Computer Sciences Commons^™

Fast Tracking Of Near-Duplicate Keyframes In Broadcast Domain With Transitivity Propagation, Chong-Wah Ngo, Wan-Lei Zhao, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

The identification of near-duplicate keyframe (NDK) pairs is a useful task for a variety of applications such as news story threading and content-based video search. In this paper, we propose a novel approach for the discovery and tracking of NDK pairs and threads in the broadcast domain. The detection of NDKs in a large data set is a challenging task due to the fact that when the data set increases linearly, the computational cost increases in a quadratic speed, and so does the number of false alarms. This paper explores the symmetric and transitive nature of near-duplicate for the effective …

Design And Analysis Of A Class-Aware Recursive Loop Scheduler For Class-Based Scheduling, Raphael Rom, Moshe Sidi, Hwee-Pink Tan

Research Collection School Of Computing and Information Systems

In this paper, we consider the problem of devising a loop scheduler that allocates slots to users according to their relative weights as smoothly as possible. Instead of the existing notion of smoothness based on balancedness, we propose a variance-based metric which is more intuitive and easier to compute.

We propose a recursive loop scheduler for a class-based scheduling scenario based on an optimal weighted round-robin scheduler. We show that it achieves very good allocation smoothness with almost no degradation in intra-class fairness. In addition, we also demonstrate the equivalence between our proposed metric and the balancedness-based metric.

Natural Document Clustering By Clique Percolation In Random Graphs, Wei Gao, Kam-Fai Wong

Research Collection School Of Computing and Information Systems

Document clustering techniques mostly depend on models that impose explicit and/or implicit priori assumptions as to the number, size, disjunction characteristics of clusters, and/or the probability distribution of clustered data. As a result, the clustering effects tend to be unnatural and stray away more or less from the intrinsic grouping nature among the documents in a corpus. We propose a novel graph-theoretic technique called Clique Percolation Clustering (CPC). It models clustering as a process of enumerating adjacent maximal cliques in a random graph that unveils inherent structure of the underlying data, in which we unleash the commonly practiced constraints in …

Viz: A Visual Analysis Suite For Explaining Local Search Behavior, Steven Halim, Roland H. C. Yap, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

NP-hard combinatorial optimization problems are common in real life. Due to their intractability, local search algorithms are often used to solve such problems. Since these algorithms are heuristic-based, it is hard to understand how to improve or tune them. We propose an interactive visualization tool, VIZ, meant for understanding the behavior of local search. VIZ uses animation of abstract search trajectories with other visualizations which are also animated in a VCR-like fashion to graphically playback the algorithm behavior. It combines generic visualizations applicable on arbitrary algorithms with algorithm and problem specific visualizations. We use a variety of techniques such as …

Two-Instant Reallocation In Two-Echelon Spare Parts Inventory Systems, Huawei Song, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

In this paper, we study the problem of deciding when and how to perform reallocation of existing spare parts in a multi-echelon reparable item inventory system. We present a mathematical model that solves the problem when there are two reallocation instants, in response to the open challenge post by Cao and Silver(2005) to consider two or more possible reallocations within a replenishment cycle.

Audio Similarity Measure By Graph Modeling And Matching, Yuxin Peng, Chong-Wah Ngo, Cuihua Fang, Xiaoou Chen, Jianguo Xiao

Research Collection School Of Computing and Information Systems

This paper proposes a new approach for the similarity measure and ranking of audio clips by graph modeling and matching. Instead of using frame-based or salient-based features to measure the acoustical similarity of audio clips, segment-based similarity is proposed. The novelty of our approach lies in two aspects: segment-based representation, and the similarity measure and ranking based on four kinds of similarity factors. In segmentbased representation, segments not only capture the change property of audio clip, but also keep and present the change relation and temporal order of audio features. In the similarity measure and ranking, four kinds of similarity …

