Artificial Intelligence and Robotics Commons^™

Improving Performance By Re-Rating In The Dynamic Estimation Of Rater Reliability, Alexey Tarasov, Sarah Jane Delany, Brian Macnamee

Conference papers

Nowadays crowdsourcing is widely used in supervised machine learning to facilitate the collection of ratings for unlabelled training sets. In order to get good quality results it is worth rejecting results from noisy/unreliable raters, as soon as they are discovered. Many techniques for filtering unreliable raters rely on the presentation of training instances to the raters identified as most accurate to date. Early in the process, the true rater reliabilities are not known and unreliable raters may be used as a result. This paper explores improving the quality of ratings for train- ing instances by performing re-rating. The re-rating relies …

Unmanned Autonomous Object Retrieval: Old Dominion University 2013 International Aerial Robotics Competition Entry, Johnathan Bailey, Austin Boyd, Chung-Hao Chen, Stephen Dailey, Lisa Henderson, Jeremy Stuart, Christina Williams

Electrical & Computer Engineering Faculty Publications

This paper describes the design implementation of a Quadrotor Unmanned Aerial Vehicle (UAV) with the capability of exploring indoor locations without the assistance of external aids. For relative position, the use of a laser range sensor, an optical flow sensor, and sonar sensor combined allows for the vehicle to generate mapping information. With relative position in mind, the vehicle uses vision algorithms to recognize immediate obstacles, sign, and entry ways to allow for quick movement responses and object recognition. A proportional-integral-differentiator controller allows for flight stability and mitigation in the tight confines of the indoor spaces. A mapping algorithm allows …

On The Recognition Of Emotion From Physiological Data, Warren Creemers

Theses: Doctorates and Masters

This work encompasses several objectives, but is primarily concerned with an experiment where 33 participants were shown 32 slides in order to create ‗weakly induced emotions‘. Recordings of the participants‘ physiological state were taken as well as a self report of their emotional state. We then used an assortment of classifiers to predict emotional state from the recorded physiological signals, a process known as Physiological Pattern Recognition (PPR). We investigated techniques for recording, processing and extracting features from six different physiological signals: Electrocardiogram (ECG), Blood Volume Pulse (BVP), Galvanic Skin Response (GSR), Electromyography (EMG), for the corrugator muscle, skin temperature …

Concept Drift Datasets, Patrick Lindstrom

Doctoral

This zip file contains the datasets used in the PhD thesis:

Lindstrom, P., 2013. Handling Concept Drift in the Context of Expensive Labels. Technological University Dublin. For more information about the datasets please see the README file and the aforementioned thesis.

Artificial Intelligence And Data Mining: Algorithms And Applications, Jianhong Xia, Fuding Xie, Yong Zhang, Craig Caulfield

Research outputs 2013

Artificial intelligence and data mining techniques have been used in many domains to solve classification, segmentation, association, diagnosis, and prediction problems. The overall aim of this special issue is to open a discussion among researchers actively working on algorithms and applications. The issue covers a wide variety of problems for computational intelligence, machine learning, time series analysis, remote sensing image mining, and pattern recognition. After a rigorous peer review process, 20 papers have been selected from 38 submissions. The accepted papers in this issue addressed the following topics: (i) advanced artificial intelligence and data mining techniques; (ii) computational intelligence in …

Knowledge-Driven Autonomous Commodity Trading Advisor, Yee Pin Lim, Shih-Fen Cheng

Research Collection School Of Computing and Information Systems

The myth that financial trading is an art has been mostly destroyed in the recent decade due to the proliferation of algorithmic trading. In equity markets, algorithmic trading has already bypass human traders in terms of traded volume. This trend seems to be irreversible, and other asset classes are also quickly becoming dominated by the machine traders. However, for asset that requires deeper understanding of physicality, like the trading of commodities, human traders still have significant edge over machines. The primary advantage of human traders in such market is the qualitative expert knowledge that requires traders to consider not just …

