Pyramids, Chufeng Xiao, Chu Han, Zhuming Zhang, Jing Qin, Tien-Tsin Wong, Guoqiang Han, Shengfeng He

Research Collection School Of Computing and Information Systems

We propose a novel deep example-based image colourization method called dense encoding pyramid network. In our study, we define the colourization as a multinomial classification problem. Given a greyscale image and a reference image, the proposed network leverages large-scale data and then predicts colours by analysing the colour distribution of the reference image. We design the network as a pyramid structure in order to exploit the inherent multi-scale, pyramidal hierarchy of colour representations. Between two adjacent levels, we propose a hierarchical decoder-encoder filter to pass the colour distributions from the lower level to higher level in order to take both …

Are The Code Snippets What We Are Searching For? A Benchmark And An Empirical Study On Code Search With Natural-Language Queries, Shuhan Yan, Hang Yu, Yuting Chen, Beijun Shen

Research Collection School Of Computing and Information Systems

Code search methods, especially those that allow programmers to raise queries in a natural language, plays an important role in software development. It helps to improve programmers' productivity by returning sample code snippets from the Internet and/or source-code repositories for their natural-language queries. Meanwhile, there are many code search methods in the literature that support natural-language queries. Difficulties exist in recognizing the strengths and weaknesses of each method and choosing the right one for different usage scenarios, because (1) the implementations of those methods and the datasets for evaluating them are usually not publicly available, and (2) some methods leverage …

Social Influence Does Matter: User Action Prediction For In-Feed Advertising., Hongyang Wang, Qingfei Meng, Ju Fan, Yuchen Li, Laizhong Cui, Xiaoman Zhao, Chong Peng, Gong Chen Chen, Xiaoyong Du

Research Collection School Of Computing and Information Systems

Social in-feed advertising delivers ads that seamlessly fit insidea user’s feed, and allows users to engage in social actions(likes or comments) with the ads. Many businesses payhigher attention to “engagement marketing” that maximizessocial actions, as social actions can effectively promote brandawareness. This paper studies social action prediction for infeedadvertising. Most existing works overlook the social influenceas a user’s action may be affected by her friends’actions. This paper introduces an end-to-end approach thatleverages social influence for action prediction, and focuseson addressing the high sparsity challenge for in-feed ads. Wepropose to learn influence structure that models who tendsto be influenced. We extract …

Does Reputational Sanctions Deter Negligence In Information Security Management? A Field Quasi-Experiment, Qian Tang, Andrew B. Whinston

Research Collection School Of Computing and Information Systems

Security negligence, a major cause of data breaches, occurs when an organization’s information technology management fails to adequately address security vulnerabilities. By conducting a field quasi-experiment using outgoing spam as a focal security issue, this study investigates the effectiveness of reputational sanctions in reducing security negligence in a global context. In the quasi-experiment, a reputational sanction mechanism based on outgoing spam was established for four countries, and for each country, reputational sanctions were imposed on the 10 organizations with the largest outgoing spam volumes—that is, these organizations were listed publicly. We find that because of our reputational sanction mechanism, organizations …

Privacy-Preserving Network Path Validation, Binanda Sengupta, Yingjiu Li, Kai Bu, Robert H. Deng

Research Collection School Of Computing and Information Systems

The end-users communicating over a network path currently have no control over the path. For a better quality of service, the source node often opts for a superior (or premium) network path to send packets to the destination node. However, the current Internet architecture provides no assurance that the packets indeed follow the designated path. Network path validation schemes address this issue and enable each node present on a network path to validate whether each packet has followed the specific path so far. In this work, we introduce two notions of privacy—path privacy and index privacy—in the context of network …

Deepdualmapper: A Gated Fusion Network For Automatic Map Extraction Using Aerial Images And Trajectories, Hao Wu, Hanyuan Zhang, Xinyu Zhang, Weiwei Sun, Baihua Zheng, Yuning Jiang

Research Collection School Of Computing and Information Systems

Automatic map extraction is of great importance to urban computing and location-based services. Aerial image and GPS trajectory data refer to two different data sources that could be leveraged to generate the map, although they carry different types of information. Most previous works on data fusion between aerial images and data from auxiliary sensors do not fully utilize the information of both modalities and hence suffer from the issue of information loss. We propose a deep convolutional neural network called DeepDualMapper which fuses the aerial image and trajectory data in a more seamless manner to extract the digital map. We …

