Edmund M-K. Lai

Verified

Edmund verified their affiliation via an institutional email.

Learn more

Verified

Edmund verified their affiliation via an institutional email.

Learn more

• PhD
• Professor at Auckland University of Technology

This paper presents an Adaptive Dynamic Attribute and Rule (ADAR) framework designed to address the challenges posed by high-dimensional data in neuro-fuzzy inference systems. By integrating dual weighting mechanisms-assigning adaptive importance to both attributes and rules-together with automated growth and pruning strategies, ADAR adaptively str...

In evolutionary multitasking, strategies such as crossover operators and skill factor assignment are critical for effective knowledge transfer. Existing improvements to crossover operators primarily focus on low-dimensional variable combinations, such as arithmetic crossover or partially mapped crossover, which are insufficient for modeling complex...

This study proposes a dynamic safe car-following strategy that is based on dynamic adjustment of headway time with jerk suppression. Reinforcement learning models trained with this strategy result in enhanced safety and driving comfort, validated using real driving data from the Next Generation Simulation (NGSIM) I-80 and HighD datasets. Simulation...

This survey explores the evolution of test scenario generation for autonomous vehicles (AVs), distinguishing between non-adaptive and adaptive scenario approaches. Non-adaptive scenarios, where dynamic objects follow predetermined scripts, provide repeatable and reliable tests but fail to capture the complexity and unpredictability of real-world tr...

Distinguishing stable and fluctuating psychopathological features in young individuals at Ultra High Risk (UHR) for psychosis is challenging, but critical for building robust, accurate, early clinical detection and prevention capabilities. Over a 24-month period, 159 UHR individuals were assessed using the Positive and Negative Symptom Scale (PANSS...

Data augmentation is crucial for enhancing the performance of text classification models when labelled training data are scarce. For natural language processing (NLP) tasks, large language models (LLMs) are able to generate high-quality augmented data. But a fundamental understanding of the reasons for their effectiveness remains limited. This pape...

Data augmentation is necessary if the amount of training data is insufficient for supervised learning. For natural language processing tasks, obtaining good quality augmented data is not easy. This paper introduces GATFilter, a novel method for filtering out inappropriate augmented textual data for text classification (TC). Utilizing geometric conc...

Quantification research has sought to accurately estimate class distributions under dataset shift. While existing methods perform well under assumed conditions of shift, it is not always clear whether such assumptions will hold in a given application. This work extends the analysis and experimental evaluation of our Gain-Some-Lose-Some (GSLS) model...

Serverless computing allows developers to create workflows for complex tasks through the composition of serverless functions. Current serverless workflow engines rely on master-side pattern which do not permit direct interaction between consecutive serverless functions in the workflow. In this paper, a decentralized worker-side pattern is proposed...

The phenomenon known as the “echo chamber” has been widely acknowledged as a significant force affecting society. This has been particularly evident during the Covid-19 pandemic, wherein the echo chamber effect has significantly influenced public responses. Therefore, detecting echo chambers and mitigating their adverse impacts has become crucial t...

Selecting informative features, such as accurate biomarkers for disease diagnosis, prognosis and response to treatment, is an essential task in the field of bioinformatics. Medical data often contain thousands of features and identifying potential biomarkers is challenging due to small number of samples in the data, method dependence and non-reprod...

To effectively extract and classify the information from reports or documents and protect the privacy of the extracted results, we propose a privacy classification named Word Embedding Combination Privacy-preserving Support Vector Machine (WECPPSVM) model to classify the text. In addition, this paper also proposes the Privacy-preserving Distributio...

In this study, we explore the phenomenon of neural collapse (NC) in text classification using convolutional neural networks (CNNs) applied to the AG News dataset [23]. Initially, our findings indicate the occurrence of NC, which initially underperforms compared to a non-collapsed CNN. However, upon closer examination, we uncover an intriguing insig...

