Abstract Integrating machine learning techniques into medical diagnostic systems holds great promise for enhancing disease identification and treatment. Among the various options for training such systems, the extreme learning machine (ELM) stands out due to its rapid learning capability and computational efficiency. However, the random selection of input weights and hidden neuron biases in the ELM can lead to suboptimal performance. To address this issue, our study introduces a novel approach called modified Harris hawks optimizer (MHHO) to optimize these parameters in ELM for medical classification tasks. By applying the MHHO‐based method to seven medical datasets, our experimental results demonstrate its superiority over seven other evolutionary‐based ELM trainer models. The findings strongly suggest that the MHHO approach can serve as a valuable tool for enhancing the performance of ELM in medical diagnosis.

In recent years, the development of robotics and artificial intelligence (AI) systems has been nothing short of remarkable. As these systems continue to evolve, they are being utilized in increasingly complex and unstructured environments, such as autonomous driving, aerial robotics, and natural language processing. As a consequence, programming their behaviors manually or defining their behavior through the reward functions [as done in reinforcement learning (RL)] has become exceedingly difficult. This is because such environments require a high degree of flexibility and adaptability, making it challenging to specify an optimal set of rules or reward signals that can account for all the possible situations. In such environments, learning from an expert's behavior through imitation is often more appealing. This is where imitation learning (IL) comes into play - a process where desired behavior is learned by imitating an expert's behavior, which is provided through demonstrations.This article aims to provide an introduction to IL and an overview of its underlying assumptions and approaches. It also offers a detailed description of recent advances and emerging areas of research in the field. Additionally, this article discusses how researchers have addressed common challenges associated with IL and provides potential directions for future research. Overall, the goal of this article is to provide a comprehensive guide to the growing field of IL in robotics and AI.

Uncertainty quantification (UQ) for predictions generated by neural networks (NNs) is of vital importance in safety-critical applications. An ideal model is supposed to generate low uncertainty for correct predictions and high uncertainty for incorrect predictions. The main focus of state-of-the-art training algorithms is to optimize the NN parameters to improve the accuracy-related metrics. Training based on uncertainty metrics has been fully ignored or overlooked in the literature. This article introduces a novel uncertainty-aware training algorithm for classification tasks. A novel predictive uncertainty estimate-based objective function is defined and optimized using the stochastic gradient descent method. This new multiobjective loss function covers both accuracy and uncertainty accuracy (UA) simultaneously during training. The performance of the proposed training framework is compared from different aspects with other UQ techniques for different benchmarks. The obtained results demonstrate the effectiveness of the proposed framework for developing the NN models capable of generating reliable uncertainty estimates.

In this article, a new feature selection (FS) algorithm, called simple, fast, and efficient (SFE), is proposed for high-dimensional datasets. The SFE algorithm performs its search process using a search agent and two operators: 1) nonselection and 2) selection. It comprises two phases: 1) exploration and 2) exploitation. In the exploration phase, the nonselection operator performs a global search in the entire problem search space for the irrelevant, redundant, trivial, and noisy features and changes the status of the features from selected mode to nonselected mode. In the exploitation phase, the selection operator searches the problem search space for the features with a high impact on the classification results and changes the status of the features from nonselected mode to selected mode. The proposed SFE is successful in FS from high-dimensional datasets. However, after reducing the dimensionality of a dataset, its performance cannot be increased significantly. In these situations, an evolutionary computational method could be used to find a more efficient subset of features in the new and reduced search space. To overcome this issue, this article proposes a hybrid algorithm, SFE-PSO (particle swarm optimization) to find an optimal feature subset. The efficiency and effectiveness of the SFE and the SFE-PSO for FS are compared on 40 high-dimensional datasets. Their performances were compared with six recently proposed FS algorithms. The results obtained indicate that the two proposed algorithms significantly outperform the other algorithms and can be used as efficient and effective algorithms in selecting features from high-dimensional datasets.

The automatic and accurate analysis of medical images (e.g., segmentation,detection, classification) are prerequisites for modern disease diagnosis and prognosis. Computer-aided diagnosis (CAD) systems empower accurate and effective detection of various diseases and timely treatment decisions. The past decade witnessed a spur in deep learning (DL)-based CADs showing outstanding performance across many health care applications. Medical imaging is hindered by multiple sources of uncertainty ranging fromnteasurement (aleatoric) errors, physiological variability, and limited medical knowledge (epistemic errors). However, uncertainty quantification (UQ) in most existing DL methods is insufficiently investigated, particularly in medical image analysis. Therefore, to address this gap, in this article, we propose a simple yet novel hierarchical attentive multilevel feature fusion model with an uncertainty-aware module for medical image classification coinedHercules. This approach is tested on several real medical image classification challenges. The proposedHerculesmodel consists of two main feature fusion blocks, where the former concentrates on attention-based fusion with uncertainty quantification module and the latter uses the raw features.Herculeswas evaluated across three medical imaging datasets, i.e., retinal OCT, lung CT, and chest X-ray.Herculesproduced the best classification accuracy in retinal OCT (94.21%), lung CT (99.59%), and chest X-ray (96.50%) datasets, respectively, against other state-of-the-art medical image classification methods.

Wind power forecasting is very crucial for power system planning and scheduling. Deep neural networks (DNNs) are widely used in forecasting applications due to their exceptional performance. However, the DNNs’ architectural configuration has a significant impact on their performance, and the selection of proper hyper-parameters determines the success or failure of these models. Therefore, one of the challenging issues in DNNs is how to assess their hyper-parameter values effectively. Most of the previous researches in the literature have tuned the DNNs’ hyper-parameters manually, which is a weak and time-consuming task. Using optimization/evolutionary algorithms is an effective way to obtain the optimal values of DNNs’ hyper-parameters automatically. In this article, we propose a novel evolutionary algorithm that is based on the grasshopper optimization algorithm (GOA) improved by adding two evolutionary operators, opposition-based learning and chaos theory, to the optimization process. Overall, a novel probabilistic wind power forecasting model named neural GOA deep auto-regressive (NGOA-DeepAr) is proposed based on an auto-regressive recurrent neural network in which the proposed evolutionary algorithm has optimized its hyper-parameters. The performance of the proposed NGOA-DeepAr model is tested on two different datasets: One is the publicly available GEFCom-2014 dataset and the other is the Australian Energy Market Operator dataset. The prediction interval coverage probability and pinball loss for the two datasets are$[0.902, 0.320]$and$[0.933, 1.4885]$, respectively. According to the experimental findings, our proposed NGOA-DeepAr is much faster in learning and outperforms the benchmark DNNs and the other neuroevolutionary models.

Human Activity Recognition (HAR) is one of the essential building blocks of so many applications like security, monitoring, the internet of things and human-robot interaction. The research community has developed various methodologies to detect human activity based on various input types. However, most of the research in the field has been focused on applications other than human-in-the-centre applications. This paper focused on optimising the input signals to maximise the HAR performance from wearable sensors. A model based on Convolutional Neural Networks (CNN) has been proposed and trained on different signal combinations of three Inertial Measurement Units (IMU) that exhibit the movements of the dominant hand, leg and chest of the subject. The results demonstrate k-fold cross-validation accuracy between 99.77 and 99.98% for signals with the modality of 12 or higher. The performance of lower dimension signals, except signals containing information from both chest and ankle, was far inferior, showing between 73 and 85% accuracy.

This paper proposes transferred initialization with modified fully connected layers for COVID-19 diagnosis. Convolutional neural networks (CNN) achieved a remarkable result in image classification. However, training a high-performing model is a very complicated and time-consuming process because of the complexity of image recognition applications. On the other hand, transfer learning is a relatively new learning method that has been employed in many sectors to achieve good performance with fewer computations. In this research, the PyTorch pre-trained models (VGG19_bn and WideResNet -101) are applied in the MNIST dataset for the first time as initialization and with modified fully connected layers. The employed PyTorch pre-trained models were previously trained in ImageNet. The proposed model is developed and verified in the Kaggle notebook, and it reached the outstanding accuracy of 99.77% without taking a huge computational time during the training process of the network. We also applied the same methodology to the SIIM-FISABIO-RSNA COVID-19 Detection dataset and achieved 80.01% accuracy. In contrast, the previous methods need a huge compactional time during the training process to reach a high-performing model. Codes are available at the following link: github.com/dipuk0506/Spina1Net

Human walking is a complex activity with a high level of cooperation and interaction between different systems in the body. Accurate detection of the phases of the gait in real-time is crucial to control lower-limb assistive devices like exoskeletons and prostheses. There are several ways to detect the walking gait phase, ranging from cameras and depth sensors to the sensors attached to the device itself or the human body. Electromyography (EMG) is one of the input methods that has captured lots of attention due to its precision and time delay between neuromuscular activity and muscle movement. This study proposes a few Machine Learning (ML) based models on lower-limb EMG data for human walking. The proposed models are based on Gaussian Naive Bayes (NB), Decision Tree (DT), Random Forest (RF), Linear Discriminant Analysis (LDA) and Deep Convolutional Neural Networks (DCNN). The traditional ML models are trained on hand-crafted features or their reduced components using Principal Component Analysis (PCA). On the contrary, the DCNN model utilises convolutional layers to extract features from raw data. The results show up to 75% average accuracy for traditional ML models and 79% for Deep Learning (DL) model. The highest achieved accuracy in 50 trials of the training DL model is 89.5%.

Human Activity Recognition (HAR) is one of the fundamental building blocks of human assistive devices like orthoses and exoskeletons. There are different approaches to HAR depending on the application. Numerous studies have been focused on improving them by optimising input data or classification algorithms. However, most of these studies have been focused on applications like security and monitoring, smart devices, the internet of things, etc. On the other hand, HAR can help adjust and control wearable assistive devices, yet there has not been enough research facilitating its implementation. In this study, we propose several models to predict four activities from inertial sensors located in the ankle area of a lower-leg assistive device user. This choice is because they do not need to be attached to the user’s skin and can be directly implemented inside the control unit of the device. The proposed models are based on Artificial Neural Networks and could achieve up to 92.8% average classification accuracy.

Industry 5.0 is here, and human interaction experts claim that in the process of augmenting a high production/manufacturing workplace, a safety critical situation is created with the introduction of “Cobots”. A Multi-Agent Safety System (MASS) is presented as a solution in this paper which uses commercial, wearable technologies with high data sharing acceptance rates such as the Apple watch to collect and share real time ECG signals with the Cobot. Principal Component Analysis (PCA) is selected as a dimension reduction tool because it is well established and meets the requirements for reliability in the development of a human-centric, safety system. Five Machine Learning (ML) classifiers (KNN, NB, RF, DT and GBM) are used with binary classification to predict whether the human is Distracted (Event 1) or Not Distracted (Event 0) to determine if this will pose a safety risk to the Human Robot Collaboration (HRC) System. Decision Tree (DT) classifier with 4 Principal Components (PCs) is evaluated at 98% Accuracy and 99%AUC and is the recommended model for future development of the MASS. A road map is also presented to ensure the longevity of MASS while signifying the inclusion of real time data which can close the demographic data gap and help to improve the privacy, efficiency and contextual reliability of the MASS model in the Industry 5.0 workplace.

Abstract Coronary artery disease (CAD) is the leading cause of morbidity and death worldwide. Invasive coronary angiography is the most accurate technique for diagnosing CAD, but is invasive and costly. Hence, analytical methods such as machine learning and data mining techniques are becoming increasingly more popular. Although physicians need to know which arteries are stenotic, most of the researchers focus only on CAD detection and few studies have investigated stenosis of the right coronary artery (RCA), left circumflex (LCX) artery and left anterior descending (LAD) artery separately. Meanwhile, most of the datasets in this field are noisy (data uncertainty). However, to the best of our knowledge, there is no study conducted to address this important problem. This study uses the extension of the Z‐Alizadeh Sani dataset, containing 303 records with 54 features. A new feature selection algorithm is proposed in this work. Meanwhile, by discretization of data, we also handle the uncertainty in CAD prediction. To the best of our knowledge, this is the first study attempted to handle uncertainty in CAD prediction. Finally, the genetic algorithm (GA) is used to determine the hyper‐parameters of the support vector machine (SVM) kernels. We have achieved high accuracy for the stenosis diagnosis of each main coronary artery. The results of this study can aid the clinicians to validate their manual stenosis diagnosis of RCA, LCX and LAD coronary arteries.

