Computer Sciences Commons^™

Trusting Artificial Intelligence In Healthcare, W. Wang, Keng Siau

Research Collection School Of Computing and Information Systems

Artificial Intelligence (AI) is able to perform at humans and even surpass human’s performances in some tasks. Recent cases about self-driving cars, cashier-free supermarket Amazon Go, and virtual assistants such as Apple’s Siri and Google Assistant have illustrated the current and future potential of AI. AI and its applications have infiltrated human’s work and daily life. It is inevitable that humans need to build a working relationship with AI and its applications. On one hand, humans can benefit from this new technology, for instance, a home robot can release housewife from mundane and monotonous tasks (Siau 2017, Siau 2018). On …

Ethical And Moral Issues With Ai, Weiyu Wang, Keng Siau

Research Collection School Of Computing and Information Systems

AI-based technology has achieved many great things, such as facial recognition, medical diagnosis, and self-driving cars. AI promises enormous benefits for economic growth, social development, as well as human well-being and safety improvement. However, the low-level of explainability, data security, data privacy, and ethical problems of AI-based technology also pose significant risks for users, developers, and governments. As the AI advances, one critical issue is how to address the ethical and moral challenges associated with AI. This study will focus on the ethics and morality issues that may be caused by AI, andmay arise because of AI. This research uses …

Offline Versus Online: A Meaningful Categorization Of Ties For Retweets, Felicia Natali, Feida Zhu

Research Collection School Of Computing and Information Systems

With the recent proliferation of news being shared through online social networks, it is crucial to determine how news is spread and what drives people to share certain stories. In this paper, we focus on the social networking site Twitter and analyse user’s retweets. We study retweeting patterns between offline and online friends, particularly, how tweet novelty and tweet topic differ between tweets retweeted by offline friends and those retweeted by online friends.

Practical Attribute-Based Multi-Keyword Search Scheme In Mobile Crowdsourcing, Yinbin Miao, Jianfeng Ma, Ximeng Liu, Xinghua Li, Zhiquan Liu, Hui Li

Research Collection School Of Computing and Information Systems

Cloud-based mobile crowd-sourcing has been an attractive solution to provide data storage and share services for resource-limited mobile devices in a privacy-preserving manner, but how to enable mobile users to issue search queries and achieve fine-grained access control over ciphertexts simultaneously is still a big challenge for various circumstances. Although the ciphertext-policy attribute-based keyword search technology combining attribute-based encryption with searchable encryption has become a hot research topic, it just deals with equivalent attributes rather than more practical attribute comparisons, like “greater than” or “less than.” In this paper, we devise a practical cryptographic primitive called attribute-based multi-keyword search scheme …

Knowledge As A Bridge: Improving Cross-Domain Answer Selection With External Knowledge, Yang Deng, Ying Shen, Min Yang, Yaliang Li, Nan Du, Wei Fan, Kai Lei

Research Collection School Of Computing and Information Systems

Answer selection is an important but challenging task. Significant progresses have been made in domains where a large amount of labeled training data is available. However, obtaining rich annotated data is a time-consuming and expensive process, creating a substantial barrier for applying answer selection models to a new domain which has limited labeled data. In this paper, we propose Knowledge-aware Attentive Network (KAN), a transfer learning framework for cross-domain answer selection, which uses the knowledge base as a bridge to enable knowledge transfer from the source domain to the target domains. Specifically, we design a knowledge module to integrate the …

Deep Learning For Practical Image Recognition: Case Study On Kaggle Competitions, Xulei Yang, Zeng Zeng, Sin G. Teo, Li Wang, Vijay Chandrasekar, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

In past years, deep convolutional neural networks (DCNN) have achieved big successes in image classification and object detection, as demonstrated on ImageNet in academic field. However, There are some unique practical challenges remain for real-world image recognition applications, e.g., small size of the objects, imbalanced data distributions, limited labeled data samples, etc. In this work, we are making efforts to deal with these challenges through a computational framework by incorporating latest developments in deep learning. In terms of two-stage detection scheme, pseudo labeling, data augmentation, cross-validation and ensemble learning, the proposed framework aims to achieve better performances for practical image …

