Detection of evoked resonant neural activity in Parkinson's disease

Objective. This study investigated a machine-learning approach to detect the presence of evoked resonant neural activity (ERNA) recorded during deep brain stimulation (DBS) of the subthalamic nucleus (STN) in people with Parkinson's disease.Approach. Seven binary classifiers were trained to distinguish ERNA from the background neural activity using eight different time-domain signal features.Main results. Nested cross-validation revealed a strong classification performance of 99.1% accuracy, with 99.6% specificity and 98.7% sensitivity to detect ERNA. Using a semi-simulated ERNA dataset, the results show that a signal-to-noise ratio of 15 dB is required to maintain a 90% classifier sensitivity. ERNA detection is feasible with an appropriate combination of signal processing, feature extraction and classifier. Future work should consider reducing the computational complexity for use in real-time applications.Significance. The presence of ERNA can be used to indicate the location of a DBS electrode array during implantation surgery. The confidence score of the detector could be useful for assisting clinicians to adjust the position of the DBS electrode array inside/outside the STN.

Ecological inferences about marine mammals from passive acoustic data

Monitoring on the basis of sound recordings, or passive acoustic monitoring, can complement or serve as an alternative to real-time visual or aural monitoring of marine mammals and other animals by human observers. Passive acoustic data can support the estimation of common, individual-level ecological metrics, such as presence, detection-weighted occupancy, abundance and density, population viability and structure, and behaviour. Passive acoustic data also can support estimation of some community-level metrics, such as species richness and composition. The feasibility of estimation and certainty of estimates is highly context dependent, and understanding the factors that affect the reliability of measurements is useful for those considering whether to use passive acoustic data. Here, we review basic concepts and methods of passive acoustic sampling in marine systems that often are applicable to marine mammal research and conservation. Our ultimate aim is to facilitate collaboration among ecologists, bioacousticians, and data analysts. Ecological applications of passive acoustics require one to make decisions about sampling design, which in turn requires consideration of sound propagation, sampling of signals, and data storage. One also must make decisions about signal detection and classification and evaluation of the performance of algorithms for these tasks. Investment in the research and development of systems that automate detection and classification, including machine learning, are increasing. Passive acoustic monitoring is more reliable for detection of species presence than for estimation of other species-level metrics. Use of passive acoustic monitoring to distinguish among individual animals remains difficult. However, information about detection probability, vocalisation or cue rate, and relations between vocalisations and the number and behaviour of animals increases the feasibility of estimating abundance or density. Most sensor deployments are fixed in space or are sporadic, making temporal turnover in species composition more tractable to estimate than spatial turnover. Collaborations between acousticians and ecologists are most likely to be successful and rewarding when all partners critically examine and share a fundamental understanding of the target variables, sampling process, and analytical methods.

CS-based multi-task learning network for arrhythmia reconstruction and classification using ECG signals

Objective. Although deep learning-based current methods have achieved impressive results in electrocardiograph (ECG) arrhythmia classification issues, they rely on using the original data to identify arrhythmia categories. However, a large amount of data generated by long-term ECG monitoring pose a significant challenge to the limited-bandwidth and real-time systems, which limits the application of deep learning in ECG monitoring.Approach. This paper, therefore, proposed a novel multi-task network that combined compressed sensing and convolutional neural networks, namely CSML-Net. According to the proposed model, the ECG signals were compressed by utilizing a learning measurement matrix and then recovered and classified simultaneously via shared layers and two task branches. Among them, the multi-scale feature module was designed to improve model performance.Main results. Experimental results on the MIT-BIH arrhythmia dataset demonstrate that our proposed method is superior to all the approaches that have been compared in terms of reconstruction quality and classification performance.Significance. Consequently, the proposed model achieving the reconstruction and classification in the compressed domain can be an improvement and become a promising approach for ECG arrhythmia reconstruction and classification.

Deep-Learning-Based Classification of Digitally Modulated Signals Using Capsule Networks and Cyclic Cumulants

This paper presents a novel deep-learning (DL)-based approach for classifying digitally modulated signals, which involves the use of capsule networks (CAPs) together with the cyclic cumulant (CC) features of the signals. These were blindly estimated using cyclostationary signal processing (CSP) and were then input into the CAP for training and classification. The classification performance and the generalization abilities of the proposed approach were tested using two distinct datasets that contained the same types of digitally modulated signals, but had distinct generation parameters. The results showed that the classification of digitally modulated signals using CAPs and CCs proposed in the paper outperformed alternative approaches for classifying digitally modulated signals that included conventional classifiers that employed CSP-based techniques, as well as alternative DL-based classifiers that used convolutional neural networks (CNNs) or residual networks (RESNETs) with the in-phase/quadrature (I/Q) data used for training and classification.

A Deep Learning Framework for the Detection of Abnormality in Cerebral Blood Flow Velocity Using Transcranial Doppler Ultrasound

Transcranial doppler (TCD) ultrasound is a non-invasive imaging technique that can be used for continuous monitoring of blood flow in the brain through the major cerebral arteries by calculating the cerebral blood flow velocity (CBFV). Since the brain requires a consistent supply of blood to function properly and meet its metabolic demand, a change in CBVF can be an indication of neurological diseases. Depending on the severity of the disease, the symptoms may appear immediately or may appear weeks later. For the early detection of neurological diseases, a classification model is proposed in this study, with the ability to distinguish healthy subjects from critically ill subjects. The TCD ultrasound database used in this study contains signals from the middle cerebral artery (MCA) of 6 healthy subjects and 12 subjects with known neurocritical diseases. The classification model works based on the maximal blood flow velocity waveforms extracted from the TCD ultrasound. Since the signal quality of the recorded TCD ultrasound is highly dependent on the operator's skillset, a noisy and corrupted signal can exist and can add biases to the classifier. Therefore, a deep learning classifier, trained on a curated and clean biomedical signal can reliably detect neurological diseases. For signal classification, this study proposes a Self-organized Operational Neural Network (Self-ONN)-based deep learning model Self-ResAttentioNet18, which achieves classification accuracy of 96.05% with precision, recall, f1 score, and specificity of 96.06%, 96.05%, 96.06%, and 96.09%, respectively. With an area under the ROC curve of 0.99, the model proves its feasibility to confidently classify middle cerebral artery (MCA) waveforms in near real-time.

