Search

This paper comprehensively reviews hardware acceleration techniques and the deployment of convolutional neural networks (CNNs) for analyzing electroencephalogram (EEG) signals across various application areas, including emotion classification, motor imagery, epilepsy detection, and sleep monitoring. Previous reviews on EEG have mainly focused on software solutions. However, these reviews often overlook key challenges associated with hardware implementation, such as scenarios that require a small size, low power, high security, and high accuracy. This paper discusses the challenges and opportunities of hardware acceleration for wearable EEG devices by focusing on these aspects. Specifically, this review classifies EEG signal features into five groups and discusses hardware implementation solutions for each category in detail, providing insights into the most suitable hardware acceleration strategies for various application scenarios. In addition, it explores the complexity of efficient CNN architectures for EEG signals, including techniques such as pruning, quantization, tensor decomposition, knowledge distillation, and neural architecture search. To the best of our knowledge, this is the first systematic review that combines CNN hardware solutions with EEG signal processing. By providing a comprehensive analysis of current challenges and a roadmap for future research, this paper provides a new perspective on the ongoing development of hardware-accelerated EEG systems. [ABSTRACT FROM AUTHOR]

To address the challenge of accurately locating unmanned aerial vehicles (UAVs) in situations where radar tracking is not feasible and visual observation is difficult, this paper proposes an innovative acoustic source localization method based on improved Empirical Mode Decomposition (EMD) within an adaptive frequency window. In this study, the collected flight signals of UAVs undergo smoothing filtering. Additionally, Robust Empirical Mode Decomposition (REMD) is applied to decompose the signals into Intrinsic Mode Function (IMF) components for spectrum analysis. We introduce a sliding frequency window with adjustable bandwidth, which is automatically determined using a Grey Wolf Optimizer (GWO) with a sliding index. This window is used to lock and extract specific frequencies from the IMFs. Based on predefined criteria, the extracted IMF components are reconstructed, and trigger signal times are analyzed and recorded from these reconstructed IMFs. The time differences between sensor receptions are then calculated. Furthermore, this study introduces the Chan–Taylor localization algorithm based on weighted least squares. This advanced algorithm takes sensor time delay parameters as input and solves a set of nonlinear equations to determine the target's location. Simulations and real-world signal tests are used to validate the robustness and performance of the proposed method. The results indicate that the localization error remains below 5% within a 15 m × 15 m measurement area. This provides an efficient and real-time method for detecting the location of small UAVs. [ABSTRACT FROM AUTHOR]

The main purpose of this paper is to provide information on how to create a convolutional neural network (CNN) for extracting features from EEG signals. Our task was to understand the primary aspects of creating and fine-tuning CNNs for various application scenarios. We considered the characteristics of EEG signals, coupled with an exploration of various signal processing and data preparation techniques. These techniques include noise reduction, filtering, encoding, decoding, and dimension reduction, among others. In addition, we conduct an in-depth analysis of well-known CNN architectures, categorizing them into four distinct groups: standard implementation, recurrent convolutional, decoder architecture, and combined architecture. This paper further offers a comprehensive evaluation of these architectures, covering accuracy metrics, hyperparameters, and an appendix that contains a table outlining the parameters of commonly used CNN architectures for feature extraction from EEG signals. [ABSTRACT FROM AUTHOR]

Speech is a complex mechanism allowing us to communicate our needs, desires and thoughts. In some cases of neural dysfunctions, this ability is highly affected, which makes everyday life activities that require communication a challenge. This paper studies different parameters of an intelligent imaginary speech recognition system to obtain the best performance according to the developed method that can be applied to a low-cost system with limited resources. In developing the system, we used signals from the Kara One database containing recordings acquired for seven phonemes and four words. We used in the feature extraction stage a method based on covariance in the frequency domain that performed better compared to the other time-domain methods. Further, we observed the system performance when using different window lengths for the input signal (0.25 s, 0.5 s and 1 s) to highlight the importance of the short-term analysis of the signals for imaginary speech. The final goal being the development of a low-cost system, we studied several architectures of convolutional neural networks (CNN) and showed that a more complex architecture does not necessarily lead to better results. Our study was conducted on eight different subjects, and it is meant to be a subject's shared system. The best performance reported in this paper is up to 37% accuracy for all 11 different phonemes and words when using cross-covariance computed over the signal spectrum of a 0.25 s window and a CNN containing two convolutional layers with 64 and 128 filters connected to a dense layer with 64 neurons. The final system qualifies as a low-cost system using limited resources for decision-making and having a running time of 1.8 ms tested on an AMD Ryzen 7 4800HS CPU. [ABSTRACT FROM AUTHOR]

Finding relevant features that can represent different types of faults under a noisy environment is the key to practical applications of intelligent fault diagnosis. However, high classification accuracy cannot be achieved with only a few simple empirical features, and advanced feature engineering and modelling necessitate extensive specialised knowledge, resulting in restricted widespread use. This paper has proposed a novel and efficient fusion method, named MD-1d-DCNN, that combines statistical features from multiple domains and adaptive features retrieved using a one-dimensional dilated convolutional neural network. Moreover, signal processing techniques are utilised to uncover statistical features and realise the general fault information. To offset the negative influence of noise in signals and achieve high accuracy of fault diagnosis in noisy settings, 1d-DCNN is adopted to extract more dispersed and intrinsic fault-associated features, while also preventing the model from overfitting. In the end, fault classification based on fusion features is accomplished by the usage of fully connected layers. Two bearing datasets containing varying amounts of noise are used to verify the effectiveness and robustness of the suggested approach. The experimental results demonstrate MD-1d-DCNN's superior anti-noise capability. When compared to other benchmark models, the proposed method performs better at all noise levels. [ABSTRACT FROM AUTHOR]

