Robust Automatic Speaker Diarisation of Audio Documents by Exploiting Prior Sources of Information. Speaker Diarisation, the task of determining who spoke when, is a technology fundamental in deriving intelligent information from audio and multimedia resources. The requirement for efficient and accurate Speaker Diarisation systems, portable across different domains is heightened by the explosive growth of audio and multimedia archives online and throughout the world. This research will provide t ....Robust Automatic Speaker Diarisation of Audio Documents by Exploiting Prior Sources of Information. Speaker Diarisation, the task of determining who spoke when, is a technology fundamental in deriving intelligent information from audio and multimedia resources. The requirement for efficient and accurate Speaker Diarisation systems, portable across different domains is heightened by the explosive growth of audio and multimedia archives online and throughout the world. This research will provide the foundation for a commercial service of automatic Speaker Diarisation to be developed, growing Australia's impact on the information and communications technology (ICT) sector. The outcome of this research will also assist in the tracking of terrorist and unlawful activity by enabling effective intelligence gathering from different audio sources.Read moreRead less
Scalable Robust Video Surveillance over Constrained Networks. Real-time monitoring of large numbers of people is becoming increasingly important for applications such as efficient service delivery and security against both common crime and terrorism. The use of human operators for such tasks is infeasible due to the large amount of data collected. Existing autonomous video surveillance systems are prone to high numbers of false alarms and often require expensive hardware. This proposal seeks ....Scalable Robust Video Surveillance over Constrained Networks. Real-time monitoring of large numbers of people is becoming increasingly important for applications such as efficient service delivery and security against both common crime and terrorism. The use of human operators for such tasks is infeasible due to the large amount of data collected. Existing autonomous video surveillance systems are prone to high numbers of false alarms and often require expensive hardware. This proposal seeks to address both difficulties by using rigorous statistical signal processing methods to optimally fuse information from a network of low-cost cameras.Read moreRead less
Development of an active noise control system for sleeper seats on large commercial aircraft. Possible avenues will be investigated to actively reduce aircraft cabin noise experienced by passengers in sleeper seats, using localised active noise control (ANC). Previous work has focused on headsets and upright seat headrests which represent a different problem to the partially enclosed sleeper seats considered here. Efficiency and robustness problems that affect existing ANC systems will be addres ....Development of an active noise control system for sleeper seats on large commercial aircraft. Possible avenues will be investigated to actively reduce aircraft cabin noise experienced by passengers in sleeper seats, using localised active noise control (ANC). Previous work has focused on headsets and upright seat headrests which represent a different problem to the partially enclosed sleeper seats considered here. Efficiency and robustness problems that affect existing ANC systems will be addressed. A prototype system will be produced for a business class sleeper seat in a wide body aircraft. A second outcome is the establishment of a robust integrated system design procedure that can be used to quickly develop ANC systems for future designs.Read moreRead less
Data Fusion Techniques for Electro-Mechanical Braking Systems. The main focus of this project is to develop data fusion techniques for clamp force estimation and optimum utilisation of redundant information in a brake-by-wire system. Efficient integration of redundant information in an EMB system is expected to significantly improve the reliability and fault tolerance of such systems. The need for costly and complicated clamp force measurement sensors in electric callipers will also be eliminate ....Data Fusion Techniques for Electro-Mechanical Braking Systems. The main focus of this project is to develop data fusion techniques for clamp force estimation and optimum utilisation of redundant information in a brake-by-wire system. Efficient integration of redundant information in an EMB system is expected to significantly improve the reliability and fault tolerance of such systems. The need for costly and complicated clamp force measurement sensors in electric callipers will also be eliminated by accurate estimation of the clamp force signal, through fusion of more readily available measurements. Development of the proposed data fusion techniques influences the design of future EMBs and enhances the functionality of existing brake-by-wire systems.Read moreRead less
Compositional determination of liquefied petroleum gas: Improving engine cold start performance in multipoint LPG-injected engines. Unlike gasoline, the composition of liquefied petroleum gas (LPG) is subject to change depending on a variety of factors including reservoir location and local market pricing. During normal automotive multipoint injection engine operation, closed loop feedback from engine sensors allows the effects of the compositional variations to be overcome and the engine to ope ....Compositional determination of liquefied petroleum gas: Improving engine cold start performance in multipoint LPG-injected engines. Unlike gasoline, the composition of liquefied petroleum gas (LPG) is subject to change depending on a variety of factors including reservoir location and local market pricing. During normal automotive multipoint injection engine operation, closed loop feedback from engine sensors allows the effects of the compositional variations to be overcome and the engine to operate close to optimal levels. However during cold start, the feedback sensors are not operational, and engine performance may deteriorate due to unknown fuel composition - in the worst case the engine may not start at all. This project aims to develop unique methods of estimating the composition of LPG based on existing sensor information to improve performance during cold start.Read moreRead less