Continuous Nearest Neighbor Monitoring In Road Networks, Kyriakos Mouratidis, Man Lung Yiu, Dimitris Papadias, Nikos Mamoulis

Research Collection School Of Computing and Information Systems

Recent research has focused on continuous monitoring of nearest neighbors (NN) in highly dynamic scenarios, where the queries and the data objects move frequently and arbitrarily. All existing methods, however, assume the Euclidean distance metric. In this paper we study k-NN monitoring in road networks, where the distance between a query and a data object is determined by the length of the shortest path connecting them. We propose two methods that can handle arbitrary object and query moving patterns, as well as °uctuations of edge weights. The ¯rst one maintains the query results by processing only updates that may invalidate …

Rights Protection For Data Cubes, Jie Guo, Yingjiu Li, Robert H. Deng, Kefei Chen

Research Collection School Of Computing and Information Systems

We propose a rights protection scheme for data cubes. The scheme embeds ownership information by modifying a set of selected cell values. The embedded message will not affect the usefulness of data cubes in the sense that the sum queries at any aggregation level are not affected. At the same time, the errors introduced to individual cell values are under control. The embedded message can be detected with a high probability even in the presence of typical data cube attacks. The proposed scheme can thus be used for protecting data cubes from piracy in an open, distributed environment.

Practical Private Data Matching Deterrent To Spoofing Attacks, Yanjiang Yang, Robert H. Deng, Feng Bao

Research Collection School Of Computing and Information Systems

Private data matching between the data sets of two potentially distrusted parties has a wide range of applications. However, existing solutions have substantial weaknesses and do not meet the needs of many practical application scenarios. In particular, practical private data matching applications often require discouraging the matching parties from spoofing their private inputs. In this paper, we address this challenge by forcing the matching parties to "escrow" the data they use for matching to an auditorial agent, and in the "after-the-fact" period, they undertake the liability to attest the genuineness of the escrowed data.

Masking Page Reference Patterns In Encryption Databases On Untrusted Storage, Xi Ma, Hwee Hwa Pang, Kian-Lee Tan

Research Collection School Of Computing and Information Systems

To support ubiquitous computing, the underlying data have to be persistent and available anywhere-anytime. The data thus have to migrate from devices that are local to individual computers, to shared storage volumes that are accessible over open network. This potentially exposes the data to heightened security risks. In particular, the activity on a database exhibits regular page reference patterns that could help attackers learn logical links among physical pages and then launch additional attacks. We propose two countermeasures to mitigate the risk of attacks initiated through analyzing the shared storage server’s activity for those page patterns. The first countermeasure relocates …

Three Architectures For Trusted Data Dissemination In Edge Computing, Shen-Tat Goh, Hwee Hwa Pang, Robert H. Deng, Feng Bao

Research Collection School Of Computing and Information Systems

Edge computing pushes application logic and the underlying data to the edge of the network, with the aim of improving availability and scalability. As the edge servers are not necessarily secure, there must be provisions for users to validate the results—that values in the result tuples are not tampered with, that no qualifying data are left out, that no spurious tuples are introduced, and that a query result is not actually the output from a different query. This paper aims to address the challenges of ensuring data integrity in edge computing. We study three schemes that enable users to check …

Cuhk At Imageclef 2005: Cross-Language And Cross Media Image Retrieval, Steven Hoi, Jianke Zhu, Michael R. Lyu

Research Collection School Of Computing and Information Systems

In this paper, we describe our studies of cross-language and cross-media image retrieval at the ImageCLEF 2005. This is the first participation of our CUHK (The Chinese University of Hong Kong) group at ImageCLEF. The task in which we participated is the “bilingual ad hoc retrieval” task. There are three major focuses and contributions in our participation. The first is the empirical evaluation of language models and smoothing strategies for cross-language image retrieval. The second is the evaluation of cross-media image retrieval, i.e., combining text and visual contents for image retrieval. The last is the evaluation of bilingual image retrieval …