This article introduces an uncertainty-aware cloud-fog-based framework for power management of smart grids using a multiagent-based system. The power management is a social welfare optimization problem. A multiagent-based algorithm is suggested to solve this problem, in which agents are defined as volunteering consumers and dispatchable generators. In the proposed method, every consumer can voluntarily put a price on its power demand at each interval of operation to benefit from the equal opportunity of contributing to the power management process provided for all generation and consumption units. In addition, the uncertainty analysis using a deep learning method is also applied in a distributive way with the local calculation of prediction intervals for sources with stochastic nature in the system, such as loads, small wind turbines (WTs), and rooftop photovoltaics (PVs). Using the predicted ranges of load demand and stochastic generation outputs, a range for power consumption/generation is also provided for each agent called "preparation range" to demonstrate the predicted boundary, where the accepted power consumption/generation of an agent might occur, considering the uncertain sources. Besides, fog computing is deployed as a critical infrastructure for fast calculation and providing local storage for reasonable pricing. Cloud services are also proposed for virtual applications as efficient databases and computation units. The performance of the proposed framework is examined on two smart grid test systems and compared with other well-known methods. The results prove the capability of the proposed method to obtain the optimal outcomes in a short time for any scale of grid.

This article proposes a two-layer in-depth secured management architecture for the optimal operation of energy internet in hybrid microgrids. In the cyber layer of the proposed architecture, a two-level intrusion detection system (IDS) is proposed to detect various cyber-attacks (i.e., Sybil attacks, spoofing attacks, false data injection attacks) on wireless-based advanced metering infrastructures. The sequential probability ratio testing approach is utilized in both levels of the proposed IDS to detect cyber-attacks based on a sequence of anomalies rather than only one piece of evidence. The process of making a decision in the proposed IDS is a random walk that starts from a point between two thresholds and moves toward one of them concerning received data samples. The feasibility and performance of the proposed architecture are examined on the IEEE 33-bus test system and the results are provided for both islanded and grid-connected operation modes.

Accurate prediction of solar energy is an important issue for photovoltaic power plants to enable early participation in energy auction industries and cost-effective resource planning. This article introduces a new deep learning-based multistep ahead approach to improve the forecasting performance of global horizontal irradiance (GHI). A deep convolutional long short-term memory is used to extract optimal features for accurate prediction of the GHI. The performance of such deep neural networks directly depends on their architectures. To deal with this problem, a swarm evolutionary optimization method, called the sine-cosine algorithm, is applied and advanced to automatically optimize the network architecture. A three-phase modification model is proposed to increase the diversity of population and avoid premature convergence in the optimization mechanism. The performance of the proposed method is investigated using three datasets collected from three solar stations in the east of the United States. The experimental results demonstrate the superiority of the proposed method in comparison to other forecasting models.

Prediction with uncertainty quantification (UQ) is becoming a vital part of the grid management with the increased uncertainty caused by the recent installation of renewable power sources. Specialized algorithms are developed and applied to predict electricity demand, renewable generations and other non-fossil-fuel generations in point predictions. The required fossil fuel generation (RFFG) of a grid is predicted from the subtraction of other generations from the demand. A prediction interval (PI) constructed from intervals of different components results in a higher coverage probability with much higher width. This paper presents the direct construction of smart RFFG PIs, maintains a narrower width with the expected coverage probability. The time series array of the RFFG is obtained from the subtraction of the sum of other generations from the electricity demand. A modified NN based Lower Upper Bound Estimation (LUBE) method is applied with a continuous cost function to construct PIs; as the LUBE method can construct smart PIs for an asymmetric and heteroscedastic probability distribution. Many inter-related uncertainties between the electricity demand and renewables are canceled out with the difference; result in a narrower and smarter PI with less computation.

Recommender systems are known as intelligent systems which have many applications in enormous domains such as social networks, e-commerce services, and online shopping. Deep neural networks have shown significant improvement in the performance of recommender systems by learning the latent features of users/items based on input data. However, it is a challenging issue to how to apply deep neural networks on different resources and how to integrate their results. In this regard, we propose a recommender system in this paper based on deep sparse autoencoder and particle swarm optimization. In particular, a deep sparse autoencoder is utilized to learn latent features based on the ratings matrix, trust relationships, and tag information. Then, particle swarm optimization is used to find the optimal weights of these latent features in calculating unknown ratings. Experiments on two datasets show the superiority of the proposed method in comparison with state of the art recommender algorithms.

This study aims to explore different pre-trained models offered in the Torchvision package which is available in the PyTorch library. And investigate their effectiveness on fine-grained images classification. Transfer Learning is an effective method of achieving extremely good performance with insufficient training data. In many real-world situations, people cannot collect sufficient data required to train a deep neural network model efficiently. Transfer Learning models are pre-trained on a large data set, and can bring a good performance on smaller datasets with significantly lower training time. Torchvision package offers us many models to apply the Transfer Learning on smaller datasets. Therefore, researchers may need a guideline for the selection of a good model. We investigate Torchvision pre-trained models on four different data sets: 10 Monkey Species, 225 Bird Species, Fruits 360, and Oxford 102 Flowers. These data sets have images of different resolutions, class numbers, and different achievable accuracies. We also apply their usual fully-connected layer and the Spinal fully-connected layer to investigate the effectiveness of SpinalNet. The Spinal fully-connected layer brings better performance in most situations. We apply the same augmentation for different models for the same data set for a fair comparison. This paper may help future Computer Vision researchers in choosing a proper Transfer Learning model.

Human Activity Recognition (HAR) is a crucial technology for many applications such as smart homes, surveillance, human assistance and health care. This technology utilises pattern recognition and can contribute to the development of human-in-the-loop control of different systems such as orthoses and exoskeletons. The majority of reported studies use a small dataset collected from an experiment for a specific purpose. The downsides of this approach include: 1) it is hard to generalise the outcome to different people with different biomechanical characteristics and health conditions, and 2) it cannot be implemented in applications other than the original experiment. To address these deficiencies, the current study investigates using a publicly available dataset collected for pathology diagnosis purposes to train Machine Learning (ML) algorithms. A dataset containing knee motion of participants performing different exercises has been used to classify human activity. The algorithms used in this study are Gaussian Naive Bayes, Decision Tree, Random Forest, K-Nearest Neighbors Vote, Support Vector Machine and Gradient Boosting. Furthermore, two training approaches are compared to raw data (de-noised) and manually extracted features. The results show up to 0.94 performance of the Area Under the ROC Curve (AUC) metric for 11-fold cross-validation for Gradient Boosting algorithm using raw data. This outcome reflects the validity and potential use of the proposed approach for this type of dataset.

The usage of autonomous vehicles in the transportation sector can achieve the objective of a safe environment. To increase riding comfort in an autonomous vehicle, one main challenge is to implement motion scenarios according to the passenger’s driving behaviours. This leads to customization of the driving style of an autonomous vehicle according to the preference of its passenger. The main disadvantage of the current autonomous vehicles is the regeneration of driving motion signals without taking into consideration the comfort/discomfort of the passengers according to their driving behaviours and preferred driving styles such as acceleration/deceleration rate and steering styles. In this paper, a nonlinear autoregressive network model is developed and trained based on the generated motion scenarios of the passenger and the position of the autonomous vehicle, in order to predict and replicate the motion signals based on the passenger’s driving behaviours. The MATLAB toolbox is used to train the network and forecast the motion signals. The results show the usefulness of the proposed method in terms of a higher shape similarity level and a lower mean square error rate between the actual and forecasted motion signals. These regenerated motion signals can increase the riding comfort of autonomous vehicle’s passengers as it is able to imitate the behaviour of the passengers.

Deep learning-based collaborative filtering methods are studied in recommendation systems as efficient feature mapping techniques. The aim of these methods is to project the users and items to a common representation space and obtain their latent features. Although these methods have been widely used in the literature, they suffer from the limited expressiveness of Dot product function. In other words, Dot product cannot describe different impacts of various latent factors. To solve this issue, we propose a novel recommender system named Deep-MSR which exploits the multilayer perceptron (MLP) neural network and stacked auto-encoder network (SAN) to extract item latent factors and user latent factors from user-item interaction matrix. The obtained latent factors are used in the proposed rating prediction module which integrates user preferences and item features in the recommendation process. Our experiments on two well-known datasets show that our method can outperform the competitive baseline recommendation methods.

This paper proposes a new approach to produce classification rules based on evolutionary computation with novel crossover and mutation operators customized for execution on graphics processing unit (GPU). Also, a novel method is presented to define the fitness function, i.e. the function which measures quantitatively the accuracy of the rule. The proposed fitness function is benefited from parallelism due to the parallel execution of data instances. To this end, two novel concepts; coverage matrix and reduction vectors are used and an altered form of the reduction vector is compared with previous works. Our CUDA program performs operations on coverage matrix and reduction vector in parallel. Also these data structures are used for evaluation of fitness function and calculation of genetic operators in parallel. We proposed a vector called average coverage to handle crossover and mutation properly. Our proposed method obtained a maximum accuracy of 99.74% for Hepatitis C Virus (HCV) dataset, 95.73% for Poker dataset, and 100% for COVID-19 dataset. Our speedup is higher than 20% for HCV and COVID-19, and 50% for Poker, compared to using single core processors.

The problem of electricity load forecasting has emerged as an essential topic for power systems and electricity markets seeking to minimize costs. However, this topic has a high level of complexity. Over the past few years, convolutional neural networks (CNNs) have been used to solve several complex deep learning challenges, making substantial progress in some fields and contributing to state of the art performances. Nevertheless, CNN architecture design remains a challenging problem. Moreover, designing an optimal architecture for CNNs leads to improve their performance in the prediction process. This article proposes an effective approach for the electricity load forecasting problem using a deep neuroevolution algorithm to automatically design the CNN structures using a novel modified evolutionary algorithm called enhanced grey wolf optimizer (EGWO). The architecture of CNNs and its hyperparameters are optimized by the novel discrete EGWO algorithm for enhancing its load forecasting accuracy. The proposed method is evaluated on real time data obtained from datasets of Australian Energy Market Operator in the year 2018. The simulation results demonstrated that the proposed method outperforms other compared forecasting algorithms based on different evaluation metrics.

The early and reliable detection of COVID-19 infected patients is essential to prevent and limit its outbreak. The PCR tests for COVID-19 detection are not available in many countries, and also, there are genuine concerns about their reliability and performance. Motivated by these shortcomings, this article proposes a deep uncertainty-aware transfer learning framework for COVID-19 detection using medical images. Four popular convolutional neural networks (CNNs), including VGG16, ResNet50, DenseNet121, and InceptionResNetV2, are first applied to extract deep features from chest X-ray and computed tomography (CT) images. Extracted features are then processed by different machine learning and statistical modeling techniques to identify COVID-19 cases. We also calculate and report the epistemic uncertainty of classification results to identify regions where the trained models are not confident about their decisions (out of distribution problem). Comprehensive simulation results for X-ray and CT image data sets indicate that linear support vector machine and neural network models achieve the best results as measured by accuracy, sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC). Also, it is found that predictive uncertainty estimates are much higher for CT images compared to X-ray images.

This work was partly supported by the MINECO/ FEDER under the RTI2018-098913-B100, CV20-45250 and A-TIC-080-UGR18 projects.

Uncertainty quantification (UQ) from similar events brings transparency. However, the presence of an irrelevant event may degrade the performance of similarity-based algorithms. This paper presents a UQ technique from similarity and sensitivity. A traditional neural network (NN) for the point prediction is trained at first to obtain the sensitivity of different input parameters at different points. The relative range of each input parameter is set based on sensitivity. When the sensitivity of one parameter is very high, a small deviation in that parameter may result in a large deviation in output. While selecting similar events, we allow a small deviation in highly sensitive parameters and a large deviation in less sensitive parameters. Uncertainty bounds are computed based on similar events. Similar events contain exact matches and slightly different samples. Therefore, we train a NN for bound correction. The bound-corrected uncertainty bounds (UB) provide a fair and domain-independent uncertainty bound. Finally, we train NNs to compute UB directly. The end-user need to run the final NN to obtain UB, instead of following the entire process. The code of the proposed method is also uploaded to Github. Also, users need to run only the fifth script to train a NN of a different UB.

