Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Physics (392)
- Computer Sciences (181)
- Social and Behavioral Sciences (180)
- Life Sciences (145)
- Engineering (108)
-
- Earth Sciences (92)
- Environmental Sciences (82)
- Geology (72)
- Mathematics (57)
- Chemistry (51)
- Business (42)
- Statistics and Probability (34)
- Education (29)
- Databases and Information Systems (28)
- Electrical and Computer Engineering (28)
- Sustainability (28)
- Oceanography and Atmospheric Sciences and Meteorology (25)
- Public Affairs, Public Policy and Public Administration (25)
- Applied Mathematics (22)
- Medicine and Health Sciences (22)
- Mechanical Engineering (21)
- Sociology (21)
- Computer Engineering (20)
- Biostatistics (18)
- Law (18)
- Public Policy (16)
- Software Engineering (16)
- Atomic, Molecular and Optical Physics (15)
- Management Information Systems (15)
- Keyword
-
- For (49)
- Conference Papers (42)
- Journal Articles (41)
- Analysis (34)
- System (34)
-
- Systems (34)
- Based (31)
- Human (25)
- Power (25)
- Australia (24)
- Data (24)
- Modelling (23)
- Image (21)
- CMMB (20)
- Quality (20)
- Using (19)
- Articles (18)
- Recognition (18)
- ARPES (17)
- Detection (17)
- Distribution (17)
- Era2015 (17)
- GeoQUEST (17)
- Model (17)
- Approach (15)
- Control (15)
- Feature (15)
- Cuprates (14)
- Estimation (14)
- Health (14)
- Publication
-
- Arun Bansil (71)
- Pran Nath (65)
- Christian Binek (61)
- Professor Philip Ogunbona (53)
- Alessandro Vespignani (39)
-
- Professor Salim Bouzerdoum (30)
- Associate Professor Sarath Perera (28)
- Professor Yi Mu (28)
- Associate Professor Wanqing Li (27)
- Professor Willy Susilo (23)
- Robert Markiewicz (22)
- Konstantin Läufer (20)
- Associate Professor Golshah Naghdy (18)
- Bernardo Barbiellini (18)
- Dr Duane Robinson (17)
- J. A. Aquilina (16)
- Ning Wu (16)
- Carrick M Eggleston (15)
- Dr Ping Yu (15)
- Dr Jun Shen (13)
- Dr Jun Yan (13)
- Saber Elaydi (13)
- Associate Professor Mark Nelson (12)
- Professor Pascal Perez (12)
- Chris Gibson (11)
- Dr Christian Ritz (11)
- Hsin Lin (11)
- William E. Price (11)
- Associate Professor Minjie Zhang (10)
- Christopher Cook (10)
Articles 1 - 30 of 1625
Full-Text Articles in Physical Sciences and Mathematics
Assessing Content Validity Through Correlation And Relevance Tools A Bayesian Randomized Equivalence Experiment, Byron Gajewski, Diane Boyle, Marjorie Bott, Larry Price, Jamie Leopold, Nancy Dunton
Assessing Content Validity Through Correlation And Relevance Tools A Bayesian Randomized Equivalence Experiment, Byron Gajewski, Diane Boyle, Marjorie Bott, Larry Price, Jamie Leopold, Nancy Dunton
Diane Kay Boyle PhD, RN, FAAN
Content validity elicits expert opinion regarding items of a psychometric instrument. Expert opinion can be elicited in many forms: for example, how essential an item is or its relevancy to a domain. This study developed an alternative tool that elicits expert opinion regarding correlations between each item and its respective domain. With 109 Registered Nurse (RN) site coordinators from National Database of Nursing Quality Indicators, we implemented a randomized Bayesian equivalence trial with coordinators completing ‘‘relevance’’ or ‘‘correlation’’ content tools regarding the RN Job Enjoyment Scale. We confirmed our hypothesis that the two tools would result in equivalent content information. …
Meteor-Radar Observed Mesospheric Semi-Annual Oscillation (Sao) And Quasi-Biennial Oscillation (Qbo) Over Maui, Hawaii, Tao Li, Alan Liu, Xian Lu, Zhenhua Li, Steven Franke, Gary Swenson, Xiankang Dou
Meteor-Radar Observed Mesospheric Semi-Annual Oscillation (Sao) And Quasi-Biennial Oscillation (Qbo) Over Maui, Hawaii, Tao Li, Alan Liu, Xian Lu, Zhenhua Li, Steven Franke, Gary Swenson, Xiankang Dou
Zhenhua Li
No abstract provided.
