Deep gaze estimation works well in controlled capture but degrades in unconstrained settings, where systems must reject unreliable predictions. Single-pass uncertainty (e.g., heteroscedastic regression) infers uncertainty from pixels without explicit input-validity cues, while sampling based methods are often too costly for real time use. We propose Factor-Informed Uncertainty Distillation (FIUD), a teacher-student framework that aligns uncertainty with interpretable image-quality failure modes. A gradient-boosting teacher predicts expected gaze error from factors such as illumination, sharpness, eye visibility and symmetry; a neural student distills these signals via curriculum learning and ranking supervision into a lightweight single-pass uncertainty head. Across ETH-XGaze, Gaze360, and MPIIFaceGaze (>300k samples), FIUD improves uncertainty, error rank correlation and selective prediction versus deterministic and sampling-based baselines, with the largest gains in unconstrained settings.

Blockchain technology has become a trusted method for establishing secure and transparent transactions through a distributed, encrypted network. The operation of blockchain is governed by consensus algorithms, among which Proof of Stake (PoS) is popular yet has its drawbacks, notably the potential for centralising power in nodes with larger stakes or higher rewards. Our proposed novel solution, Fuzzychain, leverages fuzzy sets to define stake semantics, introducing a degree of softness in validator selection. This approach mitigates rigid threshold-based decision-making by allowing gradual transitions between stake levels, reducing sharp disparities among validators. By incorporating this enhanced stake evaluation, Fuzzychain promotes a more adaptive and distributed selection process, ensuring a fairer and more inclusive blockchain network. A thorough assessment of a real-time multi-agent blockchain system to examine validator selection and reduce inequality, promoting a more equitable distribution of stakes among validators compared to other consensus mechanisms. This fosters a more inclusive selection process and a more equitably distributed network.

In data stream (DS) learning, the system has to extract knowledge from data generated continuously, usually at high speed and in large volumes, making it impossible to store the entire set of data to be processed in batch mode. Hence, machine learning models must be built incrementally by processing the incoming examples, as data arrive, while updating the model to be compatible with the current data. In fuzzy DS clustering, the model can either absorb incoming data into existing clusters or initiate a new cluster. As the volume of data increases, there is a possibility that the clusters will overlap to the point where it is convenient to merge two or more clusters into one. Then, a cluster comparison measure (CM) should be applied, to decide whether such clusters should be combined, also in an incremental manner. This defines an incremental fusion process based on aggregation functions that can aggregate the incoming inputs without storing all the previous inputs. The objective of this article is to solve the fuzzy DS clustering problem of incrementally comparing fuzzy clusters on a formal basis. First, we formalize and operationalize incremental fusion processes of fuzzy clusters by introducing recursively extendable (RE) aggregation functions, studying construction methods and different classes of such functions. Second, we propose two approaches to compare clusters: 1) similarity and 2) overlapping between clusters, based on RE aggregation functions. Finally, we analyze the effect of those incremental CMs on the online and offline phases of the well-known fuzzy clustering algorithm d-FuzzStream, showing that our new approach outperforms the original algorithm and presents better or comparable performance to other state-of-the-art DS clustering algorithms found in the literature.

The Steady-State Visual Evoked Potential (SSVEP) is a robust method for creating a fast Brain-Computer Interface (BCI); however, the time window of Electroencephalography (EEG) trials has to be reduced to improve the BCI's speed. This reduction leads to a decrease in the Signal-to-noise ratio (SNR), making it more difficult to classify these signals accurately. Conversely, combining Fuzzy Neural Block (FNB) that includes Type-l Fuzzy (T1F) in deep learning architecture has improved classification accuracy over data obtained in noisy environments. However, T1F has limitations in accurately modeling uncertainty and handling complex systems compared to Interval Type-2 Fuzzy (IT2F), which is particularly suitable for applications where robustness, adaptability, and accuracy are crucial. In this work, we proposed a deep learning framework that integrates the FNB using IT2F called FNB- IT2F. It is included parallel to the linear and final layers to assess their effectiveness. Thus, this study presents a unification of EEG- TCNet-LSTM with FNB-IT2F, which we call EEG- TCNet-LSTM-FNB-IT2F (i.e. EEG- TCF2Net). Our results reported a maximum recog-nition accuracy of 51.0% to 76.5% using the proposed method of EEG- TCF2N et in a subject-independent classification across all 10 subjects for 0.2 to 0.5 s time window. Overall, including FNB- IT2F in this deep learning architecture outperformed those without it, as well as baseline methods such as Filter-Bank Canonical Correlation Analysis (FBCCA) [1] and Task-related component analysis (TRCA) [2].

