Modelling hot deformation of low alloy steels is important for optimising processing efficiency and cost reduction. Existing approaches lack generalisation as they primarily focus on single steel grades, ignoring chemical composition. To address this, a dataset comprising 58 distinct low-alloy steels and an Attention-Based Multi-Head Feature Fusion Network (AMHFnet) has been established and proposed. AMHFnet uses multi-head residual modules and a head weighting mechanism to adaptively learn high-dimensional representations of both chemical composition and processing variables, which are then fused and processed via a feature filtering and repeat step decision mechanism to predict hot deformation response. It demonstrated superior accuracy and generalisability in 10-fold cross-validation compared to existing decision tree-based models and state-of-the-art deep learning models. Ablation studies demonstrate the effectiveness of individual components of the network. An investigation of the effect of carbon demonstrated that AMHFnet could reliably reflect elemental effects on hot deformation behaviour, further validating its reliability and applicability. The model successfully captures work hardening behaviour and dynamic recrystallisation for most compositions. By accurately predicting hot deformation behaviour across diverse low-alloy steels, this work can simplify the alloy-composition design process and target the experimental testing.

Advancements in neuroimaging have facilitated unprecedented insights into brain connectivity, making the study of brain effective connectivity networks (ECNs) essential for understanding neurological functions and diseases. Recently, neural networks (NNs) have emerged as powerful tools for ECN estimation due to their prominent universal approximation ability and less reliance on prior knowledge. However, most NN-based approaches fail to eliminate redundant temporal information and lack rigorous causal validation mechanisms. This paper introduces a novel end-to-end framework for estimating ECNs utilising Least Absolute Shrinkage and Selection Operator (Lasso) regression of Temporal Convolutional Networks (TCNs), named the Causal Validation augmented Temporal Convolutional Framework (CVTCF). In the CVTCF, a convolutional Hierarchical Group Lasso (cHGL) is proposed to detect Granger Causality (GC) inputs and eliminate redundant temporal information during GC detection. Additionally, the framework incorporates permutation importance validation based on the Wilcoxon signed-rank test to enhance the reliability of GC detection. The proposed CVTCF generally outperformed state-of-the-art methods in a controlled simulation using the chaotic Lorenz-96 model and the publicly available blood-oxygen-level-dependent (BOLD) benchmark dataset. Furthermore, the proposed CVTCF has enabled a detailed analysis of the causal interactions within the cerebral cortex, bringing to light the intricate relationships that underlie neurological functioning and impairment of neurodegenerative conditions like Alzheimer's Disease (AD) and Parkinson's Disease (PD). This study demonstrates the potential of using ECN estimation based on the CVTCF as indicators for neurodegenerative diseases and paves the way for future diagnostic and therapeutic strategies.

Existing computer vision-based approaches struggle to identify machinery actions due to the challenges posed by environmental complexity and various obstructions in construction. This study introduces a novel two-stage framework that benefits from a newly proposed Residual Fusion Graph Convolution Network (RFGCN) to classify machinery actions with enhanced robustness and accuracy. The framework first extracts key machinery components from video data, subsequently transforming them into a graph-based representation. This spatio-temporal graph is then fed into the RFGCN model, specifically designed to overcome issues like partial obstructions and missing information common in busy construction sites. Experimental evaluations reveal the method’s high efficacy, achieving an accuracy of up to 96.4% and outperforming state-of-the-art. Additionally, the proposed RFGCN model achieved state-of-the-art performance on four established benchmark datasets for graph classification using spatial data only. These results suggest the potential of the proposed framework in facilitating the transition towards more intelligent and automated construction sites.

Ocular surface diseases affect a significant portion of the population worldwide. Accurate segmentation and quantification of different ocular surface structures are crucial for the understanding of these diseases and clinical decision-making. However, the automated segmentation of the ocular surface structure is relatively unexplored and faces several challenges. Ocular surface structure boundaries are often inconspicuous and obscured by glare from reflections. In addition, the segmentation of different ocular structures always requires training of multiple individual models. Thus, developing a one-model-fits-all segmentation approach is desirable. In this paper, we introduce a randomness-restricted diffusion model for multiple ocular surface structure segmentation. First, a time-controlled fusion-attention module (TFM) is proposed to dynamically adjust the information flow within the diffusion model, based on the temporal relationships between the network's input and time. TFM enables the network to effectively utilize image features to constrain the randomness of the generation process. We further propose a low-frequency consistency filter and a new loss to alleviate model uncertainty and error accumulation caused by the multi-step denoising process. Extensive experiments have shown that our approach can segment seven different ocular surface structures. Our method performs better than both dedicated ocular surface segmentation methods and general medical image segmentation methods. We further validated the proposed method over two clinical datasets, and the results demonstrated that it is beneficial to clinical applications, such as the meibomian gland dysfunction grading and aqueous deficient dry eye diagnosis.