A Formal Specification And Verification Framework For Timed Security Protocols, Li Li, Jun Sun, Yang Liu, Meng Sun, Jin Song Dong

Research Collection School Of Computing and Information Systems

Nowadays, protocols often use time to provide better security. For instance, critical credentials are often associated with expiry dates in system designs. However, using time correctly in protocol design is challenging, due to the lack of time related formal specification and verification techniques. Thus, we propose a comprehensive analysis framework to formally specify as well as automatically verify timed security protocols. A parameterized method is introduced in our framework to handle timing parameters whose values cannot be decided in the protocol design stage. In this work, we first propose timed applied p-calculus as a formal language for specifying timed security …

Server-Aided Attribute-Based Signature With Revocation For Resource-Constrained Industrial-Internet-Of-Things Devices, Hui Cui, Robert H. Deng, Joseph K. Liu, Xun Yi, Yingjiu Li

Research Collection School Of Computing and Information Systems

The industrial Internet-of-things (IIoT) can be seen as the usage of Internet-of-things technologies in industries, which provides a way to improve the operational efficiency. An attribute-based signature (ABS) has been a very useful technique for services requiring anonymous authentication in practice, where a signer can sign a message over a set of attributes without disclosing any information about his/her identity, and a signature only attests to the fact that it is created by a signer with several attributes satisfying some claim predicate. However, an ABS scheme requires exponentiation and/or pairing operations in the signature generation and verification algorithms, and hence, …

A Characterization Of The Medical-Legal Partnership (Mlp) Of Nebraska Medicine, Jordan Pieper

Capstone Experience: Master of Public Health

This research study was completed at Legal Aid of Nebraska’s Health, Education, and Law Project through the partnership it has formed working with Nebraska Medicine and Iowa Legal Aid. Traditionally, health and disease have always been viewed exclusively as "healthcare" issues. But with healthcare consistently growing towards holistic approaches to help patients, we now know there are deeper, structural conditions of society that can act as strong driving forces of a person's poor daily living conditions that can negatively impact health. The importance of a Medical-Legal Partnership is that it considers a patient's social determinants of health (SDHs). The goal …

Building Test Anonymity Networks In A Cybersecurity Lab Environment, John Schriner

Student Theses

This paper explores current methods for creating test anonymity networks in a laboratory environment for the purpose of improving these networks while protecting user privacy. We first consider how each of these networks is research-driven and interested in helping researchers to conduct their research ethically. We then look to the software currently available for researchers to set up in their labs. Lastly we explore ways in which digital forensics and cybersecurity students could get involved with these projects and look at several class exercises that help students to understand particular attacks on these networks and ways they can help to …

Fusing Multi-Abstraction Vector Space Models For Concern Localization, Yun Zhang, David Lo, Xin Xia, Giuseppe Scanniello, Tien-Duy B. Le, Jianling Sun

Research Collection School Of Computing and Information Systems

Concern localization refers to the process of locating code units that match a particular textual description. It takes as input textual documents such as bug reports and feature requests and outputs a list of candidate code units that are relevant to the bug reports or feature requests. Many information retrieval (IR) based concern localization techniques have been proposed in the literature. These techniques typically represent code units and textual descriptions as a bag of tokens at one level of abstraction, e.g., each token is a word, or each token is a topic. In this work, we propose a multi-abstraction concern …

Exact Processing Of Uncertain Top-K Queries In Multi-Criteria Settings, Kyriakos Mouratidis, Bo Tang

Research Collection School Of Computing and Information Systems

Traditional rank-aware processing assumes a dataset that contains available options to cover a specific need (e.g., restaurants, hotels, etc) and users who browse that dataset via top-k queries with linear scoring functions, i.e., by ranking the options according to the weighted sum of their attributes, for a set of given weights. In practice, however, user preferences (weights) may only be estimated with bounded accuracy, or may be inherently uncertain due to the inability of a human user to specify exact weight values with absolute accuracy. Motivated by this, we introduce the uncertain top-k query (UTK). Given uncertain preferences, that is, …

Pusc: Privacy-Preserving User-Centric Skyline Computation Over Multiple Encrypted Domains, Ximeng Liu, Kim-Kwang Raymond Choo, Robert H. Deng, Yang Yang