In today's world, it is vital to have strong cybersecurity measures in place. To combat the ever-evolving threats, adopting advanced models like cybersecurity mesh is necessary to enhance our protection. Cybersecurity mesh is an architecture scalable, flexible, composable, robust and resilient and allows the interoperability and coordination between intelligent systems to provide security services. Designing a cybersecurity mesh faces three major challenges: scalability, distributed or federated systems, and technology integration. For the design, it is necessary to apply security tools that support scalability because millions and millions of data are stored, processed, and analysed. Federated systems are needed to improve interoperability in a decentralized cybersecurity mesh. However, it can be tough to integrate different security tools and communication protocols. Cryptographic algorithms and AI models like federated learning, swarming intelligence and blockchain technologies are useful for security services. It is essential to study the integration of existing methods to determine the best technology for the job. We conduct a comprehensive analysis of intelligent systems, including federated learning, blockchain technology, and swarming intelligence, with a particular focus on how they have been and can be used to enhance cybersecurity. We examine the latest trends in these technologies, explore their connections, and weigh the pros and cons of each approach. To conduct this review, we utilized the Web of Science and Scopus databases and followed the PRISMA guidelines.

The Wang-Mendel Approach (WMA) focuses on combining the numerical as well as linguistic information for achieving greater explainability for inference models. The standard WMA models the linguistic information using type-1 (T1) fuzzy sets (FSs), which have a reduced capability to model the semantics of linguistic information. Therefore, we propose a novel Enhanced WMA, which models the linguistic information using the type-2 (T2) FSs. Further, our Enhanced T2 FS based WMA can be modified to reflect the use of interval type-2 (IT2) FSs, for modeling linguistic uncertainty. IT2 FSs are suitable when better uncertainty handling capabilities are required compared to T1 FSs, however, at a computational cost lesser than the T2 FSs. Performance of Enhanced WMA is demonstrated through a real-world crop-yield prediction problem in smart agriculture and an additional exemplar application on users' satisfaction ratings. Further, we have compared our approach with the performance obtained from the T1 FS based WMA and the original estimations given in the original data. We found that our Enhanced WMA achieves better precision than the other two with 95% confidence level. To the best of our knowledge, no one has proposed the use of T2 FSs for modeling linguistic uncertainty in the WMA before.

In this paper we propose a new version of penalty-based aggregation functions, the Multi Cost Aggregation choosing functions (MCAs), in which the function to minimize is constructed using a convex combination of two relaxed versions of restricted equivalence and dissimilarity functions instead of a penalty function. We additionally suggest two different alternatives to train a MCA in a supervised classification task in order to adapt the aggregation to each vector of inputs. We apply the proposed MCA in a Motor Imagery-based Brain Computer Interface (MI-BCI) system to improve its decision making phase. We also evaluate the classical aggregation with our new aggregation procedure in two publicly available datasets. We obtain an accuracy of 82.31% for a left vs. right hand in the Clinical BCI challenge (CBCIC) dataset, and a performance of 62.43% for the four-class case in the BCI Competition IV 2a dataset compared to a 82.15% and 60.56% using the arithmetic mean. Finally, we have also tested the goodness of our proposal against other MI-BCI systems, obtaining better results than those using other decision making schemes and Deep Learning on the same datasets.

Microblogging site Twitter (re-branded to X since July 2023) is one of the most influential online social media websites, which offers a platform for the masses to communicate, expresses their opinions, and shares information on a wide range of subjects and products, resulting in the creation of a large amount of unstructured data. This has attracted significant attention from researchers who seek to understand and analyze the sentiments contained within this massive user-generated text. The task of sentiment analysis (SA) entails extracting and identifying user opinions from the text, and various lexicon-and machine learning-based methods have been developed over the years to accomplish this. However, deep learning (DL)-based approaches have recently become dominant due to their superior performance. This study briefs on standard preprocessing techniques and various word embeddings for data preparation. It then delves into a taxonomy to provide a comprehensive summary of DL-based approaches. In addition, the work compiles popular benchmark datasets and highlights evaluation metrics employed for performance measures and the resources available in the public domain to aid SA tasks. Furthermore, the survey discusses domain-specific practical applications of SA tasks. Finally, the study concludes with various research challenges and outlines future outlooks for further investigation.

