Computer Sciences Commons^™

Preference-Aware Task Assignment In On-Demand Taxi Dispatching: An Online Stable Matching Approach, Boming Zhao, Pan Xu, Yexuan Shi, Yongxin Tong, Zimu Zhou, Yuxiang Zeng

Research Collection School Of Computing and Information Systems

No abstract provided.

Culture Clubs: Processing Speech By Deriving And Exploiting Linguistic Subcultures, David Guy Brizan

Dissertations, Theses, and Capstone Projects

Spoken language understanding systems are error-prone for several reasons, including individual speech variability. This is manifested in many ways, among which are differences in pronunciation, lexical inventory, grammar and disfluencies. There is, however, a lot of evidence pointing to stable language usage within subgroups of a language population. We call these subgroups linguistic subcultures.

The two broad problems are defined and a survey of the work in this space is performed. The two broad problems are: linguistic subculture detection, commonly performed via Language Identification, Accent Identification or Dialect Identification approaches; and speech and language processing tasks taken which may see …

Deep Learning Based Medical Image Analysis With Limited Data, Jiaxing Tan

Dissertations, Theses, and Capstone Projects

Deep Learning Methods have shown its great effort in the area of Computer Vision. However, when solving the problems of medical imaging, deep learning’s power is confined by limited data available. We present a series of novel methodologies for solving medical imaging analysis problems with limited Computed tomography (CT) scans available. Our method, based on deep learning, with different strategies, including using Generative Adversar- ial Networks, two-stage training, infusing the expert knowledge, voting based or converting to other space, solves the data set limitation issue for the cur- rent medical imaging problems, specifically cancer detection and diagnosis, and shows very …

Real-Time Ray Traced Global Illumination Using Fast Sphere Intersection Approximation For Dynamic Objects, Reed Phillip Garmsen

Master's Theses

Realistic lighting models are an important component of modern computer generated, interactive 3D applications. One of the more difficult to emulate aspects of real-world lighting is the concept of indirect lighting, often referred to as global illumination in computer graphics. Balancing speed and accuracy requires carefully considered trade-offs to achieve plausible results and acceptable framerates.

We present a novel technique of supporting global illumination within the constraints of the new DirectX Raytracing (DXR) API used with DirectX 12. By pre-computing spherical textures to approximate the diffuse color of dynamic objects, we build a smaller set of approximate geometry used for …

Awareness And Perception Of Cybercrimes And Cybercriminals, Hannarae Lee, Hyeyoung Lim

International Journal of Cybersecurity Intelligence & Cybercrime

Awareness is a starting point to recognize, understand, or know a situation or fact, and the perception makes a difference in how to deal with it. Although the term cybercrime may not be new to the most public and the police, not all of them are well aware of the nature and extent of cybercrimes, cybercriminals, and cyber-victims, which in turn affects their perceptions of matters. The four papers in this issue of the International Journal of Cybersecurity Intelligence and Cybercrime empirically examine these important topics and discuss policy implications.

Phishing And Cybercrime Risks In A University Student Community, Roderic Broadhurst, Katie Skinner, Nicholas Sifniotis, Bryan Matamoros-Macias, Yuguang Ipsen

International Journal of Cybersecurity Intelligence & Cybercrime

In an exploratory quasi-experimental observational study, 138 participants recruited during a university orientation week were exposed to social engineering directives in the form of fake email or phishing attacks over several months in 2017. These email attacks attempted to elicit personal information from participants or entice them into clicking links which may have been compromised in a real-world setting. The study aimed to determine the risks of cybercrime for students by observing their responses to social engineering and exploring attitudes to cybercrime risks before and after the phishing phase. Three types of scam emails were distributed that varied in the …

Examining Perceptions Of Online Harassment Among Constables In England And Wales, Thomas J. Holt, Jin R. Lee, Roberta Liggett, Karen M. Holt, Adam Bossler

International Journal of Cybersecurity Intelligence & Cybercrime

The ubiquity of the Internet and computer technology has enabled individuals to engage in bullying, threats, and harassing communications online. Limited research has found that local line officers may not view these offenses as serious compared to real world crimes despite their negative physical and emotional impact on victims. The perceptions of officers can produce poor interactions with victims during calls for service, particularly victim blaming, which can reduce citizens’ confidence in police agencies generally. However, local law enforcement agencies are increasingly mandated to respond to these cases, calling to question how their views may impact the community. This study …