Structural health monitoring (SHM) systems are used to analyze the health of infrastructures such as bridges, using data from various types of sensors. While SHM systems consist of various stages, feature extraction and pattern recognition steps are the most important. Consequently, signal processing techniques in the feature extraction stage and machine learning algorithms in the pattern recognition stage play an effective role in analyzing the health of bridges. In other words, there exists a plethora of signal processing techniques and machine learning algorithms, and the selection of the appropriate technique/algorithm is guided by the limitations of each technique/algorithm. The selection also depends on the requirements of SHM in terms of damage identification level and operating conditions. This has provided the motivation to conduct a Systematic literature review (SLR) of feature extraction techniques and pattern recognition algorithms for the structural health monitoring of bridges. The existing literature reviews describe the current trends in the field with different focus aspects. However, a systematic literature review that presents an in-depth comparative study of different applications of machine learning algorithms in the field of SHM of bridges does not exist. Furthermore, there is a lack of analytical studies that investigate the SHM systems in terms of several design considerations including feature extraction techniques, analytical approaches (classification/ regression), operational functionality levels (diagnosis/prognosis) and system implementation techniques (data-driven/model-based). Consequently, this paper identifies 45 recent research practices (during 2016–2023), pertaining to feature extraction techniques and pattern recognition algorithms in SHM for bridges through an SLR process. First, the identified research studies are classified into three different categories: supervised learning algorithms, neural networks and a combination of both. Subsequently, an in-depth analysis of various machine learning algorithms is performed in each category. Moreover, the analysis of selected research studies (total = 45) in terms of feature extraction techniques is made, and 25 different techniques are identified. Furthermore, this article also explores other design considerations like analytical approaches in the pattern recognition process, operational functionality and system implementation. It is expected that the outcomes of this research may facilitate the researchers and practitioners of the domain during the selection of appropriate feature extraction techniques, machine learning algorithms and other design considerations according to the SHM system requirements. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach to creating a graphical summary of a subject's activity during a protocol in a Semi Free-Living Environment. Thanks to this new visualization, human behavior, in particular locomotion, can now be condensed into an easy-to-read and user-friendly output. As time series collected while monitoring patients in Semi Free-Living Environments are often long and complex, our contribution relies on an innovative pipeline of signal processing methods and machine learning algorithms. Once learned, the graphical representation is able to sum up all activities present in the data and can quickly be applied to newly acquired time series. In a nutshell, raw data from inertial measurement units are first segmented into homogeneous regimes with an adaptive change-point detection procedure, then each segment is automatically labeled. Then, features are extracted from each regime, and lastly, a score is computed using these features. The final visual summary is constructed from the scores of the activities and their comparisons to healthy models. This graphical output is a detailed, adaptive, and structured visualization that helps better understand the salient events in a complex gait protocol. [ABSTRACT FROM AUTHOR]

Due to the wide use of gearmotor systems in industry, many diagnostic techniques have been developed/employed to prevent their failures. An insufficient lubrication of gearboxes of these machines could shorten their life and lead to catastrophic failures and losses, making it important to ensure a required lubrication level. For the first time in worldwide terms, this paper proposed to diagnose a lack of gearbox oil lubrication using motor current signature analysis (MCSA). This study proposed, investigated, and experimentally validated two new technologies to diagnose a lack of lubrication of gear motor systems based on MCSA. Two new diagnostic features were extracted from the current signals of a three-phase induction motor. The effectiveness of the proposed technologies was evaluated for different gear lubrication levels and was compared for three phases of motor current signals and for a case of averaging the proposed diagnostic features over three phases. The results confirmed a high effectiveness of the proposed technologies for diagnosing a lack of oil lubrication in gearmotor systems. Other contributions were as follows: (i) it was shown for the first time in worldwide terms, that the motor current nonlinearity level increases with the reduction of the sgearbox oil level; (ii) novel experimental validations of the proposed two diagnostic technologies via comprehensive experimental trials (iii) novel experimental comparisons of the diagnosis effectiveness of the proposed two diagnostic technologies. [ABSTRACT FROM AUTHOR]

The perception of hunger and satiety is of great importance to maintaining a healthy body weight and avoiding chronic diseases such as obesity, underweight, or deficiency syndromes due to malnutrition. There are a number of disease patterns, characterized by a chronic loss of this perception. To our best knowledge, hunger and satiety cannot be classified using non-invasive measurements. Aiming to develop an objective classification system, this paper presents a multimodal sensory system using associated signal processing and pattern recognition methods for hunger and satiety detection based on non-invasive monitoring. We used an Empatica E4 smartwatch, a RespiBan wearable device, and JINS MEME smart glasses to capture physiological signals from five healthy normal weight subjects inactively sitting on a chair in a state of hunger and satiety. After pre-processing the signals, we compared different feature extraction approaches, either based on manual feature engineering or deep feature learning. Comparative experiments were carried out to determine the most appropriate sensor channel, device, and classifier to reliably discriminate between hunger and satiety states. Our experiments showed that the most discriminative features come from three specific sensor modalities: Electrodermal Activity (EDA), infrared Thermopile (Tmp), and Blood Volume Pulse (BVP). [ABSTRACT FROM AUTHOR]

