Search

A photovoltaic (PV) power forecasting prediction is a crucial stage to utilize the stability, quality, and management of a hybrid power grid due to its dependency on weather conditions. In this paper, a short-term PV forecasting prediction model based on actual operational data collected from the PV experimental prototype installed at the engineering college of Misan University in Iraq is designed using various machine learning techniques. The collected data are initially classified into three diverse groups of atmosphere conditions—sunny, cloudy, and rainy meteorological cases—for various seasons. The data are taken for 3 min intervals to monitor the swift variations in PV power generation caused by atmospheric changes such as cloud movement or sudden changes in sunlight intensity. Then, an artificial neural network (ANN) technique is used based on the gray wolf optimization (GWO) and genetic algorithm (GA) as learning methods to enhance the prediction of PV energy by optimizing the number of hidden layers and neurons of the ANN model. The Python approach is used to design the forecasting prediction models based on four fitness functions: R2, MAE, RMSE, and MSE. The results suggest that the ANN model based on the GA algorithm accommodates the most accurate PV generation pattern in three different climatic condition tests, outperforming the conventional ANN and GWO-ANN forecasting models, as evidenced by the highest Pearson correlation coefficient values of 0.9574, 0.9347, and 0.8965 under sunny, cloudy, and rainy conditions, respectively.

Metaheuristics are primarily developed to explore optimization techniques in many practice areas. Metaheuristics refer to computational procedures leading to finding optimal solutions to optimization problems. Due to the increasing number of optimization problems with large-scale data, there is an ongoing demand for metaheuristic algorithms and the development of new algorithms with more efficiencies and improved convergence speed implemented by a mathematical model. One of the most popular optimization problems is job shop scheduling problems. This paper develops a novel metaheuristic hybrid Parthenogenetic Algorithm (NMHPGA) to optimize flexible job shop scheduling problems for single-machine and multi-machine job shops and a furnace model. This method is based on the principles of genetic algorithm (GA), underlying the combinations of different types of selections, proposed ethnic GA, and hybrid parthenogenetic algorithm. In this paper, a parthenogenetic algorithm (PGA) combined with ethnic selection GA is tested; the parthenogenetic algorithm version includes parthenogenetic operators: swap, reverse, and insert. The ethnic selection uses different selection operators such as stochastic, roulette, sexual, and aging; then, top individuals are selected from each procedure and combined to generate an ethnic population. The ethnic selection procedure is tested with the PGA types on a furnace model, single-machine job shops, and multi-machines with tardiness, earliness, and due date penalties. A comparison of obtained results of the established algorithm with other selection procedures indicated that the NMHPGA is achieving better objective functions with faster convergence speed.

Machine learning algorithms have been widely used in public health for predicting or diagnosing epidemiological chronic diseases, such as diabetes mellitus, which is classified as an epi-demic due to its high rates of global prevalence. Machine learning techniques are useful for the processes of description, prediction, and evaluation of various diseases, including diabetes. This study investigates the ability of different classification methods to classify diabetes prevalence rates and the predicted trends in the disease according to associated behavioural risk factors (smoking, obesity, and inactivity) in Saudi Arabia. Classification models for diabetes prevalence were developed using different machine learning algorithms, including linear discriminant (LD), support vector machine (SVM), K -nearest neighbour (KNN), and neural network pattern recognition (NPR). Four kernel functions of SVM and two types of KNN algorithms were used, namely linear SVM, Gaussian SVM, quadratic SVM, cubic SVM, fine KNN, and weighted KNN. The performance evaluation in terms of the accuracy of each developed model was determined, and the developed classifiers were compared using the Classification Learner App in MATLAB, according to prediction speed and training time. The experimental results on the predictive performance analysis of the classification models showed that weighted KNN performed well in the prediction of diabetes prevalence rate, with the highest average accuracy of 94.5% and less training time than the other classification methods, for both men and women datasets.

