An accurate Depth of Anaesthesia (DoA) assessment is crucial for enhancing a patient’s surgical experience, as it helps avoid intraoperative (anaesthesia) awareness and reduces postoperative recovery time and cognitive dysfunction. This article presents two novel research outcomes. The first is the development of a new DoA index using processed Electroencephalogram (EEG) signals and machine learning techniques. This research uniquely combines powerful features extracted by two distinct time series decomposition methods: the Fast Fourier Transform (FFT) and Variation Mode Decomposition (VMD). Permutation Entropy, Multiscale (Permutation) Lempel–Ziv Complexity, Hjorth’s mobility and Petrosian Fractal Dimension features trained a Support Vector Regressor producing a highly responsive DoA index of 85.8% accuracy. Secondly, a novel fixed-period Loss of Consciousness (LoC) early warning system is developed. Using the same feature set, a KNeighbors (KNN) classifier achieves an accuracy and Area Under the Receiver Operating Characteristic Curve of 82% after Synthetic Minority Oversampling Technique (SMOTE) dataset imbalance correction. The KNN model outperforms Decision Trees, Random Forests and Support Vector classification. Reliably predicting the LoC within a fixed period would greatly assist medical practitioners by ensuring an appropriate level of anaesthetic is administered to achieve the LoC, thus reducing the risk of anaesthesia awareness and preventing anaesthetic overdose.

Time series forecasting remains challenging in the presence of nonstationarity, regime changes, and observation noise. Many existing machine learning approaches rely on complex architectures that often lead to unstable training and limited robustness. To address these limitations, we propose QAAR-SIREN, a compact forecasting framework that improves stability through residual learning and complementary feature representations. Instead of predicting absolute values, the model forecasts temporal increments, mitigating nonstationarity effects. It integrates three information sources: raw temporal lags, attention-based contextual summarization, and lightweight nonlinear features extracted from a shallow variational quantum circuit applied to the most recent observation. The quantum component functions as a compact nonlinear feature extractor that enriches the input representation without increasing architectural complexity. Experiments on synthetic signals with regime transitions and heterogeneous noise, as well as real-world datasets from climate, energy demand, finance, and transportation, demonstrate that QAAR-SIREN achieves strong and stable predictive performance. The model attains coefficients of determination up to approximately 0.985 with low mean squared error. Ablation studies confirm that observed gains arise from the complementary effects of residual learning, attention-based context aggregation, and quantum feature extraction.

Fingerprint authentication is extensively adopted due to its ease of capture, low cost sensors and high recognition accuracy. The Minutia Cylinder Code (MCC) is a high-quality feature representation widely used in fingerprint authentication. However, there are two main limitations in the direct use of MCC: redundancy in the feature representation due to overlap between minutiae vicinities, which can lead to inefficient resource utilization; and vulnerability to template inversion attacks, which may expose the original fingerprint data and threaten user privacy. In this paper, we propose a lightweight privacy-preserving fingerprint authentication system that overcomes these limitations through two novel algorithms. The first algorithm, P-MCC, uses the Pearson correlation coefficient to prune MCC features to effectively reduce redundancy and improve resource utilisation, yielding a lightweight design. The second algorithm, S-MCC, applies a secure Boolean function which transforms the pruned MCC features non-invertibly to ensure privacy, thus preventing the reconstruction of original fingerprint data. Together, P-MCC and S-MCC provide a lightweight privacy-preserving fingerprint authentication system, which is well suited to resource-constrained environments, such as the Internet of Things (IoT). Experimental results demonstrate the effectiveness of the proposed system and its practicality in IoT applications.

The burgeoning 5G network brings edge servers closer to users to host online applications. These edge servers are typically kept running 24/7 to meet users' computational demands. However, the user coverage, privacy assurance, and service delay have consistently undermined users' confidence, compounded by the significant environmental damage caused by excessive energy consumption. Recently, various approaches have been proposed to tackle the energy-saving demand response issue in the multi-access edge computing (MEC) system. Unfortunately, existing attempts often compromise service quality and energy efficiency for privacy enhancement, and incur significant computational overheads and delays unsuitable for real-time services. Therefore, maintaining satisfying user coverage with energy consumption while adhering to users' privacy demands with low computational overhead is critical to achieving sustainable edge services. To address those challenges, we systematically formulate the location-privacy-preserving edge demand response (LEDR) problem and introduce a novel system named KGEES. KGEES incorporates$k$-anonymity geo-obfuscation to enhance user privacy while leveraging a heuristic approach to finalize resource allocation strategies under geo-distortion greedily to jointly improve system utility, energy, and time efficiency. Comprehensive experiments on a real-world dataset demonstrate that KGEES surpasses the representative approaches by an average of$1.187 \times$in system utility and$1.192 \times$in energy efficiency while being$ 203.5 \times$faster.