Identification Of Tcp Protocols, Juan Shao

School of Computing: Dissertations, Theses, and Student Research

Recently, many new TCP algorithms, such as BIC, CUBIC, and CTCP, have been deployed in the Internet. Investigating the deployment statistics of these TCP algorithms is meaningful to study the performance and stability of the Internet. Currently, there is a tool named Congestion Avoidance Algorithm Identification (CAAI) for identifying the TCP algorithm of a web server and then for investigating the TCP deployment statistics. However, CAAI using a simple k-NN algorithm can not achieve a high identification accuracy. In this thesis, we comprehensively study the identification accuracy of five popular machine learning models. We find that the random forest model …

Lagrangian Relaxation For Large-Scale Multi-Agent Planning, Geoffrey J. Gordon, Pradeep Varakantham, William Yeoh, Hoong Chuin Lau, Ajay S. Aravamudhan, Shih-Fen Cheng

Research Collection School Of Computing and Information Systems

Multi-agent planning is a well-studied problem with various applications including disaster rescue, urban transportation and logistics, both for autonomous agents and for decision support to humans. Due to computational constraints, existing research typically focuses on one of two scenarios: unstructured domains with many agents where we are content with heuristic solutions, or domains with small numbers of agents or special structure where we can provide provably near-optimal solutions. By contrast, in this paper, we focus on providing provably near-optimal solutions for domains with large numbers of agents, by exploiting a common domain-general property: if individual agents each have limited influence …

Lagrangian Relaxation For Large-Scale Multi-Agent Planning, Geoff Gordon, Pradeep Varakantham, William Yeoh, Hoong Chuin Lau, Shih-Fen Cheng

Research Collection School Of Computing and Information Systems

Multi-agent planning is a well-studied problem with various applications including disaster rescue, urban transportation and logistics, both for autonomous agents and for decision support to humans. Due to computational constraints, existing research typically focuses on one of two scenarios: unstructured domains with many agents where we are content with heuristic solutions, or domains with small numbers of agents or special structure where we can provide provably near-optimal solutions. By contrast, in this paper, we focus on providing provably near-optimal solutions for domains with large numbers of agents, by exploiting a common domain-general property: if individual agents each have limited influence …

A Mechanism For Organizing Last-Mile Service Using Non-Dedicated Fleet, Shih-Fen Cheng, Duc Thien Nguyen, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Unprecedented pace of urbanization and rising income levels have fueled the growth of car ownership in almost all newly formed megacities. Such growth has congested the limited road space and significantly affected the quality of life in these megacities. Convincing residents to give up their cars and use public transport is the most effective way in reducing congestion; however, even with sufficient public transport capacity, the lack of last-mile (from the transport hub to the destination) travel services is the major deterrent for the adoption of public transport. Due to the dynamic nature of such travel demands, fixed-size fleets will …

Investigating Intelligent Agents In A 3d Virtual World, Yilin Kang, Fiona Fui-Hoon Nah, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Web 3.0 involves "intelligent" web applications that utilize natural language processing, machine-based learning and reasoning, and intelligent techniques to analyze and understand user behavior. In this research, we empirically assess a specific form of Web 3.0 application in the form of intelligent agents that offer assistance to users in the virtual world. Using media naturalness theory, we hypothesize that the use of intelligent agents in the virtual world can enhance user experience by offering a more natural way of communication and assistance to users. We are interested to test if media naturalness theory holds in the context of intelligent agents …

Knowledge-Based Exploration For Reinforcement Learning In Self-Organizing Neural Networks, Teck-Hou Teng, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Exploration is necessary during reinforcement learning to discover new solutions in a given problem space. Most reinforcement learning systems, however, adopt a simple strategy, by randomly selecting an action among all the available actions. This paper proposes a novel exploration strategy, known as Knowledge-based Exploration, for guiding the exploration of a family of self-organizing neural networks in reinforcement learning. Specifically, exploration is directed towards unexplored and favorable action choices while steering away from those negative action choices that are likely to fail. This is achieved by using the learned knowledge of the agent to identify prior action choices leading to …