Automatic art analysis employs different image processing techniques to classify and categorize works of art. When working with artistic images, we need to take into account further considerations compared to classical image processing. This is because artistic paintings change drastically depending on the author, the scene depicted, and their artistic style. This can result in features that perform very well in a given task but do not grasp the whole of the visual and symbolic information contained in a painting. In this article, we show how the features obtained from different tasks in artistic image classification are suitable to solve other ones of similar nature. We present different methods to improve the generalization capabilities and performance of artistic classification systems. Furthermore, we propose an explainable artificial intelligence method to map known visual traits of an image with the features used by the deep learning model considering fuzzy rules. These rules show the patterns and variables that are relevant to solve each task and how effective is each of the patterns found. Our results show that compared to multitask learning, our proposed context-aware features can achieve up to 19% more accurate results when using the residual network architecture and 3% when using ConvNeXt. We also show that some of the features used by these models can be more clearly correlated to visual traits in the original image than other kinds of features.

As data resources grow, providing recommendations that best meet the demands has become a vital requirement in business and life to overcome the information overload problem. However, building a system suggesting relevant recommendations has always been a point of debate. One of the most cost-efficient techniques in terms of producing relevant recommendations at a low complexity is product quantization (PQ). PQ approaches have continued developing in recent years. This system's crucial challenge is improving PQ performance in terms of recall measures without compromising its complexity. This makes the algorithm suitable for problems that require a greater number of potentially relevant items without disregarding others, at high speed and low cost to keep up with traffic. This is the case of online shops where the recommendations for the purpose are important, although customers can be susceptible to scoping other products. A recent approach has been exploiting the notion of norm subvectors encoded in product quantizers. This research proposes a fuzzy approach to perform norm-based PQ. Type-2 fuzzy sets (T2FSs) define the codebook allowing subvectors (T2FSs) to be associated with more than one element of the codebook, and next, its norm calculus is resolved by means of integration. Our method finesses the recall measure up, making the algorithm suitable for problems that require querying at most possible potential relevant items without disregarding others. The proposed approach is tested with three public recommender benchmark datasets and compared against seven PQ approaches for maximum inner-product search. The proposed method outperforms all PQ approaches, such as norm-explicit PQ, PQ, and residual quantization up to +6%, +5%, and +8% by achieving a recall of 94%, 69%, and 59% in Netflix, Audio, and Cifar60k datasets, respectively. Moreover, computing time and complexity nearly equal those of the most computationally efficient existing PQ method in the state of the art.

Abstract Mental task classification (MTC), based on the electroencephalography (EEG) signals is a demanding brain–computer interface (BCI). It is independent of all types of muscular activity. MTC-based BCI systems are capable to identify cognitive activity of human. The success of BCI system depends upon the efficient feature representation from raw EEG signals for classification of mental activities. This paper mainly presents on a novel feature representation (formation of most informative features) of the EEG signal for the both, binary as well as multi MTC, using a combination of some statistical, uncertainty and memory- based coefficient. In this work, the feature formation is carried out in the two stages. In the first stage, the signal is split into different oscillatory functions with the help of three well-known empirical mode decomposition (EMD) algorithms, and a new set of eight parameters (features) are calculated from the oscillatory function in the second stage of feature vector construction. Support vector machine (SVM) is used to classify the feature vectors obtained corresponding to the different mental tasks. This study consists the problem formulation of two variants of MTC; two-class and multi-class MTC. The suggested scheme outperforms the existing work for the both types of mental tasks classification.

Wearable technology is having a profound impact in healthcare applications. In this context, one of the main goals of current wearable systems is to provide new devices capable of delivering a greater amount of more precise information. Amongst the different applications, physiological continuous monitoring is becoming one of the most wanted features. In fact, most of the commercially and research grade wearable systems include cardiac activity acquisition, which is generally performed by means of photoplethysmography sensors (PPG). These optical-based sensors present different challenges related to the prevailing of a good signal quality. Thus, in case of dealing with digital processing algorithms which are responsible for extracting different features from such signal, this fact can lead to erroneous results. On this basis, this paper presents an ongoing work towards the design of an interval type-II fuzzy-based system for the PPG signal quality assessment. Moreover, this initial proposed system is implemented into a constrained 32-bit ARM Cortex-M4 system-on-chip. Specifically, the system uses a reduced set of features together with a low complexity fuzzy rule base Mamdani inference model, and is based on a non-overlapping 3-second signal processing window. Results show that the system achieved overall accuracy of 94.84%. The proposed system has great potential for integrating accurate and reliable continuous health monitoring systems into constrained edge devices.

