Computer Sciences Commons^™

Bootbandit: A Macos Bootloader Attack, Armen Boursalian

Master's Projects

Full disk encryption (FDE) is used to protect a computer system against data theft by physical access. If a laptop or hard disk drive protected with FDE is stolen or lost, the data remains unreadable without the encryption key. To foil this defense, an intruder can gain physical access to a computer system in a so-called “evil maid” attack, install malware in the boot (pre-operating system) environment, and use the malware to intercept the victim’s password. Such an attack relies on the fact that the system is in a vulnerable state before booting into the operating system. In this paper, …

Cache Management And Load Balancing For 5g Cloud Radio Access Networks, Chin Tsai

Master's Projects

Cloud radio access network (CRAN) has been proposed for 5G mobile networks. The benefit of a CRAN includes better scalability, flexibility, and performance. The paper introduces a cache management algorithm for a baseband unit of CRAN and load balancing algorithms for virtual machines load within the CRAN. The proposed scheme, exponential decay (EXD) with analytical hierarchy process (AHP), increases hit rate and reduces network traffic. The scheme also provides preferential services for users with a higher service level agreement (SLA). Finally, the experiment shows the proposed load balancing algorithm can reduce the virtual machines’ (VM) queue size and wait time.

Cache Management Schemes For User Equipment Contexts In 5th Generation Cloud Radio Access Networks, Gurpreet Kaur

Master's Projects

Advances in cellular network technology continue to develop to address increasing demands from the growing number of devices resulting from the Internet of Things, or IoT. IoT has brought forth countless new equipment competing for service on cellular networks. The latest in cellular technology is 5th Generation Cloud Radio Access Networks, or 5G C-RAN, which consists of an architectural design created specifically to meet novel and necessary requirements for better performance, reduced latency of service, and scalability. As part of this design is the inclusion of a virtual cache, there is a necessity for useful cache management schemes and protocols, …

Time-Efficient Hybrid Approach For Facial Expression Recognition, Roshni Velluva Puthanidam

Master's Projects

Facial expression recognition is an emerging research area for improving human and computer interaction. This research plays a significant role in the field of social communication, commercial enterprise, law enforcement, and other computer interactions. In this paper, we propose a time-efficient hybrid design for facial expression recognition, combining image pre-processing steps and different Convolutional Neural Network (CNN) structures providing better accuracy and greatly improved training time. We are predicting seven basic emotions of human faces: sadness, happiness, disgust, anger, fear, surprise and neutral. The model performs well regarding challenging facial expression recognition where the emotion expressed could be one of …

“Bluff” With Ai, Tina Philip

Master's Projects

The goal of this project is to build multiple agents for the game Bluff and to conduct experiments as to which performs better. Bluff is a multi-player, non-deterministic card game where players try to get rid of all the cards in their hand. The process of bluffing involves making a move such that it misleads the opponent and thus prove to be of advantage to the player. The strategic complexity in the game arises due to the imperfect or hidden information which means that certain relevant details about the game are unknown to the players. Multiple agents followed different strategies …

A Scrabble Artificial Intelligence Game, Priyatha Joji Abraham

Master's Projects

Computer AI players have already surpassed human opponents in competitive Scrabble, however, defeating a Computer AI opponent is complex and demands efficient heuristics. The primary objective of this project is to build two intelligent AI players from scr atch for the Scrabble cross - board puzzle game having different move generation heuristics and endgame strategies to evaluate their performance based on various benchmarks like winning criteria, quality of moves, and time consumption. The first AI selected is the most popular Scrabble AI, Maven. It generates a three - ply look - ahead simulation to evaluate the most promising candidate move …

Improve And Implement An Open Source Question Answering System, Salil Shenoy

Master's Projects

A question answer system takes queries from the user in natural language and returns a short concise answer which best fits the response to the question. This report discusses the integration and implementation of question answer systems for English and Hindi as part of the open source search engine Yioop. We have implemented a question answer system for English and Hindi, keeping in mind users who use these languages as their primary language. The user should be able to query a set of documents and should get the answers in the same language. English and Hindi are very different when …

Artificial Intelligence Research In Singapore: Assisting The Development Of A Smart Nation, Pradeep Varakantham, Bo An, Bryan Low, Jie Zhang

Research Collection School Of Computing and Information Systems

Artificial Intelligence (AI) research in Singapore is focused on accelerating the country’s development into a Smart Nation. Specifically, AI has been employed extensively in either augmenting the intelligence of humans or in developing automated methods and systems to improve quality of life in Singapore.