The rapid growth of information on the Internet has led to an overwhelming amount of opinions and comments on various activities, products, and services. This makes it difficult and time-consuming for users to process all the available information when making decisions. Text summarization, a Natural Language Processing (NLP) task, has been widely e...

Serverless computing allows developers to create workflows for complex tasks through the composition of serverless functions. Current serverless workflow engines rely on master-side patterns which hinder the interaction between serverless functions, causing performance issues. In this paper, a decentralized worker-side pattern is proposed that prov...

Finding predictors of social and cognitive impairment in non-transition Ultra-High-Risk individuals (UHR) is critical in prognosis and planning of potential personalised intervention strategies. Social and cognitive functioning observed in youth at UHR for psychosis may be protective against transition to clinically relevant illness. The current st...

Influence maximization is recognized as a crucial optimization problem, which aims to identify a limited set of influencers to maximize the coverage of influence dissemination in social networks. However, real-world social networks are usually dynamic and large-scale, which leads to difficulty in capturing real-time user and diffusion features to e...

Interpretable machine learning models for gene expression datasets are important for understanding the decision-making process of a classifier and gaining insights on the underlying molecular processes of genetic conditions. Interpretable models can potentially support early diagnosis before full disease manifestation. This is particularly importan...

With the rapid advancement of the Internet and social platforms, how to maximize the influence across popular online social networks has attracted great attention from both researchers and practitioners. Almost all the existing influence diffusion models assume that influence remains constant in the process of information spreading. However, in the...

Text Summarization is recognised as one of the NLP downstream tasks and it has been extensively investigated in recent years. It can assist people with perceiving the information rapidly from the Internet, including news articles, social posts, videos, etc. Most existing research works attempt to develop summarization models to produce a better out...

Several techniques for Human Activity Recognition (HAR) in a smart indoor environment have been developed and improved along with the rapid advancement of sensor technologies. However, recognizing multiple people’s activities is still challenging due to the complexity of their activities, such as parallel and collaborative activities. To address th...

New Zealand government's Rural Broadband Initiative (RBI) aims to invest 400 million New Zealand dollar to provide 99% of New Zealanders with access to 50 Mbps peak broadband speed, with the remaining 1% at 10 Mbps by 2025. By 2017, stage 1 of the RBI has been completed, and research is needed to find out the level of usage, proficiency, and produc...

Effective supervised training of modern machine learning models often requires large labelled training datasets, which could be prohibitively costly to acquire for many practical applications. Research addressing this problem has sought ways to leverage weak supervision sources, such as the user-defined heuristic labelling functions used in the dat...

Attention mechanisms have been incorporated into many neural network-based natural language processing (NLP) models. They enhance the ability of these models to learn and reason with long input texts. A critical part of such mechanisms is the computation of attention similarity scores between two elements of the texts using a similarity score funct...

In recent years, various approaches for multiresident Human Activity Recognition (HAR) in a smart indoor environment have been developed and improved along with the rapid development of sensors and AI technologies. Research in data stream-based Online Learning (OL) for multi-resident HAR is relatively new and a majority of the existing works have b...

Testing and validation of the functionalities and safety of automated vehicles shifted from a distance-based to a scenario-based method in the past decade. A number of domain-specific languages and systems were developed to support scenario-based testing. The aim of this paper is to review and compare the features and characteristics of the major s...

A key step in influence maximization in online social networks is the identification of a small number of users, known as influencers, who are able to spread influence quickly and widely to other users. The evolving nature of the topological structure of these networks makes it difficult to locate and identify these influencers. In this paper, we p...

Centralised machine learning brings in side effect pertaining to privacy preservation, most of machine learning methods prone to using the frameworks without privacy protection, as current methods for privacy preservation will slow down model training and testing. In order to resolve this problem, we develop a new noise generating method based on i...

Multi-resident Activity Recognition (AR), which has become a popular research field in smart environments, aims to recognize the activities of multiple residents based on data collected from various types of sensors, and sensor events segmentation is an important technique for enhancing the performance of activity recognition. While quite some segm...