Wireless Indoor Positioning System With Enhanced Nearest Neighbors In Signal Space Algorithm, Quang Tran, Juki Wirawan Tantra, Ah-Hwee Tan, Ah-Hwee Tan, Kin-Choong Yow, Dongyu Qiu

Research Collection School Of Computing and Information Systems

With the rapid development and wide deployment of wireless Local Area Networks (WLANs), WLAN-based positioning system employing signal-strength-based technique has become an attractive solution for location estimation in indoor environment. In recent years, a number of such systems has been presented, and most of the systems use the common Nearest Neighbor in Signal Space (NNSS) algorithm. In this paper, we propose an enhancement to the NNSS algorithm. We analyze the enhancement to show its effectiveness. The performance of the enhanced NNSS algorithm is evaluated with different values of the parameters. Based on the performance evaluation and analysis, we recommend some …

Minimum Latency Broadcasting In Multi-Radio Multi-Channel Multi-Rate Wireless Meshes, Junaid Qadir, Archan Misra, Chun Tung Chou

Research Collection School Of Computing and Information Systems

We address the problem of minimizing the worst-case broadcast delay in multi-radio multi-channel multi-rate (MR2-MC) wireless mesh networks (WMN). The problem of 'efficient' broadcast in such networks is especially challenging due to the numerous interrelated decisions that have to be made. The multi-rate transmission capability of WMN nodes, interference between wireless transmissions, and the hardness of optimal channel assignment adds complexity to our considered problem. We present four heuristic algorithms to solve the minimum latency broadcast problem for such settings and show that the 'best' performing algorithms usually adapt themselves to the available radio interfaces and channels. We also study …

Mining Rdf Metadata For Generalized Association Rules, Tao Jiang, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

In this paper, we present a novel frequent generalized pattern mining algorithm, called GP-Close, for mining generalized associations from RDF metadata. To solve the over-generalization problem encountered by existing methods, GP-Close employs the notion of generalization closure for systematic over-generalization reduction. Empirical experiments conducted on real world RDF data sets show that our method can substantially reduce pattern redundancy and perform much better than the original generalized association rule mining algorithm Cumulate in term of time efficiency.

Disclosure Analysis For Two-Way Contingency Tables, Haibing Lu, Yingjiu Li, Xintao Wu

Research Collection School Of Computing and Information Systems

Disclosure analysis in two-way contingency tables is important in categorical data analysis. The disclosure analysis concerns whether a data snooper can infer any protected cell values, which contain privacy sensitive information, from available marginal totals (i.e., row sums and column sums) in a two-way contingency table. Previous research has been targeted on this problem from various perspectives. However, there is a lack of systematic definitions on the disclosure of cell values. Also, no previous study has been focused on the distribution of the cells that are subject to various types of disclosure. In this paper, we define four types of …

Discovering Image-Text Associations For Cross-Media Web Information Fusion, Tao Jiang, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

The diverse and distributed nature of the information published on the World Wide Web has made it difficult to collate and track information related to specific topics. Whereas most existing work on web information fusion has focused on multiple document summarization, this paper presents a novel approach for discovering associations between images and text segments, which subsequently can be used to support cross-media web content summarization. Specifically, we employ a similarity-based multilingual retrieval model and adopt a vague transformation technique for measuring the information similarity between visual features and textual features. The experimental results on a terrorist domain document set …

Multi-Learner Based Recursive Supervised Training, Laxmi R. Iyer, Kiruthika Ramanathan, Sheng-Uei Guan

Research Collection School Of Computing and Information Systems

In this paper, we propose the multi-learner based recursive supervised training (MLRT) algorithm, which uses the existing framework of recursive task decomposition, by training the entire dataset, picking out the best learnt patterns, and then repeating the process with the remaining patterns. Instead of having a single learner to classify all datasets during each recursion, an appropriate learner is chosen from a set of three learners, based on the subset of data being trained, thereby avoiding the time overhead associated with the genetic algorithm learner utilized in previous approaches. In this way MLRT seeks to identify the inherent characteristics of …