This paper investigates a novel synchronisation strategy for controlling Internet-based teleoperation systems. These kinds of systems considerably suffer from network-induced latencies. Random time-varying delays resulted by the Internet deteriorate the stability and performance of teleoperation processes. Moreover, uncertain dynamic elements, including human operators and partially known remote environments introduce further difficulties to the control design of such systems. Utilising the learning capabilities of artificial neural networks, this paper develops an adaptive algorithm to deal with time-delays and uncertainties negatively affecting an Internet-based teleoperation process. The stable convergence of the proposed control algorithm is proved by Lyapunov-Krasovskii stability criteria. Moreover, the robust performance of the controller is also verified via experimental evaluations.

End to end learning for autonomous navigation and driving has become a growing research trend in both industry and academia in recent years. Its promise is in treating the whole driving pipeline as the development of a deep neural network (DNN). Its Achilles' heel is access to thousands of images required for training of the DNN. This paper comprehensively investigates the applicability of the deep transfer learning for the specific task of end to end learning of autonomous navigation. Five state of the art DNNs including ResNet, AlexNet, and Densenet are applied here for extracting features from images taken by the front-facing camera of a mobile robot. Extracted features have different information values as DNNs have different architectures and learning capabilities. These features are then processed by a multilayer fully connected neural network to estimate the robot angular velocity. Obtained results for different DNNs indicate that the transfer learning-based models show a promising performance for accurately estimating the angular velocity purely using visual information. According to obtained results, AlexNet-base model outperforms others in terms of the estimation accuracy and the performance consistency.

Communication delays are known to create stability and performance issues in multilateral teleoperation systems. Multilateral teleoperation configurations usually include more than two communication channels, which can become problematic for robot control when limitations in network bandwidth results in delays and uncertainties in data transmission routes. This study develops a sliding surface based on the synchronization errors characterized between each sides of the considered multilateral teleoperation system. Here, two slave robots receive commands from the master system to cooperatively execute the desired teleoperation task in the remote, shared workspace. Lyapunov stability analysis approach guarantees the performance of the proposed controller. Moreover, the effectiveness of the controller is experimentally evaluated through a real-world Internet-based double-slave teleoperation system.

The chest computed tomography (CT) images have been used for COVID-19 detection. Automating the process of analyzing can save great amount of time and energy. In this paper a deep bayesian ensembling framework is proposed for automatic detection of COVID-19 cases using the chest CT scans. Data augmentation is applied to increase the size and quality of training data available. Transfer learning is utilized to extract informative features. The extracted features are used to train the three different bayesian classifiers. The uncertainty of the neural network predictions is estimated by anchored, unconstrained and regularized bayesian ensembling methods. The reliability of predictions is then delineated. The epistemic and aleatoric uncertainties are estimated and different bayesian classifiers are compared from different perspectives. We use a small dataset containing only 275 CT images of positive COVID-19 cases. The results sounds promising and they can be improved in the future, as the performance of deep neural networks is reliant to big datasets. Prediction accuracy and predictive uncertainty estimates for unseen chest CT images indicate that the deep bayesian ensembling is a promising framework for COVID-19 detection.

This paper proposes a robust adaptive algorithm that effectively copes with time-varying delay and uncertainties in Internet-based teleoperation systems. Time-delay induced by the communication network, as a major problem in teleoperation systems, along with uncertainties in modeling of robotic manipulators and remote environment warn the stability and performance of the system. A robust adaptive control algorithm is developed to deal with the system uncertainties and to provide a smooth estimation of delayed reference signals. The proposed control algorithm generates chattering-free torques which is one of the practical considerations for robotic applications. In addition, the achieved input-to-state stability gains do not necessarily require high gain control torques to retain the system's stability. Experimental simulation studies validate the effectiveness of the proposed control strategy on a teleoperation system consisting of a Phantom Omni Haptic device and SimMechanics model of the industrial manipulator UR10. The validation of the proposed control methodology was executed through a real-time Internet-based communication established over 4G mobile networks between Australia and Scotland.

Interacting with human operators, remote environment, and communication networks, teleoperation systems are considerably suffering from complexities and uncertainties. Managing these is of paramount importance for safe and smooth performance of teleoperation systems. Among the countless solutions developed by researchers, type-2 fuzzy (T2F) algorithms have shown an outstanding performance in modeling complex systems and tackling uncertainties. Moreover, artificial neural networks (NNs) are well known for their adaptive learning potentials. This article proposes an adaptive interval type-2 fuzzy neural-network control scheme for teleoperation systems with time-varying delays and uncertainties. The T2F models are developed based on the experimental data collected from a teleoperation setup over a local computer network. However, the resulted controller is evaluated on an intercontinental communication network through the Internet between Australia and Scotland. Moreover, the slave robot and the remote workspace are completely different and unforeseen. Stability and performance of the proposed control is analyzed by Lyapunov-Krasovskii method. Comprehensive comparative studies demonstrate that the proposed controller outperforms traditional techniques in experimental evaluations.

The high penetration level of renewable energy is thought to be one of the basic characteristics of future smart grids. Wind power, as one of the most increasing renewable energy, has brought a large number of uncertainties into the power systems. These uncertainties would require system operators to change their traditional ways of decision-making. This article provides a comprehensive survey of computational intelligence techniques for wind power uncertainty quantification in smart grids. First, prediction intervals (PIs) are introduced as a means to quantify the uncertainties in wind power forecasts. Various PI evaluation indices, including the latest trends in comprehensive evaluation techniques, are compared. Furthermore, computational intelligence-based PI construction methods are summarized and classified into traditional methods (parametric) and direct PI construction methods (nonparametric). In the second part of this article, methods of incorporating wind power forecast uncertainties into power system decision-making processes are investigated. Three techniques, namely, stochastic models, fuzzy logic models, and robust optimization, and different power system applications using these techniques are reviewed. Finally, future research directions, such as spatiotemporal and hierarchical forecasting, deep learning-based methods, and integration of predictive uncertainty estimates into the decision-making process, are discussed. This survey can benefit the readers by providing a complete technical summary of wind power uncertainty quantification and decision-making in smart grids.

Traditional point prediction systems compute a most probable value without representing the uncertainty. The point prediction is a value close to the mean or the median. A person or an autonomous system may require a prediction corresponds to a different cumulative probability (CP), known as the uncertainty bound. Therefore, in this paper, we present a probability density computing neural network (NN) training procedure. To overcome the limitation of an effective cost function, example uncertainty bounds are constructed with the help of correlation. Similar occurrences are selected through the correlation and weights are assigned to each similar occurrence based on both shape-similarities and ratio based similarities. Then example results from similar samples are considered. The normalized weighted distribution of examples is the probability distribution. Finally, a shallow NN with the example probability density is trained. The NN receives input circumstances and the cumulative probability. The NN returns the value corresponds to the given circumstances and the cumulative probability. Proposed cumulative probability computation point from a shallow NN is less computation extensive compared to the correlation-based similarity analysis. Moreover, we propose a probability density computation NN for the first time. We also upload an example code to the GitHub.

Driving motion simulators are widely used for their reliable, safe and cost-effective abilities to replicate real vehicle driving experience for simulator drivers in virtual environment. As all motion simulators have physical limitations, Motion Cueing Algorithm (MCA) is the most necessary algorithm for transformation of the real vehicle's linear and rotational motions to motion platform aiming to regenerate realistic driving sensation. Model Predictive Control (MPC)-based MCA has recently become one of the most popular MCAs. Scaling and limiting is an important unit of MPC-based MCA to reduce the amplitude of motion signal uniformly aiming to improve the realism of produced motion within the physical limitations of workspace. The current implementations of MPC use a basic form of scaling. In this paper, a novel MPC-based MCA is developed using an optimised nonlinear scaling unit and Genetic Algorithm (GA). The goal is to reproduce accurate motion sensation for the motion simulator drivers as close as possible to real vehicle within the platform's physical constraints. This is achieved via a polynomial scaling unit which is optimized by GA. The aim is to overcome the disadvantages associated with the tuning based on trial-and-error for MPC-based MCA scaling unit which is the main cause of inefficient platform workspace usage and motion sensation error between real vehicle driver and motion simulator driver. The proposed optimization-based method enhances the function of the nonlinear scaling units by considering some important factors such as the motion simulator's physical constraints and motion sensation error between the drivers in a real vehicle and a motion simulator platform. The proposed method is verified via simulation results which show the superiority of the optimised nonlinear scaling compared with the current trial and error based scaling method for MPC-based MCA as it is able to reduce the sensation error between the motion simulator and real vehicle drivers, enhance motion fidelity, and use the platform workspace more wisely to reduce sensation error while respecting the platform's physical boundaries.

The field of neuroevolution has received great attention in recent years due to its promising capability for developing well-performing models. It has been applied to many real-world problems ranging from medical diagnosis to autonomous robots. The choice of the evolutionary algorithm (EA) has a huge impact on the neuroevolution overall performance. Despite recent progress in the field, it is not clear what the best choice of EA is. The problem becomes more severe considering a dozen of EAs available for neuroevolution applications. In this paper, six state of the art EAs are applied for the task of autonomous robot navigation. These EAs are MultiVerse optimizer (MVO), moth-flame optimization (MFO), particle swarm optimization (PSO), cuckoo search (CS), Grey wolf optimizer (GWO) and bat algorithm. MLP networks are trained using these six evolutionary algorithms to solve the classification task related to the autonomous robot navigation. Comprehensive experiments are conducted using three datasets and obtained results are visually and statistically compared. To the best knowledge of the authors, comparison among the aforementioned algorithms has not been considered in the literature. It is found that neuroevolution methods perform well for the task of autonomous robot navigation. Amongst investigated EAs, MVOtrained achieves the highest and most consistent performance metrics.

Cardiovascular diseases are one of the main causes of death among individuals over the last decade. Early diagnosis and recognizing of warning signs of this disease facilitate medical treatment for patients. Angiography is considered a reliable tool to diagnose coronary artery disease (CAD), however, it has some demerits such as complications and costs. Data mining techniques are considered as reliable and powerful tools for early diagnosis of diseases and are widely used in the medicine filed for recent years. In this paper, we use these techniques for early detection of CAD by applying them on a well-known CAD dataset named Z-Alizadeh sani. Thus, an effective nature-inspired optimization algorithm named Multi-verse optimizer (MVO) based on Multilayer perceptron (MLP) training as well as nine states of the art supervised learning techniques are employed for CAD prediction. As this dataset has 54 features, before applying the supervised learning algorithms, we used a feature selection method to identify the most effective features. This procedure enhances the prediction capability of the utilized algorithms. The classification rates of all algorithms are compared with each other using the most usable evaluation metrics including accuracy and area under the curve. Eventually, the experimental results show that the most appropriate model to classify CAD patients is the MLP model trained by MVO among all other nine supervised learning methods.

Imitation learning is an efficient paradigm for teaching and controlling intelligent autonomous cars. Obtaining a set of suitable demonstrations to learn an end-to-end policy from raw pixels is a challenging task in imitation learning problems. Deep neural networks have recently shown outstanding results in learning from raw high dimensional data for solving a wide range of real-world applications. The success of deep neural networks depends on finding suitable hyperparameters for constructing network architecture. Besides, designing hand-crafted deep architectures is not an efficient way for achieving the best performance. To address this issue, this paper performs a neuro-evolution method based on genetic algorithm for finding the optimal deep neural networks architecture in terms of hyperparameters. The experimental results show the effectiveness of the proposed approach for training an autonomous vehicle.

This paper presents generalized noise patterns for (N+1)/N-factor non-linear down-sampling. In linear downsampling of two or three-factor, one sample is kept and the next one or two samples are discarded. N-samples are kept and the next one is discarded in the discussed (N+1)/N-factor non-linear down-sampling. The paper contains the mathematical reasoning of the generalized noise-patterns of (N+1)/N-factor non-linear down-sampling. The mathematical analysis provides the reason for the generalized behaviors and the simulation results bolster those findings. The knowledge of the generalized error pattern may help future researchers in understanding the noise pattern due to missing samples, interpolation, predictive coding, and noise suppression.