According to a recently conducted survey on surgical complication mortality rate, 47% of such cases are due to anesthetics overdose. This indicates that there is an urgent need to moderate the level of anesthesia. Recently deep learning (DL) methods have played a major role in estimating the depth of Anesthesia (DOA) of patients and has played an essential role in control anesthesia overdose. In this paper, Electroencephalography (EEG) signals have been used for the prediction of DOA. EEG signals are very complex signals which may require months of training and advanced signal processing techniques. It is a point of debate whether DL methods are an improvement over the already existing traditional EEG signal processing approaches. One of the DL algorithms is Convolutional neural network (CNN) which is very popular algorithm for object recognition and is widely growing its applications in processing hierarchy in the human visual system. In this paper, various decomposition methods have been used for extracting the features EEG signal. After acquiring the necessary signals values in image format, several CNN models have been deployed for classification of DOA depending upon their Bispectral Index (BIS) and the signal quality index (SQI). The EEG signals were converted into the frequency domain using and Empirical Mode Decomposition (EMD), and Ensemble Empirical Mode Decomposition (EEMD). However, because of the inter mode mixing observed in EMD method; EEMD have been utilized for this study. The developed CNN models were used to predict the DOA based on the EEG spectrum images without the use of handcrafted features which provides intuitive mapping with high efficiency and reliability. The best trained model gives an accuracy of 83.2%. Hence, this provides further scope and research which can be carried out in the domain of visual mapping of DOA using EEG signals and DL methods.

Abstract With the rapid growth of consumer credit and the huge amount of financial data developing effective credit scoring models is very crucial. Researchers have developed complex credit scoring models using statistical and artificial intelligence (AI) techniques to help banks and financial institutions to support their financial decisions. Neural networks are considered as a mostly wide used technique in finance and business applications. Thus, the main aim of this paper is to help bank management in scoring credit card clients using machine learning by modelling and predicting the consumer behaviour with respect to two aspects: the probability of single and consecutive missed payments for credit card customers. The proposed model is based on the bidirectional Long-Short Term Memory (LSTM) model to give the probability of a missed payment during the next month for each customer. The model was trained on a real credit card dataset and the customer behavioural scores are analysed using classical measures such as accuracy, Area Under the Curve, Brier score, Kolmogorov–Smirnov test, and H-measure. Calibration analysis of the LSTM model scores showed that they can be considered as probabilities of missed payments. The LSTM model was compared to four traditional machine learning algorithms: support vector machine, random forest, multi-layer perceptron neural network, and logistic regression. Experimental results show that, compared with traditional methods, the consumer credit scoring method based on the LSTM neural network has significantly improved consumer credit scoring.

In this paper, a new model known as YOLO-v5 is initiated to detect defects in PCB. In the past many models and different approaches have been implemented in the quality inspection for detection of defect in PCBs. This algorithm is specifically selected due to its efficiency, accuracy and speed. It is well known that the traditional YOLO models (YOLO, YOLO-v2, YOLO-v3, YOLO-v4 and Tiny-YOLO-v2) are the state-of-the-art in artificial intelligence industry. In electronics industry, the PCB is the core and the most basic component of any electronic product. PCB is almost used in each and every electronic product that we use in our daily life not only for commercial purposes, but also used in sensitive applications such defense and space exploration. These PCB should be inspected and quality checked to detect any kind of defects during the manufacturing process. Most of the electronic industries are focused on the quality of their product, a small error during manufacture or quality inspection of the electronic products such as PCB leads to a catastrophic end. Therefore, there is a huge revolution going on in the manufacturing industry where the object detection method like YOLO-v5 is a game changer for many industries such as electronic industries.

Software-Defined Networking (SDN) is an innovative technology which provides a programmable network control which is decoupled from the physical infrastructure. Network Virtualization (NV) is the phenomenon where a given physical network infrastructure and its resources are abstracted to create multiple logical virtual network slices of the underlying substrate. NV enables independent virtual networks to co-exist on one or more shared physical network infrastructure. Edge computing makes use of the edge resources in close proximity to end-users to reduce service delay and the network traffic volume in the end-to-end networks. Similarly, network slicing which is a key enabling technology for 5G networks is designed to support different services from different platforms at different scales enables sharing of physical network infrastructure on many different virtual network layers. These innovative technologies and strategies have gained significant attention from both academia and industry as they have the potential to maximize network resource utilization and optimize end–to–end network service delivery in 5G solutions deployment. To enable continuous simulation and development of applicable 5G networking concepts using these technologies, there is a need for an accessible and easy-to-learn testbed which is able to efficiently measure the performance of physical and virtual network capacities, provisioning approaches and management of multiple architectural models using large-scale network slicing configurations in a repeatable and controllable manner. These tools and toolkits provide scalable, lightweight and controlled cloud simulation environments necessary to analyse network traffic flows, allocation capacities and policies and the behaviour of multiple heterogeneous networks at an extremely low cost as compared to the huge financial commitments involved in conducting similar experiments in a real-life event. Existing solutions do not support Network Slicing and end- to -end heterogenous network automation which are key enablers of 5G network implementation. Hence in this paper, the CloudSimHypervisor framework is developed in this based on CloudSimSDN-NFV. The complete architecture and features of the CloudSimHypervisor framework and some used cases are presented in this paper. We validate the CloudSimHypervisor framework with two use case experiments in the cloud computing environment: Joint compute and network resource utilization and network traffic prioritization. Results from these experiments display the efficiency of the CloudSimHypervisor in estimating and measuring processing speed, transmission speed, compute and network usage efficiency and energy consumption.

