Wanli Ma - Academia.edu (original) (raw)

Papers by Wanli Ma

The 2013 International Joint Conference on Neural Networks (IJCNN), 2013

ABSTRACT This paper proposes a general aggregate model for improving performance of multi-class B... more ABSTRACT This paper proposes a general aggregate model for improving performance of multi-class Brain-Computer Interface (BCI) systems. In BCI systems, activation and delay are well known issues in conducting experiments. The delay of meaningful brain signal depends on subjects, tasks and experimental design. Therefore, within a trial it is not easy to identify where meaningful brain signal starts and ends. Most of current methods estimate the delay and extract a portion of meaningful brain signal in a trial and use this signal as a representative for the whole trial. Instead of doing so, our proposed aggregate model divides a trial into overlapping frames and treat them equally. These frames are classified and their results are then aggregated together to form classification result of the trial. From the general aggregate model, we derive two specific aggregate models using two state-of-the-art Common Spatial Patterns (CSP)-based methods for feature extraction. We performed experiments on Dataset 2a used in BCI Competition IV to evaluate the proposed models. This dataset was designed for motor imagery classification with 4 classes. Preliminary experimental results show that our proposed aggregate models are up to 8% better than the original CSP-based methods. Furthermore, we show that our aggregate model can be easily extended to online BCI systems.

Proceedings of 1994 IEEE Symposium on Visual Languages, 1994

Researchers have proposed many visualisation tools that assist the development of parallel progra... more Researchers have proposed many visualisation tools that assist the development of parallel programs. A number of graph formalisms or notations - which we will call graph models - have been used to visualise various aspects of parallel programs and their executions. This paper attempts to classify and compare these graph models which provide different information at different stages of parallel

The 2013 International Joint Conference on Neural Networks (IJCNN), 2013

ABSTRACT In a dynamic operational environment such as robotic or an autonomous navigation system,... more ABSTRACT In a dynamic operational environment such as robotic or an autonomous navigation system, the interactions between humans and objects around them play an important role (context-awareness). The task of recognizing and tracking such objects introduces many challenges in the machine vision research field. In this paper, we propose a novel method that combines the information from modern depth sensors with conventional machine vision techniques such as Scale-invariant Feature Transform (SIFT) to produce a system that is capable of performing object recognition and tracking with a satisfactory level of accuracy in real-time. A prototype is implemented and tested to confirm that the proposed method does provide better performance comparing with currently used methods in image processing.

Lecture Notes in Computer Science, 2013

Lecture Notes in Computer Science, 2013

2014 International Joint Conference on Neural Networks (IJCNN), 2014

Lecture Notes in Computer Science, 2013

The 2013 International Joint Conference on Neural Networks (IJCNN), 2013

ABSTRACT Kernel Generalised Learning Vector Quantisation (KGLVQ) was proposed to extend Generalis... more ABSTRACT Kernel Generalised Learning Vector Quantisation (KGLVQ) was proposed to extend Generalised Learning Vector Quantisation into the kernel feature space to deal with complex class boundaries and thus yielded promising performance for complex classification tasks in pattern recognition. However KGLVQ does not follow the maximal margin principle, which is crucial for kernel-based learning methods. In this paper we propose a maximal margin approach (MLVQ) to the KGLVQ algorithm. MLVQ inherits the merits of KGLVQ and also follows the maximal margin principle to improve the generalisation capability. Experiments performed on the well-known data sets available in UCI repository show promising classification results for the proposed method.

Advances in Intelligent Systems and Computing, 2014

ABSTRACT Recently, electroencephalography (EEG) is considered as a new potential type of user aut... more ABSTRACT Recently, electroencephalography (EEG) is considered as a new potential type of user authentication with many security advantages of being difficult to fake, impossible to observe or intercept, unique, and alive person recording require. The difficulty is that EEG signals are very weak and subject to the contamination from many artifact signals. However, for the applications in human health, true EEG signals, without the contamination, is highly desirable, but for the purposes of authentication, where stable and repeatable patterns from the source signals are critical, the origins of the signals are of less concern. In this paper, we propose an EEG-based authentication method, which is simple to implement and easy to use, by taking the advantage of EEG artifacts, generated by a number of purposely designed voluntary facial muscle movements. These tasks can be single or combined, depending on the level of security required. Our experiment showed that using EEG artifacts for user authentication in multilevel security systems is promising.

Lecture Notes in Computer Science, 2013

2014 International Joint Conference on Neural Networks (IJCNN), 2014

ICTACS 2006 - Proceedings of the First International Conference on Theories and Applications of Computer Science 2006, 2007

ICTACS 2006 - Proceedings of the First International Conference on Theories and Applications of Computer Science 2006, 2007

ICTACS 2006 - Proceedings of the First International Conference on Theories and Applications of Computer Science 2006, 2007

The keyword list-based spam email detection system uses keywords in a blacklist to detect spam em... more The keyword list-based spam email detection system uses keywords in a blacklist to detect spam emails. To avoid detection, keywords are written as misspellings, for example "virrus", "vi-rus" and "viruus" instead of "virus". The system needs to update the blacklist from time ...

2008 IEEE International Conference on Intelligence and Security Informatics, 2008

Abstract—The 3 most important issues for anomaly detection based intrusion detection systems by u... more Abstract—The 3 most important issues for anomaly detection based intrusion detection systems by using data mining methods are: feature selection, data value normalization, and the choice of data mining algorithms. In this paper, we study primarily the feature selection of ...

Lecture Notes in Computer Science, 2006

Abstract. This paper proposes using multiagent system technology to solve the problem of printing... more Abstract. This paper proposes using multiagent system technology to solve the problem of printing across heterogeneous operating systems without re-implementing printer drivers. The printing problem comes from a real world application, where we have to print from Solaris ...