Deep neural networks have proven themselves as a strong approach in image classification and object detection with high accuracy. However, they are computationally demanding and the trained networks contain millions of active parameters and connections. Two recent trends of having deeper and dense architectures and the deployment of trained networks on resource-constrained devices such as smart phones and portable tablets bring new challenges. Instead of deploying an ensemble of smaller networks, we propose a pruning methodology on a trained network so that a smaller version of a fully trained network has the same and even better accuracy in comparison to the original one. We achieve two objectives with the pruning scheme. First, we have a smaller network with a better accuracy level, and we make the trained model avoids overfitting. Accordingly, an evolutionary based framework including three steps is defined to perform further tuning on trained deep network using dropping nodes and connections. This study shows that implementing genetic algorithm, after preprocessing and training stages, not only results in partially connected networks, but also increases performance and reduces overfitting specially when the depth and width of fully connected networks are investigated in small datasets.

Stability and task accomplishment of Internet-based teleoperation systems are greatly susceptible to the network latency and uncertainty. Control of a teleoperation system aims to provide satisfactory performance of the remote task and in some cases to provide the operator with sensory feedback. This paper reviews the recent control methodologies used for teleoperation systems with model uncertainty, unknown time-varying delay, and Internet-based communication. The focus is on control algorithms that are suitable for nonlinear uncertain systems to decrease restrictions and increase application scope. The key features of these control algorithms are highlighted, and their advantages and disadvantages are comparatively discussed.

An ideal noninvasive electroencephalography (EEG) based brain-computer interface (BCI) is a user-friendly plug and play system where a new user does not need to go through the long training data collection process. To reduce the amount of training data required for a new user, active learning inspired informative instance transfer is investigated in this work as one of the potential solutions. In this informative transfer learning, query by committee is applied as query method to find informative samples from subjects own domain. On the other hand, percentile range around the mean of center distance (PRMCD) query method is introduced in this work as an alternative to existing entropy criterion to find informative samples from the past user's domain. The newly introduced PRMCD algorithm has reached the benchmark performance using only average 12% of whole subjective training set while the existing entropy-based algorithm has achieved the benchmark performance using average 17% of the whole subjective training set in case of 7 out of 9 subjects. For PRMCD algorithm, a new user can achieve the intended mean benchmark performance using reduced (only 50 which is 12.5%) amount of training data in general irrespective of subjects. Therefore, incorporation of PRMCD algorithm has added an important step towards the zero training BCI. It is a significant advancement for the practical application of motor imagery based BCI.

In this paper, an optimization methodology for the weighted autocorrelation based prediction interval is proposed and applied for the prediction of the wind power generation. The Coverage Width Based Criterion (CWC) is applied as the optimization criterion. The improved execution steps are as follows- At first, the string of 20 recent samples is autocorrelated with the similar strings of previous samples. Then, the samples next to the highest normalized correlation values and corresponding indexes are selected. After that, the amplitudes of the matched samples are adjusted by multiplying the value with the amplitude of recent string and by dividing by the amplitude of matched strings. These amplitude-adjusted samples are the prediction value for the next sample. Each prediction values are given a weight depending on the ratio of the amplitude of the string and the value of normalized correlation. The weight equation is trained with the CWC equation to find the optimum relation between amplitude and correlation values. The probability density distribution is derived from the weighted autocorrelation values. Finally, least relevant areas from corners are discarded to achieve the required coverage with smaller PI width. However, as the level of uncertainty changes over time, discarding historical percentile may result in a different coverage on later targets. Therefore, the percentage of discarding is also optimized with the CWC. Wind power generation is predicted and different weight equation and discarding percentages are achieved.

Neural network (NN) based prediction or detection systems often perform excellently with easy problems without considering 1-5% difficult problems. This work proposes an adversarial NN training method for constructing the prediction interval (PI). The proposed training method considers adverse situations where traditional NN based PIs frequently fail. First, the conventional lower upper bound estimation (LUBE) method is applied in parallel for initial training of NNs with different initialization. Each NN based PI fails to cover a few samples. Input combinations of those samples are adversely changed by a small amount to generate the adverse samples. A new dataset is generated by appending adverse samples. Finally, an NN is trained with the adverse dataset. The method is applied to construct the NN for wind power prediction. According to the result analysis, the proposed method performs better in adverse situations.

Brain-computer interface (BCI) using machine learning has the requirement for a large number of training data. This requirement makes the long training session inevitable for a new user. Many approaches including transfer learning (TL) already have been reported in the literature to abridge the long training data collection session. One of them is transferring informative instances using active learning (AL) which was approached in our previous attempts for both binary and multiclass BCI. It was associated with the classic common spatial pattern (CSP) feature extraction method. It showed the potential to obtain the benchmark performance using a reduced amount of training data. However, it has subject dependent performance and was not up to the expectation particularly for multiclass BCI. For binary BCI, it is addressed by selecting the best subject-specific features from subjective narrow frequency window using filter bank CSP (FBCSP). Since multiclass BCI has different characteristics in terms of output performance and nature of features, this work investigates the incorporation of FBCSP into informative transfer learning with AL (ITAL) for multiclass BCI. Comparing with existing direct transfer with AL (DTAL) and ITAL with CSP for multiclass BCI, ITAL with FBCSP reaches the benchmark performance for six out of nine subjects using average 42% of the full training set which is significant at 5% (p <; 0.05) significance level. For multiclass BCI as well, ITAL combined with discriminating feature extraction ensures better transfer which yields to effective reduction of the training session without sacrificing the benchmark robustness.

Robotics and intelligent sensing methods are experiencing a new wave applications through the use of machine learning systems. Intelligence is being introduced in robots and sensor platforms by utilizing machine learning techniques such as classification. In the field of robotics, generating training data can be very complex and often, expensive. In this set-up, transfer learning can greatly improve the performance of a classifier wherever and whenever enough labeled data is not available in a domain of interest (target domain), but ample labeled data can be found in a different but related domain (source domain). A new optimized method is proposed in this work to transform the observation from source domain along with a new label transfer mechanism. The transformed, or adapted, domain has the same number of features as the target domain and the same number of observations from the source domain. Labels are transferred from source to target domain using a multivariate Gaussian mixture model (GMM). Genetic algorithm is used to optimize the transformation process by minimizing a cost function that addresses both distribution difference and accuracy. Experiments show that the proposed method outperforms any classifier trained only with source or target domain data.

Learning of fuzzy parameters for system modeling using evolutionary algorithms is an interesting topic. In this paper, two optimal design and tuning of Interval type-2 fuzzy logic system are proposed using hybrid learning algorithms. The consequent parameters of the interval type-2 fuzzy logic system in both the hybrid algorithms are tuned using Kalman filter. Whereas the antecedent parameters of the system in the first hybrid algorithm is optimized using the multi-objective particle swarm optimization (MOPSO) and using the multi-objective evolutionary algorithm Based on Decomposition (MOEA/D) in the second hybrid algorithm. Root mean square error and maximum absolute error as the two accuracy objective are utilized to find the Pareto-optimal solution with the MOPSO and MOEA/D respectively. The proposed hybrid multi-objective designs of the interval type-2 fuzzy logic system are utilized to the prediction of solar photovoltaic output. It is observed that MOEA/D outperforms MOPSO in this case in terms of quality of results and its diversity. Finally, one point is selected from the obtained Pareto front and its performance is illustrated.

Facial emotion recognition (FER) is a critical task for both human-human (HHI) and human-computer interactions (HCl). In this paper, a brain-inspired neural basis computational model of FER is proposed based on emotional neural networks (ENN), fuzzy c-means (FCM) and genetic algorithms (GA). The proposed model can be applied in both HHI and HCI applications. In HHI, it can be used for improving communication skills, and in HCI it can be used in various treatment processes e.g. anxiety treatment, cancer radiation treatment and remote children/elderlies monitoring systems. The proposed model consists of main modules of emotional brain which recognize the facial emotions. In the experimental studies, the proposed model is examined on children's facial sad recognition as a case study. The results show that our model is valid and can be applied for various FER tasks.

This paper presents an approach to analysis of multiclass EEG data obtained from the brain computer interface (BCI) applications. The proposed approach comprises two stages including feature extraction using the common spatial pattern (CSP) and classification using fuzzy logic systems (FLS). CSP is used to extract significant features that are then fed into FLS as inputs for classification. The metaheuristic population-based particle swarm optimization method is used to train parameters of the FLS. The multiclass motor imagery dataset IIa from the BCI competition IV is used for experiments to highlight the superiority of the proposed approach against competing methods, which include linear discriminant analysis, naïve bayes, k-nearest neighbour, ensemble learning AdaBoost and support vector machine. Results from experiments show the great accuracy of the combination of CSP and FLS. Therefore, the proposed approach can be implemented effectively in the practical BCI systems, which would be helpful for people with impairments and rehabilitation.

Denial of service flood attacks are among the most common and powerful attacks which abuse the computational resources and the bandwidth of a network. In this paper, a heterogeneous defense method is proposed based on a combination of the Software Defined controller and fuzzy decision making. Numerical results show that the proposed method has a lower computational load and response time compared to the traditional methods centralized in the controller.

Motor imagery based brain computer interface (BCI) has drawback of long subject dependent calibration session times. This can be a very exhausting and a time consuming process. In order to alleviate it, transfer learning and active learning approaches can be utilised. Informative instances are selected by applying active learning concept from other subjects under similar circumstances. Then, they are transferred to target user domain which has low number of training data. This informative transfer learning approach is associated with common spatial pattern (CSP) as feature extraction method in our previous attempt. CSP features are widely used for motor imagery-based BCI systems. However, the classical CSP algorithm will perform poorly when operational frequency bands are inadequately selected. Therefore, in the present study, filter bank common spatial pattern (FBCSP) algorithm has been applied for extracting features from the multi-class motor imagery data. FBCSP algorithm selects subject-specific operational frequency bands for extracting discriminative features. We incorporated FBCSP features into informative instance transfer learning framework to investigate the effect of subject specific feature selection. Results show that performance of new users can be improved with reduced number of training samples when FBCSP features are used compared to the classical CSP-based features.

In this paper, the concept of prediction granules (PGs) is introduced for the real world application problems. The PGs are constructed by prediction intervals (PIs) and a learning-based method. Specifically, a granular emotional neural network (GENN) is proposed and the resulting network is examined on real world wind farm power generation dataset, obtained from New South Wales of Australia. A traditional artificial neural network (ANN) is also applied for comparison purposes. Numerical results indicate that PGs can improve the prediction results and can provide useful information for prediction tasks of real world uncertain data.

Accurate prediction of wind ramp events is critical for ensuring the reliability and stability of the power systems with high penetration of wind energy. This paper proposes a classification based approach for estimating the future class of wind ramp event based on certain thresholds. A parallelized gradient boosted regression tree based technique has been proposed to accurately classify the normal as well as rare extreme wind power ramp events. The model has been validated using wind power data obtained from the National Renewable Energy Laboratory database. Performance comparison with several benchmark techniques indicates the superiority of the proposed technique in terms of superior classification accuracy.

Prediction interval (PI) has been appeared as a promising tool to quantify the uncertainties and disturbances associated with point forecasts. Despite of its numerous applications in prediction problems, the use of PIs in control application is still limited. In this paper, a PI-based ANFIS controller is proposed and designed for nonlinear systems. In the proposed algorithm, a PI-based neural network model (PI-NN) is developed to construct the PIs, and this model is used as an online estimator of PIs for the controller. The PIs along with other traditional inputs are used to train the inverse ANFIS model. The developed PI-based ANFIS model is then used as a nonlinear PI-based controller (PIC). The performance of the proposed PIC is examined for a nonlinear numerical plant. Simulation results revealed that the proposed PIC performance is superior over the traditional ANFIS-based controller.

Non-invasive EEG signal based brain computer interface (BCI) for motor imagery task - classification requires large number of subject specific training samples for each user session that reduces the user feasibility of BCI. A generalized classifier using few subject specific sample will ease the real world implementation of motor imagery based BCI. At first, this paper applies an improved active transfer learning (ATL) on motor imagery based BCI. Then, it proposes a noble method of transferring selective instances (selected by few new subject specific data) from other subjects to new subject combining with selecting most informative subject specific data determined by active learning. Experimental results on BCI competition IV 2B dataset show that improved ATL works well on six out of nine subjects and proposed SIITAL method overcomes ATL limitation for other subjects. This means, it can achieve similar or better accuracy with a lower quantity of subject specific training data. Thus, it reduces the calibration effort.