The term “anesthetic depth” refers to the extent to which a general anesthetic agent sedates the central nervous system with specific strength concentration at which it is delivered. The depth level of anesthesia plays a crucial role in determining surgical complications, and it is imperative to keep the depth levels of anesthesia under control to perform a successful surgery. This study used electroencephalography (EEG) signals to predict the depth levels of anesthesia. Traditional preprocessing methods such as signal decomposition and model building using deep learning were used to classify anesthetic depth levels. This paper proposed a novel approach to classify the anesthesia levels based on the concept of time series feature extraction, by finding out the relation between EEG signals and the bi-spectral Index over a period of time. Time series feature extraction on basis of scalable hypothesis tests were performed to extract features by analyzing the relation between the EEG signals and Bi-Spectral Index, and machine learning models such as support vector classifier, XG boost classifier, gradient boost classifier, decision trees and random forest classifier are used to train the features and predict the depth level of anesthesia. The best-trained model was random forest, which gives an accuracy of 83%. This provides a platform to further research and dig into time series-based feature extraction in this area.

The frequency diversion in hybrid power systems is a major challenge due to the unpredictable power generation of renewable energies. An automatic generation controller (AGC) system is utilised in a hybrid power system to correct the frequency when the power generation of renewable energies and consumers’ load demand are changing rapidly. While a neural network (NN) model based on a back-propagation (BP) training algorithm is commonly used to design AGCs, it requires a complicated training methodology and a longer processing time. In this paper, a bacterial foraging algorithm (BF) was employed to enhance the learning of the NN model for AGCs based on adequately identifying the initial weights of the model. Hence, the training error of the NN model was addressed quickly when it was compared with the traditional NN model, resulting in an accurate signal prediction. To assess the proposed AGC, a power system with a photovoltaic (PV) generation test model was designed using MATLAB/Simulink. The outcomes of this research demonstrate that the AGC of the BF-NN-based model was effective in correcting the frequency of the hybrid power system and minimising its overshoot under various conditions. The BP-NN was compared to a PID, showing that the former achieved the lowest standard transit time of 5.20 s under the mismatching power conditions of load disturbance and PV power generation fluctuation.

Abstract One of the ways of increasing recognition ability in classification problem is removing outlier entries as well as redundant and unnecessary features from training set. Filtering and feature selection can have large impact on classifier accuracy and area under the curve (AUC), as noisy data can confuse classifier and lead it to catch wrong patterns in training data. The common approach in data filtering is using proximity graphs. However, the problem of the optimal filtering parameters selection is still insufficiently researched. In this paper filtering procedure based on k-nearest neighbours proximity graph was used. Filtering parameters selection was adopted as the solution of outlier minimization problem: k-NN proximity graph, power of distance and threshold parameters are selected in order to minimize outlier percentage in training data. Then performance of six commonly used classifiers (Logistic Regression, Naïve Bayes, Neural Network, Random Forest, Support Vector Machine and Decision Tree) and one heterogeneous classifiers combiner (DES-LA) are compared with and without filtering. Dynamic ensemble selection (DES) systems work by estimating the level of competence of each classifier from a pool of classifiers. Only the most competent ones are selected to classify a given test sample. This is achieved by defining a criterion to measure the level of competence of base classifiers, such as, its accuracy in local regions of the feature space around the query instance. In our case the combiner is based on the local accuracy of single classifiers and its output is a linear combination of single classifiers ranking. As results of filtering, accuracy of DES-LA combiner shows big increase for low-accuracy datasets. But filtering doesn’t have sufficient impact on DES-LA performance while working with high-accuracy datasets. The results are discussed, and classifiers, which performance was highly affected by pre-processing filtering step, are defined. The main contribution of the paper is introducing modifications to the DES-LA combiner, as well as comparative analysis of filtering impact on the classifiers of various type. Testing the filtering algorithm on real case dataset (Taiwan default credit card dataset) confirmed the efficiency of automatic filtering approach.