Research Collection School Of Computing and Information Systems

In this paper, we present a new privacy-preserving user-centric skyline computation framework over different encrypted domains, which we referred to as PUSC. With PUSC, a user can flexibly obtain the skyline set from different service providers without disclosing user preferences to third parties in the system. Specifically, we introduce a secure user-defined vector dominance protocol to compare the vector dominance relationship between two encrypted vectors, according to user's preference. This serves as the core protocol in PUSC. Detailed security analysis shows that the proposed PUSC achieves the goal of selecting skyline set according to authorized users' preferences without leaking their …

Probabilistic Collaborative Representation Learning For Personalized Item Recommendation, Aghiles Salah, Hady W. Lauw

Research Collection School Of Computing and Information Systems

We present Probabilistic Collaborative Representation Learning (PCRL), a new generative model of user preferences and item contexts. The latter builds on the assumption that relationships among items within contexts (e.g., browsing session, shopping cart, etc.) may underlie various aspects that guide the choices people make. Intuitively, PCRL seeks representations of items reflecting various regularities between them that might be useful at explaining user preferences. Formally, it relies on Bayesian Poisson Factorization to model user-item interactions, and uses a multilayered latent variable architecture to learn representations of items from their contexts. PCRL seamlessly integrates both tasks within a joint framework. However, …

Embedding Wordnet Knowledge For Textual Entailment, Yunshi Lan, Jing Jiang

Research Collection School Of Computing and Information Systems

In this paper, we study how we can improve a deep learning approach to textual entailment by incorporating lexical entailment relations from WordNet. Our idea is to embed the lexical entailment knowledge contained in WordNet in specially-learned word vectors, which we call “entailment vectors.” We present a standard neural network model and a novel set-theoretic model to learn these entailment vectors from word pairs with known lexical entailment relations derived from WordNet. We further incorporate these entailment vectors into a decomposable attention model for textual entailment and evaluate the model on the SICK and the SNLI dataset. We find that …

Online Spatio-Temporal Matching In Stochastic And Dynamic Domains, Meghna Lowalekar, Pradeep Varakantham, Patrick Jaillet

Research Collection School Of Computing and Information Systems

Online spatio-temporal matching of servers/services to customers is a problem that arises at a large scale in many domains associated with shared transportation (e.g., taxis, ride sharing, super shuttles, etc.) and delivery services (e.g., food, equipment, clothing, home fuel, etc.). A key characteristic of these problems is that the matching of servers/services to customers in one stage has a direct impact on the matching in the next stage. For instance, it is efficient for taxis to pick up customers closer to the drop off point of the customer from the first stage of matching. Traditionally, greedy/myopic approaches have been adopted …

Iterated Local Search Algorithm For The Capacitated Team Orienteering Problem, Aldy Gunawan, Kien Ming Ng, Vincent F. Yu, Gordy Adiprasetyo, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

This paper focuses on a recent variant of the Orienteering Problem (OP), namely the Capacitated Team Orienteering Problem (CTOP). In this problem, each node is associated with a demand that needs to be satisfied and a score that need to be collected. Given a set of homogeneous fleet of vehicles, the main objective is to find a path for each available vehicle in order to maximize the total score, without violating the capacity and time budget of each vehicle. We propose an Iterated Local Search algorithm that has been applied in solving various variants of the OP. We propose two …

Privacy-Preserving Biometric-Based Remote User Authentication With Leakage Resilience, Yangguang Tian, Yingjiu Li, Rongmao Chen, Ximeng Liu, Bing Chang, Xingjie Yu

Research Collection School Of Computing and Information Systems

Biometric-based remote user authentication is a useful primitive that allows an authorized user to authenticate to a remote server using his biometrics. Leakage attacks, such as side-channel attacks, allow an attacker to learn partial knowledge of secrets (e.g., biometrics) stored on any physical medium. Leakage attacks can be potentially launched to any existing biometric-based remote user authentication systems. Furthermore, applying plain biometrics is an efficient and straightforward approach when designing remote user authentication schemes. However, this approach jeopardises user’s biometrics privacy. To address these issues, we propose a novel leakage-resilient and privacy-preserving biometric-based remote user authentication framework, such that registered …