Computing Immutable Regions For Subspace Top-K Queries, Kyriakos Mouratidis, Hwee Hwa Pang
Computing Immutable Regions For Subspace Top-K Queries, Kyriakos Mouratidis, Hwee Hwa Pang
Kyriakos MOURATIDIS
Given a high-dimensional dataset, a top-k query can be used to shortlist the k tuples that best match the user’s preferences. Typically, these preferences regard a subset of the available dimensions (i.e., attributes) whose relative significance is expressed by user-specified weights. Along with the query result, we propose to compute for each involved dimension the maximal deviation to the corresponding weight for which the query result remains valid. The derived weight ranges, called immutable regions, are useful for performing sensitivity analysis, for finetuning the query weights, etc. In this paper, we focus on top-k queries with linear preference functions over …
When Would This Bug Get Reported?, Ferdian Thung, David Lo, Lingxiao Jiang, Lucia Lucia, Foyzur Rahman, Premkumar Devanbu
When Would This Bug Get Reported?, Ferdian Thung, David Lo, Lingxiao Jiang, Lucia Lucia, Foyzur Rahman, Premkumar Devanbu
David LO
Millions of people, including those in the software engineering communities have turned to microblogging services, such as Twitter, as a means to quickly disseminate information. A number of past studies by Treude et al., Storey, and Yuan et al. have shown that a wealth of interesting information is stored in these microblogs. However, microblogs also contain a large amount of noisy content that are less relevant to software developers in engineering software systems. In this work, we perform a preliminary study to investigate the feasibility of automatic classification of microblogs into two categories: relevant and irrelevant to engineering software systems. …
An Empirical Study Of Bugs In Machine Learning Systems, Ferdian Thung, Shaowei Wang, David Lo, Lingxiao Jiang
An Empirical Study Of Bugs In Machine Learning Systems, Ferdian Thung, Shaowei Wang, David Lo, Lingxiao Jiang
David LO
Many machine learning systems that include various data mining, information retrieval, and natural language processing code and libraries have being used in real world applications. Search engines, internet advertising systems, product recommendation systems are sample users of these algorithm intensive code and libraries. Machine learning code and toolkits have also been used in many recent studies on software mining and analytics that aim to automate various software engineering tasks. With the increasing number of important applications of machine learning systems, the reliability of such systems is also becoming increasingly important. A necessary step for ensuring reliability of such systems is …
Ict For Poverty Alleviation In Pacific Island Nations: Study Of Icts4d In Fiji, Deogratias Harorimana, Opeti Rokotuinivono, Emali Sewale, Fane Salaiwai, Marica Naulu, Evangelin Roy
Ict For Poverty Alleviation In Pacific Island Nations: Study Of Icts4d In Fiji, Deogratias Harorimana, Opeti Rokotuinivono, Emali Sewale, Fane Salaiwai, Marica Naulu, Evangelin Roy
Dr Deogratias Harorimana
ICT for Poverty Alleviation in Pacific Island Nations: Study of ICTs4D in Fiji There has been a vague and little knowledge on the role or potential of Information and Communications Technologies (ICTs) in relation to addressing poverty in Fiji. This may be probably due to the newness of the technology in the South Pacific Region as a whole but also probably due to the fact that only 9.7% of the current Fiji 931,000 populations are internet users (ITC Figures 2011). This paper reports on finding how ICTs is contributing towards poverty alleviation in Fiji. On the basis of reviewed best …
Terrain Constrained Stereo Correspondence, Gabrielle Inglis, Chris Roman
Terrain Constrained Stereo Correspondence, Gabrielle Inglis, Chris Roman
Christopher N. Roman
There is a persistent need in the oceanographic community for accurate three dimensional reconstructions of seafloor structures. To meet this need underwater mapping techniques have expanded to include the use of stereo vision and high frequency multibeam sonar for mapping scenes 10's to 100's of square meters in size. Both techniques have relative advantages and disadvantages that depend on the task at hand and the desired accuracy. In this paper, we develop a method to constrain the often problematic stereo correspondence search to small sections of the image that correspond to estimated ranges along the epipolar lines calculated from coregistered …