Detection and classification of atrial and ventricular cardiovascular diseases to improve the cardiac health literacy for resource constrained regions

ECG is a non-invasive way of determining cardiac health by measuring the electrical activity of the heart. A novel detection technique for feature points P, QRS and T is investigated to diagnose various atrial and ventricular cardiovascular anomalies with ECG signals for ambulatory monitoring. Before the system is worthy of field trials, it is validated with several databases and recorded their response. The QRS complex detection is based on the Pan Tompkins algorithm and difference operation method that provides positive predictivity, sensitivity and false detection rate of 99.29%, 99.49% and 1.29%, respectively. Proposed novel T wave detection provides sensitivity of 97.78%. Also, proposed P wave detection provides positive predictivity, sensitivity and false detection rate of 99.43%, 99.4% and 1.15% for the control study (normal subjects) and 82.68%, 94.3% and 25.4% for the case (patients with cardiac anomalies) study, respectively. Disease detection such as arrhythmia is based on standard R-R intervals while myocardial infarction is based on the ST-T deviations where the positive predictivity, sensitivity and accuracy are observed to be 94.6%, 84.2% and 85%, respectively. It should be noted that, since the frontal leads are only used, the anterior myocardial infarction cases are detected with the injury pattern in lead avl and ST depression in reciprocal leads. Detection of atrial fibrillation is done for both short and long duration signals using statistical methods using interquartile range and standard deviations, giving very high accuracy, 100% in most cases. The system hardware for obtaining the 2 lead ECG signal is designed using commercially available off the shelf components. Small field validation of the designed system is performed at a Public Health Centre in Gujarat, India with 42 patients (both cases and controls). 78.5% accuracy was achieved during the field validation. It is thus concluded that the proposed method is ideal for improvisation in cardiac health monitoring outreach in resource constrained regions.

Detection of Power Line Insulators in Digital Images Based on the Transformed Colour Intensity Profiles

Proper maintenance of the electricity infrastructure requires periodic condition inspections of power line insulators, which can be subjected to various damages such as burns or fractures. The article includes an introduction to the problem of insulator detection and a description of various currently used methods. Afterwards, the authors proposed a new method for the detection of the power line insulators in digital images by applying selected signal analysis and machine learning algorithms. The insulators detected in the images can be further assessed in depth. The data set used in the study consists of images acquired by an Unmanned Aerial Vehicle (UAV) during its overflight along a high-voltage line located on the outskirts of the city of Opole, Opolskie Voivodeship, Poland. In the digital images, the insulators were placed against different backgrounds, for example, sky, clouds, tree branches, elements of power infrastructure (wires, trusses), farmland, bushes, etc. The proposed method is based on colour intensity profile classification on digital images. Firstly, the set of points located on digital images of power line insulators is determined. Subsequently, those points are connected using lines that depict colour intensity profiles. These profiles were transformed using the Periodogram method or Welch method and then classified with Decision Tree, Random Forest or XGBoost algorithms. In the article, the authors described the computational experiments, the obtained results and possible directions for further research. In the best case, the proposed solution achieved satisfactory efficiency (F1 score = 0.99). Promising classification results indicate the possibility of the practical application of the presented method.

Physical Layer Authentication in Wireless Networks-Based Machine Learning Approaches

The physical layer security of wireless networks is becoming increasingly important because of the rapid development of wireless communications and the increasing security threats. In addition, because of the open nature of the wireless channel, authentication is a critical issue in wireless communications. Physical layer authentication (PLA) is based on distinctive features to provide information-theory security and low complexity. However, although many researchers are interested in the PLA and how it might be used to improve wireless security, there is surprisingly little literature on the subject, with no systematic overview of the current state-of-the-art PLA and the main foundations involved. Therefore, this paper aims to determine and systematically compare existing studies in the physical layer authentication. This study showed whether machine learning approaches in physical layer authentication models increased wireless network security performance and demonstrated the latest techniques used in PLA. Moreover, it identified issues and suggested directions for future research. This study is valuable for researchers and security model developers interested in using machine learning (ML) and deep learning (DL) approaches for PLA in wireless communication systems in future research and designs.

On the prediction of premature births in Hispanic labour patients using uterine contractions, heart beat signals and prediction machines

Preterm birth is a global epidemic affecting millions of mothers across different ethnicities. The cause of the condition remains unknown but has recognised health-based implications, in addition to financial and economic ones. Machine Learning methods have enabled researchers to combine datasets using uterine contraction signals with various forms of prediction machines to improve awareness of the likelihood of premature births. This work investigates the feasibility of enhancing these prediction methods using physiological signals including uterine contractions, and foetal and maternal heart rate signals, for a population of south American women in active labour. As part of this work, the use of the Linear Series Decomposition Learner (LSDL) was seen to lead to an improvement in the prediction accuracies of all models, which included supervised and unsupervised learning models. The results from the supervised learning models showed high prediction metrics upon the physiological signals being pre-processed by the LSDL for all variations of the physiological signals. The unsupervised learning models showed good metrics for the partitioning of Preterm/Term labour patients from their uterine contraction signals but produced a comparatively lower set of results for the various kinds of heart rate signals investigated.

An Efficient Approach for Driver Drowsiness Detection at Moderate Drowsiness Level Based on Electroencephalography Signal and Vehicle Dynamics Data

Background

Drowsy driving is one of the leading causes of severe accidents worldwide. In this study, an analyzing method based on drowsiness level proposed to detect drowsiness through electroencephalography (EEG) measurements and vehicle dynamics data.

Methods

A driving simulator was used to collect brain data in the alert and drowsy states. The tests were conducted on 19 healthy men. Brain signals from the parietal, occipital, and central parts were recorded. Observer Ratings of Drowsiness (ORD) were used for the drowsiness stages assessment. This study used an innovative method, analyzing drowsiness EEG data were in respect to ORD instead of time. Thirteen features of EEG signal were extracted, then through Neighborhood Component Analysis, a feature selection method, 5 features including mean, standard deviation, kurtosis, energy, and entropy are selected. Six classification methods including K-nearest neighbors (KNN), Regression Tree, Classification Tree, Naive Bayes, Support vector machines Regression, and Ensemble Regression are employed. Besides, the lateral position and steering angle as a vehicle dynamic data were used to detect drowsiness, and the results were compared with classification result based on EEG data.

Results

According to the results of classifying EEG data, classification tree and ensemble regression classifiers detected over 87.55% and 87.48% of drowsiness at the moderate level, respectively. Furthermore, the classification results demonstrate that if only the single-channel P4 is used, higher performance can achieve than using data of all the channels (C3, C4, P3, P4, O1, O2). Classification tree classifier and regression classifiers showed 91.31% and 91.12% performance with data from single-channel P4. The best classification results based on vehicle dynamic data were 75.11 through KNN classifier.

Conclusion

According to this study, driver drowsiness could be detected at the moderate drowsiness level based on features extracted from a single-channel P4 data.

Target-Related Alpha Attenuation in a Brain-Computer Interface Rapid Serial Visual Presentation Calibration

This study evaluated the feasibility of using occipitoparietal alpha activity to drive target/non-target classification in a brain-computer interface (BCI) for communication. EEG data were collected from 12 participants who completed BCI Rapid Serial Visual Presentation (RSVP) calibrations at two different presentation rates: 1 and 4 Hz. Attention-related changes in posterior alpha activity were compared to two event-related potentials (ERPs): N200 and P300. Machine learning approaches evaluated target/non-target classification accuracy using alpha activity. Results indicated significant alpha attenuation following target letters at both 1 and 4 Hz presentation rates, though this effect was significantly reduced in the 4 Hz condition. Target-related alpha attenuation was not correlated with coincident N200 or P300 target effects. Classification using posterior alpha activity was above chance and benefitted from individualized tuning procedures. These findings suggest that target-related posterior alpha attenuation is detectable in a BCI RSVP calibration and that this signal could be leveraged in machine learning algorithms used for RSVP or comparable attention-based BCI paradigms.