Device-free or passive localization techniques allow positioning of targets, without requiring them to carry any form of transceiver or tag. In this paper, a novel device-free visible light positioning technique is proposed. It exploits the variation of the ambient light levels caused by a moving entity. The target is localized by employing a syste...

Reducing the travel time of emergency vehicles (EVs) is an effective way to improve critical services such as ambulance, fire, and police. Route optimisation and pre-emption are powerful techniques used to reduce EV travel time. This paper presents a systematic literature review of optimisation and pre-emption techniques for routing EVs. A detailed...

Device-free localization (DFL) systems that that rely on the wireless received signal strength indicator (RSSI) metric have been reported in literature for almost a decade. Histogram Distance based DFL (HD-DFL) techniques that operate by constructing RSSI histograms are highly effective as they can localize stationary and moving people in both outd...

In this paper, we present a Convolutional AutoEncoder (CAE) for single image dehazing. Our CAE makes us of Densely Connection Networks as its encoder and decoder. It is trained with the corresponding hazy and clean images at the input and output, enabling it to remove the haze without having to rely on an atmospheric scattering model. The CAE is tr...

Device-free Localization (DFL) algorithms using the Received Signal Strength Indicator (RSSI) metric, have become a popular research focus in recent years as they allow for location-based service using Commercial-off-the-shelf (COTS) wireless equipment. However, most existing DFL approaches have limited applicability in realistic smart home environ...

Device-free localization (DFL) systems that rely on the wireless received signal strength indicator (RSSI) metric to localize targets with no device attached to them have been reported in the literature for almost a decade. Approaches using RSSI can be split into three main categories. Link-based approaches utilize weighted summation or probabilist...

Energy-efficient cognitive radio network has received considerable attention recently because of improving spectrum and energy efficiency. In light of such observations, we present a model for cognitive radio network based on stochastic geometry theory where transmitters and receivers are distributed according to Poisson point process. In this pape...

The emerging smart city paradigm e.g., intelligent transport, smart grid and participatory sensing etc. is to advance the quality, performance and experience of urban citizten services through greater connectivity. This paradigm needs to collect data from citizens, various devices and assets that could be monitored, processed and analysed for the c...

Indoor localization based on visible light and Visible Light Communication (VLC) has become a viable alternative to radio frequency wireless based techniques. Modern Visible Light Position (VLP) systems have been able to attain sub-decimeter level accuracy within standard room environments. However a major limitation is their reliance on Line-Of-Si...

This paper considers the application of finite-time control to a Cucker-Smale flocking model of autonomous agents with collision avoidance. A mathematical expression for the upper bound on the flocking time is derived. Previous results without considering collision avoidance showed that the flocking time decreases as the number of robots in the flo...

In recent years energy efficient LEDs have become a commonplace lighting solution. It is possible to create an indoor positioning system (IPS) from existing lighting infrastructure by making minor modifications to the luminaire drivers. In this paper we develop and implement an IPS by augmenting the luminaires with collocated Zigbee radios. The Hyb...

The Model Predictive Control (MPC) trajectory tracking problem of an unmanned quadrotor with input and output constraints is addressed. In this article, the dynamic models of the quadrotor are obtained purely from operational data in the form of probabilistic Gaussian Process (GP) models. This is different from conventional models obtained through...

Convolved Gaussian Process (CGP) is able to capture the correlations not only between inputs and outputs but also among the outputs. This allows a superior performance of using CGP than standard Gaussian Process (GP) in the modelling of Multiple-Input Multiple-Output (MIMO) systems when observations are missing for some of outputs. Similar to stand...

The Model Predictive Control (MPC) trajectory tracking problem of an unmanned quadrotor with input and output constraints is addressed. In this article, the dynamic models of the quadrotor are obtained purely from operational data in the form of probabilistic Gaussian Process (GP) models. This is different from conventional models obtained through...