Cybercrime And Digital Forensics: Bridging The Gap In Legislation, Investigation And Prosecution Of Cybercrime In Nigeria, Kabiru H. Mohammed, Yusuf D. Mohammed, Abiodun A. Solanke

International Journal of Cybersecurity Intelligence & Cybercrime

The advancement of Information and Communication Technologies (ICT) opens new avenues and ways for cybercriminals to commit crime. The primary goal of this paper is to raise awareness regarding gaps that exist with regards to Nigeria’s capabilities to adequately legislate, investigate and prosecute cases of cybercrimes. The major source of cybercrime legislation in Nigeria is an act of the National Assembly which is majorly a symbolic legislation rather than a full and active legislation. In perusing these avenues of inquiry, the authors seek to identify systemic impediments which hinder law enforcement agencies, prosecutors, and investigators from properly carrying out their …

Android Aplikacion: Shfrytëzimi I Baterisë Nga Aplikacionet Tjera, Shqipe Sejdiu

Theses and Dissertations

Ky punim bazohet në njohjen e zhvillimit të sistemit operativ Android dhe në zhvillimin e një aplikacioni specifik. Tregohet se si gjatë kohës është zhvilluar sistemi operativ dhe poashtu si ka arritur t'i publikoj karakteristikat të cilat rezultuan të nevojshme për një shfrytëzues të këtij sistemi operativ, si ka arritur të jetë një ndër të parët në treg dhe se si është bërë kaq fleksibil dhe lehtë i përdorshëm. Në këtë punim tregohet se cilat ishin qëllimet e para të krijimit të Android Inc., tregohet se cili ishte misioni i tyre. Po ashtu tregohen se cilat ishin marrëveshjet më të …

Artificial Intelligence Hits The Barrier Of Meaning, Melanie Mitchell

Computer Science Faculty Publications and Presentations

Today’s AI systems sorely lack the essence of human intelligence: Understanding the situations we experience, being able to grasp their meaning. The lack of humanlike understanding in machines is underscored by recent studies demonstrating lack of robustness of state-of-the-art deep-learning systems. Deeper networks and larger datasets alone are not likely to unlock AI’s “barrier of meaning”; instead the field will need to embrace its original roots as an interdisciplinary science of intelligence.

Standardizing Facilitator Development For Exploring Computer Science Professional Development, Steven Mcgee, John Wachen, Lucia Dettori, Don Yanek, Faythe Brannon, Andrew M. Rasmussen, Dale F. Reed, Ronald I. Greenberg

Computer Science: Faculty Publications and Other Works

A key strategy for broadening CS participation

in the Chicago Public Schools (CPS) has been the enactment

of a high school CS graduation requirement. The Exploring

Computer Science (ECS) curriculum and professional development

(PD) program serve as a core foundation for supporting

enactment of this policy. The CAFE´CS researcher-practitioner

partnership provides support for ECS implementation in CPS.

An important part of the sustainability of the ECS PD model in

CPS is the development of local workshop facilitators. Potential

facilitators have generally been selected based on the CAFE´CS

team’s personal familiarity with active ECS teachers. Once

selected, teachers engage in a …

Rubik's Cube: A Visual And Tactile Learning Of Algorithms And Patterns, Lawrence Muller

Open Educational Resources

This is a classroom activity report on teaching algorithms as part of a second course in computer programming. Teaching an algorithm in an introductory level programming class is often a dry task for the instructor and the rewards for the student are abstract. To make the learning of algorithms and software more rewarding, this assignment employs a Rubik’s cube.