Brain tumor classification of virtual NMR voxels based on realistic blood vessel-induced spin dephasing using support vector machines

Remodeling of tissue microvasculature commonly promotes neoplastic growth; however, there is no imaging modality in oncology yet that noninvasively quantifies microvascular changes in clinical routine. Although blood capillaries cannot be resolved in typical magnetic resonance imaging (MRI) measurements, their geometry and distribution influence the integral nuclear magnetic resonance (NMR) signal from each macroscopic MRI voxel. We have numerically simulated the expected transverse relaxation in NMR voxels with different dimensions based on the realistic microvasculature in healthy and tumor-bearing mouse brains (U87 and GL261 glioblastoma). The 3D capillary structure in entire, undissected brains was acquired using light sheet fluorescence microscopy to produce large datasets of the highly resolved cerebrovasculature. Using this data, we trained support vector machines to classify virtual NMR voxels with different dimensions based on the simulated spin dephasing accountable to field inhomogeneities caused by the underlying vasculature. In prediction tests with previously blinded virtual voxels from healthy brain tissue and GL261 tumors, stable classification accuracies above 95% were reached. Our results indicate that high classification accuracies can be stably attained with achievable training set sizes and that larger MRI voxels facilitated increasingly successful classifications, even with small training datasets. We were able to prove that, theoretically, the transverse relaxation process can be harnessed to learn endogenous contrasts for single voxel tissue type classifications on tailored MRI acquisitions. If translatable to experimental MRI, this may augment diagnostic imaging in oncology with automated voxel-by-voxel signal interpretation to detect vascular pathologies.

Identification of Characteristic Points in Multivariate Physiological Signals by Sensor Fusion and Multi-Task Deep Networks

Identification of characteristic points in physiological signals, such as the peak of the R wave in the electrocardiogram and the peak of the systolic wave of the photopletismogram, is a fundamental step for the quantification of clinical parameters, such as the pulse transit time. In this work, we presented a novel neural architecture, called eMTUnet, to automate point identification in multivariate signals acquired with a chest-worn device. The eMTUnet consists of a single deep network capable of performing three tasks simultaneously: (i) localization in time of characteristic points (labeling task), (ii) evaluation of the quality of signals (classification task); (iii) estimation of the reliability of classification (reliability task). Preliminary results in overnight monitoring showcased the ability to detect characteristic points in the four signals with a recall index of about 1.00, 0.90, 0.90, and 0.80, respectively. The accuracy of the signal quality classification was about 0.90, on average over four different classes. The average confidence of the correctly classified signals, against the misclassifications, was 0.93 vs. 0.52, proving the worthiness of the confidence index, which may better qualify the point identification. From the achieved outcomes, we point out that high-quality segmentation and classification are both ensured, which brings the use of a multi-modal framework, composed of wearable sensors and artificial intelligence, incrementally closer to clinical translation.

Radiometric Identification of Signals by Matched Whitening Transform

Radiometric identification is the problem of attributing a signal to a specific source. In this work, a radiometric identification algorithm is developed using the whitening transformation. The approach stands out from the more established methods in that it works directly on the raw IQ data and hence is featureless. As such, the commonly used dimensionality reduction algorithms do not apply. The premise of the idea is that a data set is “most white” when projected on its own whitening matrix than on any other. In practice, transformed data are never strictly white since the training and the test data differ. The Förstner-Moonen measure that quantifies the similarity of covariance matrices is used to establish the degree of whiteness. The whitening transform that produces a data set with the minimum Förstner-Moonen distance to a white noise process is the source signal. The source is determined by the output of the mode function operated on the Majority Vote Classifier decisions. Using the Förstner-Moonen measure presents a different perspective compared to maximum likelihood and Euclidean distance metrics. The whitening transform is also contrasted with the more recent deep learning approaches that are still dependent on feature vectors with large dimensions and lengthy training phases. It is shown that the proposed method is simpler to implement, requires no features vectors, needs minimal training and because of its non-iterative structure is faster than existing approaches.

A Non-Invasive Millimetre-Wave Radar Sensor for Automated Behavioural Tracking in Precision Farming-Application to Sheep Husbandry

The automated quantification of the behaviour of freely moving animals is increasingly needed in applied ethology. State-of-the-art approaches often require tags to identify animals, high computational power for data collection and processing, and are sensitive to environmental conditions, which limits their large-scale utilization, for instance in genetic selection programs of animal breeding. Here we introduce a new automated tracking system based on millimetre-wave radars for real time robust and high precision monitoring of untagged animals. In contrast to conventional video tracking systems, radar tracking requires low processing power, is independent on light variations and has more accurate estimations of animal positions due to a lower misdetection rate. To validate our approach, we monitored the movements of 58 sheep in a standard indoor behavioural test used for assessing social motivation. We derived new estimators from the radar data that can be used to improve the behavioural phenotyping of the sheep. We then showed how radars can be used for movement tracking at larger spatial scales, in the field, by adjusting operating frequency and radiated electromagnetic power. Millimetre-wave radars thus hold considerable promises precision farming through high-throughput recording of the behaviour of untagged animals in different types of environments.

Underwater Target Signal Classification Using the Hybrid Routing Neural Network

In signal analysis and processing, underwater target recognition (UTR) is one of the most important technologies. Simply and quickly identify target types using conventional methods in underwater acoustic conditions is quite a challenging task. The problem can be conveniently handled by a deep learning network (DLN), which yields better classification results than conventional methods. In this paper, a novel deep learning method with a hybrid routing network is considered, which can abstract the features of time-domain signals. The used network comprises multiple routing structures and several options for the auxiliary branch, which promotes impressive effects as a result of exchanging the learned features of different branches. The experiment shows that the used network possesses more advantages in the underwater signal classification task.

Detecting and classifying neurotransmitter signals from ultra-high sensitivity PET data: the future of molecular brain imaging

Efforts to build the next generation of brain PET scanners are underway. It is expected that a new scanner (NS) will offer anorder-of-magnitude improvementin sensitivity to counts compared to the current state-of-the-art, Siemens HRRT. Our goal was to explore the use of the anticipated increased sensitivity in combination with the linear-parametric neurotransmitter PET (lp-ntPET) model to improve detection and classification of transient dopamine (DA) signals. We simulated striatal [¹¹C]raclopride PET data to be acquired on a future NS which will offer ten times the sensitivity of the HRRT. The simulated PET curves included the effects of DA signals that varied in start-times, peak-times, and amplitudes. We assessed the detection sensitivity of lp-ntPET to various shapes of DA signal. We evaluated classification thresholds for their ability to separate 'early'- versus 'late'-peaking, and 'low'- versus 'high'-amplitude events in a 4D phantom. To further refine the characterization of DA signals, we developed a weighted k-nearest neighbors (wkNN) algorithm to incorporate information from the neighborhood around each voxel to reclassify it, with a level of certainty. Our findings indicate that the NS would expand the range of detectable neurotransmitter events to 72%, compared to the HRRT (31%). Application of wkNN augmented the detection sensitivity to DA signals in simulated NS data to 92%. This work demonstrates that the ultra-high sensitivity expected from a new generation of brain PET scanner, combined with a novel classification algorithm, will make it possible to accurately detect and classify short-lived DA signals in the brain based on their amplitude and timing.