(1) Background: Incontinence and its complications pose great difficulties in the care of the disabled. Currently, invasive incontinence monitoring methods are too invasive, expensive, and bulky to be widely used. Compared with previous methods, bowel sound monitoring is the most commonly used non-invasive monitoring method for intestinal diseases and may even provide clinical support for doctors. (2) Methods: This paper proposes a method based on the features of bowel sound signals, which uses a BP classification neural network to predict bowel defecation and realizes a non-invasive collection of physiological signals. Firstly, according to the physiological function of human defecation, bowel sound signals were selected for monitoring and analysis before defecation, and a portable non-invasive bowel sound collection system was built. Then, the detector algorithm based on iterative kurtosis and the signal processing method based on Kalman filter was used to process the signal to remove the aliasing noise in the bowel sound signal, and feature extraction was carried out in the time domain, frequency domain, and time–frequency domain. Finally, BP neural network was selected to build a classification training method for the features of bowel sound signals. (3) Results: Experimental results based on real data sets show that the proposed method can converge to a stable state and achieve a prediction accuracy of 88.71% in 232 records, which is better than other classification methods. (4) Conclusions: The result indicates that the proposed method could provide a high-precision defecation prediction result for patients with fecal incontinence, so as to prepare for defecation in advance. [ABSTRACT FROM AUTHOR]

Non-surfacing leaks constitute the dominant source of water losses for utilities worldwide. This paper presents advanced data-driven analysis methods for leak monitoring using commercial field-deployable semi-permanent vibro-acoustic sensors, evaluated on live data collected from extensive multi-sensor deployments across a sprawling metropolitan city. This necessarily includes a wide variety of pipeline sizes, materials and surrounding soils, as well as leak sources and rates brought about by external factors. The novel proposition for structural pipe health monitoring shows that excellent leak/no-leak classification results (>94% accuracy) can be observed using Convolutional Neural Networks (CNNs) trained with Short-Time Fourier Transforms (STFTs) of the raw audio files. Most notably, it is shown how this can be achieved irrespective of the sensor used, with four models from different manufactures being part of the investigation, and over time across extended densely populated areas. [ABSTRACT FROM AUTHOR]

Portable, custom-made electronic dynamometry for the foot and ankle is a promising assessment method that enables foot and ankle muscle function to be established in healthy participants and those affected by chronic conditions. Diabetic peripheral neuropathy (DPN) can alter foot and ankle muscle function. This study assessed ankle toque in participants with diabetic peripheral neuropathy and healthy participants, with the aim of developing an algorithm for optimizing the precision of data processing and interpretation of the results and to define a reference frame for ankle torque measurement in both healthy participants and those affected by DPN. This paper discloses the software chain and the signal processing methods used for voltage—torque conversion, filtering, offset detection and the muscle effort type identification, which further allowed for a primary statistical report. The full description of the signal processing methods will make our research reproducible. The applied algorithm for signal processing is proposed as a reference frame for ankle torque assessment when using a custom-made electronic dynamometer. While evaluating multiple measurements, our algorithm permits for a more detailed parametrization of the ankle torque results in healthy participants and those affected by DPN. [ABSTRACT FROM AUTHOR]

Human emotions are variant with time, non-stationary, complex in nature, and are invoked as a result of human reactions during our daily lives. Continuously detecting human emotions from one-dimensional EEG signals is an arduous task. This paper proposes an advanced signal processing mechanism for emotion detection from EEG signals using continuous wavelet transform. The space and time components of the raw EEG signals are converted into 2D spectrograms followed by feature extraction. A hybrid spatio-temporal deep neural network is implemented to extract rich features. A differential-based entropy feature selection technique adaptively differentiates features based on entropy, based on low and high information regions. Bag of Deep Features (BoDF) is applied to create clusters of similar features and computes the features vocabularies for reduction of feature dimensionality. Extensive experiments are performed on the SEED dataset, which shows the significance of the proposed method compared to state-of-the-art methods. Specifically, the proposed model achieved 96.7%, 96.2%, 95.8%, and 95.3% accuracy with the SJTU SEED dataset, for SVM, ensemble, tree, and KNN classifiers, respectively. [ABSTRACT FROM AUTHOR]

In the existing rolling bearing performance degradation assessment methods, the input signal is usually mixed with a large amount of noise and is easily disturbed by the transfer path. The time information is usually ignored when the model processes the input signal, which affects the effect of bearing performance degradation assessment. To solve the above problems, an end-to-end performance degradation assessment model of railway axle box bearing based on a deep residual shrinkage network and a deep long short-term memory network (DRSN-LSTM) is proposed. The proposed model uses DRSN to extract local abstract features from the signal and denoises the signal to obtain the denoised feature vector, then uses deep LSTM to extract the time-series information of the signal. The healthy time-series signal of the rolling bearing is input into the DRSN-LSTM reconstruction model for training. Time-domain, frequency-domain, and time–frequency-domain features are extracted from the signal both before and after reconstruction to form a multi-domain features vector. The mean square error of the two feature vectors is used as the degradation indicator to implement the performance degradation assessment. Artificially induced defects and rolling bearings life accelerated fatigue test data verify that the proposed model is more sensitive to early failures than mathematical models, shallow networks or other deep learning models. The result is similar to the development trend of bearing failures. [ABSTRACT FROM AUTHOR]