Agent-Based Virtual Humans In Co-Space: An Evaluative Study, Yilin Kang, Ah-Hwee Tan, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Co-Space refers to interactive virtual environment modelled after the real world in terms of look-and-feel, functionalities and services. We have developed a 3D virtual world named Nanyang Technological University (NTU) CoSpace populated with virtual human characters. Three key requirements of realistic virtual humans in the virtual world have been identified, namely (1) autonomy: agents can function on their own; (2) interactivity: agents can interact naturally with players; and (3) personality: agents can exhibit human traits and characteristics. Working towards these challenges, we propose a brain-inspired agent architecture that integrates goal-directed autonomy, natural language interaction and human-like personality. We conducted an …

Effect Of Business Intelligence And It Infrastructure Flexibility On Organizational Agility, Xiaofeng Chen, Keng Siau

Research Collection School Of Computing and Information Systems

There is a growing use of business intelligence (BI) for better management decisions in different industries. However, empirical studies on BI are still scarce in academic research. This research investigates BI from an organizational agility perspective. Organizational agility is the ability to sense and respond to market opportunities and threats with speed. Drawing on systems theory and literature on organizational agility, business intelligence, and IT infrastructure flexibility, we hypothesize that BI use and IT infrastructure flexibility are two major antecedents to organizational agility. We developed a research model to examine the effect of BI use and IT infrastructure flexibility on …

Agent-Based Virtual Humans In Co-Space: An Evaluative Study, Yilin Kang, Ah-Hwee Tan, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Co-Space refers to interactive virtual environment modelled after the real world in terms of look-and-feel, functionalities and services. We have developed a 3D virtual world named Nan yang Technological University (NTU) Co-Space populated with virtual human characters. Three key requirements of realistic virtual humans in the virtual world have been identified, namely (1) autonomy: agents can function on their own, (2) interactivity: agents can interact naturally with players, and (3) personality: agents can exhibit human traits and characteristics. Working towards these challenges, we propose a brain-inspired agent architecture that integrates goal-directed autonomy, natural language interaction and human-like personality. We conducted …

A System For Bidirectional Robotic Pathfinding, Tesca Fitzgerald

Computer Science Faculty Publications and Presentations

The accuracy of an autonomous robot's intended navigation can be impacted by environmental factors affecting the robot's movement. When sophisticated localizing sensors cannot be used, it is important for a pathfinding algorithm to provide opportunities for landmark usage during route execution, while balancing the efficiency of that path. Although current pathfinding algorithms may be applicable, they often disfavor paths that balance accuracy and efficiency needs. I propose a bidirectional pathfinding algorithm to meet the accuracy and efficiency needs of autonomous, navigating robots.

Benchmarking Still-To-Video Face Recognition Via Partial And Local Linear Discriminant Analysis On Cox-S2v Dataset, Zhiwu Huang, S. Shan, H. Zhang, S. Lao, A. Kuerban, X. Chen

Research Collection School Of Computing and Information Systems

In this paper, we explore the real-world Still-to-Video (S2V) face recognition scenario, where only very few (single, in many cases) still images per person are enrolled into the gallery while it is usually possible to capture one or multiple video clips as probe. Typical application of S2V is mug-shot based watch list screening. Generally, in this scenario, the still image(s) were collected under controlled environment, thus of high quality and resolution, in frontal view, with normal lighting and neutral expression. On the contrary, the testing video frames are of low resolution and low quality, possibly with blur, and captured under …

A Generalized Cluster Centroid Based Classifier For Text Categorization, Guansong Pang, Shengyi Jiang

Research Collection School Of Computing and Information Systems

In this paper, a Generalized Cluster Centroid based Classifier (GCCC) and its variants for text categorization are proposed by utilizing a clustering algorithm to integrate two wellknown classifiers, i.e., the K-nearest-neighbor (KNN) classifier and the Rocchio classifier. KNN, a lazy learning method, suffers from inefficiency in online categorization while achieving remarkable effectiveness. Rocchio, which has efficient categorization performance, fails to obtain an expressive categorization model due to its inherent linear separability assumption. Our proposed method mainly focuses on two points: one point is that we use a clustering algorithm to strengthen the expressiveness of the Rocchio model; another one is …

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 …

Self-Regulating Action Exploration In Reinforcement Learning, Teck-Hou Teng, Ah-Hwee 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 …