Delving Into Salient Object Subitizing And Detection, Shengfeng He, Jianbo Jiao, Xiaodan Zhang, Guoqiang Han, Rynson W.H Lau

Research Collection School Of Computing and Information Systems

Subitizing (i.e., instant judgement on the number) and detection of salient objects are human inborn abilities. These two tasks influence each other in the human visual system. In this paper, we delve into the complementarity of these two tasks. We propose a multi-task deep neural network with weight prediction for salient object detection, where the parameters of an adaptive weight layer are dynamically determined by an auxiliary subitizing network. The numerical representation of salient objects is therefore embedded into the spatial representation. The proposed joint network can be trained end-to-end using backpropagation. Experiments show the proposed multi-task network outperforms existing …

Efficient And Robust Emergence Of Norms Through Heuristic Collective Learning, Jianye Hao, Jun Sun, Guangyong Chen, Zan Wang, Chao Yu, Zhong Ming

Research Collection School Of Computing and Information Systems

In multiagent systems, social norms serves as an important technique in regulating agents’ behaviors to ensure effective coordination among agents without a centralized controlling mechanism. In such a distributed environment, it is important to investigate how a desirable social norm can be synthesized in a bottom-up manner among agents through repeated local interactions and learning techniques. In this article, we propose two novel learning strategies under the collective learning framework, collective learning EV-l and collective learning EV-g, to efficiently facilitate the emergence of social norms. Extensive simulations results show that both learning strategies can support the emergence of desirable …

Tensor Factorization For Low-Rank Tensor Completion, Pan Zhou, Canyi Lu, Zhouchen Lin, Chao Zhang

Research Collection School Of Computing and Information Systems

Recently, a tensor nuclear norm (TNN) based method [1] was proposed to solve the tensor completion problem, which has achieved state-of-the-art performance on image and video inpainting tasks. However, it requires computing tensor singular value decomposition (t-SVD), which costs much computation and thus cannot efficiently handle tensor data, due to its natural large scale. Motivated by TNN, we propose a novel low-rank tensor factorization method for efficiently solving the 3-way tensor completion problem. Our method preserves the lowrank structure of a tensor by factorizing it into the product of two tensors of smaller sizes. In the optimization process, our method …

A Validated Set Of Smells In Model-View-Controller Architectures, Maurício Aniche, Gabriele Bavota, Christoph Treude, Arie Van Deursen, Marco Aurélio Gerosa

Research Collection School Of Computing and Information Systems

Code smells are symptoms of poor design and implementation choices that may hinder code comprehension, and possibly increase change-and defect-proneness. A vast catalogue of smells has been defined in the literature, and it includes smells that can be found in any kind of system (e.g., God Classes), regardless of their architecture. On the other hand, software systems adopting specific architectures (e.g., the Model-View-Controller pattern) can be also affected by other types of poor practices. We surveyed and interviewed 53 MVC developers to collect bad practices to avoid while working on Web MVC applications. Then, we followed an open coding procedure …

Interactive Visual Analytics Application For Spatiotemporal Movement Data Vast Challenge 2017 Mini-Challenge 1: Award For Actionable And Detailed Analysis, Yifei Guan, Tin Seong Kam

Research Collection School Of Computing and Information Systems

The Visual Analytics Science and Technology (VAST) Challenge 2017 Mini-Challenge 1 dataset mirrored the challenging scenarios in analysing large spatiotemporal movement tracking datasets. The datasets provided contains a 13-month movement data generated by five types of sensors, for six types of vehicles passing through the Boonsong Lekagul Nature Preserve. We present an application developed with the market leading visualisation software Tableau to provide an interactive visual analysis of the multi-dimensional spatiotemporal datasets. Our interactive application allows the user to perform an interactive analysis to observe movement patterns, study vehicle trajectories and identify movement anomalies while allowing them to customise the …