Dry-type insulated transformers stand out for their higher applicability in substations, high-voltage instrumentation systems, and electrical installations. In this machine, the insulation system is constituted of dielectric materials such as epoxy resin and Nomex paper. Some critical issues in the operation of this equipment, such as overload, moisture, or heat, can induce a slow degradation of the physical–chemical properties of the dielectric materials, which can culminate in the total failure of the transformer. However, before the transformer's shutdown, it is common to detect discharge activity in the insulation system. Based on this issue, this work proposes an experimental and comparative analysis between acoustic emission and Hall-effect sensors, aiming at differentiating discharges in epoxy resin and Nomex paper, materials that constitute the insulation of the dry-type insulated transformers. Two signal processing techniques were studied: traditional frequency analysis and discrete wavelet transform. The objective is to develop signal processing techniques to differentiate each type of discharge since different discharges require different maintenance actions. The results obtained indicate that acoustic emission sensors and Hall sensors are promising in differentiating discharge in epoxy resin and Nomex paper. Furthermore, the pattern recognition tools presented by this work, which associated the wavelet levels energies and the energy of the full signals with the average band and the equivalent bandwidth, were effective to perform feature extraction of power transformer condition. [ABSTRACT FROM AUTHOR]

Diagnosis of bruxism is challenging because not all contractions of the masticatory muscles can be classified as bruxism. Conventional methods for sleep bruxism detection vary in effectiveness. Some provide objective data through EMG, ECG, or EEG; others, such as dental implants, are less accessible for daily practice. These methods have targeted the masseter as the key muscle for bruxism detection. However, it is important to consider that the temporalis muscle is also active during bruxism among masticatory muscles. Moreover, studies have predominantly examined sleep bruxism in the supine position, but other anatomical positions are also associated with sleep. In this research, we have collected EMG data to detect the maximum voluntary contraction of the temporalis and masseter muscles in three primary anatomical positions associated with sleep, i.e., supine and left and right lateral recumbent positions. A total of 10 time domain features were extracted, and six machine learning classifiers were compared, with random forest outperforming others. The models achieved better accuracies in the detection of sleep bruxism with the temporalis muscle. An accuracy of 93.33% was specifically found for the left lateral recumbent position among the specified anatomical positions. These results indicate a promising direction of machine learning in clinical applications, facilitating enhanced diagnosis and management of sleep bruxism. [ABSTRACT FROM AUTHOR]

Heart Rate Variability (HRV) refers to the capability of the heart rhythm to vary at different times, typically reflecting the regulation of the heart by the autonomic nervous system. In recent years, with advancements in Electrocardiogram (ECG) signal processing technology, HRV features reflect various aspects of cardiac activity, such as variability in heart rate, cardiac health status, and responses. We extracted key features of HRV and used them to develop and evaluate an automatic recognition model for cardiac diseases. Consequently, we proposed the HRV Heart Disease Recognition (HHDR) method, employing the Spectral Magnitude Quantification (SMQ) technique for feature extraction. Firstly, the HRV signals are extracted through electrocardiogram signal processing. Then, by analyzing parts of the HRV signal within various frequency ranges, the SMQ method extracts rich features of partial information. Finally, the Random Forest (RF) classification computational method is employed to classify the extracted information, achieving efficient and accurate cardiac disease recognition. Experimental results indicate that this method surpasses current technologies in recognizing cardiac diseases, with an average accuracy rate of 95.1% for normal/diseased classification, and an average accuracy of 84.8% in classifying five different disease categories. Thus, the proposed HHDR method effectively utilizes the local information of HRV signals for efficient and accurate cardiac disease recognition, providing strong support for cardiac disease research in the medical field. [ABSTRACT FROM AUTHOR]

The aim of this research was to enhance the classification accuracy of an electronic nose (E-nose) in different detecting applications. During the learning process of the E-nose to predict the types of different odors, the prediction accuracy was not quite satisfying because the raw features extracted from sensors’ responses were regarded as the input of a classifier without any feature extraction processing. Therefore, in order to obtain more useful information and improve the E-nose’s classification accuracy, in this paper, a Weighted Kernels Fisher Discriminant Analysis (WKFDA) combined with Quantum-behaved Particle Swarm Optimization (QPSO), i.e., QWKFDA, was presented to reprocess the original feature matrix. In addition, we have also compared the proposed method with quite a few previously existing ones including Principal Component Analysis (PCA), Locality Preserving Projections (LPP), Fisher Discriminant Analysis (FDA) and Kernels Fisher Discriminant Analysis (KFDA). Experimental results proved that QWKFDA is an effective feature extraction method for E-nose in predicting the types of wound infection and inflammable gases, which shared much higher classification accuracy than those of the contrast methods. [ABSTRACT FROM AUTHOR]

