Recognising audio-visual speech in vehicles using the AVICAR database

Interacting with technology within a vehicle environment using a voice interface can greatly reduce the effects of driver distraction. Most current approaches to this problem only utilise the audio signal, making them susceptible to acoustic noise. An obvious approach to circumvent this is to use the visual modality in addition. However, capturing, storing and distributing audio-visual data in a vehicle environment is very costly and difficult. One current dataset available for such research is the AVICAR [1] database. Unfortunately this database is largely unusable due to timing mismatch between the two streams and in addition, no protocol is available. We have overcome this problem by re-synchronising the streams on the phone-number portion of the dataset and established a protocol for further research. This paper presents the first audio-visual results on this dataset for speaker-independent speech recognition. We hope this will serve as a catalyst for future research in this area.

Face authentication test on the BANCA database

This work details the results of a face authentication test (FAT2004) (http://www.ee.surrey.ac.uk/banca/icpr2004) held in conjunction with the 17th International Conference on Pattern Recognition. The contest was held on the publicly available BANCA database (http://www.ee.surrey.ac.uk/banca) according to a defined protocol (E. Bailly-Bailliere et al., June 2003). The competition also had a sequestered part in which institutions had to submit their algorithms for independent testing. 13 different verification algorithms from 10 institutions submitted results. Also, a standard set of face recognition software packages from the Internet (http://www.cs.colostate.edu/evalfacerec) were used to provide a baseline performance measure.

Improving web database search incorporating users query information

The growing importance and need of data processing for information extraction is vital for Web databases. Due to the sheer size and volume of databases, retrieval of relevant information as needed by users has become a cumbersome process. Information seekers are faced by information overloading - too many result sets are returned for their queries. Moreover, too few or no results are returned if a specific query is asked. This paper proposes a ranking algorithm that gives higher preference to a user’s current search and also utilizes profile information in order to obtain the relevant results for a user’s query.

The scalability and the strategy for EMR database encryption techniques

EMR (Electronic Medical Record) is an emerging technology that is highly-blended between non-IT and IT area. One methodology is to link the non-IT and IT area is to construct databases. Nowadays, it supports before and after-treatment for patients and should satisfy all stakeholders such as practitioners, nurses, researchers, administrators and financial departments and so on. In accordance with the database maintenance, DAS (Data as Service) model is one solution for outsourcing. However, there are some scalability and strategy issues when we need to plan to use DAS model properly. We constructed three kinds of databases such as plan-text, MS built-in encryption which is in-house model and custom AES (Advanced Encryption Standard) - DAS model scaling from 5K to 2560K records. To perform custom AES-DAS better, we also devised Bucket Index using Bloom Filter. The simulation showed the response times arithmetically increased in the beginning but after a certain threshold, exponentially increased in the end. In conclusion, if the database model is close to in-house model, then vendor technology is a good way to perform and get query response times in a consistent manner. If the model is DAS model, it is easy to outsource the database, however, some techniques like Bucket Index enhances its utilization. To get faster query response times, designing database such as consideration of the field type is also important. This study suggests cloud computing would be a next DAS model to satisfy the scalability and the security issues.

The proposal on the effective query mechanism for the encrypted database

In the recent past, there are some social issues when personal sensitive data in medical database were exposed. The personal sensitive data should be protected and access must be accounted for. Protecting the sensitive information is possible by encrypting such information. The challenge is querying the encrypted information when making the decision. Encrypted query is practically somewhat tedious task. So we present the more effective method using bucket index and bloom filter technology. We find that our proposed method shows low memory and fast efficiency comparatively. Simulation approaches on data encryption techniques to improve health care decision making processes are presented in this paper as a case scenario.

A database for person re-identification in multi-camera surveillance networks

Person re-identification involves recognising individuals in different locations across a network of cameras and is a challenging task due to a large number of varying factors such as pose (both subject and camera) and ambient lighting conditions. Existing databases do not adequately capture these variations, making evaluations of proposed techniques difficult. In this paper, we present a new challenging multi-camera surveillance database designed for the task of person re-identification. This database consists of 150 unscripted sequences of subjects travelling in a building environment though up to eight camera views, appearing from various angles and in varying illumination conditions. A flexible XML-based evaluation protocol is provided to allow a highly configurable evaluation setup, enabling a variety of scenarios relating to pose and lighting conditions to be evaluated. A baseline person re-identification system consisting of colour, height and texture models is demonstrated on this database.