Convolved Gaussian Process (CGP) is able to capture the correlations not only between inputs and outputs but also among the outputs. This allows a superior performance of using CGP than standard Gaussian Process (GP) in the modelling of Multiple-Input Multiple-Output (MIMO) systems when observations are missing for some of outputs. Similar to stand...

Both the original Cucker-Smale flocking model and a more recent version with collision avoidance do not have any control over how tightly the system of agents flock, which is measured by the flock diameter. In this paper, a cohesive force is introduced to potentially reduce the flock diameter. This cohesive force is similar to the repelling force u...

In recent years, research into localization systems has become more popular as the proliferation of Wireless Sensor Networks (WSNs) grows. Wireless Localization can refer to either an “Active” system which tracks a mobile transceiver, or “Passive” localization which tracks a transceiver free entity by measuring the changes it makes to the surroundi...

Model Predictive Control (MPC) of an unknown system that is modelled by Gaussian Process (GP) techniques is studied in this paper. Using GP, the variances computed during the modelling and inference processes allow us to take model uncertainty into account. The main issue in using MPC to control systems modelled by GP is the propagation of such unc...

Model Predictive Control (MPC) of an unknown system that is modelled by Gaussian Process (GP) techniques is studied in this paper. Using GP, the variances computed during the modelling and inference processes allow us to take model uncertainty into account. The main issue in using MPC to control systems modelled by GP is the propagation of such unc...

In this paper, the design of a computationally efficient variable bandpass digital filter is presented. The center frequency and bandwidth of this filter can be changed online without updating the filter coefficients. The warped filters, obtained by replacing each unit delay of a digital filter with an allpass filter, are widely used for various au...

In a typical multi-standard military communication receiver, fast and reliable spectrum sensing unit is required to extract the information of multiple channels (frequency bands) present in a wideband input signal. In this paper, an energy detector based on our reconfigurable filter bank, in [5], for detecting the edge frequencies of the channels i...

The learning unknown dynamics and handling model uncertainties are two issues when using Model-based Predictive Control (MPC) scheme. In this paper, unknown Linear Time-Varying (LTV) system with external noise is represented by using probabilistic Gaussian Process (GP) models. In this way, we can explicitly evaluate model uncertainties as variances...

A cytomorphic circuit that can mimic gene expression regulation mechanisms is presented. It is shown that this circuit can efficiently predict the cellular response of the bacterium Escherichia coli in real time. The simulation outputs of the circuit are compared with biological experimental results. The significant similarity between these results...

Convolved Gaussian process (CGP) is a type Gaussian process modelling technique applicable for multiple-input multiple-output systems. It employs convolution processes to construct a covariance function that models the correlation between outputs. Modelling using CGP involves learning the hyperparameters of the latent function and the smoothing ker...

This brief presents a low-complexity linear-phase variable digital filter (VDF) design with tunable lowpass (LP), highpass (HP), bandpass (BP), and bandstop (BS) responses anywhere over the entire Nyquist band. The spectral-parameter-approximation-based VDFs (SPA-VDFs) was designed using the Farrow structure and has advantages of linear phase, lowe...

This brief presents a new low-complexity reconfigurable fast filter bank (RFFB) for wireless communication applications such as spectrum sensing and channelization. In RFFB, the bandwidth and center frequency of sub-bands can be varied with high frequency resolution without hardware reimplementation. This is achieved with an improved modified frequ...

In this paper, a new distributed block-based image compression method based on the principles of compressed sensing (CS) is introduced. The coding and decoding processes are performed entirely in the CS measurement domain. Image blocks are classified into key and non-key blocks and encoded at different rates. The encoder makes use of a new adaptive...

In this brief, an efficient implementation of reconfigurable warped digital filter with variable low-pass, high-pass, bandpass, and bandstop responses is presented. The warped filters, obtained by replacing each unit delay of a digital filter with an all-pass filter, are widely used for various audio processing applications. However, warped filters...