In this paper, a tensegrity structure (TS) design is formulated as a nonlinear programming (NLP) problem, and a winner-take-all artificial emotional neural network (WTA-ENN) is proposed to solve the resulting NLP. The main feature of proposed WTA-ENN is related to low number of learning weights and simplicity of its learning rules that make it a suitable model for complicated TS design problems. Numerical results indicate that WTA-ENN can effectively solve NLP problem obtained from basic module of a typical TS Tower. The proposed method can be effectively used in architectural, structural and robotics design.

This paper introduces an approach to classification of RNA-seq read count data using Gaussian process (GP) models. RNA-seq data are transformed into microarray-like data before applying the statistical two-sample t-test for gene selection. GP is designed as a classifier that takes discriminant genes selected by the t-test method as inputs. The proposed approach is verified by using two benchmark real datasets and the five-fold cross-validation strategy. Various performance metrics that include accuracy rate, F-measure, area under the ROC curve and mutual information are used to evaluate the classifiers. Experimental results show the significant dominance of the GP classifier against its competing methods including k-nearest neighbors, multilayer perceptron, support vector machine and ensemble learning AdaBoost. The proposed approach therefore can be implemented effectively in real practice for RNA-seq data analysis, which is useful in many applications related to disease diagnosis and monitoring at the molecular level.

The washout filter for a driving simulator is able to regenerate high fidelity vehicle translational and rotational motions within the simulator's physical limitations and return the simulator platform back to its initial position. The classical washout filter provides a popular solution that has been broadly utilized in different commercial simulators due to its simplicity, short processing time, and reasonable performance. One limitation of the classical washout filter is its sub-optimal parameter tuning process, which is based on the trial-and-error method. This leads to an inefficient workspace usage and, consequently, generation of false motion cues that lead to simulator sickness. Ignorance of a human sensation model in its design is another drawback of classical washout filters. The purpose of this study is to use Particle Swarm Optimization (PSO) to design and tune the washout filter parameters, in order to increase motion fidelity, decrease the human sensation error, and improve efficiency of the workspace usage. The proposed PSO-based washout filter is designed and implemented using the MATLAB/Simulink software package. The results indicate the effectiveness of the PSO-based washout filter in reducing the human sensation error, increasing the capability of reference shape tracking, and improving efficiency of the workspace usage.

The major challenge in the design of Interval type-2 fuzzy logic system (IT2FLS) is to determine the optimal parameters for their antecedent and consequent parts. The most frequently used objective function for the design of IT2FLSs is root mean squared error (RMSE). However, other than RMSE, the maximum absolute error (MAE) for each of identification samples is very important. This paper propose a novel hybrid learning algorithm for the design of IT2FLS. The proposed algorithm benefits from the combination of extreme learning machine (ELM) and non-dominated sorting genetic algorithm (NSGAII) to tune the parameters of the consequent and antecedent parts of the IT2FLS, respectively. The proposed method is used for forecasting of nonlinear dynamic systems. It is shown that not only the proposed method results in low RMSE, MAE achieved is also satisfactory.

An interval type-2 fuzzy logic system is introduced for cancer diagnosis using mass spectrometry-based proteomic data. The fuzzy system is incorporated with a feature extraction procedure that combines wavelet transform and Wilcoxon ranking test. The proposed feature extraction generates feature sets that serve as inputs to the type-2 fuzzy classifier. Uncertainty, noise and outliers that are common in the proteomic data motivate the use of type-2 fuzzy system. Tabu search is applied for structure learning of the fuzzy classifier. Experiments are performed using two benchmark proteomic datasets for the prediction of ovarian and pancreatic cancer. The dominance of the suggested feature extraction as well as type-2 fuzzy classifier against their competing methods is showcased through experimental results. The proposed approach therefore is helpful to clinicians and practitioners as it can be implemented as a medical decision support system in practice.

As an integral part of interval type-2 fuzzy logic system (IT2FLS), type reduction (TR) plays a vital role in determining the performance of IT2FLS. Out of many type reduction algorithms, only Karnik-Mendel type TR algorithms capture the essence of interval type-2 fuzzy sets in type reduction. Enhanced Karnik-Mendel (EKM) algorithm is the most commonly used TR algorithm. In this work, we propose three new initializations for EKM algorithm. It is shown they are performing better than EKM and one of the proposed initializations significantly outperforms others. The performance gain can be upto 40% as per comprehensive simulation results demonstrated in this paper. Our findings are justified by computational time savings and iteration requirement for switch point search.

Karnik-Mendel (KM) algorithm is the most used and researched type reduction (TR) algorithm in literature. This algorithm is iterative in nature and despite consistent long term effort, no general closed form formula has been found to replace this computationally expensive algorithm. In this research work, we demonstrate that the outcome of KM algorithm can be approximated by simple linear regression techniques. Since most of the applications will have a fixed range of inputs with small scale variations, it is possible to handle those complexities in design phase and build a fuzzy logic system (FLS) with low run time computational burden. This objective can be well served by the application of regression techniques. This work presents an overview of feasibility of regression techniques for design of data-driven type reducers while keeping the uncertainty bound in FLS intact Simulation results demonstrates the approximation error is less than 2%. Thus our work preserve the essence of Karnik-Mendel algorithm and serves the requirement of low computational complexities.

Karnik-Mendel (KM) algorithm is the most widely used type reduction (TR) method in literature for the design of interval type-2 fuzzy logic systems (IT2FLS). Its iterative nature for finding left and right switch points is its Achilles heel. Despite a decade of research, none of the alternative TR methods offer uncertainty measures equivalent to KM algorithm. This paper takes a data-driven approach to tackle the computational burden of this algorithm while keeping its key features. We propose a regression method to approximate left and right switch points found by KM algorithm. Approximator only uses the firing intervals, rules centroids, and FLS structural features as inputs. Once training is done, it can precisely approximate the left and right switch points through basic vector multiplications. Comprehensive simulation results demonstrate that the approximation accuracy for a wide variety of FLSs is 100%. Flexibility, ease of implementation, and speed are other features of the proposed method.

Prediction interval (PI) has been extensively used to predict the forecasts for nonlinear systems as PI-based forecast is superior over point-forecast to quantify the uncertainties and disturbances associated with the real processes. In addition, PIs bear more information than point-forecasts, such as forecast accuracy. The aim of this paper is to integrate the concept of informative PIs in the control applications to improve the tracking performance of the nonlinear controllers. In the present work, a PI-based controller (PIC) is proposed to control the nonlinear processes. Neural network (NN) inverse model is used as a controller in the proposed method. Firstly, a PI-based model is developed to construct PIs for every sample or time instance. The PIs are then fed to the NN inverse model along with other effective process inputs and outputs. The PI-based NN inverse model predicts the plant input to get the desired plant output. The performance of the proposed PIC controller is examined for a nonlinear process. Simulation results indicate that the tracking performance of the PIC is highly acceptable and better than the traditional NN inverse model-based controller.

Proposing efficient methods for fire protection is becoming more and more important, because a small flame of fire may cause huge problems in social safety. In this paper, an effective fire flame detection method is investigated. This fire detection method includes four main stages: in the first step, a linear transformation is applied to convert red, green, and blue (RGB) color space through a 3*3 matrix to a new color space. In the next step, fuzzy c-mean clustering method (FCM) is used to distinguish between fire flame and non-fire flame pixels. Particle Swarm Optimization algorithm (PSO) is also utilized in the last step to decrease the error value measured by FCM after conversion. Finally, we apply Otsu threshold method to the new converted images to make a binary picture. Empirical results show the strength, accuracy and fast-response of the proposed algorithm in detecting fire flames in color images.

An approach to EEG signal classification for brain-computer interface (BCI) application using fuzzy standard additive model is introduced in this paper. The Wilcoxon test is employed to rank wavelet coefficients. Top ranking wavelets are used to form a feature set that serves as inputs to the fuzzy classifiers. Experiments are carried out using two benchmark datasets, Ia and Ib, downloaded from the BCI competition II. Prevalent classifiers including feedforward neural network, support vector machine, k-nearest neighbours, ensemble learning Adaboost and adaptive neuro-fuzzy inference system are also implemented for comparisons. Experimental results show the dominance of the proposed method against competing approaches.

Utility companies provide electricity to a large number of consumers. These companies need to have an accurate forecast of the next day electricity demand. Any forecast errors will result in either reliability issues or increased costs for the company. Because of the widespread roll-out of smart meters, a large amount of high resolution consumption data is now accessible which was not available in the past. This new data can be used to improve the load forecast and as a result increase the reliability and decrease the expenses of electricity providers. In this paper, a number of methods for improving load forecast using smart meter data are discussed. In these methods, consumers are first divided into a number of clusters. Then a neural network is trained for each cluster and forecasts of these networks are added together in order to form the prediction for the aggregated load. In this paper, it is demonstrated that clustering increases the forecast accuracy significantly. Criteria used for grouping consumers play an important role in this process. In this work, three different feature selection methods for clustering consumers are explained and the effect of feature extraction methods on forecast error is investigated.

Accurate forecasting of wind power generation is quite an important as well as challenging task for the system operators and market participants due to its high uncertainty. It is essential to quantify uncertainties associated with wind power generation forecasts for their efficient application in optimal management of wind farms and integration into power systems. Prediction intervals (PIs) are well known statistical tools which are used to quantify the uncertainty related to forecasts by estimating the ranges of the future target variables. This paper investigates the application of a novel support vector machine based methodology to directly estimate the lower and upper bounds of the PIs without expensive computational burden and inaccurate assumptions about the distribution of the data. The efficiency of the method for uncertainty quantification is examined using monthly data from a wind farm in Australia. PIs for short term application are generated with a confidence level of 90%. Experimental results confirm the ability of the method in constructing reliable PIs without resorting to complex computational methods.

An optimal design of Adaptive Neuro-Fuzzy Inference System (ANFIS) traffic signal controller is presented in this paper. The proposed controller aims to adjust a set of green times for traffic lights in a single intersection with the purpose of minimizing travel delay time and traffic congestion. The ANFIS controller is trained, to learned how to set green times for each traffic phase. This intelligent controller uses the Cuckoo Search (CS) algorithm to tune its parameters during the learning pried. Evaluating the performance of the proposed controller in comparison with the performance of a FLS controller (FLC) with predefined rules and membership functions, and also three fixed-time controllers, illustrates the better performance of the optimal ANFIS controller against the other benchmark controllers.

Pixel color has proven to be a useful and robust cue for detection of most objects of interest like fire. In this paper, a hybrid intelligent algorithm is proposed to detect fire pixels in the background of an image. The proposed algorithm is introduced by the combination of a computational search method based on a swarm intelligence technique and the Kemdoids clustering method in order to form a Fire-based Color Space (FCS), in fact, the new technique converts RGB color system to FCS through a 3*3 matrix. This algorithm consists of five main stages:(1) extracting fire and non-fire pixels manually from the original image. (2) using K-medoids clustering to find a Cost function to minimize the error value. (3) applying Particle Swarm Optimization (PSO) to search and find the best W components in order to minimize the fitness function. (4) reporting the best matrix including feature weights, and utilizing this matrix to convert the all original images in the database to the new color space. (5) using Otsu threshold technique to binarize the final images. As compared with some state-of-the-art techniques, the experimental results show the ability and efficiency of the new method to detect fire pixels in color images.

A new multi-output interval type-2 fuzzy logic system (MOIT2FLS) is introduced for protein secondary structure prediction in this paper. Three outputs of the MOIT2FLS correspond to three structure classes including helix, strand (sheet) and coil. Quantitative properties of amino acids are employed to characterize twenty amino acids rather than the widely used computationally expensive binary encoding scheme. Three clustering tasks are performed using the adaptive vector quantization method to construct an equal number of initial rules for each type of secondary structure. Genetic algorithm is applied to optimally adjust parameters of the MOIT2FLS. The genetic fitness function is designed based on the Q3 measure. Experimental results demonstrate the dominance of the proposed approach against the traditional methods that are Chou-Fasman method, Garnier-Osguthorpe-Robson method, and artificial neural network models.