Face recognition offers seamless human-machine interaction and efficiency. However, its widespread adoption has heightened security and privacy concerns due to the risks associated with compromised biometric data, such as spoofing and unauthorized tracking. To mitigate these concerns, this paper introduces a novel privacy-preserving face recognition framework that integrates an enhanced dual-path feature compression approach with homomorphic encryption (HE) for secure and efficient authentication. We leverage the robust deep neural network model FaceNet to extract discriminative 512-dimensional feature vectors and propose two significantly improved complementary feature compression methods tailored specifically for encrypted biometric systems: (1) Partitioned Principal Component Analysis (P-PCA), which employs a novel segment-wise PCA transformation, preserving localized discriminative information and supporting revocable biometric templates; and (2) Segment-wise Locality-Sensitive Hashing (S-LSH), introducing segment-specific hashing optimized for efficient binary representation and privacy-preserving encrypted-domain computations. Both compressed real-valued and binary features are securely encrypted using HE, enabling direct encrypted-domain similarity computations without exposing sensitive biometric data. Extensive experiments demonstrate that our method achieves competitive authentication performance while maintaining computational efficiency and practical feasibility.

One-Shot Federated Learning (OSFL) restricts communication between the server and clients to a single round, significantly reducing communication costs and minimizing privacy leakage risks compared to traditional Federated Learning (FL), which requires multiple rounds of communication. However, existing OSFL frameworks remain vulnerable to distributional heterogeneity, as they primarily focus on model heterogeneity while neglecting data heterogeneity. To bridge this gap, we propose FedHydra, a unified, data-free, OSFL framework designed to effectively address both model and data heterogeneity. Unlike existing OSFL approaches, FedHydra introduces a novel two-stage learning mechanism. Specifically, it incorporates model stratification and heterogeneity-aware stratified aggregation to mitigate the challenges posed by both model and data heterogeneity. By this design, the data and model heterogeneity issues are simultaneously monitored from different aspects during learning. Consequently, FedHydra can effectively mitigate both issues by minimizing their inherent conflicts. We compared FedHydra with five SOTA baselines on four benchmark datasets. Experimental results show that our method outperforms the previous OSFL methods in both homogeneous and heterogeneous settings. The code is available at https://github.com/Jun-B0518/FedHydra.

Accurately measuring the Depth of Anaesthesia (DoA) during surgical procedures is crucial for patient safety. A significant challenge in developing effective machine learning models for DoA assessment is the lack of data from single organisations and preserving data privacy between institutions. Federated learning offers a solution by enabling multiple parties to collaboratively train models without exchanging data. However, traditional federated learning algorithms perform poorly in data heterogeneous, non-identically distributed data distribution scenarios. To address these challenges, we propose a one-shot federated learning framework, DoAFedP-NN, which facilitates federated learning with heterogeneous model development. The framework is tested in a range of model and data heterogeneity environments. This method enables the training of a global DoA prediction model across different medical facilities without sharing local data. The DoAFedP-NN model, utilising neural network design with entropy and spectral feature extraction, is compared to benchmark federated learning architectures, demonstrating its advantage in handling heterogeneous medical data. Experimental results show that DoAFedP-NN achieves robust DoA estimation when compared to the Bispectral (BIS) index, with high correlation coefficients of 0.8472 and 0.8542 across independent databases. The proposed model outperforms locally developed models, showing significant improvements when validated against external datasets from different medical facilities. This paper makes the key contributions: (1) introduces a one-shot pseudo-data method for federated learning; (2) demonstrates the effectiveness of this approach for EEG-based DoA using real-world databases; (3) showcases the model’s ability to achieve high correlation with the BIS index while preserving patient privacy in a range of client distribution scenarios and under cross-validation. • This study introduces a novel federated learning framework, DoAFedP-NN, which utilises neural network architecture to improve the accuracy of EEG-based Depth of Anaesthesia (DoA) monitoring. By integrating data across multiple databases without sharing local patient data, the framework respects patient privacy while enhancing model performance. • The DoAFedP-NN model, employing entropy and spectral analysis, demonstrated robust DoA estimation capabilities, achieving high correlation coefficients across independent databases. • The research utilises a novel pseudo-data federated learning aggregation method to enable heterogeneous model development through one-shot a novel federated learning framework for EEG-based DoA analysis. The DoAFedP-NN model’s superior performance compared to locally trained models and its comparability to a traditional full aggregation model demonstrate the value of federated learning in achieving high analytical precision without compromising patient privacy.