Ultra-Wideband Radar-Based Indoor Activity Monitoring for Elderly Care

In this paper, we propose an unobtrusive method and architecture for monitoring a person’s presence and collecting his/her health-related parameters simultaneously in a home environment. The system is based on using a single ultra-wideband (UWB) impulse-radar as a sensing device. Using UWB radars, we aim to recognize a person and some preselected movements without camera-type monitoring. Via the experimental work, we have also demonstrated that, by using a UWB signal, it is possible to detect small chest movements remotely to recognize coughing, for example. In addition, based on statistical data analysis, a person’s posture in a room can be recognized in a steady situation. In addition, we implemented a machine learning technique (k-nearest neighbour) to automatically classify a static posture using UWB radar data. Skewness, kurtosis and received power are used in posture classification during the postprocessing. The classification accuracy achieved is more than 99%. In this paper, we also present reliability and fault tolerance analyses for three kinds of UWB radar network architectures to point out the weakest item in the installation. This information is highly important in the system’s implementation.

NLOS Multipath Classification of GNSS Signal Correlation Output Using Machine Learning

This paper proposes a method for detecting non-line-of-sight (NLOS) multipath, which causes large positioning errors in a global navigation satellite system (GNSS). We use GNSS signal correlation output, which is the most primitive GNSS signal processing output, to detect NLOS multipath based on machine learning. The shape of the multi-correlator outputs is distorted due to the NLOS multipath. The features of the shape of the multi-correlator are used to discriminate the NLOS multipath. We implement two supervised learning methods, a support vector machine (SVM) and a neural network (NN), and compare their performance. In addition, we also propose an automated method of collecting training data for LOS and NLOS signals of machine learning. The evaluation of the proposed NLOS detection method in an urban environment confirmed that NN was better than SVM, and 97.7% of NLOS signals were correctly discriminated.

Towards Embedded Computation with Building Materials

We present results showing the capability of concrete-based information processing substrate in the signal classification task in accordance with in materio computing paradigm. As the Reservoir Computing is a suitable model for describing embedded in materio computation, we propose that this type of presented basic construction unit can be used as a source for “reservoir of states” necessary for simple tuning of the readout layer. We present an electrical characterization of the set of samples with different additive concentrations followed by a dynamical analysis of selected specimens showing fingerprints of memfractive properties. As part of dynamic analysis, several fractal dimensions and entropy parameters for the output signal were analyzed to explore the richness of the reservoir configuration space. In addition, to investigate the chaotic nature and self-affinity of the signal, Lyapunov exponents and Detrended Fluctuation Analysis exponents were calculated. Moreover, on the basis of obtained parameters, classification of the signal waveform shapes can be performed in scenarios explicitly tuned for a given device terminal.

Real-Time Leak Detection for a Gas Pipeline Using a k-NN Classifier and Hybrid AE Features

This paper introduces a technique using a k-nearest neighbor (k-NN) classifier and hybrid features extracted from acoustic emission (AE) signals for detecting leakages in a gas pipeline. The whole algorithm is embedded in a microcontroller unit (MCU) to detect leaks in real-time. The embedded system receives signals continuously from a sensor mounted on the surface of a gas pipeline to diagnose any leak. To construct the system, AE signals are first recorded from a gas pipeline testbed under various conditions and used to synthesize the leak detection algorithm via offline signal analysis. The current work explores different features of normal/leaking states from corresponding datasets and eliminates redundant and outlier features to improve the performance and guarantee the real-time characteristic of the leak detection program. To obtain the robustness of leak detection, the paper normalizes features and adapts the trained k-NN classifier to the specific environment where the system is installed. Aside from using a classifier for categorizing normal/leaking states of a pipeline, the system monitors accumulative leaking event occurrence rate (ALEOR) in conjunction with a defined threshold to conclude the state of the pipeline. The entire proposed system is implemented on the 32F746G-DISCOVERY board, and to verify this system, numerous real AE signals stored in a hard drive are transferred to the board. The experimental results show that the proposed system executes the leak detection algorithm in a period shorter than the total input data time, thus guaranteeing the real-time characteristic. Furthermore, the system always yields high average classification accuracy (ACA) despite adding a white noise to input signal, and false alarms do not occur with a reasonable ALEOR threshold.

Classification of forearm EMG signals for 10 motions using optimum feature-channel combinations

Electromyography (EMG) is the study of electrical activity in the muscles. We classify EMG signals from surface electrodes (channels) using Artificial Neural Network (ANN). We evaluate classification performance of 10 different hand motions using several feature-channel combinations with wrapper method. Highest classification accuracy of 98.7% is achieved with each feature-channel combination. Compared to previous studies, we achieve the highest accuracy for 10 classes with lower number of feature-channel combination. We reduce ANN complexity without compromising the classification accuracy for deployment in low-end hardware with limited computational power along with improving the design of a low-cost hardware for EMG signal acquisition.

Explainable artificial intelligence for heart rate variability in ECG signal

Electrocardiogram (ECG) signal is one of the most reliable methods to analyse the cardiovascular system. In the literature, there are different deep learning architectures proposed to detect various types of tachycardia diseases, such as atrial fibrillation, ventricular fibrillation, and sinus tachycardia. Even though all types of tachycardia diseases have fast beat rhythm as the common characteristic feature, existing deep learning architectures are trained with the corresponding disease-specific features. Most of the proposed works lack the interpretation and understanding of the results obtained. Hence, the objective of this letter is to explore the features learned by the deep learning models. For the detection of the different types of tachycardia diseases, the authors used a transfer learning approach. In this method, the model is trained with one of the tachycardia diseases called atrial fibrillation and tested with other tachycardia diseases, such as ventricular fibrillation and sinus tachycardia. The analysis was done using different deep learning models, such as RNN, LSTM, GRU, CNN, and RSCNN. RNN achieved an accuracy of 96.47% for atrial fibrillation data set, 90.88% accuracy for CU-ventricular tachycardia data set, and also achieved an accuracy of 94.71, and 94.18% for MIT-BIH malignant ventricular ectopy database for ECG lead I and lead II, respectively. The RNN model could only achieve an accuracy of 23.73% for the sinus tachycardia data set. A similar trend is shown by other models. From the analysis, it was evident that even though tachycardia diseases have fast beat rhythm as their common feature, the model was not able to detect different types of tachycardia diseases. The deep learning model could only detect atrial fibrillation and ventricular fibrillation and failed in the case of sinus tachycardia. From the analysis, they were able to interpret that, along with the fast beat rhythm, the model has learned the absence of P-wave which is a common feature for ventricular fibrillation and atrial fibrillation but sinus tachycardia disease has an upright positive P-wave. The time-based analysis is conducted to find the time complexity of the models. The analysis conveyed that RNN and RSCNN models could achieve better performance with lesser time complexity.