Human beings have an inherent capability to use linguistic information (LI) seamlessly even though it is vague and imprecise. Computing with Words (CWW) was proposed to impart computing systems with this capability of human beings. The interest in the field of CWW is evident from a number of publications on various CWW methodologies. These methodologies use different ways to model the semantics of the LI. However, to the best of our knowledge, the literature on these methodologies is mostly scattered and does not give an interested researcher a comprehensive but gentle guide about the notion and utility of these methodologies. Hence, to introduce the foundations and state-of-the-art CWW methodologies, we provide a concise but a wide-ranging coverage of them in a simple and easy to understand manner. We feel that the simplicity with which we give a high-quality review and introduction to the CWW methodologies is very useful for investigators or especially those embarking on the use of CWW for the first time. We also provide future research directions to build upon for the interested and motivated researchers.

In an attempt to reduce the infection rate of the COrona VIrus Disease-19 (Covid-19) countries around the world have echoed the exigency for an economical, accessible, point-of-need diagnostic test to identify Covid-19 carriers so that they (individuals who test positive) can be advised to self isolate rather than the entire community. Availability of a quick turn-around time diagnostic test would essentially mean that life, in general, can return to normality-at-large. In this regards, studies concurrent in time with ours have investigated different respiratory sounds, including cough, to recognise potential Covid-19 carriers. However, these studies lack clinical control and rely on Internet users confirming their test results in a web questionnaire (crowdsourcing) thus rendering their analysis inadequate. We seek to evaluate the detection performance of a primary screening tool of Covid-19 solely based on the cough sound from8,380clinically validated samples with laboratory molecular-test(2,339Covid-19 positive and6,041Covid-19 negative) under quantitative RT-PCR (qRT-PCR) from certified laboratories. All collected samples were clinically labelled, i.e., Covid-19 positive or negative, according to the results in addition to the disease severity based on the qRT-PCR threshold cycle (Ct) and lymphocytes count from the patients. Our proposed generic method is an algorithm based on Empirical Mode Decomposition (EMD) for cough sound detection with subsequent classification based on a tensor of audio sonographs and deep artificial neural network classifier with convolutional layers called‘DeepCough’. Two different versions of DeepCough based on the number of tensor dimensions, i.e., DeepCough2D and DeepCough3D, have been investigated. These methods have been deployed in a multi-platform prototype web-app‘CoughDetect’. Covid-19 recognition results rates achieved a promising AUC (Area Under Curve) of$98.80\% \pm 0.83\%$, sensitivity of$96.43\% \pm 1.85\%$, and specificity of$96.20\% \pm 1.74\%$and average AUC of$81.08\% \pm 5.05\%$for the recognition of three severity levels. Our proposed web tool as a point-of-need primary diagnostic test for Covid-19 facilitates the rapid detection of the infection. We believe it has the potential to significantly hamper the Covid-19 pandemic across the world.

Neurons usually converse through electrochemical signals and pooled neuronal firings feasibly be recorded on the scalp through the medium of electroencephalogram (EEG). EEG waveforms are recorded, analysed and categorized across directives concerning a Brain-Computer Interface (BCI). Deteriorated signal to noise ratio and non-stationarities stand as a paramount obstacle in steady decoding of EEG. Appearance of non-stationarities across EEG patterns notably upset the feature waveforms thus worsening the functioning of detection block and as a whole the Brain Computer Interface. Stationary Subspace schemes bring to light subspaces within which data distribution persists stably over time. Current work focuses on the development of a novel spatial transform based feature extraction scheme to address nonstationarity in EEG signals recorded against a drowsiness detection problem (a machine learning regression scenario). The presented approach: F-DIV-IT-JAD-WS derived features distinctly surpassed DivOVR-FuzzyCSP-WS based standard features across RMSE and CC performance criteria pair. We construe that the propounded feature derivation approach based on F-DIV-IT-JAD-WS will usher a significant attention in researchers who are developing algorithms for signal processing, specifically, for BCI regression scenarios.

Internet of things is projected to make its way into all spheres of human life in the near future. This has been compounded with the growing demand for contactless solutions in the wake of the recent pandemic. A potential solution could involve a privacy-preserving gesture-based control system that could control a wide range of appliances. Implementing such gesture-based control systems is mainly conducted using opaque box Artificial Intelligence (AI) models. Systems based on such opaque box AI models have shown high-performance metrics on in-distribution data in a lab environment. However, they are prone to failure when exposed to real-world out-of-distribution data where they cannot be tuned or calibrated due to their complexity and opaqueness. Interval Type-2 Fuzzy Logic-based explainable AI models offer an alternative to opaque box models showing comparable performance on lab in-distribution data. In contrast, in the real world, out-of-distribution data, the type-2 fuzzy models could be easily calibrated and tuned (thanks for their explainability) to provide similar performance to those achieved on the lab in-distribution data.