In recent years, the combination of unmanned aerial vehicles (UAVs) and wireless sensor networks (WSNs) has gained popularity in livestock management (LM) due to energy constraints and network instability. Limited energy storage of sensor nodes (SNs) and the possibility of packet loss contribute to fast energy consumption and unstable networks, respectively. UAVs serve as relay nodes and data sinks, addressing these issues by temporarily storing data to reduce SN workload and establishing mobile nodes for network stability. We propose two innovations based on previous work: 1) We introduce a multi-layer wireless network architecture, categorizing UAVs into two layers based on their functions including data collection and data processing. This enhances task parallelization, bridging performance gaps among multiple UAVs; 2) We overcome the mobility limitation of SNs, considering their real-time movement in the network. Through deep reinforcement learning, UAVs learn to cooperatively locate moving SNs. This accounts for the inevitable mobility of livestock in the industry. Additionally, we simulate the environment and compare our approach to traditional methods, evaluating metrics such as collected data per timestep (DCPS), energy consumed per timestep (ECPS), and network stability (NS). Experimental results demonstrate that our method outperforms traditional approaches, achieving a data collecting gain of 4.84% and 8.20% compared to the methods without considering SN mobility or the multi-layer characteristics of WSNs, respectively. Under energy consumption limits, our method yields energy savings of 3.00% and 1.35% respectively. Furthermore, we extensively study and validate our method against other path planning algorithms, including genetic particle swarm optimization (GPSO), modified central force optimization (MCFO), and rapidly-exploring random trees (RRT). Our approach surpasses these methods in terms of data collecting efficiency and network stability.

As with anything connected to the internet, Internet of Things (IoT) devices are also subject to severe cybersecurity threats because an adversary could exploit vulnerabilities in their internal software to perform malicious attacks. Despite the promising results of Deep Learning (DL)-based approaches, the lack of well-labeled IoT vulnerability samples available for training and explainability pose a critical challenge to deploy them in practice. In this paper, we propose, a novel DL-based approach for Effective and eXplainable IoT VULnerability detection. Specifically, inspired by recent advances of self-supervised learning in label-expensive tasks, we propose a new combinatorial contrastive loss to combine the strengths of large-scale unlabeled code corpus and limited IoT vulnerability samples. Then, given a binary detection result, provides a set of faithful and stable code statements positively contributing to the model’s predictions as understandable explanations. Experimental results indicate that outperforms state-of-the-art baselines by 33.44%-72.91% and 19.52%-98.78% with respect to the accuracy and F1 score metrics, respectively. For vulnerability explanation, improves over the best-performing baseline explainer PGExplainer by 22.97% in MSP, 49.55% in MSR, and 48.40% in MIoU, demonstrating that the explanations provided by can correctly point out the vulnerable statements relevant to the detected vulnerabilities.

This article investigates optimal control for a class of large-scale systems using a data-driven method. The existing control methods for large-scale systems in this context separately consider disturbances, actuator faults, and uncertainties. In this article, we build on such methods by proposing an architecture that accommodates simultaneous consideration of all of these effects, and an optimization index is designed for the control problem. This diversifies the class of large-scale systems amenable to optimal control. We first establish a min-max optimization index based on the zero-sum differential game theory. Then, by integrating all the Nash equilibrium solutions of the isolated subsystems, the decentralized zero-sum differential game strategy is obtained to stabilize the large-scale system. Meanwhile, by designing adaptive parameters, the impact of actuator failure on the system performance is eliminated. Afterward, an adaptive dynamic programming (ADP) method is utilized to learn the solution of the Hamilton-Jacobi-Isaac (HJI) equation, which does not need the prior knowledge of system dynamics. A rigorous stability analysis shows that the proposed controller asymptotically stabilizes the large-scale system. Finally, a multipower system example is adopted to illustrate the effectiveness of the proposed protocols.