Interactive product browsing and configuration using remote augmented reality sales services

Real-time remote sales assistance is an underdeveloped component of online sales services. Solutions involving web page text chat, telephony and video support prove problematic when seeking to remotely guide customers in their sales processes, especially with configurations of physically complex artefacts. Recently, there has been great interest in the application of virtual worlds and augmented reality to create synthetic environments for remote sales of physical artefacts. However, there is a lack of analysis and development of appropriate software services to support these processes. We extend our previous work with the detailed design of configuration context services to support the management of an interactive sales session using augmented reality. We detail the context and configuration services required, presenting a novel data service streaming configuration information to the vendor for business analytics. We expect that a fully implemented configuration management service, based on our design, will improve the remote sales experience for both customers and vendors alike via analysis of the streamed information.

Supporting the learning of rapid application development in a database environment

Intelligent Tutoring Systems (ITSs) are computer systems designed to provide individualised help to students, learning in a problem solving context. The difference between an ITS and a Computer Assisted Instruction (CAI) system is that an ITS has a Student Model which allows it to provide a better educational environment. The Student Model contains information on what the student knows, and does not know, about the domain being learnt, as well as other personal characteristics such as preferred learning style. This research has resulted in the design and development of a new ITS: Personal Access Tutor (PAT). PAT is an ITS that helps students to learn Rapid Application Development in a database environment. More specifically, PAT focuses on helping students to learn how to create forms and reports in Microsoft Access. To provide an augmented learning environment, PAT’s architecture is different to most other ITSs. Instead of having a simulation, PAT uses a widelyused database development environment (Microsoft Access). This enables the students to ask for help, while developing real applications using real database software. As part of this research, I designed and created the knowledge base required for PAT. This contains four models: the domain, student, tutoring and exercises models. The Instructional Expert I created for PAT provides individualised help to the students to help them correctly finish each exercise, and also proposes the next exercise that a student should work on. PAT was evaluated by students enrolled in the Databases subject at QUT, and by staff members involved in teaching the subject. The results of the evaluation were positive and are discussed in the thesis.

A new classification and database for stratospheric dust particles

With the increasing number of stratospheric particles available for study (via the U2 and/or WB57F collections), it is essential that a simple, yet rational, classification scheme be developed for general use. Such a scheme should be applicable to all particles collected from the stratosphere, rather than limited to only extraterrestial or chemical sub-groups. Criteria for the efficacy of such a scheme would include: (a) objectivity , (b) ease of use, (c) acceptance within the broader scientific community and (d) how well the classification provides intrinsic categories which are consistent with our knowledge of particle types present in the stratosphere.

A new database compilation of whole-rock chemical and geochronological data of igneous rocks in Queensland : a new resource for HDR geothermal resource exploration

The Geothermal industry in Australia and Queensland is in its infancy and for hot dry rock (HDR) geothermal energy, it is very much in the target identification and resource definition stages. As a key effort to assist the geothermal industry and exploration for HDR in Queensland, we are developing a comprehensive and new integrated geochemical and geochronological database on igneous rocks. To date, around 18,000 igneous rocks have been analysed across Queensland for chemical and/or age information. However, these data currently reside in a number of disparate datasets (e.g., Ozchron, Champion et al., 2007, Geological Survey of Queensland, journal publications, and unpublished university theses). The goal of this project is to collate and integrate these data on Queensland igneous rocks to improve our understanding of high heat producing granites in Queensland, in terms of their distribution (particularly in the subsurface), dimensions, ages, and controlling factors in their genesis.

Refinements and developments on the stratospheric dust database and classification scheme

Greater than 750 individual particles have now been selected from collection flags housed in the JSC Cosmic Dust Curatorial Facility and most have been documented in the Cosmic Dust Catalogs [1]. As increasing numbers of particles are placed in Cosmic Dust Collections, and a greater diversity of particles are introduced to the stratosphere through natural and man-made processes (e.g. decaying orbits of space debris [2]), there is an even greater need for a classification scheme to encompass all stratospheric particles rather than only extraterrestrial particles. The fundamental requirements for a suitable classification scheme have been outlined in earlier communications [3,4]. A quantitative survey of particles on collection flag W7017 indicates that there is some bias in the number of samples selected within a given category for the Cosmic Dust Catalog [5]. However, the sample diversity within this selection is still appropriate for the development of a reliable classification scheme. In this paper, we extend the earlier works on stratospheric particle classification to include particles collected during the period May 1981 to November 1983.