Artificial intelligence algorithms employed for classifying excavator-related activities predominantly rely on sensors embedded within individual machinery or computer vision (CV) techniques encompassing a large scene. The existing CV-based methods are often difficult to tackle an image including multiple excavators and other cooperating machinery. This study presents a novel framework tailored to the classification of excavator activities, accounting for both the excavator itself and the dumpers collaborating with the excavator during operations. Distinct from most existing related studies, this method centers on the transformed heterogeneous graph data constructed using the keypoints of all cooperating machinery extracted from an image. The resulting model leverages the relationships between the mechanical components of an excavator in varying activation states and the associations between the excavator and the collaborating machinery. The framework commences with a novel definition of keypoints representing different machinery relevant to the targetted activities. A customised Machinery Keypoint R-CNN method is then developed to extract these keypoints, forming the basis of graph notes. By considering the type, attribute and edge of nodes, a Heterogeneous Graph Convolutional Network is finally utilized for activity recognition. The results suggest that the proposed framework can effectively predict earthwork activities (with an accuracy of up to 97.5%) when the image encompasses multiple excavators and cooperating machinery. This solution holds promising potential for the automated measurement and management of earthwork productivity within the construction industry. Code and data are available at: https://github.com/gillesflash/Keypoints-Based-Heterogeneous-Graph-Convolutional-Networks.git.

Time-of-flight magnetic resonance angiography (TOF-MRA) is the least invasive and ionizing radiation-free approach for cerebrovascular imaging, but variations in imaging artifacts across different clinical centers and imaging vendors result in inter-site and inter-vendor heterogeneity, making its accurate and robust cerebrovascular segmentation challenging. Moreover, the limited availability and quality of annotated data pose further challenges for segmentation methods to generalize well to unseen datasets. In this paper, we construct the largest and most diverse TOF-MRA dataset (COSTA) from 8 individual imaging centers, with all the volumes manually annotated. Then we propose a novel network for cerebrovascular segmentation, namely CESAR, with the ability to tackle feature granularity and image style heterogeneity issues. Specifically, a coarse-to-fine architecture is implemented to refine cerebrovascular segmentation in an iterative manner. An automatic feature selection module is proposed to selectively fuse global long-range dependencies and local contextual information of cerebrovascular structures. A style self-consistency loss is then introduced to explicitly align diverse styles of TOF-MRA images to a standardized one. Extensive experimental results on the COSTA dataset demonstrate the effectiveness of our CESAR network against state-of-the-art methods. We have made 6 subsets of COSTA with the source code online available, in order to promote relevant research in the community.

Abstract With the increasingly comprehensive utilisation of Carbon Fibre-Reinforced Polymers (CFRP) in modern industry, defects detection and characterisation of these materials have become very important and draw significant research attention. During the past 10 years, Artificial Intelligence (AI) technologies have been attractive in this area due to their outstanding ability in complex data analysis tasks. Most current AI-based studies on damage characterisation in this field focus on damage segmentation and depth measurement, which also faces the bottleneck of lacking adequate experimental data for model training. This paper proposes a new framework to understand the relationship between Barely Visible Impact Damage features occurring in typical CFRP laminates to their corresponding controlled drop-test impact energy using a Deep Learning approach. A parametric study consisting of one hundred CFRP laminates with known material specification and identical geometric dimensions were subjected to drop-impact tests using five different impact energy levels. Then Pulsed Thermography was adopted to reveal the subsurface impact damage in these specimens and recorded damage patterns in temporal sequences of thermal images. A convolutional neural network was then employed to train models that aim to classify captured thermal photos into different groups according to their corresponding impact energy levels. Testing results of models trained from different time windows and lengths were evaluated, and the best classification accuracy of 99.75% was achieved. Finally, to increase the transparency of the proposed solution, a salience map is introduced to understand the learning source of the produced models.