Program Inspection And Testing Techniques For Code Clones And Refactorings In Evolving Software, Zhiyuan Chen

Student Work

Developers often perform copy-and-paste activities. This practice causes the similar code fragment (aka code clones) to be scattered throughout a code base. Refactoring for clone removal is beneficial, preventing clones from having negative effects on software quality, such as hidden bug propagation and unintentional inconsistent changes. However, recent research has provided evidence that factoring out clones does not always reduce the risk of introducing defects, and it is often difficult or impossible to remove clones using standard refactoring techniques. To investigate which or how clones can be refactored, developers typically spend a significant amount of their time managing individual clone …

Sol: A Library For Scalable Online Learning Algorithms, Yue Wu, Steven C. H. Hoi, Chenghao Liu, Jing Lu, Doyen Sahoo, Nenghai Yu

Research Collection School Of Computing and Information Systems

SOL is an open-source library for scalable online learning with high-dimensional data. The library provides a family of regular and sparse online learning algorithms for large-scale classification tasks with high efficiency, scalability, portability, and extensibility. We provide easy-to-use command-line tools, python wrappers and library calls for users and developers, and comprehensive documents for both beginners and advanced users. SOL is not only a machine learning toolbox, but also a comprehensive experimental platform for online learning research. Experiments demonstrate that SOL is highly efficient and scalable for large-scale learning with high-dimensional data.

Tagscan: Simultaneous Target Imaging And Material Identification With Commodity Rfid Devices, Ju Wang, Jie Xiong, Xiaojiang Chen, Hongbo Jiang, Rajesh Krishna Balan, Dingyi Fang

Research Collection School Of Computing and Information Systems

Target imaging and material identification play an important role in many real-life applications. This paper introduces TagScan, a system that can identify the material type and image the horizontal cut of a target simultaneously with cheap commercial of-the-shelf (COTS) RFID devices. The key intuition is that different materials and target sizes cause different amounts of phase and RSS (Received Signal Strength) changes when radio frequency (RF) signal penetrates through the target. Multiple challenges need to be addressed before we can turn the idea into a functional system including (i) indoor environments exhibit rich multipath which breaks the linear relationship between …

Which Packages Would Be Affected By This Bug Report?, Qiao Huang, David Lo, Xin Xia, Qingye Wang, Shanping Li

Research Collection School Of Computing and Information Systems

A large project (e.g., Ubuntu) usually contains a large number of software packages. Sometimes the same bug report in such project would affect multiple packages, and developers of different packages need to collaborate with one another to fix the bug. Unfortunately, the total number of packages involved in a project like Ubuntu is relatively large, which makes it time-consuming to manually identify packages that are affected by a bug report. In this paper, we propose an approach named PkgRec that consists of 2 components: a name matching component and an ensemble learning component. In the name matching component, we assign …

Semantic Reasoning In Zero Example Video Event Retrieval, M. H. T. De Boer, Yi-Jie Lu, Hao Zhang, Klamer Schutte, Chong-Wah Ngo, Wessel Kraaij

Research Collection School Of Computing and Information Systems

Searching in digital video data for high-level events, such as a parade or a car accident, is challenging when the query is textual and lacks visual example images or videos. Current research in deep neural networks is highly beneficial for the retrieval of high-level events using visual examples, but without examples it is still hard to (1) determine which concepts are useful to pre-train (Vocabulary challenge) and (2) which pre-trained concept detectors are relevant for a certain unseen high-level event (Concept Selection challenge). In our article, we present our Semantic Event Retrieval Systemwhich (1) shows the importance of high-level concepts …

On Negative Results When Using Sentiment Analysis Tools For Software Engineering Research, Robbert Jongeling, Proshanta Sarkar, Subhajit Datta, Alexander Serebrenik