Computing with Words (CWW) methodology has been used to design intelligent systems which make decisions by manipulating the linguistic information, like human beings. Human beings naturally understand (and express) themselves linguistically, and hence can reason (and make decision) just with linguistic information without any numerical measure. Perceptual Computing makes use of type 2 fuzzy sets for modeling the words in the CWW paradigm. This use of type-2 fuzzy sets enables better representation of the inherent uncertainty in the fuzzy linguistic semantics on numerous problems. To realise the potential of Perceptual Computing, its MATLAB implementation has been made freely available to the end-users/ researchers, and MATLAB is a proprietary development environment. Therefore, this contribution aims at proposing a python implementation of the Perceptual Computing, or its main processing element the perceptual computer that consists of three components viz., encoder, CWW engine and decoder. Our python implementation provides the end user with a seamless blending amongst all three components, which does not exist yet, to the best of our knowledge.

In this paper, classification of mental task-root brain-computer interfaces (BCIs) is being investigated. The mental tasks are dominant area of investigations in BCI, which utmost interest as these system can be augmented life of people having severe disabilities. The performance of BCI model primarily depends on the construction of features from brain, electroencephalography (EEG), signal, and the size of feature vector, which are obtained through multiple channels. The availability of training samples to features are minimal for mental task classification. The feature selection is used to increase the ratio for the mental task classification by getting rid of irrelevant and superfluous features. This paper suggests an approach to augment the performance of a learning algorithm for the mental task classification on the utility of power spectral density (PSD) using feature selection. This paper also deals a comparative analysis of multivariate and univariate feature selection for mental task classification. After applying the above stated method, the findings demonstrate substantial improvements in the performance of learning model for mental task classification. Moreover, the efficacy of the proposed approach is endorsed by carrying out a robust ranking algorithm and Friedman's statistical test for finding the best combinations and compare various combinations of PSD and feature selection methods.

Research in developmental cognitive neuroscience face challenges associated not only with their population (infants and children who might not be too willing to cooperate) but also in relation to the limited choice of neuroimaging techniques that can non-invasively record brain activity. For example, magnetic resonance imaging (MRI) studies are unsuitable for developmental cognitive studies because they require participants to stay still for a long time in a noisy environment. In this regard, functional Near-infrared spectroscopy (fNIRS) is a fast-emerging de-facto neuroimaging standard for recording brain activity of young infants. However, the absence of associated anatomical image, and a standard technical framework for fNIRS data analysis remains a significant impediment to advancement in gaining insights into the workings of developing brains. To this end, this work presents an Explainable Artificial Intelligence (XAI) system for infant's fNIRS data using a multivariate pattern analysis (MVPA) driven by a genetic algorithm (GA) type-2 Fuzzy Logic System (FLS) for classification of infant's brain activity evoked by different stimuli. This work contributes towards laying the foundation for a transparent fNIRS data analysis that holds the potential to enable researchers to map the classification result to the corresponding brain activity pattern which is of paramount significance in understanding how developing human brain functions.

Smart homes are a growing market in need of privacy preserving sensors paired with explainable, interpretable and reliable control systems. The recent boom in Artificial Intelligence (AI) has seen an ever-growing persistence to incorporate it in all spheres of human life including the household. This growth in AI has been met with reciprocal concern for the privacy impacts and reluctance to introduce sensors, such as cameras, into homes. This concern has led to research of sensors not traditionally found in households, mainly short range radar. There has been also increasing awareness of AI transparency and explainability. Traditional AI black box models are not trusted, despite boasting high accuracy scores, due to the inability to understand what the decisions were based on. Interval Type-2 Fuzzy Logic offers a powerful alternative, achieving close to black box levels of performance while remaining completely interpretable. This paper presents a privacy preserving short range radar sensor coupled with an Explainable AI system employing a Big Bang Big Crunch (BB-BC) Interval Type-2 Fuzzy Logic System (FLS) to classify gestures performed in an indoor environment.

Recently, the rapid development of automotive industries has given rise to large multidimensional datasets both in the production sites and after-sale services. Fault diagnostic systems are one of the services that the automotive industries provide. As a consequence of the rapid development of cars features, traditional rule-based diagnostic systems became very limited. Therefore, more sophisticated AI approaches need to be investigated towards more efficient solutions. In this paper, we focus on utilising deep learning so as to build a diagnostic system that is able to estimate the required services in an efficient and effective way. We propose a new model, called Deep Symptoms-Based Model Deep-SBM, as an approach to predict a wide range of faults by relying on the deep learning technique. The new proposed model is validated through a set of experiments in order to demonstrate how the underlying model runs and its impact on improving the overall performance metrics. We have applied the Deep-SBM on a real historical diagnostic data provided by Cognitran Ltd. The performance of the Deep-SBM was compared against the state-of-the-art approaches and better result has been reported in terms of accuracy, precision, recall, and F-Score. Based on the obtained results, some further directions are suggested in this context. The final goal is having fault prediction data collected online relying on IoT.