In this paper, an area and power efficient two-stage spectrum sensing scheme for cognitive radios (CRs) is proposed. A typical parallel spectrum sensing using filter bank has advantages of lowest mean detection time, less interference to primary users and better throughput over serial spectrum sensing. However, these advantages come at the huge cos...

Distributed Video coding based on compressed sensing is considered in this paper. Side information plays an important role in the quality of decoded non-key video frames. Existing systems generate side information based on the decoded key frames and the processes are quite complicated, increasing the computation burden at the decoder. We propose a...

In a typical multi-standard wireless communication receiver, the channelizer must have the capability of extracting multiple channels (frequency bands) of distinct bandwidths corresponding to different communication standards. The channelizer operates at the highest sampling rate in the digital front end of receiver and hence power efficient low co...

Compressed Sensing (CS) is a new approach to signal acquisition that can potentially allow us to design very simple video encoders that can be implemented on mobile devices with limited resources. However, previously proposed CS based video codec either require a conventional video codec or a feedback channel for effective operation, thus increasin...

This paper presents the design of a variable linear phase finite impulse response filter based on second order frequency transformations and coefficient decimation. The design of variable digital filters (VDFs) using first and second order frequency transformations have been proposed in literature. The VDF using second order transformation has bett...

Even though video compression has become a mature field, a lot of research is still ongoing. Indeed, as the quality of the compressed video for a given size or bit rate increases, so does users’ level of expectations and their intolerance to artefacts. The development of compression technology has enabled number of applications; key applications in...

Even though video compression has become a mature field, a lot of research is still ongoing. Indeed, as the quality of the compressed video for a given size or bit rate increases, so does users’ level of expectations and their intolerance to artefacts. The development of compression technology has enabled number of applications; key applications in...

This paper presents a new method for the design of finite impulse response (FIR) filter that provides variable frequency responses. The proposed idea is to replace each unit delay operator in a fixed-coefficient FIR filter with the 2nd order FIR fractional delay (FD) structure and the cutoff frequency, fc of the filter is changed by changing the FD...

The demand for new telecommunication services requiring higher capacities, data rates and different operating modes have motivated the development of new generation multi-standard wireless transceivers. In multi-standard design, sigma-delta based ADC ...

The ability to support multiple channels of different communication standards, in the available bandwidth, is of importance in modern software defined radio (SDR) receivers. An SDR receiver typically employs a channelizer to extract multiple narrowband channels from the received wideband signal using digital filter banks. Since the filter bank chan...

This paper discusses the power quality indices of Compact Fluorescent Lamps (CFLs) used in residential lighting. Harmonic indices are important factors when analyzing residential power quality. Research carried out in the recent past has highlighted power quality issues relating to CFLs. The experiments performed by us confirmed the stated issues....

Compressed Video Sensing (CVS) is the application of the theory and principles of Compressed Sensing to video coding. Previous research has largely ignored the effects of quantization on the random measurements. In this paper, we showed that Gaussian quantization of the CVS coefficients produce higher quality reconstructed videos compared to using...

In a typical multi-standard wireless communication receiver, the channelizer extracts multiple radio channels of distinct bandwidths from a digitized wideband input signal. The complexity of the digital front end of the receiver is dominated by the complexity of the channelizer which operates at the highest sampling rate in the system. Computationa...

Therapeutically, the closed-loop blood glucose-insulin regulation paradigm via a controllable insulin pump offers a potential solution to the management of diabetes. However, the development of such a closed-loop regulatory system to date has been hampered by two main issues: 1) the limited knowledge on the complex human physiological process of gl...

It is well known that common subexpression elimination techniques minimize the two main cost metrics namely logic operators and logic depths in realizing finite impulse response (FIR) filters. Two classes of common subexpressions occur in the canonic signed digit representation of filter coefficients, called the horizontal and the vertical subexpre...

Human decision-making is defined as a cognitive process in which a preferred option or a course of action is chosen from among a set of alternatives, based on certain information or considerations. One important facet of decision-making is to facilitate an appropriate response to a dynamic and uncertain environment. Dynamic decision-making is inher...