A new portfolio risk measure that is the uncertainty of portfolio fuzzy return is introduced in this paper. Beyond the well-known Sharpe ratio (i.e., the reward-to-variability ratio) in modern portfolio theory, we initiate the so-called fuzzy Sharpe ratio in the fuzzy modeling context. In addition to the introduction of the new risk measure, we also put forward the reward-to-uncertainty ratio to assess the portfolio performance in fuzzy modeling. Corresponding to two approaches based on TMand TWfuzzy arithmetic, two portfolio optimization models are formulated in which the uncertainty of portfolio fuzzy returns is minimized, while the fuzzy Sharpe ratio is maximized. These models are solved by the fuzzy approach or by the genetic algorithm (GA). Solutions of the two proposed models are shown to be dominant in terms of portfolio return uncertainty compared with those of the conventional mean-variance optimization (MVO) model used prevalently in the financial literature. In terms of portfolio performance evaluated by the fuzzy Sharpe ratio and the reward-to-uncertainty ratio, the model using TWfuzzy arithmetic results in higher performance portfolios than those obtained by both the MVO and the fuzzy model, which employs TMfuzzy arithmetic. We also find that using the fuzzy approach for solving multiobjective problems appears to achieve more optimal solutions than using GA, although GA can offer a series of well-diversified portfolio solutions diagrammed in a Pareto frontier.

Uncertainty of the electricity prices makes the task of accurate forecasting quite difficult for the electricity market participants. Prediction intervals (PIs) are statistical tools which quantify the uncertainty related to forecasts by estimating the ranges of the future electricity prices. Traditional approaches based on neural networks (NNs) generate PIs at the cost of high computational burden and doubtful assumptions about data distributions. In this work, we propose a novel technique that is not plagued with the above limitations and it generates high-quality PIs in a short time. The proposed method directly generates the lower and upper bounds of the future electricity prices using support vector machines (SVM). Optimal model parameters are obtained by the minimization of a modified PI-based objective function using a particle swarm optimization (PSO) technique. The efficiency of the proposed method is illustrated using data from Ontario, Pennsylvania-New Jersey-Maryland (PJM) interconnection day-ahead and real-time markets.

This brief proposes an efficient technique for the construction of optimized prediction intervals (PIs) by using the bootstrap technique. The method employs an innovative PI-based cost function in the training of neural networks (NNs) used for estimation of the target variance in the bootstrap method. An optimization algorithm is developed for minimization of the cost function and adjustment of NN parameters. The performance of the optimized bootstrap method is examined for seven synthetic and real-world case studies. It is shown that application of the proposed method improves the quality of constructed PIs by more than 28% over the existing technique, leading to narrower PIs with a coverage probability greater than the nominal confidence level.

Penetration of renewable energy resources, such as wind and solar power, into power systems significantly increases the uncertainties on system operation, stability, and reliability in smart grids. In this paper, the nonparametric neural network-based prediction intervals (PIs) are implemented for forecast uncertainty quantification. Instead of a single level PI, wind power forecast uncertainties are represented in a list of PIs. These PIs are then decomposed into quantiles of wind power. A new scenario generation method is proposed to handle wind power forecast uncertainties. For each hour, an empirical cumulative distribution function (ECDF) is fitted to these quantile points. The Monte Carlo simulation method is used to generate scenarios from the ECDF. Then the wind power scenarios are incorporated into a stochastic security-constrained unit commitment (SCUC) model. The heuristic genetic algorithm is utilized to solve the stochastic SCUC problem. Five deterministic and four stochastic case studies incorporated with interval forecasts of wind power are implemented. The results of these cases are presented and discussed together. Generation costs, and the scheduled and real-time economic dispatch reserves of different unit commitment strategies are compared. The experimental results show that the stochastic model is more robust than deterministic ones and, thus, decreases the risk in system operations of smart grids.

This paper introduces a new multi-output interval type-2 fuzzy logic system (MOIT2FLS) that is automatically constructed from unsupervised data clustering method and trained using heuristic genetic algorithm for a protein secondary structure classification. Three structure classes are distinguished including helix, strand (sheet) and coil which correspond to three outputs of the MOIT2FLS. Quantitative properties of amino acids are used to characterize the twenty amino acids rather than the widely used computationally expensive binary encoding scheme. Amino acid sequences are parsed into learnable patterns using a local moving window strategy. Three clustering tasks are performed using the adaptive vector quantization method to derive an equal number of initial rules for each type of secondary structure. Genetic algorithm is applied to optimally adjust parameters of the MOIT2FLS with the purpose of maximizing the Q3 measure. Comprehensive experimental results demonstrate the strong superiority of the proposed approach over the traditional methods including Chou-Fasman method, Garnier-Osguthorpe-Robson method, and artificial neural network models.

This paper proposes a combination of fuzzy standard additive model (SAM) with wavelet features for medical diagnosis. Wavelet transformation is used to reduce the dimension of high-dimensional datasets. This helps to improve the convergence speed of supervised learning process of the fuzzy SAM, which has a heavy computational burden in high-dimensional data. Fuzzy SAM becomes highly capable when deployed with wavelet features. This combination remarkably reduces its computational training burden. The performance of the proposed methodology is examined for two frequently used medical datasets: the lump breast cancer and heart disease. Experiments are deployed with a five-fold cross validation. Results demonstrate the superiority of the proposed method compared to other machine learning methods including probabilistic neural network, support vector machine, fuzzy ARTMAP, and adaptive neuro-fuzzy inference system. Faster convergence but higher accuracy shows a win-win solution of the proposed approach.

This paper aims at optimally adjusting a set of green times for traffic lights in a single intersection with the purpose of minimizing travel delay time and traffic congestion. Neural network (NN) and fuzzy logic system (FLS) are two methods applied to develop intelligent traffic timing controller. For this purpose, an intersection is considered and simulated as an intelligent agent that learns how to set green times in each cycle based on the traffic information. The training approach and data for both these learning methods are similar. Both methods use genetic algorithm to tune their parameters during learning. Finally, The performance of the two intelligent learning methods is compared with the performance of simple fixed-time method. Simulation results indicate that both intelligent methods significantly reduce the total delay in the network compared to the fixed-time method.

In contrast to point forecast, prediction interval-based neural network offers itself as an effective tool to quantify the uncertainty and disturbances that associated with process data. However, single best neural network (NN) does not always guarantee to predict better quality of forecast for different data sets or a whole range of data set. Literature reported that ensemble of NNs using forecast combination produces stable and consistence forecast than single best NN. In this work, a NNs ensemble procedure is introduced to construct better quality of Pis. Weighted averaging forecasts combination mechanism is employed to combine the Pi-based forecast. As the key contribution of this paper, a new Pi-based cost function is proposed to optimize the individual weights for NN in combination process. An optimization algorithm, named simulated annealing (SA) is used to minimize the PI-based cost function. Finally, the proposed method is examined in two different case studies and compared the results with the individual best NNs and available simple averaging Pis aggregating method. Simulation results demonstrated that the proposed method improved the quality of Pis than individual best NNs and simple averaging ensemble method.

The forecasting behavior of the high volatile and unpredictable wind power energy has always been a challenging issue in the power engineering area. In this regard, this paper proposes a new multi-objective framework based on fuzzy idea to construct optimal prediction intervals (Pis) to forecast wind power generation more sufficiently. The proposed method makes it possible to satisfy both the PI coverage probability (PICP) and PI normalized average width (PINAW), simultaneously. In order to model the stochastic and nonlinear behavior of the wind power samples, the idea of lower upper bound estimation (LUBE) method is used here. Regarding the optimization tool, an improved version of particle swam optimization (PSO) is proposed. In order to see the feasibility and satisfying performance of the proposed method, the practical data of a wind farm in Australia is used as the case study.

Spike sorting plays an important role in analysing electrophysiological data and understanding neural functions. Developing spike sorting methods that are highly accurate and computationally inexpensive is always a challenge in the biomedical engineering practice. This paper proposes an automatic unsupervised spike sorting method using the landmark-based spectral clustering (LSC) method in connection with features extracted by the locality preserving projection (LPP) technique. Gap statistics is employed to evaluate the number of clusters before the LSC can be performed. Experimental results show that LPP spike features are more discriminative than those of the popular wavelet transformation (WT). Accordingly, the proposed method LPP-LSC demonstrates a significant dominance compared to the existing method that is the combination between WT feature extraction and the superparamagnetic clustering. LPP and LSC are both linear algorithms that help reduce computational burden and thus their combination can be applied into realtime spike analysis.

Uncertainty is known to be a concomitant factor of almost all the real world commodities such as oil prices, stock prices, sales and demand of products. As a consequence, forecasting problems are becoming more and more challenging and ridden with uncertainty. Such uncertainties are generally quantified by statistical tools such as prediction intervals (Pis). Pis quantify the uncertainty related to forecasts by estimating the ranges of the targeted quantities. Pis generated by traditional neural network based approaches are limited by high computational burden and impractical assumptions about the distribution of the data. A novel technique for constructing high quality Pis using support vector machines (SVMs) is being proposed in this paper. The proposed technique directly estimates the upper and lower bounds of the PI in a short time and without any assumptions about the data distribution. The SVM parameters are tuned using particle swarm optimization technique by minimization of a modified Pi-based objective function. Electricity price and demand data of the Ontario electricity market is used to validate the performance of the proposed technique. Several case studies for different months indicate the superior performance of the proposed method in terms of high quality PI generation and shorter computational times.

This paper aims at optimally adjusting a set of green times for traffic lights in a single intersection with the purpose of minimizing travel delay time and traffic congestion. Fuzzy logic system (FLS) is the method applied to develop the intelligent traffic timing controller. For this purpose, an intersection is considered and simulated as an intelligent agent that learns how to set green times in each cycle based on the traffic information. The FLS controller (FLC) uses genetic algorithm to tune its parameters during learning phase. Finally, The performance of the intelligent FLC is compared with the performance of a FLC with predefined parameters and three simple fixed-time controller. Simulation results indicate that intelligent FLC significantly reduces the total delay in the network compared to the fixed-time method and FLC with manual parameter setting.

This paper aims to comprehensively investigate performance of evolutionary algorithms for design optimization of shell and tube heat exchangers (STHX). Genetic algorithm (GA) and firefly algorithm (FA) are implemented for finding the optimal values for seven key design variables of the STHX model. ε-NTU method and Bell-Delaware procedure are used for thermal modelling of STHX and calculation of shell side heat transfer coefficient and pressure drop. The purpose of STHX optimization is to maximize its thermal efficiency. Obtained results for several simulation optimizations indicate that GA is unable to find permissible and optimal solutions in the majority of cases. In contrast, design variables found by FA always lead to maximum STHX efficiency. As per optimization results, maximum efficiency (83.8%) can be achieved using several design configurations. However, these designs are bearing different dollar costs. Also it is found that the behaviour of the majority of decision variables remain consistent in different runs of the FA optimization process.

Emotional neural network (ENN) is a recently developed methodology that uses simulated emotions aiding its learning process. ENN is motivated by neurophysiological knowledge of the human's emotional brain. In this paper, ENNs are developed and examined for prediction tasks. Genetic algorithm is applied for optimal tuning of crisp numerical parameters of ENN. The performance of the proposed ENN is examined using data sets for a couple of synthetic (with constant and variable noise) and real world (wind farm power generation data) case studies. A traditional artificial neural network (ANN) is also implemented for comparison purposes. Numerical results indicate the superiority of ENN over ANN in terms of accuracy and stability.

Understanding neural functions requires the observation of the activities of single neurons that are represented via electrophysiological data. Processing and understanding these data are challenging problems in biomedical engineering. A microelectrode commonly records the activity of multiple neurons. Spike sorting is a process of classifying every single action potential (spike) to a particular neuron. This paper proposes a combination between diffusion maps (DM) and mean shift clustering method for spike sorting. DM is utilized to extract spike features, which are highly capable of discriminating different spike shapes. Mean shift clustering provides an automatic unsupervised clustering, which takes extracted features from DM as inputs. Experimental results show a noticeable dominance of the features extracted by DM compared to those selected by wavelet transformation (WT). Accordingly, the proposed integrated method is significantly superior to the popular existing combination of WT and superparamagnetic clustering regarding spike sorting accuracy.