Application Of Structured Light Imaging For High Resolution Mapping Of Underwater Archaeological Sites, Chris Roman, Gabrielle Inglis, James Rutter
Application Of Structured Light Imaging For High Resolution Mapping Of Underwater Archaeological Sites, Chris Roman, Gabrielle Inglis, James Rutter
Christopher N. Roman
This paper presents results from recent work using structured light laser profile imaging to create high resolution bathymetric maps of underwater archaeological sites. Documenting the texture and structure of submerged sites is a difficult task and many applicable acoustic and photographic mapping techniques have recently emerged. This effort was completed to evaluate laser profile imaging in comparison to stereo imaging and high frequency multibeam mapping. A ROV mounted camera and inclined 532 nm sheet laser were used to create profiles of the bottom that were then merged into maps using platform navigation data. These initial results show very promising resolution …
Perceived Similarity And Visual Descriptions In Content-Based Image Retrieval, Yuan Zhong, Lei Ye, Wanqing Li, Philip Ogunbona
Perceived Similarity And Visual Descriptions In Content-Based Image Retrieval, Yuan Zhong, Lei Ye, Wanqing Li, Philip Ogunbona
Dr Lei Yi
The use of low-level feature descriptors is pervasive in content-based image retrieval tasks and the answer to the question of how well these features describe users’ intention is inconclusive. In this paper we devise experiments to gauge the degree of alignment between the description of target images by humans and that implicitly provided by low-level image feature descriptors. Data was collected on how humans perceive similarity in images. Using images judged by humans to be similar, as ground truth, the performance of some MPEG-7 visual feature descriptors were evaluated. It is found that various descriptors play different roles in different …
Visual Perceptual Process Model And Object Segmentation, Wanqing Li, P. Ogunbona, Lei Ye, Igor Kharitonenko
Visual Perceptual Process Model And Object Segmentation, Wanqing Li, P. Ogunbona, Lei Ye, Igor Kharitonenko
Dr Lei Yi
Modeling human visual process is crucial for automatic object segmentation that is able to produce consistent results to human perception. Based on the latest understanding of how human performs the task of extracting objects from images, we proposed a graph-based computational framework to model the visual process. The model supports the hierarchical nature of human visual perception and consists of the key steps of human visual perception including pre-attentive (pre-constancy) grouping, figure-and-ground organization, and attentive (post-constancy) grouping. A divide-and-conquer implementation of the model based on the concept of shortest spanning tree (SST) has demonstrated the potential of the model for …
Traceable And Retrievable Identity-Based Encryption, Man Ho Au, Qiong Huang, Joseph K. Liu, Willy Susilo, Duncan S. Wong, Guomin Yang
Traceable And Retrievable Identity-Based Encryption, Man Ho Au, Qiong Huang, Joseph K. Liu, Willy Susilo, Duncan S. Wong, Guomin Yang
Dr Guomin Yang
Very recently, the concept of Traceable Identity-based Encryption (IBE) scheme (or Accountable Authority Identity based Encryption scheme) was introduced in Crypto 2007. This concept enables some mechanisms to reduce the trust of a private key generator (PKG) in an IBE system. The aim of this paper is threefold. First, we discuss some subtleties in the first traceable IBE scheme in the Crypto 2007 paper. Second, we present an extension to this work by having the PKG’s master secret key retrieved automatically if more than one user secret key are released. This way, the user can produce a concrete proof of …
A New Efficient Optimistic Fair Exchange Protocol Without Random Oracles, Qiong Huang, Guomin Yang, Duncan S Wong, Willy Susilo