Gamification Of Enterprise Systems, Fiona Fui-Hoon Nah, B. Eschenbrenner, C. Claybaugh, P. Koob

Research Collection School Of Computing and Information Systems

Enterprise systems have become an integral part of an organization’s operations. However, they also pose many challenges to organizations from the perspective of implementation, user training, as well as use and acceptance. Without effective usage, enterprise systems may not be able to provide the strategic or competitive advantages that organizations desire. Therefore, organizations mayconsider gamification to enhance training, acceptance, and usage. We discuss the various ways in whichenterprise system challenges can be addressed through the lens of gamification and present a frameworkforgamificationofenterprisesystems. Theframeworkiscomprisedofbasicprinciplesand key design elements of gamification, as well as their application to enterprise systems. The specific principles of …

Fpc: A New Approach To Firewall Policies Compression, Yuzhu Cheng, Weiping Wang, Jianxin Wang, Haodong Wang

Electrical and Computer Engineering Faculty Publications

Firewalls are crucial elements that enhance network security by examining the field values of every packet and deciding whether to accept or discard a packet according to the firewall policies. With the development of networks, the number of rules in firewalls has rapidly increased, consequently degrading network performance. In addition, because most real-life firewalls have been plagued with policy conflicts, malicious traffics can be allowed or legitimate traffics can be blocked. Moreover, because of the complexity of the firewall policies, it is very important to reduce the number of rules in a firewall while keeping the rule semantics unchanged and …

Continuous Smartphone Authentication Using Wristbands, Shrirang Mare, Reza Rawassizadeh, Ronald Peterson, David Kotz

Dartmouth Scholarship

Many users find current smartphone authentication methods (PINs, swipe patterns) to be burdensome, leading them to weaken or disable the authentication. Although some phones support methods to ease the burden (such as fingerprint readers), these methods require active participation by the user and do not verify the user’s identity after the phone is unlocked. We propose CSAW, a continuous smartphone authentication method that leverages wristbands to verify that the phone is in the hands of its owner. In CSAW, users wear a wristband (a smartwatch or a fitness band) with built-in motion sensors, and by comparing the wristband’s motion with …

Partially Observable Multi-Sensor Sequential Change Detection: A Combinatorial Multi-Armed Bandit Approach, Chen Zhang, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

This paper explores machine learning to address a problem of Partially Observable Multi-sensor Sequential Change Detection (POMSCD), where only a subset of sensors can be observed to monitor a target system for change-point detection at each online learning round. In contrast to traditional Multisensor Sequential Change Detection tasks where all the sensors are observable, POMSCD is much more challenging because the learner not only needs to detect on-the-fly whether a change occurs based on partially observed multi-sensor data streams, but also needs to cleverly choose a subset of informative sensors to be observed in the next learning round, in order …

Risk Pooling, Supply Chain Hierarchy, And Analysts' Forecasts, Nan Hu, Jian-Yu Ke, Ling Liu, Yue Zhang

Research Collection School Of Computing and Information Systems

We investigate whether a firm's risk pooling affects its analysts' forecasts, specifically in terms of forecast accuracy and their use of public vs. private information, and how risk pooling interacts with a firm's position in the supply chain to affect analysts' forecasts. We use a social network analysis method to operationalize risk pooling and supply chain hierarchy, and find that risk pooling significantly reduces analysts' forecast errors and increases (decreases) their use of public (private) information. We also find that the positive (negative) relationships between risk pooling and analyst forecast accuracy and analysts' use of public (private) information are more …

Bilateral Dependency Neural Networks For Cross-Language Algorithm Classification, Duy Quoc Nghi Bui, Yijun Yu, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Algorithm classification is to automatically identify the classes of a program based on the algorithm(s) and/or data structure(s) implemented in the program. It can be useful for various tasks, such as code reuse, code theft detection, and malware detection. Code similarity metrics, on the basis of features extracted from syntax and semantics, have been used to classify programs. Such features, however, often need manual selection effort and are specific to individual programming languages, limiting the classifiers to programs in the same language.To recognise the similarities and differences among algorithms implemented in different languages, this paper describes a framework of Bilateral …

Robust Estimation Of Similarity Transformation For Visual Object Tracking, Yang Li, Jianke Zhu, Steven C. H. Hoi, Wenjie Song, Zhefeng Wang, Hantang Liu

