Yuhua Li

• BEng, MSc/Eng, PhD
• Cardiff University

In neuroimaging, the difference between predicted brain age and chronological age, known as brain age delta , has shown its potential as a biomarker related to various pathological phenotypes. There is a frequently observed bias when estimating brain age delta using regression models. This bias manifests as an overestimation of brain age for youn...

This paper develops a new image synthesis approach to transfer an example image (style image) to other images (content images) by using Deep Convolutional Neural Networks (DCNN) model. When common neural style transfer methods are used, the textures and colors in the style image are usually transferred imperfectly to the content image, or some visi...

When standard neural style transfer approaches are used in portrait style transfer, they often inappropriately apply textures and colours in different regions of the style portraits to the content portraits, leading to unsatisfied transfer results. This paper presents a portrait style transfer method to transfer the style of one image to another. I...

Artificial neural networks have been used as a powerful processing tool in various areas such as pattern recognition, control, robotics, and bioinformatics. Their wide applicability has encouraged researchers to improve artificial neural networks by investigating the biological brain. Neurological research has significantly progressed in recent yea...

There is a biological evidence to prove information is coded through precise timing of spikes in the brain. However, training a population of spiking neurons in a multilayer network to fire at multiple precise times remains a challenging task. Delay learning and the effect of a delay on weight learning in a spiking neural network (SNN) have not bee...

Background: Breast cancer is the most prevalent cancer in women in most countries of the world. Many computer-aided diagnostic methods have been proposed, but there are few studies on quantitative discovery of probabilistic dependencies among breast cancer data features and identification of the contribution of each feature to breast cancer diagno...

The creation of a predictive system that correctly forecasts future changes of a stock price is crucial for investment management and algorithmic trading. The use of technical analysis for financial forecasting has been successfully employed by many researchers. Input window length is a time frame parameter required to be set when calculating many...

Collusive transactions refer to the activity whereby traders use carefully-designed trade to illegally manipulate the market. They do this by increasing specific trading volumes, thus creating a false impression that a market is more active than it actually is. The traders involved in the collusive transactions are termed as collusive clique. The c...

The term ?disruptive trading behaviour? was first proposed by the U.S. Commodity Futures Trading Commission and is now widely used by US and EU regulation (MiFID II) to describe activities that create a misleading appearance of market liquidity or depth or an artificial price movement upward or downward according to their own purposes. Such activit...

A common assumption in traditional supervised learning is the similar probability distribution of data between the training phase and the testing/operating phase. When transitioning from the training to testing phase, a shift in the probability distribution of input data is known as a covariate shift. Covariate shifts commonly arise in a wide range...

Due to the increase of physical defects in advanced manufacturing processes, Networks-on-Chip (NoC) system reliability is a critical challenge as faults often occur post manufacturing. Therefore it is important to add fault tolerance to the NoC system. In this paper, a novel routing algorithm for 2D mesh NoCs is proposed which aims to enhance the f...

This paper presents an Extended Delay Learning based Remote Supervised Method, called EDL, which extends the existing DL-ReSuMe learning method previously proposed by the authors for mapping spatio-temporal input spiking patterns into desired spike trains. EDL merges the weight adjustment property of STDP and anti-STDP with a delay shift method sim...

Reliable face detection in completely uncontrolled settings still remains a challenging task. This paper introduces a novel hybrid learning strategy that achieves robust in-plane and out-of-plane multi-view face detection through the enhanced implementation of the hierarchical bio-inspired HMAX framework using spiking neurons. Through multiple trai...

A wash trade refers to the illegal activities of traders who utilize carefully designed limit orders to manually increase the trading volumes for creating a false impression of an active market. As one of the primary formats of market abuse, a wash trade can be extremely damaging to the proper functioning and integrity of capital markets. The exist...

A novel adaptive routing algorithm – Efficient Dynamic Adaptive Routing (EDAR) is proposed to provide a fault-tolerant capability for Networks-on-Chip (NoC) via an efficient routing path selection mechanism. It is based on a weighted path selection strategy, which exploits the status of real-time NoC traffic made available via monitor modules. The...

Fault tolerance and adaptive capabilities are challenges for modern Networks-on-Chip (NoC) due to the increase in physical defects in advanced manufacturing processes. Two novel adaptive routing algorithms, namely coarse and fine-grained look-ahead algorithms, are proposed in this paper to enhance 2D mesh/torus NoC system fault-tolerant capabilitie...

Learning in the presence of dataset shifts in non-stationary environments is a major challenge. Dataset shifts in the form of covariate shifts commonly occur in a broad range of real-world systems such as, electroencephalogram (EEG) based brain-computer interfaces (BCIs). Under covariate shifts, the properties of the input data distribution may shi...