Research Collection School Of Computing and Information Systems

Recent years have seen an increasing attention to social aspects of software engineering, including studies of emotions and sentiments experienced and expressed by the software developers. Most of these studies reuse existing sentiment analysis tools such as SentiStrength and NLTK. However, these tools have been trained on product reviews and movie reviews and, therefore, their results might not be applicable in the software engineering domain. In this paper we study whether the sentiment analysis tools agree with the sentiment recognized by human evaluators (as reported in an earlier study) as well as with each other. Furthermore, we evaluate the impact …

Feature Space Augmentation: Improving Prediction Accuracy Of Classical Problems In Cognitive Science And Computer Vison, Piyush Saxena

Dissertations (1934 -)

The prediction accuracy in many classical problems across multiple domains has seen a rise since computational tools such as multi-layer neural nets and complex machine learning algorithms have become widely accessible to the research community. In this research, we take a step back and examine the feature space in two problems from very different domains. We show that novel augmentation to the feature space yields higher performance. Emotion Recognition in Adults from a Control Group: The objective is to quantify the emotional state of an individual at any time using data collected by wearable sensors. We define emotional state as …

Vungle Inc. Improves Monetization Using Big-Data Analytics, Bert De Reyck, Ioannis Fragkos, Yael Gruksha-Cockayne, Casey Lichtendahl, Hammond Guerin, Andre Kritzer

Research Collection Lee Kong Chian School Of Business

The advent of big data has created opportunities for firms to customize their products and services to unprecedented levels of granularity. Using big data to personalize an offering in real time, however, remains a major challenge. In the mobile advertising industry, once a customer enters the network, an ad-serving decision must be made in a matter of milliseconds. In this work, we describe the design and implementation of an ad-serving algorithm that incorporates machine-learning methods to make personalized ad-serving decisions within milliseconds. We developed this algorithm for Vungle Inc., one of the largest global mobile ad networks. Our approach also …

Efficient Machine Learning Approach For Optimizing Scientific Computing Applications On Emerging Hpc Architectures, Kamesh Arumugam Karunanithi

Computer Science Theses & Dissertations

Efficient parallel implementations of scientific applications on multi-core CPUs with accelerators such as GPUs and Xeon Phis is challenging. This requires - exploiting the data parallel architecture of the accelerator along with the vector pipelines of modern x86 CPU architectures, load balancing, and efficient memory transfer between different devices. It is relatively easy to meet these requirements for highly-structured scientific applications. In contrast, a number of scientific and engineering applications are unstructured. Getting performance on accelerators for these applications is extremely challenging because many of these applications employ irregular algorithms which exhibit data-dependent control-flow and irregular memory accesses. Furthermore, these …

Modeling Energy Consumption Of High-Performance Applications On Heterogeneous Computing Platforms, Gary D. Lawson Jr.

Computational Modeling & Simulation Engineering Theses & Dissertations

Achieving Exascale computing is one of the current leading challenges in High Performance Computing (HPC). Obtaining this next level of performance will allow more complex simulations to be run on larger datasets and offer researchers better tools for data processing and analysis. In the dawn of Big Data, the need for supercomputers will only increase. However, these systems are costly to maintain because power is expensive. Thus, a better understanding of power and energy consumption is required such that future hardware can benefit.

Available power models accurately capture the relationship to the number of cores and clock-rate, however the relationship …

Sensys: A Smartphone-Based Framework For Its Applications, Abdulla Ahmed Alasaadi

Computer Science Theses & Dissertations

Intelligent transportation systems (ITS) use different methods to collect and process traffic data. Conventional techniques suffer from different challenges, like the high installation and maintenance cost, connectivity and communication problems, and the limited set of data. The recent massive spread of smartphones among drivers encouraged the ITS community to use them to solve ITS challenges.