Sentence Compression With Reinforcement Learning, Liangguo Wang, Jing Jiang, Lejian Liao

Research Collection School Of Computing and Information Systems

Deletion-based sentence compression is frequently formulated as a constrained optimization problem and solved by integer linear programming (ILP). However, ILP methods searching the best compression given the space of all possible compressions would be intractable when dealing with overly long sentences and too many constraints. Moreover, the hard constraints of ILP would restrict the available solutions. This problem could be even more severe considering parsing errors. As an alternative solution, we formulate this task in a reinforcement learning framework, where hard constraints are used as rewards in a soft manner. The experiment results show that our method achieves competitive performance …

Towards An Integrated Framework For Air Quality Monitoring And Exposure Estimation - A Review, Savina Singla, Divya Bansal, Archan Misra, Gaurav Raheja

Research Collection School Of Computing and Information Systems

For the health and safety of the public, it is essential to measure spatiotemporal distribution of air pollution in a region and thus monitor air quality in a fine-grain manner. While most of the sensing-based commercial applications available until today have been using fixed environmental sensors, the use of personal devices such as smartphones, smartwatches, and other wearable devices has not been explored in depth. These kinds of devices have an advantage of being with the user continuously, thus providing an ability to generate accurate and well-distributed spatiotemporal air pollution data. In this paper, we review the studies (especially in …

Secure And Efficient Outsourcing Of Large-Scale Overdetermined Systems Of Linear Equations, Shiran Pan, Wen-Tao Zhu, Qiongxiao Wang, Bing Chang

Research Collection School Of Computing and Information Systems

We address overdetermined systems of linear equations, where the number of unknowns is smaller than the number of equations so that only approximate solutions exist instead of exact solutions. Such systems are prevalent in many areas of science and engineering, and finding the optimal solutions is mathematically known as the linear least squares (LLS) problem. Real-world overdetermined systems are often large-scale and computationally expensive to solve. Consequently, we are interested in connecting the LLS problem with cloud computing, where a resource-constrained client outsources the problem to a powerful but untrusted cloud. Among several security considerations is that the input of …

Learning Representations Of Ultrahigh-Dimensional Data For Random Distance-Based Outlier Detection, Guansong Pang, Longbing Cao, Ling Chen, Defu Lian, Huan Liu

Research Collection School Of Computing and Information Systems

Learning expressive low-dimensional representations of ultrahigh-dimensional data, e.g., data with thousands/millions of features, has been a major way to enable learning methods to address the curse of dimensionality. However, existing unsupervised representation learning methods mainly focus on preserving the data regularity information and learning the representations independently of subsequent outlier detection methods, which can result in suboptimal and unstable performance of detecting irregularities (i.e., outliers).This paper introduces a ranking model-based framework, called RAMODO, to address this issue. RAMODO unifies representation learning and outlier detection to learn low-dimensional representations that are tailored for a state-of-the-art outlier detection approach - the random …

Neural Collective Entity Linking, Yixin Cao, Lei Hou, Juanzi Li, Zhiyuan Liu

Research Collection School Of Computing and Information Systems

Entity Linking aims to link entity mentions in texts to knowledge bases, and neural models have achieved recent success in this task. However, most existing methods rely on local contexts to resolve entities independently, which may usually fail due to the data sparsity of local information. To address this issue, we propose a novel neural model for collective entity linking, named as NCEL. NCEL applies Graph Convolutional Network to integrate both local contextual features and global coherence information for entity linking. To improve the computation efficiency, we approximately perform graph convolution on a subgraph of adjacent entity mentions instead of …

Regular Lossy Functions And Their Applications In Leakage-Resilient Cryptography, Yu Chen, Baodong Qin, Haiyang Xue

Research Collection School Of Computing and Information Systems

In STOC 2008, Peikert and Waters introduced a powerful primitive called lossy trapdoor functions (LTFs). In a nutshell, LTFs are functions that behave in one of two modes. In the normal mode, functions are injective and invertible with a trapdoor. In the lossy mode, functions statistically lose information about their inputs. Moreover, the two modes are computationally indistinguishable. In this work, we put forward a relaxation of LTFs, namely, regular lossy functions (RLFs). Compared to LTFs, the functions in the normal mode are not required to be efficiently invertible or even unnecessary to be injective. Instead, they could also be …