Abstract Accurate fault diagnosis and prognosis can significantly reduce maintenance costs, increase the safety and availability of engineering systems that have become increasingly complex. It has been observed that very limited researches have been reported on fault diagnosis where multi-component degradation are presented. This is essentially a challenging Complex Systems problem where features multiple components interacting simultaneously and nonlinearly with each other and its environment on multiple levels. Even the degradation of a single component can lead to a misidentification of the fault severity level. This paper introduces a new test rig to simulate the multi-component degradation of the aircraft fuel system. A machine learning-based data analytical approach based on the classification of clustering features from both time and frequency domains is proposed. The scope of this framework is the identification of the location and severity of not only the system fault but also the multi-component degradation. The results illustrate that (a) the fault can be detected with accuracy > 99%; (b) the severity of fault can be identified with an accuracy of almost 100%; (c) the degradation level can be successfully identified with the R-square value > 0.9.

Abstract Quantitative defect and damage reconstruction play a critical role in industrial quality management. Accurate defect characterisation in Infrared Thermography (IRT), as one of the widely used Non-Destructive Testing (NDT) techniques, always demands adequate pre-knowledge which poses a challenge to automatic decision-making in maintenance. This paper presents an automatic and accurate defect profile reconstruction method, taking advantage of deep learning Neural Networks (NN). Initially, a fast Finite Element Modelling (FEM) simulation of IRT is introduced for defective specimen simulation. Mask Region-based Convolution NN (Mask-RCNN) is proposed to detect and segment the defect using a single thermal frame. A dataset with a single-type-shape defect is tested to validate the feasibility. Then, a dataset with three mixed shapes of defect is inspected to evaluate the method’s capability on the defect profile reconstruction, where an accuracy over 90% on Intersection over Union (IoU) is achieved. The results are compared with several state-of-the-art of post-processing methods in IRT to demonstrate the superiority at detailed defect corners and edges. This research lays solid evidence that AI deep learning algorithms can be utilised to provide accurate defect profile reconstruction in thermography NDT, which will contribute to the research community in material degradation analysis and structural health monitoring.

This article proposes a novel framework to characterize the morphological pattern of barely visible impact damage using machine learning. Initially, a sequence of image processing methods is introduced to extract the damage contour, which is then described by a Fourier descriptor-based filter. The uncertainty associated with the damage contour under the same impact energy level is then investigated. A variety of geometric features of the contour are extracted to develop an artificial intelligence model, which effectively groups the tested 100 samples impacted by 5 different impact energy levels with an accuracy of 96%. Predictive polynomial models are finally established to link the impact energy to the three selected features. It is found that the major axis length of the damage has the best prediction performance, with an R2value up to 0.97. Additionally, impact damage caused by low energy exhibits higher uncertainty than that of high energy, indicating lower predictability.

With the rapid increase of the integration and complexity of industrial components, the inaccessibility and inapplicability of existing nondestructive testing devices have become a bottleneck for in situ inspection of these objects. This article introduces a miniaturized active thermography system featured with a small-size, low-resolution, and low-cost thermal sensor, where two optional excitation sources including flash and laser are integrated. Dedicated data analysis approaches to evaluate defects are proposed considering the degraded signal quality. Three carbon fiber-reinforced polymer laminates with a variety of defects are evaluated quantitatively and qualitatively using the proposed system by comparing with two existing nonminiaturized inspection systems. The results show that the proposed system can work effectively for the degradation assessment of composite laminates. Even with the technical limitations that affect the detectability, for instance, the low pixel resolution, this technique will play an important role to inspect components featured with geometrically intricate space.

In this paper, a new recursive structure based on the convolution model of discrete cosine transform (DCT) for designing of a finite impulse response (FIR) digital filter is proposed. In our derivation, we start with the convolution model of DCT-II to use its Z-transform for the proposed filter structure perspective. Moreover, using the same algorithm, a filter base implementation of the inverse DCT (IDCT) for image reconstruction is developed. The computational time experiments of the proposed DCT/IDCT filter(s) demonstrate that the proposed filters achieve faster elapsed CPU time compared to the others. The image filtering and reconstruction performance of the proposed approach on ultrasound images are presented to validate the theoretical framework.