Research Collection School Of Computing and Information Systems

Most of existing correlation filter-based tracking approaches only estimate simple axis-aligned bounding boxes, and very few of them is capable of recovering the underlying similarity transformation. To tackle this challenging problem, in this paper, we propose a new correlation filter-based tracker with a novel robust estimation of similarity transformation on the large displacements. In order to efficiently search in such a large 4-DoF space in real-time, we formulate the problem into two 2-DoF sub-problems and apply an efficient Block Coordinates Descent solver to optimize the estimation result. Specifically, we employ an efficient phase correlation scheme to deal with both scale …

A Coordination Framework For Multi-Agent Persuasion And Adviser Systems, Budhitama Subagdja, Ah-Hwee Tan, Yilin Kang

Research Collection School Of Computing and Information Systems

Assistive agents have been used to give advices to the users regarding activities in daily lives. Although adviser bots are getting smarter and gaining more popularity these days they are usually developed and deployed independent from each other. When several agents operate together in the same context, their advices may no longer be effective since they may instead overwhelm or confuse the user if not properly arranged. Only little attentions have been paid to coordinating different agents to give different advices to a user within the same environment. However, aligning the advices on-the-fly with the appropriate presentation timing at the …

Transnfcm: Translation-Based Neural Fashion Compatibility Modeling, Xun Yang, Yunshan Ma, Lizi Liao, Meng Wang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Identifying mix-and-match relationships between fashion items is an urgent task in a fashion e-commerce recommender system. It will significantly enhance user experience and satisfaction. However, due to the challenges of inferring the rich yet complicated set of compatibility patterns in a large e-commerce corpus of fashion items, this task is still underexplored. Inspired by the recent advances in multi-relational knowledge representation learning and deep neural networks, this paper proposes a novel Translation-based Neural Fashion Compatibility Modeling (TransNFCM) framework, which jointly optimizes fashion item embeddings and category-specific complementary relations in a unified space via an end-to-end learning manner. TransNFCM places items …

Send Hardest Problems My Way: Probabilistic Path Prioritization For Hybrid Fuzzing, Lei Zhao, Yue Duan, Jifeng Xuan

Research Collection School Of Computing and Information Systems

Hybrid fuzzing which combines fuzzing and concolic execution has become an advanced technique for software vulnerability detection. Based on the observation that fuzzing and concolic execution are complementary in nature, the state-of-the-art hybrid fuzzing systems deploy ``demand launch'' and ``optimal switch'' strategies. Although these ideas sound intriguing, we point out several fundamental limitations in them, due to oversimplified assumptions. We then propose a novel ``discriminative dispatch'' strategy to better utilize the capability of concolic execution. We design a novel Monte Carlo based probabilistic path prioritization model to quantify each path's difficulty and prioritize them for concolic execution. This model treats …

Security Analysis Of A Large-Scale Concurrent Data Anonymous Batch Verification Scheme For Mobile Healthcare Crowd Sensing, Yinghui Zhang, Jiangang Shu, Ximeng Liu, Jin Li, Dong Zheng

Research Collection School Of Computing and Information Systems

As an important application of the Internet of Things (IoT) technologies, mobile healthcare crowd sensing (MHCS) still has challenging issues, such as privacy protection and efficiency. Quite recently in IEEE Internet of Things Journal (DOI: 10.1109/JIOT.2018.2828463), Liu et al. proposed a large-scale concurrent data anonymous batch verification scheme for mobile healthcare crowd sensing, claiming to provide batch authentication, non-repudiation, and anonymity. However, after a close look at the scheme, we point out that the scheme suffers two types of signature forgery attacks and hence fails to achieve the claimed security properties. In addition, a reasonable and rigorous probability analysis indicates …

Assessing The Effectiveness Of Computer Science Rpps: The Case Of Cafecs, Erin Henrick, Steven Mcgee, Ronald I. Greenberg, Lucia Dettori, Andrew M. Rasmussen, Don Yanek, Dale F. Reed

Computer Science: Faculty Publications and Other Works

Research Practice Partnerships (RPPs) are a relatively

recent development as a potential strategy to address the

complex challenges in computer science education. Consequently,

there is little guidance available for assessing the effectiveness of

RPPs. This paper describes the formative evaluation approach

used to assess the progress of the first year of the formalized RPP,

Chicago Alliance for Equity in Computer Science (CAFE´CS).