Some illustrative examples are provided to identify the ineffective and unrealistic characteristics of existing approaches to solving fuzzy linear programming (FLP) problems (with single or multiple objectives). We point out the error in existing methods concerning the ranking of fuzzy numbers and thence suggest an effective method to solve the FLP. Based on the consistent centroid-based ranking of fuzzy numbers, the FLP problems are transformed into non-fuzzy single (or multiple) objective linear programming. Solutions of FLP are then crisp single or multiple objective programming problems, which can respectively be obtained by conventional methods.

This paper aims at using interval type-2 fuzzy logic systems (IT2FLSs) for one-day ahead load forecasting task. It introduces an optimal type reduction (TR) algorithm for IT2FLSs to improve their approximation capability. Flexibility and adaptiveness are the key features of the proposed nonparametric optimal TR algorithm. Lower and upper firing strengths of rules as well as their consequent coefficients are fed into a neural network (NN). NN output is a crisp value that corresponds to the optimal defuzzified output of IT2FLSs. The NN type reducer is trained through minimization of an error-based cost function with the purpose of improving forecasting performance of IT2FLS models. Once the optimal NN-based type reducer is trained, IT2FLS models can be straightforwardly forecast the next-day load demand. Numerical testing using real load datasets indicate IT2FLS models equipped with the new optimal TR algorithm outperform IT2FLS models using traditional TR algorithms in terms of forecast accuracies. This benefit is achieved in no cost, as the computational requirement of the proposed optimal TR algorithm is the same as for traditional TR algorithms.

Electrical power systems are evolving from today's centralized bulk systems to more decentralized systems. Penetrations of renewable energies, such as wind and solar power, significantly increase the level of uncertainty in power systems. Accurate load forecasting becomes more complex, yet more important for management of power systems. Traditional methods for generating point forecasts of load demands cannot properly handle uncertainties in system operations. To quantify potential uncertainties associated with forecasts, this paper implements a neural network (NN)-based method for the construction of prediction intervals (PIs). A newly introduced method, called lower upper bound estimation (LUBE), is applied and extended to develop PIs using NN models. A new problem formulation is proposed, which translates the primary multiobjective problem into a constrained single-objective problem. Compared with the cost function, this new formulation is closer to the primary problem and has fewer parameters. Particle swarm optimization (PSO) integrated with the mutation operator is used to solve the problem. Electrical demands from Singapore and New South Wales (Australia), as well as wind power generation from Capital Wind Farm, are used to validate the PSO-based LUBE method. Comparative results show that the proposed method can construct higher quality PIs for load and wind power generation forecasts in a short time.

A variety of type reduction (TR) algorithms have been proposed for interval type-2 fuzzy logic systems (IT2 FLSs). The focus of existing literature is mainly on computational requirements of TR algorithm. Often researchers give more rewards to computationally less expensive TR algorithms. This paper evaluates and compares five frequently used TR algorithms from a forecasting performance perspective. Algorithms are judged based on the generalization power of IT2 FLS models developed using them. Four synthetic and real world case studies with different levels of uncertainty are considered to examine effects of TR algorithms on forecasts accuracies. It is found that Coupland-Jonh TR algorithm leads to models with a better forecasting performance. However, there is no clear relationship between the width of the type reduced set and TR algorithm.

This paper introduces a new type reduction (TR) algorithm for interval type-2 fuzzy logic systems (IT2 FLSs). Flexibility and adaptiveness are the key features of the proposed non-parametric algorithm. Lower and upper firing strengths of rules as well as their consequent coefficients are fed into a neural network (NN). NN output is a crisp value that corresponds to the defuzzified output of IT2 FLSs. The NN type reducer is trained through minimization of an error-based cost function with the purpose of improving modelling and forecasting performance of IT2 FLS models. Simulation results indicate that application of the proposed TR algorithm greatly enhances modelling and forecasting performance of IT2 FLS models. This benefit is achieved in no cost, as the computational requirement of the proposed algorithm is less than or at most equivalent to traditional TR algorithms.

Stock price forecast has long been received special attention of investors and financial institutions. As stock prices are changeable over time and increasingly uncertain in modern financial markets, their forecasting becomes more important than ever before. A hybrid approach consisting of two components, a neural network and a fuzzy logic system, is proposed in this paper for stock price prediction. The first component of the hybrid, i.e. a feedforward neural network (FFNN), is used to select inputs that are highly relevant to the dependent variables. An interval type-2 fuzzy logic system (IT2 FLS) is employed as the second component of the hybrid forecasting method. The IT2 FLS's parameters are initialized through deployment of the k-means clustering method and they are adjusted by the genetic algorithm. Experimental results demonstrate the efficiency of the FFNN input selection approach as it reduces the complexity and increase the accuracy of the forecasting models. In addition, IT2 FLS outperforms the widely used type-1 FLS and FFNN models in stock price forecasting. The combination of the FFNN and the IT2 FLS produces dominant forecasting accuracy compared to employing only the IT2 FLSs without the FFNN input selection.

This paper examines and analyzes different aggregation algorithms to improve accuracy of forecasts obtained using neural network (NN) ensembles. These algorithms include equal-weights combination of Best NN models, combination of trimmed forecasts, and Bayesian Model Averaging (BMA). The predictive performance of these algorithms are evaluated using Australian electricity demand data. The output of the aggregation algorithms of NN ensembles are compared with a Naive approach. Mean absolute percentage error is applied as the performance index for assessing the quality of aggregated forecasts. Through comprehensive simulations, it is found that the aggregation algorithms can significantly improve the forecasting accuracies. The BMA algorithm also demonstrates the best performance amongst aggregation algorithms investigated in this study.

Infectious disease prevention and control are important in improving, promoting and protecting the health of communities. Epidemiological data analysis plays a crucial role in disease prevention and control. Conventional methods such as moving average or autoregressive analysis normally require the assumption of stationarity, which is often violated in epidemiologic time series. This paper proposes the fusion of neural networks, fuzzy systems and genetic algorithms, with the aim to strengthen the modeling power for epidemiological dynamics. We deploy an additive fuzzy system into a neural network architecture in order to incorporate recurrent nodes to enable the fuzzy system to handle temporal data. The genetic algorithm is employed to optimize the fuzzy rule structure before supervised training is applied to adjust parameters. As epidemiological time series exhibit complex behavior and possibly cyclic patterns, the addition of recurrent nodes to the fuzzy system improves the modeling capability. The proposed model dominates the benchmark feedforward neural network and adaptive neuro-fuzzy inference system model regarding modeling performance. Through real applications for epidemiologic time series modeling, the fusion of soft computing techniques offer accurate forecasts that have considerable meaning in planning infectious disease-control activities.

Most of the research in time series is concerned with point forecasting. In this paper we focus on interval forecasting and its application for electricity load prediction. We extend the LUBE method, a neural network-based method for computing prediction intervals. The extended method, called LUBEX, includes an advanced feature selector and an ensemble of neural networks. Its performance is evaluated using Australian electricity load data for one year. The results showed that LUBEX is able to generate high quality prediction intervals, using a very small number of previous lag variables and having acceptable training time requirements. The use of ensemble is shown to be critical for the accuracy of the results.

Traffic congestion is one of the major problems in modern cities. This study applies machine learning methods to determine green times in order to minimize in an isolated intersection. Q-learning and neural networks are applied here to set signal light times and minimize total delays. It is assumed that an intersection behaves in a similar fashion to an intelligent agent learning how to set green times in each cycle based on traffic information. Here, a comparison between Q-learning and neural network is presented. In Q-learning, considering continuous green time requires a large state space, making the learning process practically impossible. In contrast to Q-learning methods, the neural network model can easily set the appropriate green time to fit the traffic demand. The performance of the proposed neural network is compared with two traditional alternatives for controlling traffic lights. Simulation results indicate that the application of the proposed method greatly reduces the total delay in the network compared to the alternative methods.

Creating a set of a number of neural network (NN) models in an ensemble and accumulating them can achieve better overview capability as compared to single neural network. Neural network ensembles are designed to provide solutions to particular problems. Many researchers and academicians have adopted this NN ensemble technique, especially in machine learning, and has been applied in various fields of engineering, medicine and information technology. This paper present a robust aggregation methodology for load demand forecasting based on Bayesian Model Averaging of a set of neural network models in an ensemble. This paper estimate a vector of coefficient for individual NN models' forecasts using validation data-set. These coefficients, also known as weights, are equal to posterior probabilities of the models generating the forecasts. These BMA weights are then used in combining forecasts generated from NN models with test data-set. By comparing the Bayesian results with the Simple Averaging method, it was observed that benefits are obtained by utilizing an advanced method like BMA for forecast combinations.

Neural network (NN) is a popular artificial intelligence technique for solving complicated problems due to their inherent capabilities. However generalization in NN can be harmed by a number of factors including parameter's initialization, inappropriate network topology and setting parameters of the training process itself. Forecast combinations of NN models have the potential for improved generalization and lower training time. A weighted averaging based on Variance-Covariance method that assigns greater weight to the forecasts producing lower error, instead of equal weights is practiced in this paper. While implementing the method, combination of forecasts is done with all candidate models in one experiment and with the best selected models in another experiment. It is observed during the empirical analysis that forecasting accuracy is improved by combining the best individual NN models. Another finding of this study is that reducing the number of NN models increases the diversity and, hence, accuracy.

Control of polymerization reactors is a challenging issue for researchers due to the complex reaction mechanisms. A lot of reactions occur simultaneously during polymerization. This leads to a polymerization system that is highly nonlinear in nature. In this work, a nonlinear advanced controller, named fuzzy logic controller (FLC), is developed for monitoring the batch free radical polymerization of polystyrene (PS) reactor. Temperature is used as an intermediate control variable to control polymer quality, because the products quality and quantity of polymer are directly depends on temperature. Different FLCs are developed through changing the number of fuzzy membership functions (MFs) for inputs and output. The final tuned FLC results are compared with the results of another advanced controller, named neural network based model predictive controller (NN-MPC). The simulation results reveal that the FLC performance is better than NN-MPC in terms of quantitative and qualitative performance criterion.

Making decision usually occurs in the state of being uncertain. These kinds of problems often expresses in a formula as optimization problems. It is desire for decision makers to find a solution for optimization problems. Typically, solving optimization problems in uncertain environment is difficult. This paper proposes a new hybrid intelligent algorithm to solve a kind of stochastic optimization i.e. dependent chance programming (DCP) model. In order to speed up the solution process, we used support vector machine regression (SVM regression) to approximate chance functions which is the probability of a sequence of uncertain event occurs based on the training data generated by the stochastic simulation. The proposed algorithm consists of three steps: (1) generate data to estimate the objective function, (2) utilize SVM regression to reveal a trend hidden in the data (3) apply genetic algorithm (GA) based on SVM regression to obtain an estimation for the chance function. Numerical example is presented to show the ability of algorithm in terms of time-consuming and precision.

In this paper, we apply a computational intelligence method for tunnelling settlement prediction. A supervised feed forward back propagation neural network is used to predict the surface settlement during twin-tunnelling while surface buildings are considered in the models. The performance of the statistical neural network structure is tested on a dataset provided by numerical parametric studies conducted by ABAQUS software based on Shiraz line 1 metro data. Six input variables are fed to neural network model for predicting the surface settlement. These include tunnel center depth, distance between centerlines of twin tunnels, buildings width and building bending stiffness, and building weight and distance to tunnel centerline. Simulation results indicate that the proposed NN models are able to accurately predict the surface settlement.

In planning an s-curve speed profile for a computer numerical control (CNC) machine, centripetal acceleration and its derivative have to be considered. In a CNC machine, these quantities dictate how much voltage and current should be applied to servo motor windings. In this paper, the necessity of considering centripetal jerk in speed profile generation especially in the look-ahead mode is explained. It is demonstrated that the magnitude of centripetal jerk is proportional to the curvature derivative of the path known as "sharpness". It is also explained that a proper limited jerk motion is only possible when a G2-continuous machining path is planned. Then using a simplified mathematical representation of clothoids, a novel method for approximating a given path with a sequence of clothoid segments is proposed. Using this method, a semi-parallel G2-continuous path with adjustable deviation from the original shape for a sample machining contour is generated. Maximum permissible feed rate for the generated path is also calculated.