The driver's take-over performance is of great importance for driving safety in conditionally automated driving since the driver is required to respond appropriately to control the vehicle if there is a system failure. The engagement of different non-driving activities (NDAs), considered as the main factor of the driver's take-over performance has been investigated in this study from both perspectives of the driver's situation awareness and take-over quality. The activities are divided into 2 groups, which are active interaction mode and passive interaction mode based on the engagement of human and object. The results suggest that the engagement of NDAs could reduce the driver's situation awareness. Driver's attention level is different for each activity. Particularly, active interaction mode NDAs requests more mentally demanding and drivers are not sensitive to the driving situation change when they are doing such activities. In addition, there is no significant difference in the maximum lateral error with NDAs engagement. However, it takes more time to achieve a safe control transition for drivers who are doing the NDAs. The active interaction mode NDAs request even more time. Moreover, the transition process could benefit from steering wheel haptic feedback torque, which can be considered as an effective take-over assistance system.

Predicting driver steering intention enables intelligent vehicles to optimize its assistance and collaborative strategies with the human driver in advance, which contribute to an intelligent mutual-understanding system for driver-vehicle collaboration. In this study, a deep time-series learning-enabled driver steering intention prediction system is developed based on the Electromyography (EMG) signal processing. Specifically, the connection between the upper limb EMG signals from different muscles and the steering torque is established using a deep bi-directional long short-term memory (BiLSTM) recurrent neural network (RNN). The deep time-series model is trained to predict the future steering torque with historical EMG signals, and the prediction horizon is selected as 200 ms in this study. Moreover, three different steering postures with different hand positions on the steering wheel are studied. A joint BiLSTM network with shared temporal pattern extraction layers is developed to investigate the impact of the hand positions on the steering intention prediction. It is found that based on the joint BiLSTM network, the most accurate steering intention can be achieved with both hands on 3-clock positions. The experiments are conducted on a driving simulator environment with 21 participants. The proposed system can be used for precise driver steering intention prediction system towards a better mutual-understanding module on the intelligent and automated driving vehicles.

Inverse analysis is a promising tool for quantitative evaluation offering informative model-based prediction and providing accurate reconstruction results without preinspections for characterization criteria. For the traditional defect inverse reconstruction, a large number of parameters are required to reconstruct a complex defect, and the corresponding forward modeling simulation is very time-consuming. Such issues result in ill-posed and complex inverse reconstruction results, which further reduce its practical applicability. In this article, we propose and experimentally validate an inversion technique for the reconstruction of complexly shaped delamination defects in a multilayered metallic structure using signals derived from infrared thermography (IRT) testing. First, we employ a novel defect parameterization strategy based on Fourier series fitting to represent the profile of a complicated delamination defect with relatively few coefficients. Second, the multimedium element modeling method is applied to enhance a finite element method (FEM) fast forward simulator, in order to solve the mismatching mesh issue for mesh updating during inversion. Third, a deterministic inverse algorithm based on a penalty conjugate gradient algorithm is employed to realize a robust and efficient inverse analysis. By reconstructing delamination profiles with both numerically simulated IRT signals and those obtained through laser IRT experiments, the validity, efficiency, and robustness of the proposed inversion method are demonstrated for delamination defects in a double-layered plate. Based on this strategy, not only is the feasibility of the proposed method in IRT nondestructive testing is validated, but the practical applicability of inversion reconstruction analysis is significantly improved.

Characterisation of the driver's non-driving activities (NDAs) is of great importance to the design of the take-over control strategy in Level 3 automation. Gaze estimation is a typical approach to monitor the driver's behaviour since the eye gaze is normally engaged with the human activities. However, current eye gaze tracking techniques are either costly or intrusive which limits their applicability in vehicles. This paper proposes a low-cost and non-intrusive dual-cameras based gaze mapping system that visualises the driver's gaze using a heat map. The challenges introduced by complex head movement during NDAs and camera distortion are addressed by proposing a nonlinear polynomial model to establish the relationship between the face features and eye gaze on the simulated driver's view. The Root Mean Square Error of this system in the in-vehicle experiment for the X and Y direction is 7.80±5.99 pixel and 4.64±3.47 pixel respectively with the image resolution of $1440 \times 1080$ pixels. This system is successfully demonstrated to evaluate three NDAs with visual attention. This technique, acting as a generic tool to monitor driver's visual attention, will have wide applications on NDA characterisation for intelligent design of take over strategy and driving environment awareness for current and future automated vehicles.