A New Efficient Optimistic Fair Exchange Protocol Without Random Oracles, Qiong Huang, Guomin Yang, Duncan S Wong, Willy Susilo
Dr Guomin Yang
Optimistic fair exchange (OFE) is a kind of protocols to solve the problem of fair exchange between two parties. Most of the previous work on this topic are provably secure in the random oracle model. In this work, we propose a new construction of OFE from another cryptographic primitive, called time capsule signature. The construction is efficient and brings almost no overhead other than the primitive itself. The security of our new construction is based on that of the underlying primitive without relying on the random oracle heuristic. Applying our generic construction to the time capsule signature scheme recently proposed …
A Mathematical Model For The Biological Treatment Of Industrial Wastewater In A Reactor Cascade, Rubayyi Turki Alqahtani, Mark I. Nelson, Annette L. Worthy
A Mathematical Model For The Biological Treatment Of Industrial Wastewater In A Reactor Cascade, Rubayyi Turki Alqahtani, Mark I. Nelson, Annette L. Worthy
Associate Professor Annette Worthy
Many industrial processes, particularly in the food industry, produce slurries or wastewaters containing high concentrations of biodegradable organic materials. Before these contaminated wastewaters can be discharged the concentration of the biodegradable organic pollutant must be reduced. One way to do this is to pass the wastewater through a bioreactor containing biomass which grows through consumption of the pollutant. Anaerobic conditions are often favoured for the processing of waste materials with high levels of biodegradable organic pollutants as these can be removed with low investment and operational costs. We investigate the steady state effluent concentration leaving a cascade of two reactors. …
Soliton Steering By Longitudinal Modulation Of The Nonlinearity In Waveguide Arrays, Gaetano Assanto, Luis A. Cisneros, Antonmaria A. Minzoni, Benjamin D. Skuse, Noel F. Smyth, Annette L. Worthy
Soliton Steering By Longitudinal Modulation Of The Nonlinearity In Waveguide Arrays, Gaetano Assanto, Luis A. Cisneros, Antonmaria A. Minzoni, Benjamin D. Skuse, Noel F. Smyth, Annette L. Worthy
Associate Professor Annette Worthy
We show how discrete solitary waves in one and two-dimensional waveguide arrays can be steered across the lattice via the introduction of a longitudinal periodic modulation of the nonlinear response. Through parametric energy transfer from the modulation to the solitary wave, the latter can increase its width and overcome the Peierls-Nabarro potential to propagate freely.
A Mathematical Model For The Biological Treatment Of Industrial Wastewaters In A Cascade Of Four Reactors, Annette L. Worthy, Mark I. Nelson, Rubayyi Turki Alqahtani
A Mathematical Model For The Biological Treatment Of Industrial Wastewaters In A Cascade Of Four Reactors, Annette L. Worthy, Mark I. Nelson, Rubayyi Turki Alqahtani
Associate Professor Annette Worthy
Many industrial processes, particularly in the food industry, produce slurriesor wastewaters containing high concentrations of biodegradable organicmaterials. Before these contaminated wastewaters can be dischargedthe concentration of these pollutants must be reduced. A method which has beenextensively employed to remove biodegradable organic matter is biologicaltreatment. In this process the wastewater (or slurry) is passed through abioreactor containing biomass which grows through consumption of thepollutants.The industrial treatment of wastewaters typically employs a reactor cascade.In a reactor cascade of n reactors the effluent stream from the ith reactor inthe cascade acts as the feed stream for the (i+1)th reactor, i.e. the nextreactor. The …
Propagation Of Optical Spatial Solitary Waves In Bias-Free Nematic-Liquid-Crystal Cells, Antonmaria A. Minzoni, Luke W. Sciberras, Noel F. Smyth, Annette L. Worthy
Propagation Of Optical Spatial Solitary Waves In Bias-Free Nematic-Liquid-Crystal Cells, Antonmaria A. Minzoni, Luke W. Sciberras, Noel F. Smyth, Annette L. Worthy
Associate Professor Annette Worthy