Use Of Artificial Intelligence, Machine Learning, And Autonomous Technologies In The Mining Industry, Z. Hyder, Keng Siau, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Mining is an important industrial and economic sector that plays a major role in the economic development of a country and provides many employment opportunities. Implementation of Artificial Intelligence (AI), machine learning, and autonomous technologies in the mining industry started about a decade ago with the first application to autonomous trucks. The autonomous technologies provide many economic benefits to the mining industry through cost reduction, productivity improvement, reduction in exposure of workers to hazardous conditions, continuous production, and improved safety. However, implementation of these technologies has faced economic, financial, technological, workforce, and social challenges. This paper discusses the current status …

Study Of Blockchain-As-A-Service Systems With A Case Study Of Hyperledger Fabric Implementation On Kubernetes, Aniket Jalinder Yewale

UNLV Theses, Dissertations, Professional Papers, and Capstones

Blockchain is a shared, immutable, decentralized ledger to record the transaction history. Blockchain technology has changed the world, changed the way we do the business. It has transformed the commerce across every industry, which may be supply chain, IoT, financial services, banking, healthcare, agriculture and many more. It had introduced a new way of transactional applications that bring trust, security, transparency and accountability.

To develop any blockchain use case, the main task is to develop an environment for creating and deploying the application. In our case, we created an environment on IBM Cloud Kubernetes service using Kubernetes, a container orchestration …

Evaluation Criteria For Selecting Nosql Databases In A Single Box Environment, Ryan D. Engle, Brent T. Langhals, Michael R. Grimaila, Douglas D. Hodson

Faculty Publications

In recent years, NoSQL database systems have become increasingly popular, especially for big data, commercial applications. These systems were designed to overcome the scaling and flexibility limitations plaguing traditional relational database management systems (RDBMSs). Given NoSQL database systems have been typically implemented in large-scale distributed environments serving large numbers of simultaneous users across potentially thousands of geographically separated devices, little consideration has been given to evaluating their value within single-box environments. It is postulated some of the inherent traits of each NoSQL database type may be useful, perhaps even preferable, regardless of scale. Thus, this paper proposes criteria conceived to …

Leveraging Tiled Display For Big Data Visualization Using D3.Js, Ujjwal Acharya

Boise State University Theses and Dissertations

Data visualization has proven effective at detecting patterns and drawing inferences from raw data by transforming it into visual representations. As data grows large, visualizing it faces two major challenges: 1) limited resolution i.e. a screen is limited to a few million pixels but the data can have a billion data points, and 2) computational load i.e. processing of this data becomes computationally challenging for a single node system. This work addresses both of these issues for efficient big data visualization. In the developed system, a High Pixel Density and Large Format display was used enabling the display of fine …

Fostering The Retrieval Of Suitable Web Resources In Response To Children's Educational Search Tasks, Oghenemaro Deborah Anuyah

Boise State University Theses and Dissertations

Children regularly turn to search engines (SEs) to locate school-related materials. Unfortunately, research has shown that when utilizing SEs, children do not always access resources that specifically target them. To support children, popular and child-oriented SEs make available a safe search filter, which is meant to eliminate inappropriate resources. Safe search is, however, not always the perfect deterrent as pornographic and hate-based resources may slip through the filter, while resources relevant to an educational search context may be misconstrued and filtered out. Moreover, filtering inappropriate resources in response to children searches is just one perspective to consider in offering them …

Performance, Scalability, And Robustness In Distributed File Tree Copy, Christopher Robert Sutton

Boise State University Theses and Dissertations

As storage needs continually increase, and network file systems become more common, the need arises for tools that efficiently copy to and from these types of file systems. Traditional copy tools like the Linux cp utility were originally created for traditional storage systems, where storage is managed by a single host machine. cp uses a single-threaded approach to copying files. Using a multi-threaded approach would likely not provide an advantage in this system since the disk accesses are the bottleneck for this type of operation. In a distributed file system the disk accesses are spread across multiple hosts, and many …