A load frequency controller (LFC) is a crucial part in the distribution of a power system network (PSN) to restore its frequency response when the load demand is changed rapidly. In this paper, an artificial neural network (ANN) technique is utilised to design the optimal LFC. However, the training of the optimal ANN model for a multi-area PSN is a major challenge due to its variations in the load demand. To address this challenge, a particle swarm optimization is used to distribute the nodes of a hidden layer and to optimise the initial neurons of the ANN model, resulting in obtaining the lower mean square error of the ANN model. Hence, the mean square error and the number of epochs of the ANN model are minimised to about 9.3886 × 10−8 and 25, respectively. To assess this proposal, a MATLAB/Simulink model of the PSN is developed for the single-area PSN and multi-area PSN. The results show that the LFC based on the optimal ANN is more effective for adjusting the frequency level and improves the power delivery of the multi-area PSN comparison with the single-area PSN. Moreover, it is the most reliable for avoiding the fault condition whilst achieving the lowest time multiplied absolute error about 3.45 s when compared with the conventional ANN and PID methods.

There are many surgical operations performed daily in operation rooms worldwide. Adequate anesthesia is needed during an operation. Besides hypnosis, adequate analgesia is critical to prevent autonomic reactions. Clinical experience and vital signs are usually used to adjust the dosage of analgesics. Analgesia nociception index (ANI), which ranges from 0 to 100, is derived from heart rate variability (HRV) via electrocardiogram (ECG) signals, for pain evaluation in a non-invasive manner. It represents parasympathetic activity. In this study, we compared the performance of multilayer perceptron (MLP) and long short-term memory (LSTM) algorithms in predicting expert assessment of pain score (EAPS) based on patient′s HRV during surgery. The objective of this study was to analyze how deep learning models differed from the medical doctors′ predictions of EAPS. As the input and output features of the deep learning models, the opposites of ANI and EAPS were used. This study included 80 patients who underwent operations at National Taiwan University Hospital. Using MLP and LSTM, a holdout method was first applied to 60 training patients, 10 validation patients, and 10 testing patients. As compared to the LSTM model, which had a testing mean absolute error (MAE) of 2.633 ± 0.542, the MLP model had a testing MAE of 2.490 ± 0.522, with a more appropriate shape of its prediction curves. The model based on MLP was selected as the best. Using MLP, a seven-fold cross validation method was then applied. The first fold had the lowest testing MAE of 2.460 ± 0.634, while the overall MAE for the seven-fold cross validation method was 2.848 ± 0.308. In conclusion, HRV analysis using MLP algorithm had a good correlation with EAPS; therefore, it can play role as a continuous monitor to predict intraoperative pain levels, to assist physicians in adjusting analgesic agent dosage. Further studies may consider obtaining more input features, such as photoplethysmography (PPG) and other kinds of continuous variable, to improve the prediction performance.

One of the most challenging predictive data analysis efforts is an accurate prediction of depth of anesthesia (DOA) indicators which has attracted growing attention since it provides patients a safe surgical environment in case of secondary damage caused by intraoperative awareness or brain injury. However, many researchers put heavily handcraft feature extraction or carefully tailored feature engineering to each patient to achieve very high sensitivity and low false prediction rate for a particular dataset. This limits the benefit of the proposed approaches if a different dataset is used. Recently, representations learned using the deep convolutional neural network (CNN) for object recognition are becoming a widely used model of the processing hierarchy in the human visual system. The correspondence between models and brain signals that holds the acquired activity at high temporal resolution has been explored less exhaustively. In this paper, deep learning CNN with a range of different architectures is designed for identifying related activities from raw electroencephalography (EEG). Specifically, an improved short-time Fourier transform is used to stand for the time-frequency information after extracting the spectral images of the original EEG as input to CNN. Then CNN models are designed and trained to predict the DOA levels from EEG spectrum without handcrafted features, which presents an intuitive mapping process with high efficiency and reliability. As a result, the best trained CNN model achieved an accuracy of 93.50%, interpreted as CNN's deep learning to approximate the DOA by senior anesthesiologists, which highlights the potential of deep CNN combined with advanced visualization techniques for EEG-based brain mapping.