Spikes are an important part of information transmission between neurons in the biological brain. Biological evidence shows that information is carried in the timing of individual action potentials, rather than only the firing rate. Spiking neural networks are devised to capture more biological characteristics of the brain to construct more powerfu...

Recent research has shown the potential capability of spiking neural networks (SNNs) to model complex information processing in the brain. There is biological evidence to prove the use of the precise timing of spikes for information coding. However, the exact learning mechanism in which the neuron is trained to fire at precise times remains an open...

Dataset shift is a very common issue wherein the input data distribution shifts over time in non-stationary environments. A broad range of real-world systems face the challenge of dataset shift. In such systems, continuous monitoring of the process behavior and tracking the state of shift are required in order to decide about initiating adaptive co...

Price manipulation refers to the activities of those traders who use carefully designed trading behaviors to manually push up or down the underlying equity prices for making profits. With increasing volumes and frequency of trading, price manipulation can be extremely damaging to the proper functioning and integrity of capital markets. The existing...

A major challenge to devising robust brain-computer interfaces (BCIs) based on electroencephalogram (EEG) data is the immanent non-stationary characteristics of EEG signals. Statistical properties of the signals may shift during inter-or-intra session transfers that often leads to deteriorated BCI performance. The shift in the input data distributi...

Modern Networks-on-Chip (NoC) have the capability to tolerate and adapt to the faults and failures in the hardware. Monitoring and debugging is a real challenge due to the NoC system complexity and large scale size. A key requirement is an evaluation and benchmarking mechanism to quantitatively analyse a NoC system's fault tolerant capability. A no...

Learning with dataset shift is a major challenge in non-stationary environments wherein the input data distribution may shift over time. Detecting the dataset shift point in the time-series data, where the distribution of time-series shifts its properties, is of utmost interest. Dataset shift exists in a broad range of real-world systems. In such s...

A key requirement for modern Networks-on-Chip (NoC) is the ability to detect and diagnose faults and failures. A novel approach is proposed which addresses the challenge of fault detection using an online mechanism. The approach minimises online intrusion by employing dynamic rates of testing to maximize NoC throughput while still ensuring sufficie...

Novelty detection is especially important for monitoring safety-critical systems in which novel conditions rarely occur and knowledge about novelty in that system is often limited or unavailable. There are a large number of studies in the area of novelty detection, but there is a lack of a comprehensive experimental evaluation of existing novelty d...

This paper proposes a new locally adaptive boundary evolution algorithm for level set methods (LSM)-based novelty detection. The proposed approach consists of level set function construction, boundary evolution, and evolution termination. It utilises the exterior data points lying outside the decision boundary to effect the segments of the boundary...

This paper presents a level set boundary description (LSBD) approach for novelty detection that treats the nonlinear boundary directly in the input space. The proposed approach consists of level set function (LSF) construction, boundary evolution, and termination of the training process. It employs kernel density estimation to construct the LSF of...

STDP is believed to play an important role in learning and memory. Additionally, experimental evidence shows that a few strong neural inputs can drive a neuron response and subsequently affect the learning of other inputs. Furthermore, recent studies have shown that local dendritic depolarization can impact STDP induction. This paper integrates the...

Online financial textual information contains a large amount of investor sentiment, i.e. subjective assessment and discussion with respect to financial instruments. An effective solution to automate the sentiment analysis of such large amounts of online financial texts would be extremely beneficial. This paper presents a natural language processing...

Wash trade refers to the activities of traders who utilise deliberately designed collusive transactions to increase the trading volumes for creating active market impression. Wash trade can be damaging to the proper functioning and integrity of capital markets. Existing work focuses on collusive clique detections based on certain assumptions of tra...

Market abuse has attracted much attention from financial regulators around the world but it is difficult to fully prevent. One of the reasons is the lack of thoroughly studies of the market abuse strategies and the corresponding effective market abuse approaches. In this paper, the strategies of reported price manipulation cases are analysed as wel...

Accurate forecasting of directional changes in stock prices is important for algorithmic trading and investment management. Technical analysis has been successfully used in financial forecasting and recently researchers have explored the optimization of parameters for technical indicators. This study investigates the relationship between the window...

In recent years, machine learning algorithms have become increasingly popular in financial forecasting. Their flexible, data-driven nature makes them ideal candidates for dealing with complex financial data. This paper investigates the effectiveness of a number of machine learning algorithms, and combinations of these algorithms, at generating one-...

A key requirement for modern Networks-on-Chip (NoC) is the ability to detect and diagnose faults and failures. This paper addresses the challenge of fault diagnosis using online testing where the interruption of the runtime operation (performance) under diagnosis is minimised. A novel Monitor Module (MM) is proposed to detect NoC interconnect fault...