A Brain-Computer Interface (BCI) allows its user to control machines or other devices by translating its brain activity and using it as commands. This kind of technology has as potential users people with motor disabilities since it would allow them to interact with their environment without using their peripheral nerves, helping them to regain their lost autonomy. One of the most successful BCI applications is the P300-based Speller. Its operation depends entirely on its capacity to identify and discriminate the presence of the P300 potentials from electroencephalographic (EEG) signals. For the system to do this correctly, it is necessary to choose an adequate classifier and train it with a balanced data-set. However, due to the use of an oddball paradigm to elicit the P300 potential, only unbalanced data-sets can be obtained. This paper focuses on the training stage of two classifiers, a deep feedforward network (DFN) and a deep belief network (DBN), to be used in a P300-based BCI. The data-sets obtained from healthy subjects and post-stroke victims were pre-processed and then balanced using a Self-Organizing Maps-based under-sampling approach prior training looking to increase the accuracy of the classifiers. We compared the results with our previous works and observed an increase of 7% in classification accuracy for the most critical subject. The DFN achieved a maximum classification accuracy of 93.29% for a post-stroke subject and 93.60% for a healthy one.

Advanced Brain-Computer Interface (BCI) paradigms aim to solve some problems as BCI illiteracy and unfamiliarity of the subjects to be able to control their elicited motor imagery (MI) successfully, hence improving training time and performance of BCI systems. This work evaluates the effect and performance of an Implicit BCI supported by the Gaze Monitoring (IBCI-GM) paradigm for virtual rehabilitation therapy of patients suffering from partial or total paralysis of their upper limbs; this paradigm also was compared with alternative forms of advanced BCI methods such as Virtual Reality-based BCI (VR-BCI) with a head-mounted display (HMD) and a computer screen (CS). Eight subjects participated in the experiments; four subjects tested the VR-BCI with a CS, and the rest of them tested both BCI advanced methods (IBCI-GM and VR-BCI with an HMD). The subjects were asked to control a virtual arm through MI of flexion and extension movements. The VR-BCI HMD was the approached best method; however, IBCI-GM had significant results and was more practical for users, but it depends on the ability to perform eye movements to be applied by patients. Therefore, these methods should be tested with more subjects to have definitive results.

A fuzzy genetic algorithm to optimize spatial filter selection can improve the performance of P300-based brain computer interfaces (BCI); genetic algorithm searches an optimal configuration supported by a fuzzy inference system, it would reduce the error calculated during a 4 fold crossvalidation. The performance is measured through the accuracy and the bit rate, 4 methods based on fuzzy logic and Bayesian linear discriminant analysis are considered for the performance comparison. This proposed method has obtained significant results for healthy persons and post stroke patients, accuracies above 90% and bit rates greater than 8 bits/min for the most of cases evaluated in a P300-based BCI using the Hoffman approach.

In this work, we present the use of Kernel Extreme Learning Machine (Kernel ELM) on electroencephalography EEG brain signals in order to classify the P300 wave during the subject development an oddball paradigm. Also, we propose a selection criteria in order to improve the classification accuracy. In this study, the brain signals of healthy and disabled subjects which suffered a stroke were recorded, analyzed and classified. The results reported that the best classification accuracy and average bitrate were 100% using target by block evaluation and 18.38 bits per minute, respectively . These results are compared to various machine learning algorithms so that our results outperformed them.

This paper presents a self-adaptive autonomous online learning through a general type-2 fuzzy system (GT2 FS) for the motor imagery (MI) decoding of a brain-machine interface (BMI) and navigation of a bipedal humanoid robot in a real experiment, using electroencephalography (EEG) brain recordings only. GT2 FSs are applied to BMI for the first time in this study. We also account for several constraints commonly associated with BMI in real practice: 1) the maximum number of EEG channels is limited and fixed; 2) no possibility of performing repeated user training sessions; and 3) desirable use of unsupervised and low-complexity feature extraction methods. The novel online learning method presented in this paper consists of a self-adaptive GT2 FS that can autonomously self-adapt both its parameters and structure via creation, fusion, and scaling of the fuzzy system rules in an online BMI experiment with a real robot. The structure identification is based on an online GT2 Gath-Geva algorithm where every MI decoding class can be represented by multiple fuzzy rules (models), which are learnt in a continous (trial-by-trial) non-iterative basis. The effectiveness of the proposed method is demonstrated in a detailed BMI experiment, in which 15 untrained users were able to accurately interface with a humanoid robot, in a single session, using signals from six EEG electrodes only.