The development of an error compensation model for coordinate measuring machines (CMMs) and its integration into feature measurement is presented. CMMs are widespread and dependable instruments in industry and laboratories for dimensional measurement. From the tip probe sensor to the machine display, there is a complex transformation of probed point coordinates through the geometrical feature model that makes the assessment of accuracy and uncertainty measurement results difficult. Therefore, error compensation is not standardized, conversely to other simpler instruments. Detailed coordinate error compensation models are generally based on CMM as a rigid-body and it requires a detailed mapping of the CMM's behavior. In this paper a new model type of error compensation is proposed. It evaluates the error from the vectorial composition of length error by axis and its integration into the geometrical measurement model. The non-explained variability by the model is incorporated into the uncertainty budget. Model parameters are analyzed and linked to the geometrical errors and uncertainty of CMM response. Next, the outstanding measurement models of flatness, angle, and roundness are developed. The proposed models are useful for measurement improvement with easy integration into CMM signal processing, in particular in industrial environments where built-in solutions are sought. A battery of implementation tests are presented in Part II, where the experimental endorsement of the model is included. [ABSTRACT FROM AUTHOR]

This study addresses the need for advanced machine learning-based process monitoring in smart manufacturing. A methodology is developed for near-real-time part quality prediction based on process-related data obtained from a CNC turning center. Instead of the manual feature extraction methods typically employed in signal processing, a novel one-dimensional convolutional architecture allows the trained model to autonomously extract pertinent features directly from the raw signals. Several signal channels are utilized, including vibrations, motor speeds, and motor torques. Three quality indicators—average roughness, peak-to-valley roughness, and diameter deviation—are monitored using a single model, resulting in a compact and efficient classifier. Training data are obtained via a small number of experiments designed to induce variability in the quality metrics by varying feed, cutting speed, and depth of cut. A sliding window technique augments the dataset and allows the model to seamlessly operate over the entire process. This is further facilitated by the model's ability to distinguish between cutting and non-cutting phases. The base model is evaluated via k-fold cross validation and achieves average F1 scores above 0.97 for all outputs. Consistent performance is exhibited by additional instances trained under various combinations of design parameters, validating the robustness of the proposed methodology. [ABSTRACT FROM AUTHOR]

This paper introduces a three-dimensional (3D) point cloud data obtained method based on a laser line scanner and data processing technology via a PCL open project. This paper also provides a systematical analysis of the error types of laser line scanner and common error reducing solutions and calibration of the laser line scanner. The laser line scanner is combined with a precision motorized stage to obtain the 3D information of a measurand, and the format of point cloud data is converted via the set of x, y, and z coordinates. The original signal is processed according to the noise signal types of the raw point cloud data. This paper introduced a denoise process step by step combining various segmentation methods and a more optimized three-dimensional data model is obtained. A novel method for industry inspection based on the numerous point cloud for the dimensions evaluation via feature extraction and the deviation of complex surface between scanned point cloud and designed point cloud via registration algorithm is proposed. Measurement results demonstrate the good performance of the proposed methods. An obtained point cloud precision of ±10 μm is achieved, and the precision of dimension evaluation is less than ±40 μm. The results shown in the research demonstrated that the proposed method allows a higher precision and relative efficiency in measurement of dimensions and deviation of complex surfaces in industrial inspection. [ABSTRACT FROM AUTHOR]

The bearing is a component of the support shaft that guides the rotational movement of the shaft, widely used in the mechanical industry and also called a mechanical joint. In bearing fault diagnosis, the accuracy much depends on the feature extraction, which always needs a lot of training samples and classification in the commonly used methods. Neural networks are good at latent feature extraction and fault classification, however, they have problems with instability and over-fitting, and more labeled samples must be trained. Switchable normalization and semi-supervised learning are introduced to solve the above obstacles in this paper, which proposes a novel bearing fault diagnosis method based on switchable normalization semi-supervised generative adversarial networks (SN-SSGAN) with 1-dimensional representation of vibration signals as input. Experimental results showed that the proposed method has a desirable 99.93% classification accuracy in the case of less labeled data from the public data set of West Reserve University, which is better than the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Indoor wireless local area network (WLAN) based positioning technologies have boomed recently because of the huge demands of indoor location-based services (ILBS) and the wide deployment of commercial Wi-Fi devices. Channel state information (CSI) extracted from Wi-Fi signals could be calibrated and utilized as a fine-grained positioning feature for indoor fingerprinting localization. One of the main factors that would restrict the positioning accuracy of fingerprinting systems is the spatial resolution of fingerprints (SRF). This paper mainly focuses on the improvement of SRF for indoor CSI-based positioning and a calibrated CSI feature (CCF) with high SRF is established based on the preprocess of both measured amplitude and phase. In addition, a similarity calculation metric for the proposed CCF is designed based on modified dynamic time warping (MDTW). An indoor fingerprinting method based on CCF and MDTW, named CC-DTW, is then proposed to improve the positioning accuracy in indoors. Experiments are conducted in two indoor office testbeds, and the performances of the proposed CC-DTW, one time-reversal (TR) based approach and one Euclidean distance (ED) based approach are evaluated and discussed. The results show that the SRF of CC-DTW outperforms the TR-based one and the ED-based one in both two testbeds in terms of the receiver operating characteristic (ROC) curve metric, and the area under curve (AUC) metric. [ABSTRACT FROM AUTHOR]