Using the Information Provided by Forbidden Ordinal Patterns in Permutation Entropy to Reinforce Time Series Discrimination Capabilities

Despite its widely tested and proven usefulness, there is still room for improvement in the basic permutation entropy (PE) algorithm, as several subsequent studies have demonstrated in recent years. Some of these new methods try to address the well-known PE weaknesses, such as its focus only on ordinal and not on amplitude information, and the possible detrimental impact of equal values found in subsequences. Other new methods address less specific weaknesses, such as the PE results' dependence on input parameter values, a common problem found in many entropy calculation methods. The lack of discriminating power among classes in some cases is also a generic problem when entropy measures are used for data series classification. This last problem is the one specifically addressed in the present study. Toward that purpose, the classification performance of the standard PE method was first assessed by conducting several time series classification tests over a varied and diverse set of data. Then, this performance was reassessed using a new Shannon Entropy normalisation scheme proposed in this paper: divide the relative frequencies in PE by the number of different ordinal patterns actually found in the time series, instead of by the theoretically expected number. According to the classification accuracy obtained, this last approach exhibited a higher class discriminating power. It was capable of finding significant differences in six out of seven experimental datasets-whereas the standard PE method only did in four-and it also had better classification accuracy. It can be concluded that using the additional information provided by the number of forbidden/found patterns, it is possible to achieve a higher discriminating power than using the classical PE normalisation method. The resulting algorithm is also very similar to that of PE and very easy to implement.

On the Performance of Variational Mode Decomposition-Based Radio Frequency Fingerprinting of Bluetooth Devices

Radio frequency fingerprinting (RFF) is one of the communication network's security techniques based on the identification of the unique features of RF transient signals. However, extracting these features could be burdensome, due to the nonstationary nature of transient signals. This may then adversely affect the accuracy of the identification of devices. Recently, it has been shown that the use of variational mode decomposition (VMD) in extracting features from Bluetooth (BT) transient signals offers an efficient way to improve the classification accuracy. To do this, VMD has been used to decompose transient signals into a series of band-limited modes, and higher order statistical (HOS) features are extracted from reconstructed transient signals. In this study, the performance bounds of VMD in RFF implementation are scrutinized. Firstly, HOS features are extracted from the band-limited modes, and then from the reconstructed transient signals directly. Performance comparison due to both HOS feature sets is presented. Moreover, the lower SNR bound within which the VMD can achieve acceptable accuracy in the classification of BT devices is determined. The approach has been tested experimentally with BT devices by employing a Linear Support Vector Machine (LSVM) classifier. According to the classification results, a higher classification performance is achieved (~4% higher) at lower SNR levels (-5-5 dB) when HOS features are extracted from band-limited modes in the implementation of VMD in RFF of BT devices.

Detection and classification of ECG noises using decomposition on mixed codebook for quality analysis

In this Letter, a robust technique is presented to detect and classify different electrocardiogram (ECG) noises including baseline wander (BW), muscle artefact (MA), power line interference (PLI) and additive white Gaussian noise (AWGN) based on signal decomposition on mixed codebooks. These codebooks employ temporal and spectral-bound waveforms which provide sparse representation of ECG signals and can extract ECG local waves as well as ECG noises including BW, PLI, MA and AWGN simultaneously. Further, different statistical approaches and temporal features are applied on decomposed signals for detecting the presence of the above mentioned noises. The accuracy and robustness of the proposed technique are evaluated using a large set of noise-free and noisy ECG signals taken from the Massachusetts Institute of Technology-Boston's Beth Israel Hospital (MIT-BIH) arrhythmia database, MIT-BIH polysmnographic database and Fantasia database. It is shown from the results that the proposed technique achieves an average detection accuracy of above 99% in detecting all kinds of ECG noises. Furthermore, average results show that the technique can achieve an average sensitivity of 98.55%, positive productivity of 98.6% and classification accuracy of 97.19% for ECG signals taken from all three databases.

Conditional Adversarial Domain Adaptation Neural Network for Motor Imagery EEG Decoding

Decoding motor imagery (MI) electroencephalogram (EEG) signals for brain-computer interfaces (BCIs) is a challenging task because of the severe non-stationarity of perceptual decision processes. Recently, deep learning techniques have had great success in EEG decoding because of their prominent ability to learn features from raw EEG signals automatically. However, the challenge that the deep learning method faces is that the shortage of labeled EEG signals and EEGs sampled from other subjects cannot be used directly to train a convolutional neural network (ConvNet) for a target subject. To solve this problem, in this paper, we present a novel conditional domain adaptation neural network (CDAN) framework for MI EEG signal decoding. Specifically, in the CDAN, a densely connected ConvNet is firstly applied to obtain high-level discriminative features from raw EEG time series. Then, a novel conditional domain discriminator is introduced to work as an adversarial with the label classifier to learn commonly shared intra-subjects EEG features. As a result, the CDAN model trained with sufficient EEG signals from other subjects can be used to classify the signals from the target subject efficiently. Competitive experimental results on a public EEG dataset (High Gamma Dataset) against the state-of-the-art methods demonstrate the efficacy of the proposed framework in recognizing MI EEG signals, indicating its effectiveness in automatic perceptual decision decoding.

Selection of optimum frequency bands for detection of epileptiform patterns

The significant research effort in the domain of epilepsy has been directed toward the development of an automated seizure detection system. In their usage of the electrophysiological recordings, most of the proposals thus far have followed the conventional practise of employing all frequency bands following signal decomposition as input features for a classifier. Although seemingly powerful, this approach may prove counterproductive since some frequency bins may not carry relevant information about seizure episodes and may, instead, add noise to the classification process thus degrading performance. A key thesis of the work described here is that the selection of frequency subsets may enhance seizure classification rates. Additionally, the authors explore whether a conservative selection of frequency bins can reduce the amount of training data needed for achieving good classification performance. They have found compelling evidence that using spectral components with <25 Hz frequency in scalp electroencephalograms can yield state-of-the-art classification accuracy while reducing training data requirements to just a tenth of those employed by current approaches.

Diagnosis of attention deficit hyperactivity disorder using non-linear analysis of the EEG signal

Attention deficit hyperactivity disorder (ADHD) is a common behavioural disorder that may be found in 5%-8% of the children. Early diagnosis of ADHD is crucial for treating the disease and reducing its harmful effects on education, employment, relationships, and life quality. On the other hand, non-linear analysis methods are widely applied in processing the electroencephalogram (EEG) signals. It has been proved that the brain neuronal activity and its related EEG signals have chaotic behaviour. Hence, chaotic indices can be employed to classify the EEG signals. In this study, a new approach is proposed based on the combination of some non-linear features to distinguish ADHD from normal children. Lyapunov exponent, fractal dimension, correlation dimension and sample, fuzzy and approximate entropies are the non-linear extracted features. For computing, the chaotic time series of obtained EEG in the brain frontal lobe (FP1, FP2, F3, F4, and Fz) need to be analysed. Experiments on a set of EEG signal obtained from 50 ADHD and 26 normal cases yielded a sensitivity, specificity, and accuracy of 98, 92.31, and 96.05%, respectively. The obtained accuracy provides a significant improvement in comparison to the other similar studies in identifying and classifying children with ADHD.