Pain is a complex term that describes various sensations that create discomfort in various ways or types inside the human body. Generally, pain has consequences that range from mild to severe in different organs of the body and will depend on the way it is caused, which could be an injury, illness or medical procedures including testing, surgeries or therapies, etc. With recent advances in artificial-intelligence (AI) systems associated in biomedical and healthcare settings, the contiguity of physician, clinician and patient has shortened. AI, however, has more scope to interpret the pain associated in patients with various conditions by using any physiological or behavioral changes. Facial expressions are considered to give much information that relates with emotions and pain, so clinicians consider these changes with high importance for assessing pain. This has been achieved in recent times with different machine-learning and deep-learning models. To accentuate the future scope and importance of AI in medical field, this study reviews the explainable AI (XAI) as increased attention is given to an automatic assessment of pain. This review discusses how these approaches are applied for different pain types.

In this paper, an effective electrocardiogram (ECG) recurrence plot (RP)-based arrhythmia classification algorithm that can be implemented in portable devices is presented. Public databases from PhysioNet were used to conduct this study including the MIT-BIH Atrial Fibrillation Database, the MIT-BIH Arrhythmia Database, the MIT-BIH Malignant Ventricular Ectopy Database, and the Creighton University Ventricular Tachyarrhythmia Database. ECG time series were segmented and converted using an RP, and two-dimensional images were used as inputs to the CNN classifiers. In this study, two-stage classification is proposed to improve the accuracy. The ResNet-18 architecture was applied to detect ventricular fibrillation (VF) and noise during the first stage, whereas normal, atrial fibrillation, premature atrial contraction, and premature ventricular contractions were detected using ResNet-50 in the second stage. The method was evaluated using 5-fold cross-validation which improved the results when compared to previous studies, achieving first and second stage average accuracies of 97.21% and 98.36%, sensitivities of 96.49% and 97.92%, positive predictive values of 95.54% and 98.20%, and F1-scores of 95.96% and 98.05%, respectively. Furthermore, a 5-fold improvement in the memory requirement was achieved when compared with a previous study, making this classifier feasible for use in resource-constricted environments such as portable devices. Even though the method is successful, first stage training requires combining four different arrhythmia types into one label (other), which generates more data for the other category than for VF and noise, thus creating a data imbalance that affects the first stage performance.

This study evaluates cardiovascular and cerebral hemodynamics systems by only using non-invasive electrocardiography (ECG) signals. The Massachusetts General Hospital/Marquette Foundation (MGH/MF) and Cerebral Hemodynamic Autoregulatory Information System Database (CHARIS DB) from the PhysioNet database are used for cardiovascular and cerebral hemodynamics, respectively. For cardiovascular hemodynamics, the ECG is used for generating the arterial blood pressure (ABP), central venous pressure (CVP), and pulmonary arterial pressure (PAP). Meanwhile, for cerebral hemodynamics, the ECG is utilized for the intracranial pressure (ICP) generator. A deep convolutional autoencoder system is applied for this study. The cross-validation method with Pearson’s linear correlation (R), root mean squared error (RMSE), and mean absolute error (MAE) are measured for the evaluations. Initially, the ECG is used to generate the cardiovascular waveform. For the ABP system—the systolic blood pressure (SBP) and diastolic blood pressures (DBP)—the R evaluations are 0.894 ± 0.004 and 0.881 ± 0.005, respectively. The MAE evaluations for SBP and DBP are, respectively, 6.645 ± 0.353 mmHg and 3.210 ± 0.104 mmHg. Furthermore, for the PAP system—the systolic and diastolic pressures—the R evaluations are 0.864 ± 0.003 mmHg and 0.817 ± 0.006 mmHg, respectively. The MAE evaluations for systolic and diastolic pressures are, respectively, 3.847 ± 0.136 mmHg and 2.964 ± 0.181 mmHg. Meanwhile, the mean CVP evaluations are 0.916 ± 0.001, 2.220 ± 0.039 mmHg, and 1.329 ± 0.036 mmHg, respectively, for R, RMSE, and MAE. For the mean ICP evaluation in cerebral hemodynamics, the R and MAE evaluations are 0.914 ± 0.003 and 2.404 ± 0.043 mmHg, respectively. This study, as a proof of concept, concludes that the non-invasive cardiovascular and cerebral hemodynamics systems can be potentially investigated by only using the ECG signal.