As the size of the radar hardware platform becomes smaller and smaller, the cost becomes lower and lower. The application of indoor radar-based human motion recognition has become a reality, which can be realized in a low-cost device with simple architecture. Compared with narrow-band radar (such as continuous wave radar, etc.), the human motion echo signal of the carrier-free ultra-wideband (UWB) radar contains more abundant characteristic information of human motion, which is helpful for identifying different types of human motion. In this paper, a novel feature extraction method by two-dimensional variational mode decomposition (2D-VMD) algorithm is proposed. And it is used for extracting the primary features of human motion. The 2D-VMD algorithm is an adaptive non-recursive multiscale decomposition method for nonlinear and nonstationary signals. Firstly, the original 2D radar echo signals are decomposed by the 2D-VMD algorithm to capture several 2D intrinsic mode function (BIMFs) which represent different groups of central frequency components of a certain type of human motion. Secondly, original echo signals are reconstructed according to the several BIMFs, which not only have a certain inhibitory effect on the clutter in the echo signal, but can also further demonstrate that the BIMFs obtained by the 2D-VMD algorithm can represent the original 2D echo signal well. Finally, based on the measured ten different types of UWB radar human motion 2D echo analysis signals, the characteristics of these different types of human motion are extracted and the original echo signal are reconstructed. Then, the three indicators of the PCC, UQI, and PSNR between the original echo signals and extraction/reconstruction 2D signals are analyzed, which illustrate the effectiveness of 2D-VMD algorithm to extract feature of human motion 2D echo signals of the carrier-free UWB radar. Experimental results show that BIMFs by 2D-VMD algorithm can well represent the echo signal characteristics of this type of human motion, which is a very effective tool for human motion radar echo signal feature extraction. [ABSTRACT FROM AUTHOR]

This paper describes the development and validation of the currently smallest aerial platform with olfaction capabilities. The developed Smelling Nano Aerial Vehicle (SNAV) is based on a lightweight commercial nano-quadcopter (27 g) equipped with a custom gas sensing board that can host up to two in situ metal oxide semiconductor (MOX) gas sensors. Due to its small form-factor, the SNAV is not a hazard for humans, enabling its use in public areas or inside buildings. It can autonomously carry out gas sensing missions of hazardous environments inaccessible to terrestrial robots and bigger drones, for example searching for victims and hazardous gas leaks inside pockets that form within the wreckage of collapsed buildings in the aftermath of an earthquake or explosion. The first contribution of this work is assessing the impact of the nano-propellers on the MOX sensor signals at different distances to a gas source. A second contribution is adapting the 'bout' detection algorithm, proposed by Schmuker et al. (2016) to extract specific features from the derivative of the MOX sensor response, for real-time operation. The third and main contribution is the experimental validation of the SNAV for gas source localization (GSL) and mapping in a large indoor environment (160 m2) with a gas source placed in challenging positions for the drone, for example hidden in the ceiling of the room or inside a power outlet box. Two GSL strategies are compared, one based on the instantaneous gas sensor response and the other one based on the bout frequency. From the measurements collected (in motion) along a predefined sweeping path we built (in less than 3 min) a 3D map of the gas distribution and identified the most likely source location. Using the bout frequency yielded on average a higher localization accuracy than using the instantaneous gas sensor response (1.38 m versus 2.05 m error), however accurate tuning of an additional parameter (the noise threshold) is required in the former case. The main conclusion of this paper is that a nano-drone has the potential to perform gas sensing tasks in complex environments. [ABSTRACT FROM AUTHOR]

Distributed Acoustic Sensing (DAS) is a promising new technology for pipeline monitoring and protection. However, a big challenge is distinguishing between relevant events, like intrusion by an excavator near the pipeline, and interference, like land machines. This paper investigates whether it is possible to achieve adequate detection accuracy with classic machine learning algorithms using simulations and real system implementation. Then, we compare classical machine learning with a deep learning approach and analyze the advantages and disadvantages of both approaches. Although acceptable performance can be achieved with both approaches, preliminary results show that deep learning is the more promising approach, eliminating the need for laborious feature extraction and offering a six times lower event detection delay and twelve times lower execution time. However, we achieved the best results by combining deep learning with the knowledge-based and classical machine learning approaches. At the end of this manuscript, we propose general guidelines for efficient system design combining knowledge-based, classical machine learning, and deep learning approaches. [ABSTRACT FROM AUTHOR]

This paper proposes a Gaussian mixture model-based (GMM) bearing fault band selection (GMM-WBBS) method for signal processing. The proposed method benefits reliable feature extraction using fault frequency oriented Gaussian mixture model (GMM) window series. Selecting exclusively bearing fault frequency harmonics, it eliminates the interference of bearing normal vibrations in the lower frequencies, bearing natural frequencies, and the higher frequency contents that prove to be useful only for anomaly detection but do not provide any insight into the bearing fault location. The features are extracted from time- and frequency- domain signals that exclusively contain the bearing fault frequency harmonics. Classification is done using the Weighted KNN algorithm. The experiments performed with the data containing the vibrations recorded from artificially damaged bearings show the positive effect of utilizing the proposed GMM-WBBS signal processing to filter out the discriminative data of uncertain origin. All comparison methods retrofitted with the proposed method demonstrated classification performance improvements when provided with vibration data with suppressed bearing natural frequencies and higher frequency contents. [ABSTRACT FROM AUTHOR]