Detection of focal electroencephalogram signals using higher-order moments in EMD-TKEO domain

Detection of epileptogenic focus based on electroencephalogram (EEG) signal screening is an important pre-surgical step to remove affected regions inside the human brain. Considering the fact above, in this work, a novel technique for detection of focal EEG signals is proposed using a combination of empirical mode decomposition (EMD) and Teager–Kaiser energy operator (TKEO). EEG signals belonging to focal (Fo) and non-focal (NFo) groups were at first decomposed into a set of intrinsic mode functions (IMFs) using EMD. Next, TKEO was applied on each IMF and two higher-order statistical moments namely skewness and kurtosis were extracted as features from TKEO of each IMF. The statistical significance of the selected features was evaluated using student's t-test and based on the statistical test, features from first three IMFs which show very high discriminative capability were selected as inputs to a support vector machine classifier for discrimination of Fo and NFo signals. It was observed that the classification accuracy of 92.65% is obtained in classifying EEG signals using a radial basis kernel function, which demonstrates the efficacy of proposed EMD-TKEO based feature extraction method for computer-based treatment of patients suffering from focal seizures.

Automatic detection of sleep apnea events based on inter-band energy ratio obtained from multi-band EEG signal

Sleep apnea is a potentially serious sleep disorder characterised by abnormal pauses in breathing. Electroencephalogram (EEG) signal analysis plays an important role for detecting sleep apnea events. In this research work, a method is proposed on the basis of inter-band energy ratio features obtained from multi-band EEG signals for subject-specific classification of sleep apnea and non-apnea events. The K-nearest neighbourhood classifier is used for classification purpose. Unlike conventional methods, instead of classifying apnea patient and healthy person, the objective here is to differentiate apnea and non-apnea events of an apnea patient, which makes the task very challenging. Extensive experimentation is carried out on EEG data of several subjects obtained from a publicly available database. Comprehensive experimental results reveal that the proposed method offers very satisfactory classification performance in terms of sensitivity, specificity and accuracy.

A Novel Method for Classifying Liver and Brain Tumors Using Convolutional Neural Networks, Discrete Wavelet Transform and Long Short-Term Memory Networks

Rapid classification of tumors that are detected in the medical images is of great importance in the early diagnosis of the disease. In this paper, a new liver and brain tumor classification method is proposed by using the power of convolutional neural network (CNN) in feature extraction, the power of discrete wavelet transform (DWT) in signal processing, and the power of long short-term memory (LSTM) in signal classification. A CNN-DWT-LSTM method is proposed to classify the computed tomography (CT) images of livers with tumors and to classify the magnetic resonance (MR) images of brains with tumors. The proposed method classifies liver tumors images as benign or malignant and then classifies brain tumor images as meningioma, glioma, and pituitary. In the hybrid CNN-DWT-LSTM method, the feature vector of the images is obtained from pre-trained AlexNet CNN architecture. The feature vector is reduced but strengthened by applying the single-level one-dimensional discrete wavelet transform (1-D DWT), and it is classified by training with an LSTM network. Under the scope of the study, images of 56 benign and 56 malignant liver tumors that were obtained from Fırat University Research Hospital were used and a publicly available brain tumor dataset were used. The experimental results show that the proposed method had higher performance than classifiers, such as K-nearest neighbors (KNN) and support vector machine (SVM). By using the CNN-DWT-LSTM hybrid method, an accuracy rate of 99.1% was achieved in the liver tumor classification and accuracy rate of 98.6% was achieved in the brain tumor classification. We used two different datasets to demonstrate the performance of the proposed method. Performance measurements show that the proposed method has a satisfactory accuracy rate at the liver tumor and brain tumor classifying.

Embedded Dimension and Time Series Length. Practical Influence on Permutation Entropy and Its Applications

Permutation Entropy (PE) is a time series complexity measure commonly used in a variety of contexts, with medicine being the prime example. In its general form, it requires three input parameters for its calculation: time series length N, embedded dimension m, and embedded delay τ. Inappropriate choices of these parameters may potentially lead to incorrect interpretations. However, there are no specific guidelines for an optimal selection of N, m, or τ, only general recommendations such as N>>m!, τ=1, or m=3,…,7. This paper deals specifically with the study of the practical implications of N>>m!, since long time series are often not available, or non-stationary, and other preliminary results suggest that low N values do not necessarily invalidate PE usefulness. Our study analyses the PE variation as a function of the series length N and embedded dimension m in the context of a diverse experimental set, both synthetic (random, spikes, or logistic model time series) and real–world (climatology, seismic, financial, or biomedical time series), and the classification performance achieved with varying N and m. The results seem to indicate that shorter lengths than those suggested by N>>m! are sufficient for a stable PE calculation, and even very short time series can be robustly classified based on PE measurements before the stability point is reached. This may be due to the fact that there are forbidden patterns in chaotic time series, not all the patterns are equally informative, and differences among classes are already apparent at very short lengths.

Characterization of Artifact Influence on the Classification of Glucose Time Series Using Sample Entropy Statistics

This paper analyses the performance of SampEn and one of its derivatives, Fuzzy Entropy (FuzzyEn), in the context of artifacted blood glucose time series classification. This is a difficult and practically unexplored framework, where the availability of more sensitive and reliable measures could be of great clinical impact. Although the advent of new blood glucose monitoring technologies may reduce the incidence of the problems stated above, incorrect device or sensor manipulation, patient adherence, sensor detachment, time constraints, adoption barriers or affordability can still result in relatively short and artifacted records, as the ones analyzed in this paper or in other similar works. This study is aimed at characterizing the changes induced by such artifacts, enabling the arrangement of countermeasures in advance when possible. Despite the presence of these disturbances, results demonstrate that SampEn and FuzzyEn are sufficiently robust to achieve a significant classification performance, using records obtained from patients with duodenal-jejunal exclusion. The classification results, in terms of area under the ROC of up to 0.9, with several tests yielding AUC values also greater than 0.8, and in terms of a leave-one-out average classification accuracy of 80%, confirm the potential of these measures in this context despite the presence of artifacts, with SampEn having slightly better performance than FuzzyEn.

Model Selection for Body Temperature Signal Classification Using Both Amplitude and Ordinality-Based Entropy Measures

Many entropy-related methods for signal classification have been proposed and exploited successfully in the last several decades. However, it is sometimes difficult to find the optimal measure and the optimal parameter configuration for a specific purpose or context. Suboptimal settings may therefore produce subpar results and not even reach the desired level of significance. In order to increase the signal classification accuracy in these suboptimal situations, this paper proposes statistical models created with uncorrelated measures that exploit the possible synergies between them. The methods employed are permutation entropy (PE), approximate entropy (ApEn), and sample entropy (SampEn). Since PE is based on subpattern ordinal differences, whereas ApEn and SampEn are based on subpattern amplitude differences, we hypothesized that a combination of PE with another method would enhance the individual performance of any of them. The dataset was composed of body temperature records, for which we did not obtain a classification accuracy above 80% with a single measure, in this study or even in previous studies. The results confirmed that the classification accuracy rose up to 90% when combining PE and ApEn with a logistic model.