This work presents a brain computer interface (BCI) framework for upper limb rehabilitation of post stroke patients, combining BCI and virtual reality (VR) technology; a VR feedback is shown to the participants to achieve a greater activation of certain brain regions involved with the performing of upper limb motor task. This system uses an adaptive neuro-fuzzy inference system (ANFIS) classifier to discriminate between a motor task and rest condition, the first one classifies between extension and rest conditions; and the second one classifies between flexion and rest conditions. In the training stage, eight healthy subjects participated in the sessions, the best accuracies are 99.3% and 88.9%, as a result of cross-validation. Meanwhile, the best accuracy in online test is 89%. The methodology here presented can be straightforwardly employed as a rehabilitation system for brain repair in individuals with neurological diseases or brain injury.

Adaptive neuro fuzzy Inference systems (ANFIS) has been applied in brain computer interfaces (BcI) in different ways such as mapping of P300 or fusing information from EEG channels and it has reached high classification accuracy. This work proposes a combination of ANFIS classifiers by voting for a single-trial detection of a P300 wave in a BCI, using four channels; five healthy subjects and three post-stroke patients have participated in this study, each participant performs 4 BCI sessions, crossvalidation is applied to evaluate the classifier performance. The results of average accuracy were greater than 75% for all subjects, similar results were gotten for healthy subjects and post-stroke patients, but the better classifiers for each subject have achieved accuracies greater than 80%.

In this paper, a novel technique for the computation of effective brain connectivity in functional Near-Infrared Spectroscopy (fNIRS) data is presented. The estimation of effective brain connectivity using the proposed approach of higher order Fuzzy Cognitive Maps (FCMs), used in conjunction with Genetic Algorithm (GA), is shown to be more accurate. Owing to lack of dependency on human knowledge, the FCM-GA model becomes more robust to subjective beliefs of experts from various domains when establishing connectivity matrix. Furthermore, higher order FCMs are capable of assessing causal relations in historical data with variable time lag, g, therefore generating more accurate predictions for complex causal data such as fNIRS where the causality may not necessarily follow a first order dynamics. The computation model of higher order FCM-GA is shown to perform better than Granger Causality (GC) for estimating effective brain connectivity in synthetic fNIRS data at 95% significance level. The proposed approach is also tested on real fNIRS data, and shown to estimate the causal structure amongst region of interests (ROIs) with improved accuracy.

With a massive influx of multimodality data, the role of data analytics in health informatics has grown rapidly in the last decade. This has also prompted increasing interests in the generation of analytical, data driven models based on machine learning in health informatics. Deep learning, a technique with its foundation in artificial neural networks, is emerging in recent years as a powerful tool for machine learning, promising to reshape the future of artificial intelligence. Rapid improvements in computational power, fast data storage, and parallelization have also contributed to the rapid uptake of the technology in addition to its predictive power and ability to generate automatically optimized high-level features and semantic interpretation from the input data. This article presents a comprehensive up-to-date review of research employing deep learning in health informatics, providing a critical analysis of the relative merit, and potential pitfalls of the technique as well as its future outlook. The paper mainly focuses on key applications of deep learning in the fields of translational bioinformatics, medical imaging, pervasive sensing, medical informatics, and public health.

This paper provides an overview of recent developments in big data in the context of biomedical and health informatics. It outlines the key characteristics of big data and how medical and health informatics, translational bioinformatics, sensor informatics, and imaging informatics will benefit from an integrated approach of piecing together different aspects of personalized information from a diverse range of data sources, both structured and unstructured, covering genomics, proteomics, metabolomics, as well as imaging, clinical diagnosis, and long-term continuous physiological sensing of an individual. It is expected that recent advances in big data will expand our knowledge for testing new hypotheses about disease management from diagnosis to prevention to personalized treatment. The rise of big data, however, also raises challenges in terms of privacy, security, data ownership, data stewardship, and governance. This paper discusses some of the existing activities and future opportunities related to big data for health, outlining some of the key underlying issues that need to be tackled.