The estimation of vascular network topology in complex networks is important in understanding the relationship between vascular changes and a wide spectrum of diseases. Automatic classification of the retinal vascular trees into arteries and veins is of direct assistance to the ophthalmologist in terms of diagnosis and treatment of eye disease. However, it is challenging due to their projective ambiguity and subtle changes in appearance, contrast, and geometry in the imaging process. In this paper, we propose a novel method that is capable of making the artery/vein (A/V) distinction in retinal color fundus images based on vascular network topological properties. To this end, we adapt the concept of dominant set clustering and formalize the retinal blood vessel topology estimation and the A/V classification as a pairwise clustering problem. The graph is constructed through image segmentation, skeletonization, and identification of significant nodes. The edge weight is defined as the inverse Euclidean distance between its two end points in the feature space of intensity, orientation, curvature, diameter, and entropy. The reconstructed vascular network is classified into arteries and veins based on their intensity and morphology. The proposed approach has been applied to five public databases, namely INSPIRE, IOSTAR, VICAVR, DRIVE, and WIDE, and achieved high accuracies of 95.1%, 94.2%, 93.8%, 91.1%, and 91.0%, respectively. Furthermore, we have made manual annotations of the blood vessel topologies for INSPIRE, IOSTAR, VICAVR, and DRIVE datasets, and these annotations are released for public access so as to facilitate researchers in the community.

Since age is the most significant risk factor for the development of Alzheimer's disease (AD), it is important to understand the effect of normal ageing on brain network characteristics before we can accurately diagnose the condition based on information derived from resting state electroencephalogram (EEG) recordings, aiming to detect brain network disruption. This article proposes a novel brain functional connectivity imaging method, particularly targeting the contribution of nonlinear dynamics of functional connectivity, on distinguishing participants with AD from healthy controls (HC). We describe a parametric method established upon a Nonlinear Finite Impulse Response model, and a revised orthogonal least squares algorithm used to estimate the linear, nonlinear and combined connectivity between any two EEG channels without fitting a full model. This approach, where linear and non-linear interactions and their spatial distribution and dynamics can be estimated independently, offered us the means to dissect the dynamic brain network disruption in AD from a new perspective and to gain some insight into the dynamic behaviour of brain networks in two age groups (above and below 70) with normal cognitive function. Although linear and stationary connectivity dominates the classification contributions, quantitative results have demonstrated that nonlinear and dynamic connectivity can significantly improve the classification accuracy, barring the group of participants below the age of 70, for resting state EEG recorded during eyes open. The developed approach is generic and can be used as a powerful tool to examine brain network characteristics and disruption in a user friendly and systematic way.

Precise characterization and analysis of corneal nerve fiber tortuosity are of great importance in facilitating examination and diagnosis of many eye-related diseases. In this paper we propose a fully automated method for image-level tortuosity estimation, comprising image enhancement, exponential curvature estimation, and tortuosity level classification. The image enhancement component is based on an extended Retinex model, which not only corrects imbalanced illumination and improves image contrast in an image, but also models noise explicitly to aid removal of imaging noise. Afterwards, we take advantage of exponential curvature estimation in the 3D space of positions and orientations to directly measure curvature based on the enhanced images, rather than relying on the explicit segmentation and skeletonization steps in a conventional pipeline usually with accumulated pre-processing errors. The proposed method has been applied over two corneal nerve microscopy datasets for the estimation of a tortuosity level for each image. The experimental results show that it performs better than several selected state-of-the-art methods. Furthermore, we have performed manual gradings at tortuosity level of four hundred and three corneal nerve microscopic images, and this dataset has been released for public access to facilitate other researchers in the community in carrying out further research on the same and related topics.

In the above article[1], there were two errors in the printed article that the authors want to correct.