Understanding perception of active noise control system through multichannel EEG analysis

In this Letter, a method is proposed to investigate the effect of noise with and without active noise control (ANC) on multichannel electroencephalogram (EEG) signal. The multichannel EEG signal is recorded during different listening conditions such as silent, music, noise, ANC with background noise and ANC with both background noise and music. The multiscale analysis of EEG signal of each channel is performed using the discrete wavelet transform. The multivariate multiscale matrices are formulated based on the sub-band signals of each EEG channel. The singular value decomposition is applied to the multivariate matrices of multichannel EEG at significant scales. The singular value features at significant scales and the extreme learning machine classifier with three different activation functions are used for classification of multichannel EEG signal. The experimental results demonstrate that, for ANC with noise and ANC with noise and music classes, the proposed method has sensitivity values of 75.831% (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$p \lt 0.001$\end{document}p<0.001) and 99.31% (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$p \lt 0.001$\end{document}p<0.001), respectively. The method has an accuracy value of 83.22% for the classification of EEG signal with music and ANC with music as stimuli. The important finding of this study is that by the introduction of ANC, music can be better perceived by the human brain.

Using brain connectivity metrics from synchrostates to perform motor imagery classification in EEG-based BCI systems

Phase synchronisation between different neural groups is considered an important source of information to understand the underlying mechanisms of brain cognition. This Letter investigated phase-synchronisation patterns from electroencephalogram (EEG) signals recorded from ten healthy participants performing motor imagery (MI) tasks using schematic emotional faces as stimuli. These phase-synchronised states, named synchrostates, are specific for each cognitive task performed by the user. The maximum and minimum number of occurrence states were selected for each subject and task to extract the connectivity network measures based on graph theory to feed a set of classification algorithms. Two MI tasks were successfully classified with the highest accuracy of 85% with corresponding sensitivity and specificity of 85%. In this work, not only the performance of different supervised learning techniques was studied, as well as the optimal subset of features to obtain the best discrimination rates. The robustness of this classification method for MI tasks indicates the possibility of expanding its use for online classification of the brain-computer interface (BCI) systems.

Enhanced inter-subject brain computer interface with associative sensorimotor oscillations

Electroencephalography (EEG) captures electrophysiological signatures of cortical events from the scalp with high-dimensional electrode montages. Usually, excessive sources produce outliers and potentially affect the actual event related sources. Besides, EEG manifests inherent inter-subject variability of the brain dynamics, at the resting state and/or under the performance of task(s), caused probably due to the instantaneous fluctuation of psychophysiological states. A wavelet coherence (WC) analysis for optimally selecting associative inter-subject channels is proposed here and is being used to boost performances of motor imagery (MI)-based inter-subject brain computer interface (BCI). The underlying hypothesis is that optimally associative inter-subject channels can reduce the effects of outliers and, thus, eliminate dissimilar cortical patterns. The proposed approach has been tested on the dataset IVa from BCI competition III, including EEG data acquired from five healthy subjects who were given visual cues to perform 280 trials of MI for the right hand and right foot. Experimental results have shown increased classification accuracy (81.79%) using the WC-based selected 16 channels compared to the one (56.79%) achieved using all the available 118 channels. The associative channels lie mostly around the sensorimotor regions of the brain, reinforced by the previous literature, describing spatial brain dynamics during sensorimotor oscillations. Apparently, the proposed approach paves the way for optimised EEG channel selection that could boost further the efficiency and real-time performance of BCI systems.

Automated detection of heart ailments from 12-lead ECG using complex wavelet sub-band bi-spectrum features

The complex wavelet sub-band bi-spectrum (CWSB) features are proposed for detection and classification of myocardial infarction (MI), heart muscle disease (HMD) and bundle branch block (BBB) from 12-lead ECG. The dual tree CW transform of 12-lead ECG produces CW coefficients at different sub-bands. The higher-order CW analysis is used for evaluation of CWSB. The mean of the absolute value of CWSB, and the number of negative phase angle and the number of positive phase angle features from the phase of CWSB of 12-lead ECG are evaluated. Extreme learning machine and support vector machine (SVM) classifiers are used to evaluate the performance of CWSB features. Experimental results show that the proposed CWSB features of 12-lead ECG and the SVM classifier are successful for classification of various heart pathologies. The individual accuracy values for MI, HMD and BBB classes are obtained as 98.37, 97.39 and 96.40%, respectively, using SVM classifier and radial basis function kernel function. A comparison has also been made with existing 12-lead ECG-based cardiac disease detection techniques.

Analysis of physiological signals using state space correlation entropy

In this letter, the authors propose a new entropy measure for analysis of time series. This measure is termed as the state space correlation entropy (SSCE). The state space reconstruction is used to evaluate the embedding vectors of a time series. The SSCE is computed from the probability of the correlations of the embedding vectors. The performance of SSCE measure is evaluated using both synthetic and real valued signals. The experimental results reveal that, the proposed SSCE measure along with SVM classifier have sensitivity value of 91.60%, which is higher than the performance of both sample entropy and permutation entropy features for detection of shockable ventricular arrhythmia.

Fuzzy-entropy threshold based on a complex wavelet denoising technique to diagnose Alzheimer disease

The presence of irregularities in electroencephalographic (EEG) signals entails complexities during the Alzheimer's disease (AD) diagnosis. In addition, the uncertainty presented on EEG raises major issues in the improvement of the classification rate. The multi-resolution analysis through an optimum threshold will likely achieve better results in distinguishing AD and normal EEG signals. Hence, a fuzzy-entropy concept defined in a complex multi-resolution wavelet has been proposed to obtain the most appropriate threshold. First, the complex coefficients are fuzzified using a Gaussian membership function. Afterwards, the ability of the proposed fuzzy-entropy threshold has been compared with traditional thresholds in complex wavelet domain. Experimental results show that the authors' methodology produces a higher signal-to-noise ratio and a lower root-mean-square error than traditional approaches. Moreover, a neural network scheme is performed along several features to classify AD from normal EEG signals obtaining a specificity of 87.5%.

HeartSearcher: finds patients with similar arrhythmias based on heartbeat classification

Long-term electrocardiogram data can be acquired by linking a Holter monitor to a mobile phone. However, most systems of this variety are simply designed to detect arrhythmia through heartbeat classification, and do not provide any additional support for clinical decisions. HeartSearcher identifies patients with similar arrhythmias from heartbeat classifications, by summarising each patient's typical heartbeat pattern in the form of a regular expression, and then ranking patients according to the similarities of their patterns. Results obtained using electrocardiogram data from the MIT-BIH arrhythmia database show that this abstraction reduces the volume of heartbeat classifications by 98% on average, offering great potential to support clinical decisions.

Algorithm for heart rate extraction in a novel wearable acoustic sensor

Phonocardiography is a widely used method of listening to the heart sounds and indicating the presence of cardiac abnormalities. Each heart cycle consists of two major sounds – S1 and S2 – that can be used to determine the heart rate. The conventional method of acoustic signal acquisition involves placing the sound sensor at the chest where this sound is most audible. Presented is a novel algorithm for the detection of S1 and S2 heart sounds and the use of them to extract the heart rate from signals acquired by a small sensor placed at the neck. This algorithm achieves an accuracy of 90.73 and 90.69%, with respect to heart rate value provided by two commercial devices, evaluated on more than 38 h of data acquired from ten different subjects during sleep in a pilot clinical study. This is the largest dataset for acoustic heart sound classification and heart rate extraction in the literature to date. The algorithm in this study used signals from a sensor designed to monitor breathing. This shows that the same sensor and signal can be used to monitor both breathing and heart rate, making it highly useful for long-term wearable vital signs monitoring.