Bias And Controversy: Beyond The Statistical Deviation, Hady W. Lauw, Ee Peng Lim, Ke Wang

Research Collection School Of Computing and Information Systems

In this paper, we investigate how deviation in evaluation activities may reveal bias on the part of reviewers and controversy on the part of evaluated objects. We focus on a 'data-centric approach' where the evaluation data is assumed to represent the ground truth'. The standard statistical approaches take evaluation and deviation at face value. We argue that attention should be paid to the subjectivity of evaluation, judging the evaluation score not just on 'what is being said' (deviation), but also on 'who says it' (reviewer) as well as on 'whom it is said about' (object). Furthermore, we observe that bias …

Architectural Control And Value Migration In Platform Industries, C. Jason Woodard

Research Collection School Of Computing and Information Systems

carry some pre-computation information of each region. We also propose multiple client-side algorithms to facilitate the processing of

A Hybrid Architecture Combining Reactive Plan Execution And Reactive Learning, Samin Karim, Liz Sonenberg, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Developing software agents has been complicated by the problem of how knowledge should be represented and used. Many researchers have identified that agents need not require the use of complex representations, but in many cases suffice to use “the world” as their representation. However, the problem of introspection, both by the agents themselves and by (human) domain experts, requires a knowledge representation with a higher level of abstraction that is more ‘understandable’. Learning and adaptation in agents has traditionally required knowledge to be represented at an arbitrary, low-level of abstraction. We seek to create an agent that has the capability …

An Energy-Efficient And Access Latency Optimized Indexing Scheme For Wireless Data Broadcast, Yuxia Yao, Xueyan Tang, Ee Peng Lim, Aixin Sun

Research Collection School Of Computing and Information Systems

Data broadcast is an attractive data dissemination method in mobile environments. To improve energy efficiency, existing air indexing schemes for data broadcast have focused on reducing tuning time only, i.e., the duration that a mobile client stays active in data accesses. On the other hand, existing broadcast scheduling schemes have aimed at reducing access latency through nonflat data broadcast to improve responsiveness only. Not much work has addressed the energy efficiency and responsiveness issues concurrently. This paper proposes an energy-efficient indexing scheme called MHash that optimizes tuning time and access latency in an integrated fashion. MHash reduces tuning time by …

Collaborative Image Retrieval Via Regularized Metric Learning, Luo Si, Rong Jin, Steven C. H. Hoi, Michael R. Lyu

Research Collection School Of Computing and Information Systems

In content-based image retrieval (CBIR), relevant images are identified based on their similarities to query images. Most CBIR algorithms are hindered by the semantic gap between the low-level image features used for computing image similarity and the high-level semantic concepts conveyed in images. One way to reduce the semantic gap is to utilize the log data of users' feedback that has been collected by CBIR systems in history, which is also called “collaborative image retrieval.” In this paper, we present a novel metric learning approach, named “regularized metric learning,” for collaborative image retrieval, which learns a distance metric by exploring …

Learning The Unified Kernel Machines For Classification, Steven C. H. Hoi, Michael R. Lyu, Edward Y. Chang

Research Collection School Of Computing and Information Systems

Kernel machines have been shown as the state-of-the-art learning techniques for classification. In this paper, we propose a novel general framework of learning the Unified Kernel Machines (UKM) from both labeled and unlabeled data. Our proposed framework integrates supervised learning, semi-supervised kernel learning, and active learning in a unified solution. In the suggested framework, we particularly focus our attention on designing a new semi-supervised kernel learning method, i.e., Spectral Kernel Learning (SKL), which is built on the principles of kernel target alignment and unsupervised kernel design. Our algorithm is related to an equivalent quadratic programming problem that can be efficiently …