The propagation of a bulk optical solitary wave in a rectangular cell filled with a nematic liquid crystal—a nematicon—is mathematically modelled. In order to overcome the Freédricksz threshold the cell walls are rubbed to pretilt the nematic. A modulation theory, based on a Lagrangian formulation, is developed for the (2+1)-dimensional propagation of the solitary wave beam down the cell. This modulation theory is based on two different formulations of the director distribution. The relative advantages and disadvantages of these two methods are discussed. A previously unexplored method based on images is found to possess significant advantages. Excellent agreement with full …
Tteleconsultation Technology And Its Benefits: In The Case Of Public Hospitals In Malaysia, Nurazean Maarop, Sukdershan Hazara Singh, Khin Than Win
Tteleconsultation Technology And Its Benefits: In The Case Of Public Hospitals In Malaysia, Nurazean Maarop, Sukdershan Hazara Singh, Khin Than Win
Dr Khin Win
The ultimate objectives of this study are to describe teleconsultation activities and explore the benefits of teleconsultation technology in the context of public health care environment in Malaysia. The materials of this study were based on an exploratory mixed method studies involving semi-structured interviews with key informants and questionnaires survey of health care providers to obtain information about existing teleconsultation activities as well as to uncover the benefits of teleconsultation technology. The notable benefits from teleconsultation implementation were further discussed. The findings confirmed that teleconsultation service has improved health care delivery in the underserved areas to consult with specialist. One …
Experiences Using Case Studies To Teach Risk, A. Fuller, Khin Than Win, L. Dei
Experiences Using Case Studies To Teach Risk, A. Fuller, Khin Than Win, L. Dei
Dr Khin Win
Most software development projects today are facing increased risks. Despite this risk management planning is virtually nonexistent, as managers have not been trained in risk management. Few current software engineering curricula provide comprehensive coverage of risk, nor any practical experience in risk assessment. In this paper we discuss our experience using case studies to teach risk as part of a final year course in software process management with a view to determining the effectiveness of the particular case studies. This experience will be used as a foundation for implementing the full semester course in 2003.
Data Security And Information Privacy For Pda Accessible Clinical-Log For Medical Education In Problem-Based Learning (Pbl) Approach, Rattiporn Luanrattana, Khin Than Win, John A. Fulcher
Data Security And Information Privacy For Pda Accessible Clinical-Log For Medical Education In Problem-Based Learning (Pbl) Approach, Rattiporn Luanrattana, Khin Than Win, John A. Fulcher
Dr Khin Win
Data security and information privacy are the important aspects to consider for the use of mobile technology for recording clinical experience and encounter in medical education. Objective: This study aims to address the qualitative findings of the appropriate data security and information privacy for PDA accessible clinical-log in problem-based learning (PBL) approach in medical education. Method: The semi-structured interviews were conducted with the medical faculty members, honorary clinical academics and medical education technology specialists. Results: Data security and information access plan were determined for managing clinical-log data. The results directed the guideline for the future development and implementation of clinical-log …
Electronic Health Record System Evaluation Based On Patient Safety, Yung-Yu Su, Khin Than Win, John A. Fulcher
Electronic Health Record System Evaluation Based On Patient Safety, Yung-Yu Su, Khin Than Win, John A. Fulcher
Dr Khin Win
After describing the general characteristics of Electronic Health Records (EHRs), we consider patient safety. We then proceed to discuss IS evaluation in general terms, followed by HIS system evaluation in particular. The D&M IS Success model, Technology Acceptance model and Task-Technology Fit model are considered as potential candidates for EHR System evaluation. Based upon a critical review of the available literature, we draw some conclusions about the appropriateness of current HIS/EHR evaluation approaches. Finally, we suggest that by incorporating patient safety attributes in any EHR System evaluation framework, then this could lead to improved accuracy, and in turn improved patient …