The reconstruction and analysis of tree-like topological structures in the biomedical images is crucial for biologists and surgeons to understand biomedical conditions and plan surgical procedures. The underlying tree-structure topology reveals how different curvilinear components are anatomically connected to each other. Existing automated topology reconstruction methods have great difficulty in identifying the connectivity when two or more curvilinear components cross or bifurcate, due to their projection ambiguity, imaging noise and low contrast. In this paper, we propose a novel curvilinear structural similarity measure to guide a dominant-set clustering approach to address this indispensable issue. The novel similarity measure takes into account both intensity and geometric properties in representing the curvilinear structure locally and globally, and group curvilinear objects at crossover points into different connected branches by dominant-set clustering. The proposed method is applicable to different imaging modalities, and quantitative and qualitative results on retinal vessel, plant root, and neuronal network datasets show that our methodology is capable of advancing the current state-of-the-art techniques.

Nondestructive testing (NDT), including active thermography, has become an inevitable part of composite process and product verification, post manufacturing. However, there is no reliable NDT technique available to ensure the interlaminar bond integrity during composite laminate integration, bonding or repair where the presence of thin air gaps in the interface of dissimilar polymer composite materials would be detrimental to structural integrity. This paper introduces a novel approach attempting to quantify the damage thickness of composites (the thickness of air gaps inside composites) through a single-side inspection of pulsed thermography. The potential of this method is demonstrated by testing on three specimens with different types of defect, where the Pearson correlation coefficients of the thickness estimation for block defects and flat-bottom holes are 0.75 and 0.85, respectively. This approach will considerably enhance the degradation assessment performance of active thermography by extending damage measurement from currently two dimensions to three dimensions, and become an enabling technology on quality assurance of structural integrity.

Autonomous driving presents an exciting new development in vehicle technology. It poses a new challenge in driver-automation collaboration particularly during handover transitions between human and machine. In order to deal with this problem, this paper proposes a novel control framework for the haptic take-over system. The high-level framework of the haptic take-over control system, which takes driver cognitive workload, neuromuscular dynamics and optimal trajectory planning into consideration, is developed. Under the proposed framework, the determination approach of the optimal input sequence is introduced. The model of the allowed driver take-over authority, which is associated with driver's cognitive workload, as well as muscle readiness during take- over, is investigated and developed. The haptic feedback torque controller is then designed so as to minimize the deviation between the allowed control authority and driver's current degree of participation. A handover process, along with the proposed take-over control method, is also simulated. The simulation results validate the feasibility and effectiveness of the proposed approach.

Different from the existing super-resolution (SR) reconstruction approaches working under either the frequency-domain or the spatial- domain, this paper proposes an improved video SR approach based on both frequency and spatial-domains to improve the spatial resolution and recover the noiseless high-frequency components of the observed noisy low-resolution video sequences with global motion. An iterative planar motion estimation algorithm followed by a structure-adaptive normalised convolution reconstruction method are applied to produce the estimated low-frequency sub-band. The discrete wavelet transform process is employed to decompose the input low-resolution reference frame into four sub-bands, and then the new edge-directed interpolation method is used to interpolate each of the high-frequency sub-bands. The novelty of this algorithm is the introduction and integration of a nonlinear soft thresholding process to filter the estimated high-frequency sub-bands in order to better preserve the edges and remove potential noise. Another novelty of this algorithm is to provide flexibility with various motion levels, noise levels, wavelet functions, and the number of used low-resolution frames. The performance of the proposed method has been tested on three well-known videos. Both visual and quantitative results demonstrate the high performance and improved flexibility of the proposed technique over the conventional interpolation and the state-of-the-art video SR techniques in the wavelet- domain.

Automated detection of vascular structures is of great importance in understanding the mechanism, diagnosis, and treatment of many vascular pathologies. However, automatic vascular detection continues to be an open issue because of difficulties posed by multiple factors, such as poor contrast, inhomogeneous backgrounds, anatomical variations, and the presence of noise during image acquisition. In this paper, we propose a novel 2-D/3-D symmetry filter to tackle these challenging issues for enhancing vessels from different imaging modalities. The proposed filter not only considers local phase features by using a quadrature filter to distinguish between lines and edges, but also uses the weighted geometric mean of the blurred and shifted responses of the quadrature filter, which allows more tolerance of vessels with irregular appearance. As a result, this filter shows a strong response to the vascular features under typical imaging conditions. Results based on eight publicly available datasets (six 2-D data sets, one 3-D data set, and one 3-D synthetic data set) demonstrate its superior performance to other state-of-the-art methods.