Prediction-Based Gesture Detection In Lecture Videos By Combining Visual, Speech And Electronic Slides, Feng Wang, Chong-Wah Ngo, Ting-Chuen Pong

Research Collection School Of Computing and Information Systems

This paper presents an efficient algorithm for gesture detection in lecture videos by combining visual, speech and electronic slides. Besides accuracy, response time is also considered to cope with the efficiency requirements of real-time applications. Candidate gestures are first detected by visual cue. Then we modifity HMM models for complete gestures to predict and recognize incomplete gestures before the whole gestures paths are observed. Gesture recognition is used to verify the results of gesture detection. The relations between visual, speech and slides are analyzed. The correspondence between speech and gesture is employed to improve the accuracy and the responsiveness of …

Ontosearch: A Full-Text Search Engine For The Semantic Web, Xing Jiang, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

OntoSearch, a full-text search engine that exploits ontological knowledge for document retrieval, is presented in this paper. Different from other ontology based search engines, OntoSearch does not require a user to specify the associated concepts of his/her queries. Domain ontology in OntoSearch is in the form of a semantic network. Given a keyword based query, OntoSearch infers the related concepts through a spreading activation process in the domain ontology. To provide personalized information access, we further develop algorithms to learn and exploit user ontology model based on a customized view of the domain ontology. The proposed system has been applied …

Authenticating Multi-Dimensional Query Results In Data Publishing, Weiwei Cheng, Hwee Hwa Pang, Kian-Lee Tan

Research Collection School Of Computing and Information Systems

In data publishing, the owner delegates the role of satisfying user queries to a third-party publisher. As the publisher may be untrusted or susceptible to attacks, it could produce incorrect query results. This paper introduces a mechanism for users to verify that their query answers on a multi-dimensional dataset are correct, in the sense of being complete (i.e., no qualifying data points are omitted) and authentic (i.e., all the result values originated from the owner). Our approach is to add authentication information into a spatial data structure, by constructing certified chains on the points within each partition, as well as …

A Novel Privacy Preserving Authentication And Access Control Scheme For Pervasive Computing Environments, K. Ren, Wenjing Lou, K. Kim, Robert H. Deng

Research Collection School Of Computing and Information Systems

Privacy and security are two important but seemingly contradictory objectives in a pervasive computing environment (PCE). On one hand, service providers want to authenticate legitimate users and make sure they are accessing their authorized services in a legal way. On the other hand, users want to maintain the necessary privacy without being tracked down for wherever they are and whatever they are doing. In this paper, a novel privacy preserving authentication and access control scheme to secure the interactions between mobile users and services in PCEs is proposed. The proposed scheme seamlessly integrates two underlying cryptographic primitives, namely blind signature …

Extraction Of Coherent Relevant Passages Using Hidden Markov Models, Jing Jiang, Chengxiang Zhai

Research Collection School Of Computing and Information Systems

In information retrieval, retrieving relevant passages, as opposed to whole documents, not only directly benefits the end user by filtering out the irrelevant information within a long relevant document, but also improves retrieval accuracy in general. A critical problem in passage retrieval is to extract coherent relevant passages accurately from a document, which we refer to as passage extraction. While much work has been done on passage retrieval, the passage extraction problem has not been seriously studied. Most existing work tends to rely on presegmenting documents into fixed-length passages which are unlikely optimal because the length of a relevant passage …

Crossing The Chasm: The Xid Technologies Story, Arcot Desai Narasimhalu, Roberto Mariani

Research Collection School Of Computing and Information Systems

XID Technologies is a face processing start up company built initially around a disruptive face recognition technology. The technology innovation came from Kent Ridge Digital Labs, a publicly funded software research laboratory in Singapore. Face recognition is the least intrusive and harmless among the various biometric solutions available in the market. The basic approach to human face recognition is to identify a robust feature set that was unique enough to differentiate amongst the many millions of human faces that the system was required to verify. The technology innovation used by XID framed the problem differently and thereby overcame the challenges …