Incorporating edge and cloud computing with robotics provides extended options for robots to perform real-time sensing and actuation operations in various cyber–physical systems (CPSs), including smart farms. Such systems are prone to uncertain failures triggered by mechanical disruptions. Consequently, the overall system performance degrades, primarily when location-specific tasks are already assigned to a faulty robot and require immediate recovery. Using edge and cloud computing resources is not always feasible due to communication and latency constraints. Therefore, this article exclusively focuses on harnessing the mobility of robots to support the computation tasks affected by uncertain failures of previously assigned robots and ensure faster resiliency management by relocating active robots near task sources. The proposed mobility-as-a-resilience-service (MaaRS) is formulated using a Markov decision process (MDP). Later, an edge server proximal to the robots is trained using deep reinforcement learning (DRL) to assign tasks among the robots. Specifically, a multiple deep$Q$-network (MDQN)-based dynamic task allocation mechanism is proposed to converge to a solution exploring reward uncertainties with the best exploitation. Numerical evaluation using Python and TensorFlow validates the effectiveness of the proposed approach compared to other benchmarks.

This article studies the decentralized control of large-scale systems with sparsity and communication delays. The large-scale system is defined over a directed connected graph and the information structure is partially nested. Based on the decomposition of the noise history, the optimal problem of the overall large-scale system can be decomposed into independent subproblems. Hence, the data-driven decentralized control method is investigated to find the optimal controllers using adaptive dynamic programming (ADP), which could release the dependence on the knowledge of model. In addition, state feedback and output feedback policy iteration algorithms are developed, respectively. Rigorous stability analysis shows that the proposed algorithms can stabilize the large-scale systems asymptotically. Finally, the effectiveness of the proposed theoretical methods is demonstrated by the application of heavy duty vehicle (HDV) platooning.

This paper aims to identify the license plates under difficult image conditions, such as low/high contrast, foggy, distorted, and dusty conditions. This paper proposes an efficient descriptor, multi-level extended local binary pattern, for the license plates (LPs) detection system. A pre-processing Gaussian filter with contrast-limited adaptive histogram equalization enhancement method is applied with the proposed descriptor to capture all the representative features. The corresponding bins histogram features for a license plate image at each different level are calculated. The extracted features are used as the input to an extreme learning machine classifier for multiclass vehicle LPs identification. The dataset with English cars LPs is extended using an online photo editor to make changes on the original dataset to improve the accuracy of the LPs detection system. The experimental results show that the proposed method has a high detection accuracy with an extremely high computational efficiency in both training and detection processes compared to the most popular detection methods. The detection rate is 99.10% with a false positive rate of 5% under difficult images. The average training and detection time per vehicle image is 4.25 and 0.735 s, respectively.

Accurate and reliable forecasting models for electricity demand (G) are critical in engineering applications. They assist renewable and conventional energy engineers, electricity providers, end-users, and government entities in addressing energy sustainability challenges for the National Electricity Market (NEM) in Australia, including the expansion of distribution networks, energy pricing, and policy development. In this study, data-driven techniques for forecasting short-term (24-h) G-data are adopted using 0.5 h, 1.0 h, and 24 h forecasting horizons. These techniques are based on the Multivariate Adaptive Regression Spline (MARS), Support Vector Regression (SVR), and Autoregressive Integrated Moving Average (ARIMA) models. This study is focused in Queensland, Australia’s second largest state, where end-user demand for energy continues to increase. To determine the MARS and SVR model inputs, the partial autocorrelation function is applied to historical (area aggregated) G data in the training period to discriminate the significant (lagged) inputs. On the other hand, single input G data is used to develop the univariate ARIMA model. The predictors are based on statistically significant lagged inputs and partitioned into training (80%) and testing (20%) subsets to construct the forecasting models. The accuracy of the G forecasts, with respect to the measured G data, is assessed using statistical metrics such as the Pearson Product-Moment Correlation coefficient (r), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). Normalized model assessment metrics based on RMSE and MAE relative to observed means (RMSEG¯andMAEG¯), Willmott’s Index (WI), Legates and McCabe Index (ELM), and Nash–Sutcliffe coefficients (ENS) are also utilised to assess the models’ preciseness. For the 0.5 h and 1.0 h short-term forecasting horizons, the MARS model outperforms the SVR and ARIMA models displaying the largest WI (0.993 and 0.990) and lowest MAE (45.363 and 86.502 MW), respectively. In contrast, the SVR model is superior to the MARS and ARIMA models for the daily (24 h) forecasting horizon demonstrating a greater WI (0.890) and MAE (162.363 MW). Therefore, the MARS and SVR models can be considered more suitable for short-term G forecasting in Queensland, Australia, when compared to the ARIMA model. Accordingly, they are useful scientific tools for further exploration of real-time electricity demand data forecasting.

