Open Access. Powered by Scholars. Published by Universities.®

Physical Sciences and Mathematics Commons™

Open Access. Powered by Scholars. Published by Universities.®

Research Collection School Of Computing and Information Systems

Computer Engineering

2012

Articles 1 - 15 of 15

Full-Text Articles in Physical Sciences and Mathematics

Action Disambiguation Analysis Using Normalized Google-Like Distance Correlogram, Qianru Sun, Hong Liu Nov 2012

Action Disambiguation Analysis Using Normalized Google-Like Distance Correlogram, Qianru Sun, Hong Liu

Research Collection School Of Computing and Information Systems

Classifying realistic human actions in video remains challenging for existing intro-variability and inter-ambiguity in action classes. Recently, Spatial-Temporal Interest Point (STIP) based local features have shown great promise in complex action analysis. However, these methods have the limitation that they typically focus on Bag-of-Words (BoW) algorithm, which can hardly discriminate actions’ ambiguity due to ignoring of spatial-temporal occurrence relations of visual words. In this paper, we propose a new model to capture this contextual relationship in terms of pairwise features’ co-occurrence. Normalized Google-Like Distance (NGLD) is proposed to numerically measuring this co-occurrence, due to its effectiveness in semantic correlation analysis. …

Go to article

Fashionask: Pushing Community Answers To Your Fingertips, Wei Zhang, Lei Pang, Chong-Wah Ngo Nov 2012

Fashionask: Pushing Community Answers To Your Fingertips, Wei Zhang, Lei Pang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

We demonstrate a multimedia-based question-answering system, named FashionAsk, by allowing users to ask questions referring to pictures snapped by mobile devices. Specifically, instead of asking verbose questions to depict visual instances, direct pictures are provided as part of questions. To answer these multi-modal questions, FashionAsk performs a large-scale instance search to infer the names of instances, and then matches with similar questions from communitycontributed QA websites as answers. The demonstration is conducted on a million-scale dataset of Web images and QA pairs in the domain of fashion products. Asking a multimedia question through FashionAsk can take as short as five …

Go to article

Cognitive Architectures And Autonomy: Commentary And Response, Włodzisław Duch, Ah-Hwee Tan, Stan Franklin Nov 2012

Cognitive Architectures And Autonomy: Commentary And Response, Włodzisław Duch, Ah-Hwee Tan, Stan Franklin

Research Collection School Of Computing and Information Systems

This paper provides a very useful and promising analysis and comparison of current architectures of autonomous intelligent systems acting in real time and specific contexts, with all their constraints. The chosen issue of Cognitive Architectures and Autonomy is really a challenge for AI current projects and future research. I appreciate and endorse not only that challenge but many specific choices and claims; in particular: (i) that “autonomy” is a key concept for general intelligent systems; (ii) that “a core issue in cognitive architecture is the integration of cognitive processes ....”; (iii) the analysis of features and capabilities missing in current …

Go to article

Predicting Domain Adaptivity: Redo Or Recycle?, Ting Yao, Chong-Wah Ngo, Shiai Zhu Nov 2012

Predicting Domain Adaptivity: Redo Or Recycle?, Ting Yao, Chong-Wah Ngo, Shiai Zhu

Research Collection School Of Computing and Information Systems

Over the years, the academic researchers have contributed various visual concept classifiers. Nevertheless, given a new dataset, most researchers still prefer to develop large number of classifiers from scratch despite expensive labeling efforts and limited computing resources. A valid question is why not multimedia community “embrace the green” and recycle off-the-shelf classifiers for new dataset. The difficulty originates from the domain gap that there are many different factors that govern the development of a classifier and eventually drive its performance to emphasize certain aspects of dataset. Reapplying a classifier to an unseen dataset may end up GIGO (garbage in, garbage …

Go to article

Community As A Connector: Associating Faces With Celebrity Names In Web Videos, Zhineng Chen, Chong-Wah Ngo, Juan Cao, Wei Zhang Nov 2012

Community As A Connector: Associating Faces With Celebrity Names In Web Videos, Zhineng Chen, Chong-Wah Ngo, Juan Cao, Wei Zhang

Research Collection School Of Computing and Information Systems

Associating celebrity faces appearing in videos with their names is of increasingly importance with the popularity of both celebrity videos and related queries. However, the problem is not yet seriously studied in Web video domain. This paper proposes a Community connected Celebrity Name-Face Association approach (CCNFA), where the community is regarded as an intermediate connector to facilitate the association. Specifically, with the names and faces extracted from Web videos, C-CNFA decomposes the association task into a three-step framework: community discovering, community matching and celebrity face tagging. To achieve the goal of efficient name-face association under this umbrella, algorithms such as …