Using smartphones in ITS is gaining an increasing interest among researchers and developers. Typically, the set of sensors that comes with smartphones is utilized to develop tools and services in order to enhance safety and driving experience. GPS, cameras, Bluetooth, inertial sensors and other embedded …

Every Step You Take, I’Ll Be Watching You: Practical Stepauth-Entication Of Rfid Paths, Kai Bu, Yingjiu Li

Research Collection School Of Computing and Information Systems

Path authentication thwarts counterfeits in RFID-based supply chains. Its motivation is that tagged products taking invalid paths are likely faked and injected by adversaries at certain supply chain partners/steps. Existing solutions are path-grained in that they simply regard a product as genuine if it takes any valid path. Furthermore, they enforce distributed authentication by offloading the sets of valid paths to some or all steps from a centralized issuer. This not only imposes network and storage overhead but also leaks transaction privacy. We present StepAuth, the first step-grained path authentication protocol that is practically efficient for authenticating products with strict …

Every Step You Take, I’Ll Be Watching You: Practical Stepauth-Entication Of Rfid Paths, Kai Bu, Yingjiu Li

Research Collection School Of Computing and Information Systems

Path authentication thwarts counterfeits in RFID-based supply chains. Its motivation is that tagged products taking invalid paths are likely faked and injected by adversaries at certain supply chain partners/steps. Existing solutions are path-grained in that they simply regard a product as genuine if it takes any valid path. Furthermore, they enforce distributed authentication by offloading the sets of valid paths to some or all steps from a centralized issuer. This not only imposes network and storage overhead but also leaks transaction privacy. We present StepAuth, the first step-grained path authentication protocol that is practically efficient for authenticating products with strict …

Target Material Identification With Commodity Rfid Devices, Xinyi Li, Chao Feng, Nana Ding, Ju Wang, Jie Xiong, Yuhui Ren, Xiaojiang Chen, Dingyi Fang

Research Collection School Of Computing and Information Systems

Target material identification plays an important role in many reallife applications. This paper introduces a system that can identify the material type with cheap commercial off-the-shelf (COTS) RFID devices. The key intuition is that different materials cause different amounts of phase and RSS (Received Signal Strength) changes when radio frequency (RF) signal penetrates through the target. However, without knowing either material type, trying to obtain the information is challenging. We propose a method to address this challenge and evaluate the method's performance in real-world environment. The results show that we achieve higher than 94% material identification accuracies for 10 liquids …

O2o Service Composition With Social Collaboration, Wenyi Qian, Xin Peng, Jun Sun, Yijun Yu, Bashar Nuseibeh, Wenyun Zhao

Research Collection School Of Computing and Information Systems

In Online-to-Offline (O2O) commerce, customer services may need to be composed from online and offline services. Such composition is challenging, as it requires effective selection of appropriate services that, in turn, support optimal combination of both online and offline services. In this paper, we address this challenge by proposing an approach to O2O service composition which combines offline route planning and social collaboration to optimize service selection. We frame general O2O service composition problems using timed automata and propose an optimization procedure that incorporates: (1) a Markov Chain Monte Carlo (MCMC) algorithm to stochastically select a concrete composite service, and …

Spatio-Temporal Analysis And Prediction Of Cellular Traffic In Metropolis, Xu Wang, Zimu Zhou, Zheng Yang, Yunhao Liu, Chunyi Peng

Research Collection School Of Computing and Information Systems

Understanding and predicting cellular traffic at large-scale and fine-granularity is beneficial and valuable to mobile users, wireless carriers and city authorities. Predicting cellular traffic in modern metropolis is particularly challenging because of the tremendous temporal and spatial dynamics introduced by diverse user Internet behaviours and frequent user mobility citywide. In this paper, we characterize and investigate the root causes of such dynamics in cellular traffic through a big cellular usage dataset covering 1.5 million users and 5,929 cell towers in a major city of China. We reveal intensive spatio-temporal dependency even among distant cell towers, which is largely overlooked in …

Benchmarking Single-Image Reflection Removal Algorithms, Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, Alex C. Kot

Research Collection School Of Computing and Information Systems

Removing undesired reflections from a photo taken in front of a glass is of great importance for enhancing the efficiency of visual computing systems. Various approaches have been proposed and shown to be visually plausible on small datasets collected by their authors. A quantitative comparison of existing approaches using the same dataset has never been conducted due to the lack of suitable benchmark data with ground truth. This paper presents the first captured Single-image Reflection Removal dataset `SIR 2 ' with 40 controlled and 100 wild scenes, ground truth of background and reflection. For each controlled scene, we further provide …