Evaluating The Implementation Of Emr Systems From The Perspective Of Health Professionals, Yung-Yu Su, John A. Fulcher, Khin Than Win, Herng-Chia Chiu, Gui-Fen Chiu
Evaluating The Implementation Of Emr Systems From The Perspective Of Health Professionals, Yung-Yu Su, John A. Fulcher, Khin Than Win, Herng-Chia Chiu, Gui-Fen Chiu
Dr Khin Win
In health informatics, the "updated DeLone and McLean IS success model" is reviewed as a mature model in measuring health information system (HIS) success. This research provided an evaluation model to estimate the implementation of electronic medical records (EMR) systems from a health professional perspective by combined the updated DeLone and McLean IS success model, data quality management model, and EMR systems safety attributes. Based on evidence-based management (EBM), this research could be regarded as an empirical example for further EMR systems research since it not only provided a model to measure the Taiwanese EMR systems in two hospitals by …
Analyzing The Key Variables In The Adoption Process Of Hl7, Alejandro E. Flores Zuniga, Khin Than Win
Analyzing The Key Variables In The Adoption Process Of Hl7, Alejandro E. Flores Zuniga, Khin Than Win
Dr Khin Win
The intention of this paper is to provide an analysis of variables that could affect the adoption of HL7 message standard. Based on the review of 33 cases where HL7 was successfully implemented the authors present relevant evidence related to inherent limitation of HL7. The result from this study indicates that it is necessary to enhance the standard to overcome particular limitations and facilitate the implementation of inter-institutional software interfaces based on HL7.
The Path Space Of A Higher-Rank Graph, Samuel B. Webster
The Path Space Of A Higher-Rank Graph, Samuel B. Webster
Dr Samuel Webster
We construct a locally compact Hausdorff topology on the path space of a finitely aligned k -graph Λ . We identify the boundary-path space ∂Λ as the spectrum of a commutative C ∗ -subalgebra D Λ of C ∗ (Λ) . Then, using a construction similar to that of Farthing, we construct a finitely aligned k -graph Λ ˜ with no sources in which Λ is embedded, and show that ∂Λ is homeomorphic to a subset of ∂Λ ˜ . We show that when Λ is row-finite, we can identify C ∗ (Λ) with a full corner of C ∗ …
On Binary Reflected Gray Codes And Functions, Martin W. Bunder, Keith P. Tognetti, Glen Wheeler
On Binary Reflected Gray Codes And Functions, Martin W. Bunder, Keith P. Tognetti, Glen Wheeler
Dr Keith Tognetti
The Binary Reflected Gray Code function b is defined as follows: If m is a nonnegative integer, then b(m) is the integer obtained when initial zeros are omitted from the binary reflected Gray code of length m. This paper examines this Gray code function and its inverse and gives simple algorithms to generate both. It also simplifies Conder’s result that the jth letter of the kth word of the binary reflected Gray code of length n, is (2n − 2n−j − 1 [2n − 2n−j−1 − k/2]) mod 2, by replacing the binomial coefficient by [(k-1)/(2n-j+1)+1/2].
Fuzzy Logic-Based Image Fusion For Multi-View Through-The-Wall Radar, Cher Hau Seng, Abdesselam Bouzerdoum, Fok Hing Chi Tivive, Moeness G. Amin
Fuzzy Logic-Based Image Fusion For Multi-View Through-The-Wall Radar, Cher Hau Seng, Abdesselam Bouzerdoum, Fok Hing Chi Tivive, Moeness G. Amin
Dr Fok Hing Chi Tivive
In this paper, we propose a new technique for image fusion in multi-view through-the-wall radar imaging system. As most existing image fusion methods for through-the-wall radar imaging only consider a global fusion operator, it is desirable to consider the differences between each pixel using a local operator. Here, we present a fuzzy logic-based method for pixel-wise image fusion. The performance of the proposed method is evaluated on both simulated and real data from through-the-wall radar imaging system. Experimental results show that the proposed method yields improved performance, compared to existing methods.