This paper contributes to the RPP literature by providing a case

study of how an RPP effectiveness framework can be adapted

and used to inform partnership improvement efforts in computer

science education.

Grand Challenges In Accessible Maps, Jon E. Froehlich, Anke M. Brock, Anat Caspi, Joao Guerreiro, Kotaro Hara, Reuben Kirkham, Johannes Schoning, Benjamin Tannert

Research Collection School Of Computing and Information Systems

In this forum we celebrate research that helps to successfully bring the benefits of computing technologies to children, older adults, people with disabilities, and other populations that are often ignored in the design of mass-marketed products.

Adaptive Cost-Sensitive Online Classification, Peilin Zhao, Yifan Zhang, Min Wu, Steven C. H. Hoi, Mingkui Tan, Junzhou Huang

Research Collection School Of Computing and Information Systems

Cost-Sensitive Online Classification has drawn extensive attention in recent years, where the main approach is to directly online optimize two well-known cost-sensitive metrics: (i) weighted sum of sensitivity and specificity; (ii) weighted misclassification cost. However, previous existing methods only considered first-order information of data stream. It is insufficient in practice, since many recent studies have proved that incorporating second-order information enhances the prediction performance of classification models. Thus, we propose a family of cost-sensitive online classification algorithms with adaptive regularization in this paper. We theoretically analyze the proposed algorithms and empirically validate their effectiveness and properties in extensive experiments. Then, …

Understanding Open Ports In Android Applications: Discovery, Diagnosis, And Security Assessment, Daoyuan Wu, Debin Gao, Rocky K. C. Chang, En He, Eric K. T. Cheng, Robert H. Deng

Research Collection School Of Computing and Information Systems

Open TCP/UDP ports are traditionally used by servers to provide application services, but they are also found in many Android apps. In this paper, we present the first open-port analysis pipeline, covering the discovery, diagnosis, and security assessment, to systematically understand open ports in Android apps and their threats. We design and deploy a novel on-device crowdsourcing app and its server-side analytic engine to continuously monitor open ports in the wild. Over a period of ten months, we have collected over 40 million port monitoring records from 3,293 users in 136 countries worldwide, which allow us to observe the actual …

Cryptocurrency Mining On Mobile As An Alternative Monetization Approach, Nguyen Phan Sinh Huynh, Kenny Choo, Rajesh Krishna Balan, Youngki Lee

Research Collection School Of Computing and Information Systems

Can cryptocurrency mining (crypto-mining) be a practical ad-free monetization approach for mobile app developers? We conducted a lab experiment and a user study with 228 real Android users to investigate different aspects of mobile crypto-mining. In particular, we show that mobile devices have computational resources to spare and that these can be utilized for crypto-mining with minimal impact on the mobile user experience. We also examined the profitability of mobile crypto-mining and its stability as compared to mobile advertising. In many cases, the profit of mining can exceed mobile advertising's. Most importantly, our study shows that the majority (72%) of …

Verifiable Computation Using Re-Randomizable Garbled Circuits, Qingsong Zhao, Qingkai Zeng, Ximeng Liu, Huanliang Xu

Research Collection School Of Computing and Information Systems

Yao's garbled circuit allows a client to outsource a function computation to a server with verifiablity. Unfortunately, the garbled circuit suffers from a one-time usage. The combination of fully homomorphic encryption (FHE) and garbled circuits enables the client and the server to reuse the garbled circuit with multiple inputs (Gennaro et al.). However, there still seems to be a long way to go for improving the efficiency of all known FHE schemes and it need much stronger security assumption. On the other hand, the construction is only proven to be secure in a weaker model where an adversary can not …

Automatic Code Review By Learning The Revision Of Source Code, Shu-Ting Shi, Ming Li, David Lo, Ferdian Thung, Xuan Huo

Research Collection School Of Computing and Information Systems

Code review is the process of manual inspection on the revision of the source code in order to find out whether the revised source code eventually meets the revision requirements. However, manual code review is time-consuming, and automating such the code review process will alleviate the burden of code reviewers and speed up the software maintenance process. To construct the model for automatic code review, the characteristics of the revisions of source code (i.e., the difference between the two pieces of source code) should be properly captured and modeled. Unfortunately, most of the existing techniques can easily model the overall …