Design of Neonatal Seizure Diagnosis Methods Using Time-Frequency Signal Processing Techniques. Seizures occur in approximately 0.5% of all newborns. They are often the only indicator of an early dysfunction in central nervous system (CNS). Their occurrence raises concerns about the underlying cause, its effect on the brain, and the appropriate treatment. Newborn seizures are mostly sub-clinical and only detected through the Electroencephalogram. For an efficient diagnosis, seizure classificatio ....Design of Neonatal Seizure Diagnosis Methods Using Time-Frequency Signal Processing Techniques. Seizures occur in approximately 0.5% of all newborns. They are often the only indicator of an early dysfunction in central nervous system (CNS). Their occurrence raises concerns about the underlying cause, its effect on the brain, and the appropriate treatment. Newborn seizures are mostly sub-clinical and only detected through the Electroencephalogram. For an efficient diagnosis, seizure classification systems were proposed based on visual observations. This project proposes developing a novel approach to automate the classification process using time-frequency (TF) signal processing techniques based on the multi-channel characteristics of the seizure; namely: A) TF signature B) origin, and C) propagation behaviour.Read moreRead less
Dynamic Scheduling and Stochastic Control for Sensor Networks. Sensor networks are rapidly becoming important in applications from environmental monitoring, navigation to border surveillance. However, due to bandwidth constraints, even very simple networks have proven to be very complex to properly control. It is now necessary to efficiently allocate the 'limited available bandwidth' to sensors in order to share the most valuable data over the network. Therefore, this project proposes new techn ....Dynamic Scheduling and Stochastic Control for Sensor Networks. Sensor networks are rapidly becoming important in applications from environmental monitoring, navigation to border surveillance. However, due to bandwidth constraints, even very simple networks have proven to be very complex to properly control. It is now necessary to efficiently allocate the 'limited available bandwidth' to sensors in order to share the most valuable data over the network. Therefore, this project proposes new techniques using concepts of dynamic sensor scheduling and stochastic control to provide computationally feasible and near optimal solutions to the limited and varying bandwidth problem. This work will greatly enhance the operational performance of distributed sensor networks.Read moreRead less
The next generation speaker recognition system. The next generation of speaker recognition technologies developed through this project will enable secure person authentication by voice in financial transactions and benefit the community through the elimination of identity fraud. This project will safeguard Australia by identifying criminal suspects using their voice and combat terrorism by using voice to locate and track terrorists.
Scaling Up Satellite Communications for the Internet of Things. The Internet of Things (IoT) is a revolution in sensing and automation that is becoming vital for industries including farming and mining. However, in remote areas, it is especially challenging to connect the large numbers of devices needed. This project will develop novel signal processing and communications approaches to deliver high quality data services to vast numbers of remote IoT devices, distributed over continental scales c ....Scaling Up Satellite Communications for the Internet of Things. The Internet of Things (IoT) is a revolution in sensing and automation that is becoming vital for industries including farming and mining. However, in remote areas, it is especially challenging to connect the large numbers of devices needed. This project will develop novel signal processing and communications approaches to deliver high quality data services to vast numbers of remote IoT devices, distributed over continental scales connected via low earth orbit (LEO) satellite constellations. It will provide the tools for LEO satellite service providers to dimension their networks and assist IoT providers to scale their remote sensor networks and IoT deployments, with ever increasing demand on the limited satellite bandwidth.Read moreRead less
Developing a Smart Monitoring System for Leakage Currents from Insulators on Wooden Poles. Numerous wooden poles are used for electricity power transmission in urban and rural areas of Australia. Insulators suspended on poles are subject to contamination and moisture that cause partial discharge currents to flow through the wooden poles, resulting in pole fires leading to loss of power to customers and possible bush fires. This project aims at studying the characteristics of leakage currents fr ....Developing a Smart Monitoring System for Leakage Currents from Insulators on Wooden Poles. Numerous wooden poles are used for electricity power transmission in urban and rural areas of Australia. Insulators suspended on poles are subject to contamination and moisture that cause partial discharge currents to flow through the wooden poles, resulting in pole fires leading to loss of power to customers and possible bush fires. This project aims at studying the characteristics of leakage currents from insulators on wooden poles in Australian conditions and developing a smart monitoring system to detect and prevent pole fires caused by leakage currents. The outcomes will reduce the risk of pole fires, hence improving public safety, reliability of power supply and sustainability of the Australian power industry.Read moreRead less