In this paper an original approach is proposed which makes possible autonomous scenes recognition performed on-line by an evolving self-learning classifier. Existing approaches for scene recognition are off-line and used in intelligent albums for picture categorization/selection. The emergence of powerful mobile platforms with camera on board and sensor-based autonomous (robotic) systems is pushing forward the requirement for efficient self-learning and adaptive/evolving algorithms. Fast real-time and online algorithms for categorisation of the real world environment based on live video stream are essential for understanding and situation awareness as well as for localization and context awareness. In scene analysis the critical problem is feature extraction mechanism for a quick description of the scene. In this paper we apply a well known technique called spatial envelop or GIST. Visual scenes can be quite different but very often they can be grouped in similar types/categories. For example, pictures from different cities across the Globe, e.g. Tokyo, Vancouver, New York Moscow, Dusseldorf, etc. bear the similar pattern of an urban scene high rise buildings, despite the differences in the architectural style. Same applies for the beaches of Miami, Maldives, Varna, Costa del Sol, etc. One assumption based on which such automatic video classifiers can be build is to pre-train them using a large number of such images from different groups. Variety of possible scenes suggests the limitations of such an approach. Therefore, we use in this paper the recently propose evolving fuzzy rule-based classifier, simpleClass, which is self learning and thus updates its rules and categories descriptions with each new image. In addition, it is fully recursive, computationally efficient and yet linguistically transparent.

A new approach to real-time human activity recognition (HAR) using evolving self-learning fuzzy rule-based classifier (eClass) will be described in this paper. A recursive version of the principle component analysis (PCA) and linear discriminant analysis (LDA) pre-processing methods is coupled with the eClass leading to a new approach for HAR which does not require computation and time consuming pre-training and data from many subjects. The proposed new method for evolving HAR (eHAR) takes into account the specifics of each user and possible evolution in time of her/his habits. Data streams from several wearable devices which make possible to develop a pervasive intelligence enabling them to personalize/tune to the specific user were used for the experimental part of the paper.

This paper presents the sequel of evolving fuzzy rule-based classifier eClass, called here as simplified evolving classifier, simpl_eClass. Similarly to eClass, simpl_eClass comprises of two different classifiers, namely zero and first order (simpl_eClass0 and simpl_eClass1). The two classifiers differ from each other in terms of the consequent part of the fuzzy rules, and the classification strategy used. The design of simpl_eClass is based on the density increment principle introduced recently in so called simpl_eTS+ approach. The rule learning in simpl_eClass does not involve computation of potential values that allows it to attain computationally much less expensive model update phase compared to eClass. As compared to other FRB classifiers, it retains all the advantages of eClass, such as being on-line and evolving, having zero and first order. In comparison with other non-fuzzy classifiers it has the advantage of interpretability and transparency (especially zero order type). The goals of this paper are to demonstrate the applicability of simpl_eTS+ to classification task, and to empirically show that the simplification of eClass to simpl_eClass by using potential-free approach does not compromise the accuracy of the classifiers. In order to attain the goals, the classifiers are tested by performing several experiments using benchmark data sets. The simpl_eClass1 classifier is also applied to the real-life problem of on-line scene categorization for low-resource devices benefiting from its low computational cost. The results obtained from the experiments endorse that simpl_eClass achieves the accuracy of eClass while simplifying rule learning process.

A new approach to real-time knowledge extraction from streaming data generated by wearable wireless accelerometers based on self-learning evolving fuzzy rule-based classifier is proposed and evaluated in this paper. Based on experiments with real subjects we collected data from 18 different classifieds activities. After preprocessing and classifying data depending on the sequence of activities regarding time, we achieved up to 99.81% of accuracy in recognizing a sequence of activities. This technique allows re-training the system as long as the application is running on the wearable intelligent/smart sensor, getting a better classification rate throughout the time without an increase of the delay in performance.

In this paper we present results and algorithm used to predict 14 days horizon from a number of time series provided by the NN GC1 concerning transportation datasets [1]. Our approach is based on applying the well known Evolving Takagi-Sugeno (eTS) Fuzzy Systems [2-6] to self-learn from the time series. ETS are characterized by the fact that they self-learn and evolve the fuzzy rule-based system which, in fact, represents their structure from the data stream on-line and in real-time mode. That means we used all the data samples from the time series only once, at any instant in time we only used one single input vector (which consist of few data samples as described below) and we do not iterate or memorize the whole sequence. It should be emphasized that this is a huge practical advantage which, unfortunately cannot be compared directly to the other competitors in NN GC1 if only precision/error is taken as a criteria. It is also worth to require time for calculations and memory usage as well as iterations and computational complexity to be provided and compared to build a fuller picture of the advantages the proposed technique offers. Nevertheless, we offer a computationally light and easy to use approach which in addition does not require any user-or problem-specific thresholds or parameters to be specified. Additionally, this approach is flexible in terms not only of its structure (fuzzy rule based and automatic self-development), but also in terms of automatic input selection as will be described below.