In order to develop an advanced haptic take-over system for highly automated vehicles, research into the driver's neuromuscular dynamics is needed. In this paper a dynamic model of drivers' neuromuscular interaction with a steering wheel is firstly established. The transfer function and the natural frequency of the systems are analysed. In order to identify the key parameters of the driver-steering-wheel coupled system and investigate the system properties under different situations, experiments with drive-in-the-loop are carried out. For each test subject, two steering tasks, namely the passive and active steering tasks, are instructed to be completed. Furthermore, during the experiments, subjects manipulated the steering wheel with two distinct postures and three different hand positions. Based on the test results, key parameters of the transfer function and system properties are identified and investigated. The data and characteristics of the driver neuromuscular system are discussed and compared with respect to different steering tasks, hand positions and driver postures. These test results identified system properties that provide a good foundation for the development of a haptic take-over control system for automated vehicles.

Leakage in retinal angiography currently is a key feature for confirming the activities of lesions in the management of a wide range of retinal diseases, such as diabetic maculopathy and paediatric malarial retinopathy. This paper proposes a new saliency-based method for the detection of leakage in fluorescein angiography. A superpixel approach is firstly employed to divide the image into meaningful patches (or superpixels) at different levels. Two saliency cues, intensity and compactness, are then proposed for the estimation of the saliency map of each individual superpixel at each level. The saliency maps at different levels over the same cues are fused using an averaging operator. The two saliency maps over different cues are fused using a pixel-wise multiplication operator. Leaking regions are finally detected by thresholding the saliency map followed by a graph-cut segmentation. The proposed method has been validated using the only two publicly available datasets: one for malarial retinopathy and the other for diabetic retinopathy. The experimental results show that it outperforms one of the latest competitors and performs as well as a human expert for leakage detection and outperforms several state-of-the-art methods for saliency detection.

An important step in the identification of cellular automata (CA) is to detect the correct neighborhood before parameter estimation. Many authors have suggested procedures based on the removal of redundant neighbors from a very large initial neighborhood one by one to find the real model, but this often induces ill conditioning and overfitting. This is true particularly for a large initial neighborhood where there are few significant terms, and this will be demonstrated by an example in this paper. By introducing a new criteria and three new techniques, this paper proposes a new adaptive fast CA orthogonal-least-square (Adaptive-FCA-OLS) algorithm, which cannot only adaptively search for the correct neighborhood without any preset tolerance but can also considerably reduce the computational complexity and memory usage. Several numerical examples demonstrate that the Adaptive-FCA-OLS algorithm has better robustness to noise and to the size of the initial neighborhood than other recently developed neighborhood detection methods in the identification of binary CA.

In this brief, by combining an efficient wavelet representation with a coupled map lattice model, a new family of adaptive wavelet neural networks, called lattice dynamical wavelet neural networks (LDWNNs), is introduced for spatio-temporal system identification. A new orthogonal projection pursuit (OPP) method, coupled with a particle swarm optimization (PSO) algorithm, is proposed for augmenting the proposed network. A novel two-stage hybrid training scheme is developed for constructing a parsimonious network model. In the first stage, by applying the OPP algorithm, significant wavelet neurons are adaptively and successively recruited into the network, where adjustable parameters of the associated wavelet neurons are optimized using a particle swarm optimizer. The resultant network model, obtained in the first stage, however, may be redundant. In the second stage, an orthogonal least squares algorithm is then applied to refine and improve the initially trained network by removing redundant wavelet neurons from the network. An example for a real spatio-temporal system identification problem is presented to demonstrate the performance of the proposed new modeling framework.

Extracting the rules from spatio-temporal patterns generated by the evolution of cellular automata (CA) usually requires a priori information about the observed system, but in many applications little information will be known about the pattern. This paper introduces a new neighborhood detection algorithm which can determine the range of the neighborhood without any knowledge of the system by introducing a criterion based on mutual information (and an indication of over-estimation). A coarse-to-fine identification routine is then proposed to determine the CA rule from the observed pattern. Examples, including data from a real experiment, are employed to evaluate the new algorithm.