This study proposes a novel non-parametric method for construction of prediction intervals (PIs) using interval type-2 Takagi-Sugeno-Kang fuzzy logic systems (IT2 TSK FLSs). The key idea in the proposed method is to treat the left and right end points of the type-reduced set as the lower and upper bounds of a PI. This allows us to construct PIs without making any special assumption about the data distribution. A new training algorithm is developed to satisfy conditions imposed by the associated confidence level on PIs. Proper adjustment of premise and consequent parameters of IT2 TSK FLSs is performed through the minimization of a PI-based objective function, rather than traditional error-based cost functions. This new cost function covers both validity and informativeness aspects of PIs. A metaheuristic method is applied for minimization of the non-linear non-differentiable cost function. Quantitative measures are applied for assessing the quality of PIs constructed using IT2 TSK FLSs. The demonstrated results for four benchmark case studies with homogenous and heterogeneous noise clearly show the proposed method is capable of generating high quality PIs useful for decision-making.

Accurate forecasting of wind farm power generation is essential for successful operation and management of wind farms and to minimize risks associated with their integration into energy systems. However, due to the inherent wind intermittency, wind power forecasts are highly prone to error and often far from being perfect. The purpose of this paper is to develop statistical methods for quantifying uncertainties associated with wind power generation forecasts. Prediction intervals (PIs) with a prescribed confidence level are constructed using the delta and bootstrap methods for neural network forecasts. The moving block bootstrap method is applied to preserve the correlation structure in wind power observations. The effectiveness and efficiency of these two methods for uncertainty quantification is examined using two month datasets taken from a wind farm in Australia. It is demonstrated that while all constructed PIs are theoretically valid, bootstrap PIs are more informative than delta PIs, and are therefore more useful for decision-making.

Prediction intervals (PIs) are excellent tools for quantification of uncertainties associated with point forecasts and predictions. This paper adopts and develops the lower upper bound estimation (LUBE) method for construction of PIs using neural network (NN) models. This method is fast and simple and does not require calculation of heavy matrices, as required by traditional methods. Besides, it makes no assumption about the data distribution. A new width-based index is proposed to quantitatively check how much PIs are informative. Using this measure and the coverage probability of PIs, a multi-objective optimization problem is formulated to train NN models in the LUBE method. The optimization problem is then transformed into a training problem through definition of a PI-based cost function. Particle swarm optimization (PSO) with the mutation operator is used to minimize the cost function. Experiments with synthetic and real-world case studies indicate that the proposed PSO-based LUBE method can construct higher quality PIs in a simpler and faster manner.

Accurate Short Term Load Forecasting (STLF) is essential for a variety of decision making processes. However, forecasting accuracy may drop due to presence of uncertainty in the operation of energy systems or unexpected behavior of exogenous variables. This paper proposes the application of Interval Type-2 Fuzzy Logic Systems (IT2 FLSs) for the problem of STLF. IT2 FLSs, with extra degrees of freedom, are an excellent tool for handling prevailing uncertainties and improving the prediction accuracy. Experiments conducted with real datasets show that IT2 FLS models appropriately approximate future load demands with an acceptable accuracy. Furthermore, they demonstrate an encouraging degree of accuracy superior to feedforward neural networks used in this study.

The bootstrap method is one of the most widely used methods in literature for construction of confidence and prediction intervals. This paper proposes a new method for improving the quality of bootstrap-based prediction intervals. The core of the proposed method is a prediction interval-based cost function, which is used for training neural networks. A simulated annealing method is applied for minimization of the cost function and neural network parameter adjustment. The developed neural networks are then used for estimation of the target variance. Through experiments and simulations it is shown that the proposed method can be used to construct better quality bootstrap-based prediction intervals. The optimized prediction intervals have narrower widths with a greater coverage probability compared to traditional bootstrap-based prediction intervals.

Evolving artificial neural networks has attracted much attention among researchers recently, especially in the fields where plenty of data exist but explanatory theories and models are lacking or based upon too many simplifying assumptions. Financial time series forecasting is one of them. A hybrid model is used to forecast the hourly electricity price from the California Power Exchange. A collaborative approach is adopted to combine ANN and evolutionary algorithm. The main contributions of this thesis include: Investigated the effect of changing values of several important parameters on the performance of the model, and selected the best combination of these parameters; good forecasting results have been obtained with the implemented hybrid model when the best combination of parameters is used. The lowest MAPE through a single run is 5.28134%. And the lowest averaged MAPE over 10 runs is 6.088%, over 30 runs is 6.786%; through the investigation of the parameter period, it is found that by including “future values” of the homogenous moments of the instant being forecasted into the input vector, forecasting accuracy is greatly enhanced. A comparison of results with other works reported in the literature shows that the proposed model gives superior performance on the same data set.

The performance of an adaptive neurofuzzy inference system (ANFIS) significantly drops when uncertainty exists in the data or system operation. Prediction intervals (PIs) can quantify the uncertainty associated with ANFIS point predictions. This paper first presents a methodology to adapt the delta technique for the construction of PIs for outcomes of the ANFIS models. As the ANFIS models are linear in their consequent part, the ANFIS-based PIs are computationally less expensive than neural network (NN)-based PIs. Second, this paper proposes a method to optimize ANFIS-based PIs. A new PI-based cost function is developed for the training of the ANFIS models. A simulated annealing-based algorithm is applied to minimize the new nonlinear cost function and adjust the premise and consequent parameters of the ANFIS model. Using three real-world case studies, it is shown that ANFIS-based PIs are computationally less expensive than NN-based PIs. The application of the proposed optimization algorithm leads to better quality PIs than optimized NN-based PIs.

The accurate prediction of travel times is desirable but frequently prone to error. This is mainly attributable to both the underlying traffic processes and the data that are used to infer travel time. A more meaningful and pragmatic approach is to view travel time prediction as a probabilistic inference and to construct prediction intervals (PIs), which cover the range of probable travel times travelers may encounter. This paper introduces the delta and Bayesian techniques for the construction of PIs. Quantitative measures are developed and applied for a comprehensive assessment of the constructed PIs. These measures simultaneously address two important aspects of PIs: 1) coverage probability and 2) length. The Bayesian and delta methods are used to construct PIs for the neural network (NN) point forecasts of bus and freeway travel time data sets. The obtained results indicate that the delta technique outperforms the Bayesian technique in terms of narrowness of PIs with satisfactory coverage probability. In contrast, PIs constructed using the Bayesian technique are more robust against the NN structure and exhibit excellent coverage probability.

Prediction intervals (PIs) have been proposed in the literature to provide more information by quantifying the level of uncertainty associated to the point forecasts. Traditional methods for construction of neural network (NN) based PIs suffer from restrictive assumptions about data distribution and massive computational loads. In this paper, we propose a new, fast, yet reliable method for the construction of PIs for NN predictions. The proposed lower upper bound estimation (LUBE) method constructs an NN with two outputs for estimating the prediction interval bounds. NN training is achieved through the minimization of a proposed PI-based objective function, which covers both interval width and coverage probability. The method does not require any information about the upper and lower bounds of PIs for training the NN. The simulated annealing method is applied for minimization of the cost function and adjustment of NN parameters. The demonstrated results for 10 benchmark regression case studies clearly show the LUBE method to be capable of generating high-quality PIs in a short time. Also, the quantitative comparison with three traditional techniques for prediction interval construction reveals that the LUBE method is simpler, faster, and more reliable.

This paper evaluates the four leading techniques proposed in the literature for construction of prediction intervals (PIs) for neural network point forecasts. The delta, Bayesian, bootstrap, and mean-variance estimation (MVE) methods are reviewed and their performance for generating high-quality PIs is compared. PI-based measures are proposed and applied for the objective and quantitative assessment of each method's performance. A selection of 12 synthetic and real-world case studies is used to examine each method's performance for PI construction. The comparison is performed on the basis of the quality of generated PIs, the repeatability of the results, the computational requirements and the PIs variability with regard to the data uncertainty. The obtained results in this paper indicate that: 1) the delta and Bayesian methods are the best in terms of quality and repeatability, and 2) the MVE and bootstrap methods are the best in terms of low computational load and the width variability of PIs. This paper also introduces the concept of combinations of PIs, and proposes a new method for generating combined PIs using the traditional PIs. Genetic algorithm is applied for adjusting the combiner parameters through minimization of a PI-based cost function subject to two sets of restrictions. It is shown that the quality of PIs produced by the combiners is dramatically better than the quality of PIs obtained from each individual method.

This study aims at developing abstract metamodels for approximating highly nonlinear relationships within a metal casting plant. Metal casting product quality nonlinearly depends on many controllable and uncontrollable factors. For improving the productivity of the system, it is vital for operation planners to predict in advance the amount of high quality products. Neural networks metamodels are developed and applied in this study for predicting the amount of saleable products. Training of metamodels is done using the Levenberg-Marquardt and Bayesian learning methods. Statistical measures are calculated for the developed metamodels over a grid of neural network structures. Demonstrated results indicate that Bayesian-based neural network metamodels outperform the Levenberg-Marquardt-based metamodels in terms of both prediction accuracy and robustness to the metamodel complexity. In contrast, the latter metamodels are computationally less expensive and generate the results more quickly.

A rich literature discussing techniques for adopting neural networks for metamodelling of complex systems exists. The main focus in many studies conducted so far has been on training and utilising neural networks as point estimators/predictors. Uncertainties prevailing within complex systems and dependencies amongst constituent entities are real threats for prediction performance of these types of metamodels. From a practical point of view, an indication of prediction accuracy is necessary before making a decision based on results yielded by a metamodel. In this paper we adopt neural network metamodels for constructing prediction intervals of stochastic system performance measures. Upper and lower bounds of a prediction interval are computed such that the real system performance will lie between them with a high probability. Demonstrated results for a real world case study show that the constructed prediction intervals cover the targets, are more informative and more suited for decision making, when compared with point predictions.

Finding optimal structures for neural networks is remains an open problem, despite the rich array of literature on the application of neural networks in different areas of science and engineering. The stochastic nature of operations common in complex systems makes point prediction performance of neural network metamodels an additional challenge. We propose a method for selecting the best structure of a neural network metamodel. For selecting the network structure, the new method uses interval prediction capability of neural networks and chooses a topology that yields the narrowest prediction band for targets. This is an improvement on traditional criteria, such as mean square error or mean absolute percentage error. As a case study, the interval prediction method is applied to a metamodel of a complex system composed of many inextricably interconnected entities and stochastic processes. The demonstrated results expressly show that selecting the network structure based on the proposed method yields more reliable estimates.

Not considered in the analytical model of the plant, uncertainties always dramatically decrease the performance of the fault detection task in the practice. To cope better with this prevalent problem, in this paper we develop a methodology using Modal Interval Analysis which takes into account those uncertainties in the plant model. A fault detection method is developed based on this model which is quite robust to uncertainty and results in no false alarm. As soon as a fault is detected, an ANFIS model is trained in online to capture the major behavior of the occurred fault which can be used for fault accommodation. The simulation results understandably demonstrate the capability of the proposed method for accomplishing both tasks appropriately.

Many researchers have investigated short term load forecasting (STLF) in recent decades because of its importance in power system operation. In this paper a multi layers perceptron (MLP) neural network (NN) is designed for load forecasting in normal weather condition and ordinary days. The architecture of the proposed network is a three-layer feedforward neural network whose parameters are tuned by Levenberg-Marquardt backpropagation (LMBP) augmented by an early stopping (ES) method tried out for increasing the speed of convergence. For abrupt weather changes and special holidays, we have added a fuzzy inference systems (FIS) to modify the forecasted load appropriately. We show that this method satisfy the Iran electricity market rule. Simulation examples for Iran National Power System (INPS) and any of its regions, Bakhtar Region Electric Co. (BREC) demonstrate capabilities of proposed method for load forecasting.

In this paper, a new approach for sensor and actuator fault detection and estimation in unknown nonlinear systems is proposed. Model-free structure and no a priori knowledge about the faults are two main properties of the proposed method that make it a viable candidate for real-time applications. First, a neuro-fuzzy technique is used to obtain a nominal models of the system based on input-output data in normal system operation. Actuator and sensor faults are then estimated such that the error between the output of the model and the actual output is minimized. The gradient descent method is used to update the fault estimated values. The estimated values are subsequently used for fault accommodation. Simulation results for a two link planar robot manipulator are presented to demonstrate the effectiveness of the proposed approach.