The 2013 International Joint Conference on Neural Networks (IJCNN), 2013

ABSTRACT This paper proposes a general aggregate model for improving performance of multi-class B... more ABSTRACT This paper proposes a general aggregate model for improving performance of multi-class Brain-Computer Interface (BCI) systems. In BCI systems, activation and delay are well known issues in conducting experiments. The delay of meaningful brain signal depends on subjects, tasks and experimental design. Therefore, within a trial it is not easy to identify where meaningful brain signal starts and ends. Most of current methods estimate the delay and extract a portion of meaningful brain signal in a trial and use this signal as a representative for the whole trial. Instead of doing so, our proposed aggregate model divides a trial into overlapping frames and treat them equally. These frames are classified and their results are then aggregated together to form classification result of the trial. From the general aggregate model, we derive two specific aggregate models using two state-of-the-art Common Spatial Patterns (CSP)-based methods for feature extraction. We performed experiments on Dataset 2a used in BCI Competition IV to evaluate the proposed models. This dataset was designed for motor imagery classification with 4 classes. Preliminary experimental results show that our proposed aggregate models are up to 8% better than the original CSP-based methods. Furthermore, we show that our aggregate model can be easily extended to online BCI systems.

Proceedings of 1994 IEEE Symposium on Visual Languages, 1994

Researchers have proposed many visualisation tools that assist the development of parallel progra... more Researchers have proposed many visualisation tools that assist the development of parallel programs. A number of graph formalisms or notations - which we will call graph models - have been used to visualise various aspects of parallel programs and their executions. This paper attempts to classify and compare these graph models which provide different information at different stages of parallel

The 2013 International Joint Conference on Neural Networks (IJCNN), 2013

ABSTRACT In a dynamic operational environment such as robotic or an autonomous navigation system,... more ABSTRACT In a dynamic operational environment such as robotic or an autonomous navigation system, the interactions between humans and objects around them play an important role (context-awareness). The task of recognizing and tracking such objects introduces many challenges in the machine vision research field. In this paper, we propose a novel method that combines the information from modern depth sensors with conventional machine vision techniques such as Scale-invariant Feature Transform (SIFT) to produce a system that is capable of performing object recognition and tracking with a satisfactory level of accuracy in real-time. A prototype is implemented and tested to confirm that the proposed method does provide better performance comparing with currently used methods in image processing.

Lecture Notes in Computer Science, 2013

Lecture Notes in Computer Science, 2013

2014 International Joint Conference on Neural Networks (IJCNN), 2014

Lecture Notes in Computer Science, 2013

The 2013 International Joint Conference on Neural Networks (IJCNN), 2013

ABSTRACT Kernel Generalised Learning Vector Quantisation (KGLVQ) was proposed to extend Generalis... more ABSTRACT Kernel Generalised Learning Vector Quantisation (KGLVQ) was proposed to extend Generalised Learning Vector Quantisation into the kernel feature space to deal with complex class boundaries and thus yielded promising performance for complex classification tasks in pattern recognition. However KGLVQ does not follow the maximal margin principle, which is crucial for kernel-based learning methods. In this paper we propose a maximal margin approach (MLVQ) to the KGLVQ algorithm. MLVQ inherits the merits of KGLVQ and also follows the maximal margin principle to improve the generalisation capability. Experiments performed on the well-known data sets available in UCI repository show promising classification results for the proposed method.

Advances in Intelligent Systems and Computing, 2014

ABSTRACT Recently, electroencephalography (EEG) is considered as a new potential type of user aut... more ABSTRACT Recently, electroencephalography (EEG) is considered as a new potential type of user authentication with many security advantages of being difficult to fake, impossible to observe or intercept, unique, and alive person recording require. The difficulty is that EEG signals are very weak and subject to the contamination from many artifact signals. However, for the applications in human health, true EEG signals, without the contamination, is highly desirable, but for the purposes of authentication, where stable and repeatable patterns from the source signals are critical, the origins of the signals are of less concern. In this paper, we propose an EEG-based authentication method, which is simple to implement and easy to use, by taking the advantage of EEG artifacts, generated by a number of purposely designed voluntary facial muscle movements. These tasks can be single or combined, depending on the level of security required. Our experiment showed that using EEG artifacts for user authentication in multilevel security systems is promising.

Lecture Notes in Computer Science, 2013

2014 International Joint Conference on Neural Networks (IJCNN), 2014

ICTACS 2006 - Proceedings of the First International Conference on Theories and Applications of Computer Science 2006, 2007

ICTACS 2006 - Proceedings of the First International Conference on Theories and Applications of Computer Science 2006, 2007

ICTACS 2006 - Proceedings of the First International Conference on Theories and Applications of Computer Science 2006, 2007

The keyword list-based spam email detection system uses keywords in a blacklist to detect spam em... more The keyword list-based spam email detection system uses keywords in a blacklist to detect spam emails. To avoid detection, keywords are written as misspellings, for example "virrus", "vi-rus" and "viruus" instead of "virus". The system needs to update the blacklist from time ...

2008 IEEE International Conference on Intelligence and Security Informatics, 2008

Abstract—The 3 most important issues for anomaly detection based intrusion detection systems by u... more Abstract—The 3 most important issues for anomaly detection based intrusion detection systems by using data mining methods are: feature selection, data value normalization, and the choice of data mining algorithms. In this paper, we study primarily the feature selection of ...

Lecture Notes in Computer Science, 2006

Abstract. This paper proposes using multiagent system technology to solve the problem of printing... more Abstract. This paper proposes using multiagent system technology to solve the problem of printing across heterogeneous operating systems without re-implementing printer drivers. The printing problem comes from a real world application, where we have to print from Solaris ...