A major challenge in brain-computer interfaces (BCIs) based on electroencephalogram (EEG) signals is the immanent non-stationarities in EEG data. Statistical properties of the signals may shift during inter- or intra-session transfers that often lead to deteriorated BCI performance. We propose to handle this issue with a transductive learning appro...

Multi-Agent Systems (MAS) have been recognised as a promising solution to address complex problems in many areas. However such systems are extremely hungry in terms of computational resources. Field Programmable Gate Arrays (FPGAs) offer great performance improvement over software implementations in terms of computational resource allocation but ap...

This paper proposes a locally adaptive level set boundary description (LALSBD) method for novelty detection. The proposed method adjusts the nonlinear boundary directly in the input space and consists of a number of processes including level set function (LSF) construction, local boundary evolution and termination. It employs kernel density estimat...

Dataset shift is a major challenge in the non-stationary environments wherein the input data distribution may change over time. Detecting the dataset shift point in the time-series data, where the distribution of time-series changes its properties, is of utmost interest. Dataset shift exists in a broad range of real-world systems. In such systems,...

Price manipulation refers to the act of using illegal trading behaviour to manually change an equity price with the aim of making profits. With increasing volumes of trading, price manipulation can be extremely damaging to the proper functioning and integrity of capital markets. Effective approaches for analysing and real-time detection of price ma...

Dataset shift is a major challenge in the non-stationary environments wherein the input data distribution may change over time. In a time-series data, detecting the dataset shift point, where the distribution changes its properties is of utmost interest. Dataset shift exists in a broad range of real-world systems. In such systems, there is a need f...

Linear time series models, such as the autoregressive integrated moving average (ARIMA) model, are among the most popular statistical models used to forecast time series. In recent years non-linear computational models, such as artificial neural networks (ANN), have been shown to outperform traditional linear models when dealing with complex data,...

The problem of learning from imbalanced data is of critical importance in a large number of application domains and can be a bottleneck in the performance of various conventional learning methods that assume the data distribution to be balanced. The class imbalance problem corresponds to dealing with the situation where one class massively outnumbe...

This paper addresses the application of two classifier algorithms, namely LibSVM (ν-SVM) and Mutual Information Matching (MIM), to single and multi-domain sentiment analysis. The aim is to improve the performance of sentiment classification accuracy in multiple domains. Analysis of the performance of the two classifiers shows that the use of LibSVM...

A reliable novelty detector employs a model that encloses the normal dataset tightly. As nonparametric probability density function estimation methods make no assumptions about the probability distribution of a dataset, this paper applies kernel density estimation to construct the initial boundaries surrounding the normal data points. Afterwards, t...

Instance-based learning algorithms make prediction/generalization based on the stored instances. Storing all instances of large data size applications causes huge memory requirements and slows program execution speed; it may make the prediction process impractical or even impossible. Therefore researchers have made great efforts to reduce the data...

The technique of machinery fault diagnosis has been greatly enhanced over recent years with the application of many pattern classification methods. However, these classification methods suffer from the “curse of dimensionality” when applied to high-dimensional fault diagnosis data. In order to solve the problem, this paper proposes a hybrid model w...

This paper proposes a training points selection method for one-class support vector machines. It exploits the feature of a trained one-class SVM, which uses points only residing on the exterior region of data distribution as support vectors. Thus, the proposed training set reduction method selects the so-called extreme points which sit on the bound...

Pattern selection methods have been traditionally developed with a dependency on a specific classifier. In contrast, this paper presents a method that selects critical patterns deemed to carry essential information applicable to train those types of classifiers which require spatial information of the training data set. Critical patterns include th...

The technique of machinery condition monitoring has been greatly enhanced over recent years with the application of many effective classifiers. However, these classification methods suffer from the 'curse of dimensionality' when applied to high-dimensional condition monitoring data. Actually, many classification algorithms are simply intractable wh...

A complex modern manufacturing process is normally under consistent surveillance via the monitoring of signals/variables collected from sensors. However, not all of these signals are equally valuable in a specific monitoring system. The measured signals contain a combination of useful information, irrelevant information as well as noise. It is ofte...

This paper proposes an efficient training strategy for one-class support vector machines. The strategy exploits the feature of a trained one-class SVM which uses points only residing on the exterior region of data distribution as support vectors. Thus the proposed training set reduction method selects the so-called extreme points which sit on the b...

In engineering applications, we often face highly imbalanced data problems where majority of the data are from a condition and small minority are from others. Directly learning classifier on such problems would be prone to a biased classification performance by the majority class, so resulting in poor predication on the minority class. This paper p...