Unified framework for triaxial accelerometer-based fall event detection and classification using cumulants and hierarchical decision tree classifier

In this Letter, the authors present a unified framework for fall event detection and classification using the cumulants extracted from the acceleration (ACC) signals acquired using a single waist-mounted triaxial accelerometer. The main objective of this Letter is to find suitable representative cumulants and classifiers in effectively detecting and classifying different types of fall and non-fall events. It was discovered that the first level of the proposed hierarchical decision tree algorithm implements fall detection using fifth-order cumulants and support vector machine (SVM) classifier. In the second level, the fall event classification algorithm uses the fifth-order cumulants and SVM. Finally, human activity classification is performed using the second-order cumulants and SVM. The detection and classification results are compared with those of the decision tree, naive Bayes, multilayer perceptron and SVM classifiers with different types of time-domain features including the second-, third-, fourth- and fifth-order cumulants and the signal magnitude vector and signal magnitude area. The experimental results demonstrate that the second- and fifth-order cumulant features and SVM classifier can achieve optimal detection and classification rates of above 95%, as well as the lowest false alarm rate of 1.03%.

Automatic classifier based on heart rate variability to identify fallers among hypertensive subjects

Accidental falls are a major problem of later life. Different technologies to predict falls have been investigated, but with limited success, mainly because of low specificity due to a high false positive rate. This Letter presents an automatic classifier based on heart rate variability (HRV) analysis with the goal to identify fallers automatically. HRV was used in this study as it is considered a good estimator of autonomic nervous system (ANS) states, which are responsible, among other things, for human balance control. Nominal 24 h electrocardiogram recordings from 168 cardiac patients (age 72 ± 8 years, 60 female), of which 47 were fallers, were investigated. Linear and nonlinear HRV properties were analysed in 30 min excerpts. Different data mining approaches were adopted and their performances were compared with a subject-based receiver operating characteristic analysis. The best performance was achieved by a hybrid algorithm, RUSBoost, integrated with feature selection method based on principal component analysis, which achieved satisfactory specificity and accuracy (80 and 72%, respectively), but low sensitivity (51%). These results suggested that ANS states causing falls could be reliably detected, but also that not all the falls were due to ANS states.

Ultrasonic sensor signals and optimum path forest classifier for the microstructural characterization of thermally-aged inconel 625 alloy

Secondary phases, such as laves and carbides, are formed during the final solidification stages of nickel-based superalloy coatings deposited during the gas tungsten arc welding cold wire process. However, when aged at high temperatures, other phases can precipitate in the microstructure, like the γ” and δ phases. This work presents an evaluation of the powerful optimum path forest (OPF) classifier configured with six distance functions to classify background echo and backscattered ultrasonic signals from samples of the inconel 625 superalloy thermally aged at 650 and 950 °C for 10, 100 and 200 h. The background echo and backscattered ultrasonic signals were acquired using transducers with frequencies of 4 and 5 MHz. The potentiality of ultrasonic sensor signals combined with the OPF to characterize the microstructures of an inconel 625 thermally aged and in the as-welded condition were confirmed by the results. The experimental results revealed that the OPF classifier is sufficiently fast (classification total time of 0.316 ms) and accurate (accuracy of 88.75% and harmonic mean of 89.52) for the application proposed.

Classification of Alzheimer's disease from quadratic sample entropy of electroencephalogram

Currently accepted input parameter limitations in entropy-based, non-linear signal processing methods, for example, sample entropy (SampEn), may limit the information gathered from tested biological signals. The ability of quadratic sample entropy (QSE) to identify changes in electroencephalogram (EEG) signals of 11 patients with a diagnosis of Alzheimer's disease (AD) and 11 age-matched, healthy controls is investigated. QSE measures signal regularity, where reduced QSE values indicate greater regularity. The presented method allows a greater range of QSE input parameters to produce reliable results than SampEn. QSE was lower in AD patients compared with controls with significant differences (p < 0.01) for different parameter combinations at electrodes P3, P4, O1 and O2. Subject- and epoch-based classifications were tested with leave-one-out linear discriminant analysis. The maximum diagnostic accuracy and area under the receiver operating characteristic curve were 77.27 and more than 80%, respectively, at many parameter and electrode combinations. Furthermore, QSE results across all r values were consistent, suggesting QSE is robust for a wider range of input parameters than SampEn. The best results were obtained with input parameters outside the acceptable range for SampEn, and can identify EEG changes between AD patients and controls. However, caution should be applied because of the small sample size.

Patient-specific ECG beat classification technique

Electrocardiogram (ECG) beat classification plays an important role in the timely diagnosis of the critical heart condition. An automated diagnostic system is proposed to classify five types of ECG classes, namely normal (N), ventricular ectopic beat (V), supra ventricular ectopic beat (S), fusion (F) and unknown (Q) as recommended by the Association for the Advancement of Medical Instrumentation (AAMI). The proposed method integrates the Stockwell transform (ST), a bacteria foraging optimisation (BFO) algorithm and a least mean square (LMS)-based multiclass support vector machine (SVM) classifier. The ST is utilised to extract the important morphological features which are concatenated with four timing features. The resultant combined feature vector is optimised by removing the redundant and irrelevant features using the BFO algorithm. The optimised feature vector is applied to the LMS-based multiclass SVM classifier for automated diagnosis. In the proposed technique, the LMS algorithm is used to modify the Lagrange multiplier, which in turn modifies the weight vector to minimise the classification error. The updated weights are used during the testing phase to classify ECG beats. The classification performances are evaluated using the MIT-BIH arrhythmia database. Average accuracy and sensitivity performances of the proposed system for V detection are 98.6% and 91.7%, respectively, and for S detections, 98.2% and 74.7%, respectively over the entire database. To generalise the capability, the classification performance is also evaluated using the St. Petersburg Institute of Cardiological Technics (INCART) database. The proposed technique performs better than other reported heartbeat techniques, with results suggesting better generalisation capability.

DCT domain feature extraction scheme based on motor unit action potential of EMG signal for neuromuscular disease classification

A feature extraction scheme based on discrete cosine transform (DCT) of electromyography (EMG) signals is proposed for the classification of normal event and a neuromuscular disease, namely the amyotrophic lateral sclerosis. Instead of employing DCT directly on EMG data, it is employed on the motor unit action potentials (MUAPs) extracted from the EMG signal via a template matching-based decomposition technique. Unlike conventional MUAP-based methods, only one MUAP with maximum dynamic range is selected for DCT-based feature extraction. Magnitude and frequency values of a few high-energy DCT coefficients corresponding to the selected MUAP are used as the desired feature which not only reduces computational burden, but also offers better feature quality with high within-class compactness and between-class separation. For the purpose of classification, the K-nearest neighbourhood classifier is employed. Extensive analysis is performed on clinical EMG database and it is found that the proposed method provides a very satisfactory performance in terms of specificity, sensitivity and overall classification accuracy.