Go to article

Sensor Openflow: Enabling Software-Defined Wireless Sensor Networks, Tie Luo, Hwee-Pink Tan, Tony Q. S. Quek Oct 2012

Sensor Openflow: Enabling Software-Defined Wireless Sensor Networks, Tie Luo, Hwee-Pink Tan, Tony Q. S. Quek

Research Collection School Of Computing and Information Systems

While it has been a belief for over a decade that wireless sensor networks (WSN) are application-specific, we argue that it can lead to resource underutilization and counter-productivity. We also identify two other main problems with WSN: rigidity to policy changes and difficulty to manage. In this paper, we take a radical, yet backward and peer compatible, approach to tackle these problems inherent to WSN. We propose a Software-Defined WSN architecture and address key technical challenges for its core component, Sensor OpenFlow. This work represents the first effort that synergizes software-defined networking and WSN.

Go to article

A Probabilistic Graphical Model For Topic And Preference Discovery On Social Media, Lu Liu, Feida Zhu, Lei Zhang, Shiqiang Yang Oct 2012

A Probabilistic Graphical Model For Topic And Preference Discovery On Social Media, Lu Liu, Feida Zhu, Lei Zhang, Shiqiang Yang

Research Collection School Of Computing and Information Systems

Many web applications today thrive on offering services for large-scale multimedia data, e.g., Flickr for photos and YouTube for videos. However, these data, while rich in content, are usually sparse in textual descriptive information. For example, a video clip is often associated with only a few tags. Moreover, the textual descriptions are often overly specific to the video content. Such characteristics make it very challenging to discover topics at a satisfactory granularity on this kind of data. In this paper, we propose a generative probabilistic model named Preference-Topic Model (PTM) to introduce the dimension of user preferences to enhance the …

Go to article

Ifalcon: A Neural Architecture For Hierarchical Planning, Budhitama Subagdja, Ah-Hwee Tan Jun 2012

Ifalcon: A Neural Architecture For Hierarchical Planning, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Hierarchical planning is an approach of planning by composing and executing hierarchically arranged predefined plans on the fly to solve some problems. This approach commonly relies on a domain expert providing all semantic and structural knowledge. One challenge is how the system deals with incomplete ill-defined knowledge while the solution can be achieved on the fly. Most symbolic-based hierarchical planners have been devised to allow the knowledge to be described expressively. However, in some cases, it is still difficult to produce the appropriate knowledge due to the complexity of the problem domain especially if the missing knowledge must be acquired …

Go to article

Energy-Efficient Continuous Activity Recognition On Mobile Phones: An Activity-Adaptive Approach, Zhixian Yan, Vigneshwaran Subbaraju, Dipanjan Chakraborty, Archan Misra, Karl Aberer Jun 2012

Energy-Efficient Continuous Activity Recognition On Mobile Phones: An Activity-Adaptive Approach, Zhixian Yan, Vigneshwaran Subbaraju, Dipanjan Chakraborty, Archan Misra, Karl Aberer

Research Collection School Of Computing and Information Systems

Power consumption on mobile phones is a painful obstacle towards adoption of continuous sensing driven applications, e.g., continuously inferring individual’s locomotive activities (such as ‘sit’, ‘stand’ or ‘walk’) using the embedded accelerometer sensor. To reduce the energy overhead of such continuous activity sensing, we first investigate how the choice of accelerometer sampling frequency & classification features affects, separately for each activity, the “energy overhead” vs. “classification accuracy” tradeoff. We find that such tradeoff is activity specific. Based on this finding, we introduce an activity-sensitive strategy (dubbed “A3R” – Adaptive Accelerometer-based Activity Recognition) for continuous activity recognition, where the choice of …

Go to article

Spatial Queries In Wireless Broadcast Environments [Keynote Speech], Kyriakos Mouratidis May 2012

Spatial Queries In Wireless Broadcast Environments [Keynote Speech], Kyriakos Mouratidis

Research Collection School Of Computing and Information Systems

Wireless data broadcasting is a promising technique for information dissemination that exploits the computational capabilities of mobile devices, in order to enhance the scalability of the system. Under this environment, the data are continuously broadcast by the server, interleaved with some indexing information for query processing. Clients may tune in the broadcast channel and process their queries locally without contacting the server. In this paper we focus on spatial queries in particular. First, we review existing methods on this topic. Next, taking shortest path computation as an example, we showcase technical challenges arising in this processing model and describe techniques …