Mcdpc: Multi‐Center Density Peak Clustering, Yizhang Wang, Di Wang, Xiaofeng Zhang, Wei Pang, Chunyan Miao, Ah-Hwee Tan, You Zhou

Research Collection School Of Computing and Information Systems

Density peak clustering (DPC) is a recently developed density-based clustering algorithm that achieves competitive performance in a non-iterative manner. DPC is capable of effectively handling clusters with single density peak (single center), i.e., based on DPC’s hypothesis, one and only one data point is chosen as the center of any cluster. However, DPC may fail to identify clusters with multiple density peaks (multi-centers) and may not be able to identify natural clusters whose centers have relatively lower local density. To address these limitations, we propose a novel clustering algorithm based on a hierarchical approach, named multi-center density peak clustering (McDPC). …

Multi-Level Fine-Scaled Sentiment Sensing With Ambivalence Handling, Zhaoxia Wang, Seng-Beng Ho, Erik Cambria

Research Collection School Of Computing and Information Systems

Social media represent a rich source of information, such as critiques, feedback, and other opinions posted online by Internet users. Such information is typically a good reflection of users’ sentiments and attitudes towards various services, topics, or products. Sentiment analysis has become an increasingly important natural language processing (NLP) task to help users make sense of what is happening in the Internet blogosphere and it can be useful for companies as well as public organizations. However, most existing sentiment analysis techniques are only able to analyze data at the aggregate level, merely providing a binary classification (positive vs. negative), and …

Ausearch: Accurate Api Usage Search In Github Repositories With Type Resolution, Muhammad Hilmi Asyrofi, Ferdian Thung, David Lo, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Nowadays, developers use APIs to implement their applications. To know how to use an API, developers may search for code examples that use the API in repositories such as GitHub. Although code search engines have been developed to help developers perform such search, these engines typically only accept a query containing the description of the task that needs to be implemented or the names of the APIs that the developer wants to use without the capability for the developer to specify particular search constraints, such as the class and parameter types that the relevant API should take. These engines are …

Essential Sentences For Navigating Stack Overflow Answers, Sarah Nadi, Christoph Treude

Research Collection School Of Computing and Information Systems

Stack Overflow (SO) has become an essential resource for software development. Despite its success and prevalence, navigating SO remains a challenge. Ideally, SO users could benefit from highlighted navigational cues that help them decide if an answer is relevant to their task and context. Such navigational cues could be in the form of essential sentences that help the searcher decide whether they want to read the answer or skip over it. In this paper, we compare four potential approaches for identifying essential sentences. We adopt two existing approaches and develop two new approaches based on the idea that contextual information …

Analysis Of Blockchain Protocol Against Static Adversarial Miners Corrupted By Long Delay Attackers, Quan Yuan, Puwen Wei, Keting Jia, Haiyang Xue

Research Collection School Of Computing and Information Systems

Bitcoin, which was initially introduced by Nakamoto, is the most disruptive and impactive cryptocurrency. The core Bitcoin technology is the so-called blockchain protocol. In recent years, several studies have focused on rigorous analyses of the security of Nakamoto’s blockchain protocol in an asynchronous network where network delay must be considered. Wei, Yuan, and Zheng investigated the effect of a long delay attack against Nakamoto’s blockchain protocol. However, their proof only holds in the honest miner setting. In this study, we improve Wei, Yuan and Zheng’s result using a stronger model where the adversary can perform long delay attacks and corrupt …

Workshop On The Development And Evaluation Of Digital Therapeutics For Health Behavior Change: Science, Methods, And Projects, Alan J. Budney, Lisa A. Marsch, Will M. Aklin, Jacob T. Borodovsky, Mary F. Brunette, Andrew T. Campbell, Jesse Dallery, David Kotz, Ashley A. Knapp, Sarah E. Lord, Edward V. Nunes, Emily A. Scherer, Catherine Stanger, William C. Torrey