In semi conductor manufacturing the wafer fabrication process is under constant surveillance via the stringent monitoring of measurements and signals collected from metrology steps and machine sensors. However, not all of this data is equally valuable within this process control domain. Engineers typically have a much larger number of signals than...

There has been a pronounced increase in novelty detection research in recent years due to the driving force from applications such as monitoring of safety-critical systems and detection of novel objects in image sequences. This paper presents a novelty detection method from a new perspective by analysing the fundamental properties of novelty detect...

Feature selection method has become the focus of research in the area of engineering data processing where there exists a large amount of high-dimensional data from the high-frequency acquisition system. For high-dimensional data processing, engineers often resort to feature extraction methods and statistical theories to convert the original featur...

Instantaneous angular speed (IAS)-based condition monitoring is an area in which significant progress has been achieved over the recent years. This condition monitoring technique is less known compared to the existing conventional methods. This paper presents model-predicted simulation and experimental results of broken rotor bar faults in a three-...

The increasing complexity of modern machinery systems demands an effective fault diagnosis strategy with low cost, high efficiency and reliability. This paper reports work which attempts to explore the potential offered by a Relevance Vector Machine (RVM) in machinery fault diagnosis. This work starts with a full investigation into the demands of m...

Sentence similarity measures play an increasingly important role in text-related research and applications in areas such as text mining, Web page retrieval, and dialogue systems. Existing methods for computing sentence similarity have been adopted from approaches used for long text documents. These methods process sentences in a very high-dimension...

In order to discriminate small changes for early fault diagnosis of rotating machines, condition monitoring demands that the measurement of instantaneous angular speed (IAS) of the machines be as accurate as possible. This paper develops the theoretical basis and practical implementation of IAS data acquisition and IAS estimation when noise influen...

Instantaneous angular speed (IAS)-based condition monitoring is an area in which significant progress has been achieved over the recent years. This condition monitoring technique is less known compared to the existing conventional methods. This paper presents model-predicted simulation and experimental results of broken rotor bar faults in a three-...

Many different methods have been developed for the measurement of angular speed. Each successive method has attempted to improve measurement performance using a different strategy to process encoder signals based on two basic principles: counting the number of pulses in a given time duration and measuring the elapsed time for a single cycle of enco...

Recently, requirements for enhanced reliability of rotating equipment are more critical than ever before, and the demands continue to grow constantly. Due to the progress made in engineering and materials science, rotating machinery is becoming faster and lighter. They are also required to run for longer periods of time. All of these factors mean t...

This paper presents a novel algorithm for computing similarity between very short texts of sentence length. It will introduce a method that takes account of not only semantic information but also word order information implied in the sentences. Firstly, semantic similarity between two sentences is derived from information from a structured lexical...

This paper describes the growing need for a novel approach to a Condition Monitoring Database Management System (CMDBMS). Through the study of a condition monitoring case and the examination of commonly used maintenance management systems, the needs of this system have been identified. From the case study, it has been found that to obtain maintenan...

Cavitation is a common fault in centrifugal pumps. The detection and diagnosis of the onset and severity of the cavitation provide the means of preventing the cavitation from causing harmful effects such as deterioration of the hydraulic performance, damage to pump components and the pollution by vibration and noise. This paper presents a new appro...

Full-text of this article is not available in this e-prints service. This article was originally published following peer-review in IEEE Transactions on Knowledge and Data Engineering, published by and copyright IEEE. Semantic similarity between words is becoming a generic problem for many applications of computational linguistics and artificial in...

This paper presents a novel technique which may be used to determine an appropriate threshold for interpreting the outputs of a trained Radial Basis Function (RBF) classifier. Results from two experiments demonstrate that this method can be used to improve the performance of RBF classifiers in practical applications. Keywords: Radial basis function...

This paper investigates the determination of semantic similarity by the incorporation of structural semantic knowledge from a lexical database and the learning ability of neural networks. The lexical database is assumed to be organised in a hierarchical structure. The extracted lexical knowledge contains the relative location of the concerned words...

This paper investigates the determination of semantic similarity by the incorporation of structural semantic knowledge from a lexical database and the learning ability of neural networks. The lexical database is assumed to be organised in a hierarchical structure. The extracted lexical knowledge contains the relative location of the concerned words...

In this paper, results are presented from a comprehensive series of studies aimed at assessing the suitability of multilayered perceptron (MLP) and radial basis function (RBF) networks for use in embedded, microcontroller-based, condition monitoring and fault diagnosis (CMFD) applications. Our assessment criteria include the performance of each cla...

Technical advances and environmental legislation in recent years have stimulated the development of a number of techniques for condition monitoring and fault diagnosis (CMFD) in diesel engines. This paper firstly summarises common faults, fault mechanisms and their effect on diesel engine performance. Corresponding measurands are presented. Standar...