Go to article

Provable De-Anonymization Of Large Datasets With Sparse Dimensions, Anupam Datta, Divya Sharma, Arunesh Sinha Apr 2012

Provable De-Anonymization Of Large Datasets With Sparse Dimensions, Anupam Datta, Divya Sharma, Arunesh Sinha

Research Collection School Of Computing and Information Systems

There is a significant body of empirical work on statistical de-anonymization attacks against databases containing micro-dataabout individuals, e.g., their preferences, movie ratings, or transactiondata. Our goal is to analytically explain why such attacks work. Specifically, we analyze a variant of the Narayanan-Shmatikov algorithm thatwas used to effectively de-anonymize the Netflix database of movie ratings. We prove theorems characterizing mathematical properties of thedatabase and the auxiliary information available to the adversary thatenable two classes of privacy attacks. In the first attack, the adversarysuccessfully identifies the individual about whom she possesses auxiliaryinformation (an isolation attack). In the second attack, the adversarylearns additional …

Go to article

Towards Fine-Grained Radio-Based Indoor Location, Jie Xiong, Kyle Jamieson Feb 2012

Towards Fine-Grained Radio-Based Indoor Location, Jie Xiong, Kyle Jamieson

Research Collection School Of Computing and Information Systems

Location systems are key to a rich experience for mobile users. When they roam outdoors, mobiles can usually count on a clear GPS signal for an accurate location, but indoors, GPS usually fades, and so up until recently, mobiles have had to rely mainly on rather coarse-grained signal strength readings for location. What has changed this status quo is the recent trend of dramatically increasing numbers of antennas at the indoor AP, mainly to bolster capacity and coverage with multiple-input, multiple-output (MIMO) techniques. In the near future, the number of antennas at the access point will increase several-fold, to meet …

Go to article

Extreme Learning Machine Terrain-Based Navigation For Unmanned Aerial Vehicles, Ee May Kan, Meng Hiot Lim, Yew Soon Ong, Ah-Hwee Tan, Swee Ping Yeo Feb 2012

Extreme Learning Machine Terrain-Based Navigation For Unmanned Aerial Vehicles, Ee May Kan, Meng Hiot Lim, Yew Soon Ong, Ah-Hwee Tan, Swee Ping Yeo

Research Collection School Of Computing and Information Systems

Unmanned aerial vehicles (UAVs) rely on global positioning system (GPS) information to ascertain its position for navigation during mission execution. In the absence of GPS information, the capability of a UAV to carry out its intended mission is hindered. In this paper, we learn alternative means for UAVs to derive real-time positional reference information so as to ensure the continuity of the mission. We present extreme learning machine as a mechanism for learning the stored digital elevation information so as to aid UAVs to navigate through terrain without the need for GPS. The proposed algorithm accommodates the need of the …

Go to article

Self‐Regulating Action Exploration In Reinforcement Learning, Teck-Hou Teng, Ah-Hwee Tan, Yuan-Sin Tan Jan 2012

Self‐Regulating Action Exploration In Reinforcement Learning, Teck-Hou Teng, Ah-Hwee Tan, Yuan-Sin Tan

Research Collection School Of Computing and Information Systems

The basic tenet of a learning process is for an agent to learn for only as much and as long as it is necessary. With reinforcement learning, the learning process is divided between exploration and exploitation. Given the complexity of the problem domain and the randomness of the learning process, the exact duration of the reinforcement learning process can never be known with certainty. Using an inaccurate number of training iterations leads either to the non-convergence or the over-training of the learning agent. This work addresses such issues by proposing a technique to self-regulate the exploration rate and training duration …

Go to article

Preface: Trends In Natural And Machine Intelligence, Jonathan H. Chan, Ah-Hwee Tan Jan 2012

Preface: Trends In Natural And Machine Intelligence, Jonathan H. Chan, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Trends in natural and machine intelligence are increasingly reflecting a convergence in these two well-established fields of study. The Third International Neural Network Society Winter Conference (INNS-WC 2012) was held in Bangkok, Thailand, on October 3-5, 2012. INNS-WC2012, with an aim to bring together scientists, practitioners, and students worldwide, to discuss the past, present, and future challenges and trends in the area of natural and machine intelligence. This event has been a bi-annual conference of the International Neural Network Society (INNS) to provide a forum for international researchers to exchange latest ideas and advances on neural networks and related discipline.

Go to article