Hypertension affects a huge number of people around the world. It also has a great contribution to cardiovascular- and renal-related diseases. This study investigates the ability of a deep convolutional autoencoder (DCAE) to generate continuous arterial blood pressure (ABP) by only utilizing photoplethysmography (PPG). A total of 18 patients are utilized. LeNet-5- and U-Net-based DCAEs, respectively abbreviated LDCAE and UDCAE, are compared to the MP60 IntelliVue Patient Monitor, as the gold standard. Moreover, in order to investigate the data generalization, the cross-validation (CV) method is conducted. The results show that the UDCAE provides superior results in producing the systolic blood pressure (SBP) estimation. Meanwhile, the LDCAE gives a slightly better result for the diastolic blood pressure (DBP) prediction. Finally, the genetic algorithm-based optimization deep convolutional autoencoder (GDCAE) is further administered to optimize the ensemble of the CV models. The results reveal that the GDCAE is superior to either the LDCAE or UDCAE. In conclusion, this study exhibits that systolic blood pressure (SBP) and diastolic blood pressure (DBP) can also be accurately achieved by only utilizing a single PPG signal.

Estimating the depth of anaesthesia (DoA) in operations has always been a challenging issue due to the underlying complexity of the brain mechanisms. Electroencephalogram (EEG) signals are undoubtedly the most widely used signals for measuring DoA. In this paper, a novel EEG-based index is proposed to evaluate DoA for 24 patients receiving general anaesthesia with different levels of unconsciousness. Sample Entropy (SampEn) algorithm was utilised in order to acquire the chaotic features of the signals. After calculating the SampEn from the EEG signals, Random Forest was utilised for developing learning regression models with Bispectral index (BIS) as the target. Correlation coefficient, mean absolute error, and area under the curve (AUC) were used to verify the perioperative performance of the proposed method. Validation comparisons with typical nonstationary signal analysis methods (i.e., recurrence analysis and permutation entropy) and regression methods (i.e., neural network and support vector machine) were conducted. To further verify the accuracy and validity of the proposed methodology, the data is divided into four unconsciousness-level groups on the basis of BIS levels. Subsequently, analysis of variance (ANOVA) was applied to the corresponding index (i.e., regression output). Results indicate that the correlation coefficient improved to 0.72 ± 0.09 after filtering and to 0.90 ± 0.05 after regression from the initial values of 0.51 ± 0.17. Similarly, the final mean absolute error dramatically declined to 5.22 ± 2.12. In addition, the ultimate AUC increased to 0.98 ± 0.02, and the ANOVA analysis indicates that each of the four groups of different anaesthetic levels demonstrated significant difference from the nearest levels. Furthermore, the Random Forest output was extensively linear in relation to BIS, thus with better DoA prediction accuracy. In conclusion, the proposed method provides a concrete basis for monitoring patients’ anaesthetic level during surgeries.

Evaluation of depth of anaesthesia (DoA) is critical in clinical surgery. Indices derived from electroencephalogram (EEG) are currently widely used to quantify DoA. However, there are known to be inaccurate under certain conditions; therefore, experienced anaesthesiologists rely on the monitoring of vital signs such as body temperature, pulse rate, respiration rate, and blood pressure to control the procedure. Because of the lack of an ideal approach for quantifying level of consciousness, studies have been conducted to develop improved methods of measuring DoA. In this study, a short-term index known as the similarity and distribution index (SDI) is proposed. The SDI is generated using heart rate variability (HRV) in the time domain and is based on observations of data distribution differences between two consecutive 32 s HRV data segments. A comparison between SDI results and expert assessments of consciousness level revealed that the SDI has strong correlation with anaesthetic depth. To optimise the effect, artificial neural network (ANN) models were constructed to fit the SDI, and ANN blind cross-validation was conducted to overcome random errors and overfitting problems. An ensemble ANN was then employed and was discovered to provide favourable DoA assessment in comparison with commonly used Bispectral Index. This study demonstrated the effectiveness of this method of DoA assessment, and the results imply that it is feasible and meaningful to use the SDI to measure DoA with the additional use of other measurement methods, if appropriate.