This study proposes a novel approach blending optimum allocation (OA) technique and spectral density estimation to analyse and classify epileptic electroencephalogram (EEG) signals. This study employs the OA to determine representative sample points from the original EEG data and then applies periodogram (PD), autoregressive (AR), and the mixture of PD and AR to extract the discriminative features from each OA sample group. The obtained feature sets are evaluated by three popular machine learning methods: support vector machine (SVM), quadratic discriminant analysis (QDA), and k ‐nearest neighbour ( k ‐NN). Several output coding approaches of the SVM classifier are tested for selecting the best feature sets. This scheme was implemented on a benchmark epileptic EEG database for evaluation and also compared with existing methods. The experimental results show that the OA_AR feature set yields better performances by the SVM with an overall accuracy of 100%, and outperforms the state‐of‐the‐art works with a 14.1% improvement. Thus, the findings of this study prove that the proposed OA‐based AR scheme has significant potential to extract features from EEG signals. The proposed method will assist experts to automatically analyse a large volume of EEG data and benefit epilepsy research.

The use of intelligent technologies for providing useful recommendations to patients suffering chronic diseases may play a positive role in improving the general life quality of patients and help reduce the workload and cost involved in their daily healthcare. The objective of this study is to deve lop an intelligent recommender system based on predictive analysis for advising patients in the telehealth environment concerning whether they need to take the body test one day in advance by analyzing medical measurements of a patient for the past k days. The proposed algorithms supporting the recommender system have been validated using a time series telehealth data recorded from heart disease patients which were collected from May to January 2012, from our industry collaborator Tunstall. The experimental results show that the proposed system yields satisfactory recommendation accuracy and offer a promising way for saving the workload for patients to conduct body tests every day. This study highlights the possible usefulness of the computerized analysis of time series telehealth data in providing appropriate recommendations to patients suffering chronic diseases such as heart diseases patients.

A new algorithm for single hidden layer feedforward neural networks (SLFN), Orthogonal Basis Extreme Learning (OBEL) algorithm, is proposed and the algorithm derivation is given in the paper. The algorithm can decide both the NNs parameters and the neuron number of hidden layer(s) during training while providing extreme fast learning speed. It will provide a practical way to develop NNs. The simulation results of function approximation showed that the algorithm is effective and feasible with good accuracy and adaptability.

This study proposes a novel index ML DoA to identify different anaesthetic states of a patient during surgery. Based on the new index ML DoA , the assessment of depth of anaesthesia (DoA) for a patient can be clearly monitored. Firstly, a modified Bayesian wavelet threshold is proposed to de‐noise the electroencephalogram (EEG) signals. Secondly, the Hurst exponent is obtained to classify four states of anaesthesia: deep anaesthesia, moderate anaesthesia, light anaesthesia and awake. Finally, the index ML DoA is derived based on the Hurst exponent and maximum‐likelihood function. The ML DoA index is evaluated using clinically obtained EEG signals and the bispectral (BIS) data. The results show that the new index remains robust in the case of poor signal quality where BIS does not. Moreover, the new index ML DoA responds faster than the BIS index during the anaesthetic state transitions of patients. To validate the proposed method, the analysis of variance method is used to compare the new index ML DoA with the BIS index. The results indicate that the ML DoA distribution is better in distinguishing the five DoA states.

The existing sleep stages classification methods are mainly based on time or frequency features. This paper classifies the sleep stages based on graph domain features from a single-channel electroencephalogram (EEG) signal. First, each epoch (30 s) EEG signal is mapped into a visibility graph (VG) and a horizontal VG (HVG). Second, a difference VG (DVG) is obtained by subtracting the edges set of the HVG from the edges set of the VG to extract essential degree sequences and to detect the gait-related movement artifact recordings. The mean degrees (MDs) and degree distributions (DDs) P (k) on HVGs and DVGs are analyzed epoch-by-epoch from 14,963 segments of EEG signals. Then, the MDs of each DVG and HVG and seven distinguishable DD values of P (k) from each DVG are extracted. Finally, nine extracted features are forwarded to a support vector machine to classify the sleep stages into two, three, four, five, and six states. The accuracy and kappa coefficients of six-state classification are 87.5% and 0.81, respectively. It was found that the MDs of the VGs on the deep sleep stage are higher than those on the awake and light sleep stages, and the MDs of the HVGs are just the reverse.