A Gender Recognition System Using Shunting Inhibitory Convolutional Neural Networks, Fok Hing Chi Tivive, Abdesselam Bouzerdoum
A Gender Recognition System Using Shunting Inhibitory Convolutional Neural Networks, Fok Hing Chi Tivive, Abdesselam Bouzerdoum
Dr Fok Hing Chi Tivive
In this paper, we employ shunting inhibitory convolutional neural networks to develop an automatic gender recognition system. The system comprises two modules: a face detector and a gender classifier. The human faces are first detected and localized in the input image. Each detected face is then passed to the gender classifier to determine whether it is a male or female. Both the face detection and gender classification modules employ the same neural network architecture; however, the two modules are trained separately to extract different features for face detection and gender classification. Tested on two different databases, Web and BioID database, …
Automatic Human Motion Classification From Doppler Spectrograms, Fok Hing Chi Tivive, Abdesselam Bouzerdoum, Moeness G. Amin
Automatic Human Motion Classification From Doppler Spectrograms, Fok Hing Chi Tivive, Abdesselam Bouzerdoum, Moeness G. Amin
Dr Fok Hing Chi Tivive
No abstract provided.
Adaptive Hierarchical Architecture For Visual Recognition, Fok Hing Chi Tivive, Abdesselam Bouzerdoum, Son Lam Phung, Khan M. Iftekharuddin
Adaptive Hierarchical Architecture For Visual Recognition, Fok Hing Chi Tivive, Abdesselam Bouzerdoum, Son Lam Phung, Khan M. Iftekharuddin
Dr Fok Hing Chi Tivive
We propose a new hierarchical architecture for visual pattern classification. The new architecture consists of a set of fixed, directional filters and a set of adaptive filters arranged in a cascade structure. The fixed filters are used to extract primitive features such as orientations and edges that are present in a wide range of objects, whereas the adaptive filters can be trained to find complex features that are specific to a given object. Both types of filters are based on the biological mechanism of shunting inhibition. The proposed architecture is applied to two problems: pedestrian detection and car detection. Evaluation …
Improved Facial Expression Recognition With Trainable 2-D Filters And Support Vector Machines, Peiyao Li, Son Lam Phung, Abdesselam Bouzerdoum, Fok Hing Chi Tivive
Improved Facial Expression Recognition With Trainable 2-D Filters And Support Vector Machines, Peiyao Li, Son Lam Phung, Abdesselam Bouzerdoum, Fok Hing Chi Tivive
Dr Fok Hing Chi Tivive
Facial expression is one way humans convey their emotional states. Accurate recognition of facial expressions is essential in perceptual human-computer interface, robotics and mimetic games. This paper presents a novel approach to facial expression recognition from static images that combines fixed and adaptive 2-D filters in a hierarchical structure. The fixed filters are used to extract primitive features. They are followed by the adaptive filters that are trained to extract more complex facial features. Both types of filters are non-linear and are based on the biological mechanism of shunting inhibition. The features are finally classified by a support vector machine. …
A Car Detection System Based On Hierarchical Visual Features, Fok Hing Chi Tivive, Abdesselam Bouzerdoum
A Car Detection System Based On Hierarchical Visual Features, Fok Hing Chi Tivive, Abdesselam Bouzerdoum
Dr Fok Hing Chi Tivive
In this paper, we address the problem of detecting and localizing cars in still images. The proposed car detection system is based on a hierarchical feature detector in which the processing units are shunting inhibitory neurons. To reduce the training time and complexity of the network, the shunting inhibitory neurons in the first layer are implemented as directional nonlinear filters, whereas the neurons in the second layer have trainable parameters. A multi-resolution processing scheme is implemented so as to detect cars of different sizes, and to reduce the number of false positives during the detection stage, an adaptive thresholding strategy …