The ultrasonic guided lamb wave approach is an effective non-destructive testing (NDT) method used for detecting localized mechanical damage, corrosion, and welding defects in metallic pipelines. The signal processing of guided waves is often challenging due to the complexity of the operational conditions and environment in the pipelines. Machine learning approaches in recent years, including convolutional neural networks (CNN) and long short-term memory (LSTM), have exhibited their advantages to overcome these challenges for the signal processing and data classification of complex systems, thus showing great potential for damage detection in critical oil/gas pipeline structures. In this study, a CNN-LSTM hybrid model was utilized for decoding ultrasonic guided waves for damage detection in metallic pipelines, and twenty-nine features were extracted as input to classify different types of defects in metallic pipes. The prediction capacity of the CNN-LSTM model was assessed by comparing it to those of CNN and LSTM. The results demonstrated that the CNN-LSTM hybrid model exhibited much higher accuracy, reaching 94.8%, as compared to CNN and LSTM. Interestingly, the results also revealed that predetermined features, including the time, frequency, and time–frequency domains, could significantly improve the robustness of deep learning approaches, even though deep learning approaches are often believed to include automated feature extraction, without hand-crafted steps as in shallow learning. Furthermore, the CNN-LSTM model displayed higher performance when the noise level was relatively low (e.g., SNR = 9 or higher), as compared to the other two models, but its prediction dropped gradually with the increase of the noise. [ABSTRACT FROM AUTHOR]

Sound classification has been widely used in many fields. Unlike traditional signal-processing methods, using deep learning technology for sound classification is one of the most feasible and effective methods. However, limited by the quality of the training dataset, such as cost and resource constraints, data imbalance, and data annotation issues, the classification performance is affected. Therefore, we propose a sound classification mechanism based on convolutional neural networks and use the sound feature extraction method of Mel-Frequency Cepstral Coefficients (MFCCs) to convert sound signals into spectrograms. Spectrograms are suitable as input for CNN models. To provide the function of data augmentation, we can increase the number of spectrograms by setting the number of triangular bandpass filters. The experimental results show that there are 50 semantic categories in the ESC-50 dataset, the types are complex, and the amount of data is insufficient, resulting in a classification accuracy of only 63%. When using the proposed data augmentation method (K = 5), the accuracy is effectively increased to 97%. Furthermore, in the UrbanSound8K dataset, the amount of data is sufficient, so the classification accuracy can reach 90%, and the classification accuracy can be slightly increased to 92% via data augmentation. However, when only 50% of the training dataset is used, along with data augmentation, the establishment of the training model can be accelerated, and the classification accuracy can reach 91%. [ABSTRACT FROM AUTHOR]

Not long ago, hearables paved the way for biosensing, fitness, and healthcare monitoring. Smart earbuds today are not only producing sound but also monitoring vital signs. Reliable determination of cardiovascular and pulmonary system information can explore the use of hearables for physiological monitoring. Recent research shows that photoplethysmography (PPG) signals not only contain details on oxygen saturation level (SPO2) but also carry more physiological information including pulse rate, respiration rate, blood pressure, and arterial-related information. The analysis of the PPG signal from the ear has proven to be reliable and accurate in the research setting. (1) Background: The present integrative review explores the existing literature on an in-ear PPG signal and its application. This review aims to identify the current technology and usage of in-ear PPG and existing evidence on in-ear PPG in physiological monitoring. This review also analyzes in-ear (PPG) measurement configuration and principle, waveform characteristics, processing technology, and feature extraction characteristics. (2) Methods: We performed a comprehensive search to discover relevant in-ear PPG articles published until December 2022. The following electronic databases: Institute of Electrical and Electronics Engineers (IEEE), ScienceDirect, Scopus, Web of Science, and PubMed were utilized to conduct the studies addressing the evidence of in-ear PPG in physiological monitoring. (3) Results: Fourteen studies were identified but nine studies were finalized. Eight studies were on different principles and configurations of hearable PPG, and eight studies were on processing technology and feature extraction and its evidence in in-ear physiological monitoring. We also highlighted the limitations and challenges of using in-ear PPG in physiological monitoring. (4) Conclusions: The available evidence has revealed the future of in-ear PPG in physiological monitoring. We have also analyzed the potential limitation and challenges that in-ear PPG will face in processing the signal. [ABSTRACT FROM AUTHOR]

The electroencephalography (EEG) signal is a noninvasive and complex signal that has numerous applications in biomedical fields, including sleep and the brain–computer interface. Given its complexity, researchers have proposed several advanced preprocessing and feature extraction methods to analyze EEG signals. In this study, we analyze a comprehensive review of numerous articles related to EEG signal processing. We searched the major scientific and engineering databases and summarized the results of our findings. Our survey encompassed the entire process of EEG signal processing, from acquisition and pretreatment (denoising) to feature extraction, classification, and application. We present a detailed discussion and comparison of various methods and techniques used for EEG signal processing. Additionally, we identify the current limitations of these techniques and analyze their future development trends. We conclude by offering some suggestions for future research in the field of EEG signal processing. [ABSTRACT FROM AUTHOR]