This paper evaluates depth of anesthesia (DoA) monitoring using a new index. The proposed method preconditions raw EEG data using an adaptive threshold technique to remove spikes and low-frequency noise. We also propose an adaptive window length technique to adjust the length of the sliding window. The information pertinent to DoA is then extracted to develop a feature function using discrete wavelet transform and power spectral density. The evaluation demonstrates that the new index reflects the patient's transition from consciousness to unconsciousness with the induction of anesthesia in real time.

With an increasing amount of semi-structured data XML has become important. XML documents may contain private information that cannot be shared by all user communities. Therefore, securing XML data is becoming important. Several specifications progressed toward providing a comprehensive standards framework for securing XML-based application have been presented. These applications can be effective to protect information in a website. In this paper, we present XML and Web service security main standards and most specifications for these standards. Each standard which connects with protecting XML based documents is discussed, especially we present XML undeniable signature as an application with XML digital signature. We also briefly describe the relations with these standards based on existing technologies. Finally, comparisons with related works are analyzed.

This paper introduces the design and testing of tension control prototype systems to minimise these tension variations, which includes a fluidic muscle powered take up arm, a fluidic muscle wire accumulator and felt pad. First the model and their limitations for existing tensioning systems are identified. Then, they are theoretically analysed in simulations. The simulation results show that the acceleration and deceleration of the wire due to the changing wire path length causes a cyclic tension fluctuation. An online tension sensor verified the predictions of the model. The key for a successful design is to remove tension variations. We propose to add a wire flattening machine which includes an accumulator and tensioning device, and replace the conventional pneumatic cylinder powering the accumulator with a fluidic muscle. The simulation shows that the new prototype system almost doubles the winding speed with a tolerable tension fluctuation.

In this paper, a method based on wavelet coefficients in low-pass bands is proposed for the image classification with adaptive processing of data structures to organize a large image database. After an image is decomposed by wavelet, its features can be characterized by the distribution of histograms of wavelet coefficients. The coefficients are respectively projected onto x and y directions. For different images, the distribution of histograms of wavelet coefficients in low-pass bands is substantially different. However, the one in high-pass bands is not as different, which makes the performance of classification not reliable. This paper presents a method for image classification based on wavelet coefficients in low-pass bands only. Images are arranged into a tree structure. The nodes can then be represented by the distribution of histograms of these wavelet coefficients. 2940 images derived from seven categories are used for image classification. Based on the wavelet coefficients in low-pass bands, the improvement of classification rate on the training data set is up to 11%, and the improvement of classification rate on the testing data set reaches 20%. Experimental results show that our proposed approach for image classification is more effective and reliable.

Image classification is a challenging problem in organizing a large image database. However, an effective method for such an objective is still under investigation. This paper presents a method based on wavelet and Independent Analysis Component (ICA) for image classification with adaptive processing of data structures. With wavelet, an image is decomposed into low frequency bands and high frequency bands. An image can be characterized by wavelet coefficients in the form of tree representation. While the histograms of low frequency wavelet bands are effective in characterizing images, the histograms of high frequency wavelet bands are similar for different images and therefore they cannot be directly used as features. We make use of ICA for feature extraction from high frequency bands to improve image classification. Two sets of features are used together to classify images using a structured neural network. In total, 2940 images generated from seven categories are used in experiments. Half of the images are used for training the neural network and the other images used for testing. The classification rate of the training set is 92%, and the classification rate of the test set reaches 89%. The experimental results show the effectiveness of the proposed method based on combining wavelet and ICA for image classification.

The purpose of this work is to develop an interactive tool which helps botanists to extract the vein system with its hierarchical properties with as little user interaction as possible. In this paper, we present a new venation extraction method using independent component analysis (ICA). The popular and efficient FastICA algorithm is applied to patches of leaf images to learn a set of linear basis functions or features for the images and then the basis functions are used as the pattern map for vein extraction. In our experiments, the training sets are randomly generated from different leaf images. Experimental results demonstrate that ICA is a promising technique for extracting leaf veins and edges of objects. ICA, therefore, can play an important role in automatically identifying living plants.

This paper studies a network based real-time control system, and proposes to model this system as a periodic real-time computing system. With efficient scheduling algorithms and software fault-tolerance deadline mechanism, this model proves that the system can meet its task timing constraints while tolerating system faults. The simulation study shows that in cases with high failure probability, the lower priority tasks suffer a lot in completion rate. In cases with low failure probability, this algorithm works well with both high priority and lower priority task. This conclusion suggests that an Internet based control system should manage to keep the failure rate to the minimum to achieve a good system performance.