One concern to the patients is the off-line detection of pneumonia infection status after using the ventilator in the intensive care unit. Hence, machine learning methods for ventilator-associated pneumonia (VAP) rapid diagnose are proposed. A popular device, Cyranose 320 e-nose, is usually used in research on lung disease, which is a highly integrated system and sensor comprising 32 array using polymer and carbon black materials. In this study, a total of 24 subjects were involved, including 12 subjects who are infected with pneumonia, and the rest are non-infected. Three layers of back propagation artificial neural network and support vector machine (SVM) methods were applied to patients’ data to predict whether they are infected with VAP with Pseudomonas aeruginosa infection. Furthermore, in order to improve the accuracy and the generalization of the prediction models, the ensemble neural networks (ENN) method was applied. In this study, ENN and SVM prediction models were trained and tested. In order to evaluate the models’ performance, a fivefold cross-validation method was applied. The results showed that both ENN and SVM models have high recognition rates of VAP with Pseudomonas aeruginosa infection, with 0.9479 ± 0.0135 and 0.8686 ± 0.0422 accuracies, 0.9714 ± 0.0131, 0.9250 ± 0.0423 sensitivities, and 0.9288 ± 0.0306, 0.8639 ± 0.0276 positive predictive values, respectively. The ENN model showed better performance compared to SVM in the recognition of VAP with Pseudomonas aeruginosa infection. The areas under the receiver operating characteristic curve of the two models were 0.9842 ± 0.0058 and 0.9410 ± 0.0301, respectively, showing that both models are very stable and accurate classifiers. This study aims to assist the physician in providing a scientific and effective reference for performing early detection in Pseudomonas aeruginosa infection or other diseases.

To assess the improvement of human body balance, a low cost and portable measuring device of center of pressure (COP), known as center of pressure and complexity monitoring system (CPCMS), has been developed for data logging and analysis. In order to prove that the system can estimate the different magnitude of different sways in comparison with the commercial Advanced Mechanical Technology Incorporation (AMTI) system, four sway tests have been developed (i.e., eyes open, eyes closed, eyes open with water pad, and eyes closed with water pad) to produce different sway displacements. Firstly, static and dynamic tests were conducted to investigate the feasibility of the system. Then, correlation tests of the CPCMS and AMTI systems have been compared with four sway tests. The results are within the acceptable range. Furthermore, multivariate empirical mode decomposition (MEMD) and enhanced multivariate multiscale entropy (MMSE) analysis methods have been used to analyze COP data reported by the CPCMS and compare it with the AMTI system. The improvements of the CPCMS are 35% to 70% (open eyes test) and 60% to 70% (eyes closed test) with and without water pad. The AMTI system has shown an improvement of 40% to 80% (open eyes test) and 65% to 75% (closed eyes test). The results indicate that the CPCMS system can achieve similar results to the commercial product so it can determine the balance.

EEG (Electroencephalography) signals can express the human awareness activities and consequently it can indicate the depth of anesthesia. On the other hand, Bispectral-index (BIS) is often used as an indicator to assess the depth of anesthesia. This study is aimed at using an advanced signal processing method to analyze EEG signals and compare them with existing BIS indexes from a commercial product (i.e., IntelliVue MP60 BIS module). Multivariate empirical mode decomposition (MEMD) algorithm is utilized to filter the EEG signals. A combination of two MEMD components (IMF2 + IMF3) is used to express the raw EEG. Then, sample entropy algorithm is used to calculate the complexity of the patients’ EEG signal. Furthermore, linear regression and artificial neural network (ANN) methods were used to model the sample entropy using BIS index as the gold standard. ANN can produce better target value than linear regression. The correlation coefficient is 0.790 ± 0.069 and MAE is 8.448 ± 1.887. In conclusion, the area under the receiver operating characteristic (ROC) curve (AUC) of sample entropy value using ANN and MEMD is 0.969 ± 0.028 while the AUC of sample entropy value without filter is 0.733 ± 0.123. It means the MEMD method can filter out noise of the brain waves, so that the sample entropy of EEG can be closely related to the depth of anesthesia. Therefore, the resulting index can be adopted as the reference for the physician, in order to reduce the risk of surgery.

In monitoring the depth of anesthesia (DOA), the electroencephalography (EEG) signals of patients have been utilized during surgeries to diagnose their level of consciousness. Different entropy methods were applied to analyze the EEG signal and measure its complexity, such as spectral entropy, approximate entropy (ApEn) and sample entropy (SampEn). However, as a weak physiological signal, EEG is easily subject to interference from external sources such as the electric power, electric knives and other electrophysiological signal sources, which lead to a reduction in the accuracy of DOA determination. In this study, we adopt the multivariate empirical mode decomposition (MEMD) to decompose and reconstruct the EEG recorded from clinical surgeries according to its best performance among the empirical mode decomposition (EMD), the ensemble EMD (EEMD), and the complementary EEMD (CEEMD) and the MEMD. Moreover, according to the comparison between SampEn and ApEn in measuring DOA, the SampEn is a practical and efficient method to monitor the DOA during surgeries at real time.