Dartmouth Scholarship

The health care field has integrated advances into digital technology at an accelerating pace to improve health behavior, health care delivery, and cost-effectiveness of care. The realm of behavioral science has embraced this evolution of digital health, allowing for an exciting roadmap for advancing care by addressing the many challenges to the field via technological innovations. Digital therapeutics offer the potential to extend the reach of effective interventions at reduced cost and patient burden and to increase the potency of existing interventions. Intervention models have included the use of digital tools as supplements to standard care models, as tools that …

Metrics To Meet Security & Privacy Requirements With Agile Software Development Methods In A Regulated Environment, Torrey J. Wagner, Thomas C. Ford

Faculty Publications

This work examines metrics that can be used to measure the ability of agile software development methods to meet security and privacy requirements of communications applications. Many implementations of communication protocols, including those in vehicular networks, occur within regulated environments where agile development methods are traditionally discouraged. We propose a framework and metrics to measure adherence to security, quality and software effectiveness regulations if developers desire the cost and schedule benefits of agile methods. After providing an overview of specific challenges that a regulated environment imposes on communications software development, we proceed to examine the 12 agile principles and how …

Robust Neural Machine Translation, Abdul Rafae Khan

Dissertations, Theses, and Capstone Projects

This thesis aims for general robust Neural Machine Translation (NMT) that is agnostic to the test domain. NMT has achieved high quality on benchmarks with closed datasets such as WMT and NIST but can fail when the translation input contains noise due to, for example, mismatched domains or spelling errors. The standard solution is to apply domain adaptation or data augmentation to build a domain-dependent system. However, in real life, the input noise varies in a wide range of domains and types, which is unknown in the training phase. This thesis introduces five general approaches to improve NMT accuracy and …

Designing Fractal Line Pied-De-Poules: A Case Study In Algorithmic Design Mediating Between Culture And Fractal Mathematics, Loe M.G. Feijs

Journal of Humanistic Mathematics

Millions of people own and wear pied-de-poule (houndstooth) garments. The pattern has an intriguing basic figure and a typical set of symmetries. The origin of the pattern lies in a specific type of weaving. In this article I apply computational techniques to modernize this ancient decorative pattern. In particular I describe a way to enrich pied-de-poule with a fractal structure.

Although a first fractal line pied-de-poule was shown at Bridges 2015, a number of fundamental questions still remained. The following questions are addressed in this article: Does the original pied-de-poule appear as a limit case when the fractal structure is …

A Framework For Online Social Network Volatile Data Analysis: A Case For The Fast Fashion Industry, Anoud Bani-Hani, Feras Al-Obeidat, Elhadj Benkhelifa, Oluwasegun Adedugbe

All Works

Consumer satisfaction is an important part for any business as it has been shown to be a major factor for consumer loyalty. Identifying satisfaction in products is also important as it allows businesses alter production plans based on the level of consumer satisfaction for a product. With consumer satisfaction data being very volatile for some products due to a short requirement period for such products, current consumer satisfaction must be identified within a shorter period before the data becomes obsolete. The fast fashion industry, which is part of the fashion industry, is adopted as a case study in this research. …

Beyond Reasonable Doubt: A Proposal For Undecidedness Blocking In Abstract Argumentation, Pierpaolo Dondio, Luca Longo

Articles

In Dung’s abstract semantics, the label undecided is always propagated from the attacker to the attacked argument, unless the latter is also attacked by an accepted argument. In this work we propose undecidedness blocking abstract argumentation semantics where the undecided label is confined to the strong connected component where it was generated and it is not propagated to the other parts of the argumentation graph. We show how undecidedness blocking is a fundamental reasoning pattern absent in abstract argumentation but present in similar fashion in the ambiguity blocking semantics of Defeasible logic, in the beyond reasonable doubt legal principle or …

Preface To The Special Issue On Advances In Argumentation In Artificial Intelligence, Pierpaolo Dondio, Luca Longo, Stefano Bistarelli

Articles

Now at the forefront of automated reasoning, argumentation has become a key research topic within Artificial Intelligence. It involves the investigation of those activities for the production and exchange of arguments, where arguments are attempts to persuade someone of something by giving reasons for accepting a particular conclusion or claim as evident. The study of argumentation has been the focus of attention of philosophers and scholars, from Aristotle and classical rhetoric to the present day. The computational study of arguments has emerged as a field of research in AI in the last two decades, mainly fuelled by the interest from …