Falls are unpredictable accidents and resulting injuries can be serious to the elderly. A preventative solution can be the use of vibration stimulus of white noise to improve the sense of balance. In this work, a pair of vibration shoes were developed and controlled by a touch-type switch which can generate mechanical vibration noise to stimulate the patient’s feet while wearing the shoes. In order to evaluate the balance stability and treatment effect of vibrating insoles in these shoes, multivariate multiscale entropy (MMSE) algorithm is applied to calculate the relative complexity index of reconstructed center of pressure (COP) signals in antero-posterior and medio-lateral directions by the multivariate empirical mode decomposition (MEMD). The results show that the balance stability of 61.5% elderly subjects is improved after wearing the developed shoes, which is more than 30.8% using multiscale entropy. In conclusion, MEMD-enhanced MMSE is able to distinguish the smaller differences between before and after the use of vibration shoes in both two directions, which is more powerful than the empirical mode decomposition (EMD)-enhanced MSE in each individual direction.

Entropy as an estimate of complexity of the electroencephalogram is an effective parameter for monitoring the depth of anesthesia (DOA) during surgery. Multiscale entropy (MSE) is useful to evaluate the complexity of signals over different time scales. However, the limitation of the length of processed signal is a problem due to observing the variation of sample entropy (SE) on different scales. In this study, the adaptive resampling procedure is employed to replace the process of coarse-graining in MSE. According to the analysis of various signals and practical EEG signals, it is feasible to calculate the SE from the adaptive resampled signals, and it has the highly similar results with the original MSE at small scales. The distribution of the MSE of EEG during the whole surgery based on adaptive resampling process is able to show the detailed variation of SE in small scales and complexity of EEG, which could help anesthesiologists evaluate the status of patients.

This study evaluates four databases from PhysioNet: The American Heart Association database (AHADB), Creighton University Ventricular Tachyarrhythmia database (CUDB), MIT-BIH Arrhythmia database (MITDB), and MIT-BIH Noise Stress Test database (NSTDB). The ANSI/AAMI EC57:2012 is used for the evaluation of the algorithms for the supraventricular ectopic beat (SVEB), ventricular ectopic beat (VEB), atrial fibrillation (AF), and ventricular fibrillation (VF) via the evaluation of the sensitivity, positive predictivity and false positive rate. Sample entropy, fast Fourier transform (FFT), and multilayer perceptron neural network with backpropagation training algorithm are selected for the integrated detection algorithms. For this study, the result for SVEB has some improvements compared to a previous study that also utilized ANSI/AAMI EC57. In further, VEB sensitivity and positive predictivity gross evaluations have greater than 80%, except for the positive predictivity of the NSTDB database. For AF gross evaluation of MITDB database, the results show very good classification, excluding the episode sensitivity. In advanced, for VF gross evaluation, the episode sensitivity and positive predictivity for the AHADB, MITDB, and CUDB, have greater than 80%, except for MITDB episode positive predictivity, which is 75%. The achieved results show that the proposed integrated SVEB, VEB, AF, and VF detection algorithm has an accurate classification according to ANSI/AAMI EC57:2012. In conclusion, the proposed integrated detection algorithm can achieve good accuracy in comparison with other previous studies. Furthermore, more advanced algorithms and hardware devices should be performed in future for arrhythmia detection and evaluation.

This paper aims to find the optimal set of initial weights to enhance the accuracy of artificial neural networks (ANNs) by using genetic algorithms (GA). The sample in this study included 228 patients with first low-trauma hip fracture and 215 patients without hip fracture, both of them were interviewed with 78 questions. We used logistic regression to select 5 important factors (i.e., bone mineral density, experience of fracture, average hand grip strength, intake of coffee, and peak expiratory flow rate) for building artificial neural networks to predict the probabilities of hip fractures. Three-layer (one hidden layer) ANNs models with back-propagation training algorithms were adopted. The purpose in this paper is to find the optimal initial weights of neural networks via genetic algorithm to improve the predictability. Area under the ROC curve (AUC) was used to assess the performance of neural networks. The study results showed the genetic algorithm obtained an AUC of 0.858±0.00493 on modeling data and 0.802 ± 0.03318 on testing data. They were slightly better than the results of our previous study (0.868±0.00387 and 0.796±0.02559, resp.). Thus, the preliminary study for only using simple GA has been proved to be effective for improving the accuracy of artificial neural networks.