The purpose of this work is to increase the security of the perimeter of an area from unauthorized intrusions by creating an improved algorithm for classifying acoustic impacts recorded with a sensor system based on a phase-sensitive optical time reflectometer (phi-OTDR). The algorithm includes machine learning, so a dataset consisting of two classes was assembled. The dataset consists of two classes. The first class is the data of the steps, and the second class is other non-stepping influences (engine noise, a passing car, a passing cyclist, etc.). As an intrusion signal, a human walking signal is analyzed and recorded in frames of 5 s, which passed the threshold condition. Since, in most cases, the intruder moves on foot to overcome the perimeter, the analysis of the acoustic effects generated during the step will increase the efficiency of the perimeter detection tools. When walking quietly, step signals can be quite weak, and background signals can contain high energy and visually resemble the signals you are looking for. Therefore, an algorithm was created that processes space–time diagrams developed in real time, which are grayscale images. At the same time, during the processing of one image, two more images are calculated, which are the result of processing the denoised autoencoder and the created mathematical model of the adaptive correlation. Then, the three obtained images are fed to the input of the created three-channel neural network classifier, which includes convolutional layers for the automatic extraction of spatial features. The probability of correctly detecting steps is 98.3% and that of background actions is 97.93%. [ABSTRACT FROM AUTHOR]

Brain-Computer Interface (BCI) is an advanced and multidisciplinary active research domain based on neuroscience, signal processing, biomedical sensors, hardware, etc. Since the last decades, several groundbreaking research has been conducted in this domain. Still, no comprehensive review that covers the BCI domain completely has been conducted yet. Hence, a comprehensive overview of the BCI domain is presented in this study. This study covers several applications of BCI and upholds the significance of this domain. Then, each element of BCI systems, including techniques, datasets, feature extraction methods, evaluation measurement matrices, existing BCI algorithms, and classifiers, are explained concisely. In addition, a brief overview of the technologies or hardware, mostly sensors used in BCI, is appended. Finally, the paper investigates several unsolved challenges of the BCI and explains them with possible solutions. [ABSTRACT FROM AUTHOR]

Maintaining a high quality of conversation between doctors and patients is essential in telehealth services, where efficient and competent communication is important to promote patient health. Assessing the quality of medical conversations is often handled based on a human auditory-perceptual evaluation. Typically, trained experts are needed for such tasks, as they follow systematic evaluation criteria. However, the daily rapid increase of consultations makes the evaluation process inefficient and impractical. This paper investigates the automation of the quality assessment process of patient–doctor voice-based conversations in a telehealth service using a deep-learning-based classification model. For this, the data consist of audio recordings obtained from Altibbi. Altibbi is a digital health platform that provides telemedicine and telehealth services in the Middle East and North Africa (MENA). The objective is to assist Altibbi's operations team in the evaluation of the provided consultations in an automated manner. The proposed model is developed using three sets of features: features extracted from the signal level, the transcript level, and the signal and transcript levels. At the signal level, various statistical and spectral information is calculated to characterize the spectral envelope of the speech recordings. At the transcript level, a pre-trained embedding model is utilized to encompass the semantic and contextual features of the textual information. Additionally, the hybrid of the signal and transcript levels is explored and analyzed. The designed classification model relies on stacked layers of deep neural networks and convolutional neural networks. Evaluation results show that the model achieved a higher level of precision when compared with the manual evaluation approach followed by Altibbi's operations team. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) performs a vital function in various fields, including healthcare, rehabilitation, elder care, and monitoring. Researchers are using mobile sensor data (i.e., accelerometer, gyroscope) by adapting various machine learning (ML) or deep learning (DL) networks. The advent of DL has enabled automatic high-level feature extraction, which has been effectively leveraged to optimize the performance of HAR systems. In addition, the application of deep-learning techniques has demonstrated success in sensor-based HAR across diverse domains. In this study, a novel methodology for HAR was introduced, which utilizes convolutional neural networks (CNNs). The proposed approach combines features from multiple convolutional stages to generate a more comprehensive feature representation, and an attention mechanism was incorporated to extract more refined features, further enhancing the accuracy of the model. The novelty of this study lies in the integration of feature combinations from multiple stages as well as in proposing a generalized model structure with CBAM modules. This leads to a more informative and effective feature extraction technique by feeding the model with more information in every block operation. This research used spectrograms of the raw signals instead of extracting hand-crafted features through intricate signal processing techniques. The developed model has been assessed on three datasets, including KU-HAR, UCI-HAR, and WISDM datasets. The experimental findings showed that the classification accuracies of the suggested technique on the KU-HAR, UCI-HAR, and WISDM datasets were 96.86%, 93.48%, and 93.89%, respectively. The other evaluation criteria also demonstrate that the proposed methodology is comprehensive and competent compared to previous works. [ABSTRACT FROM AUTHOR]

Vibration analysis is an effective tool for the condition monitoring and fault diagnosis of wind turbine drivetrains. It enables the defect location of mechanical subassemblies and health indicator construction for remaining useful life prediction, which is beneficial to reducing the operation and maintenance costs of wind farms. This paper analyzes the structure features of different drivetrains of mainstream wind turbines and introduces a vibration data acquisition system. Almost all the research on the vibration-based diagnosis algorithm for wind turbines in the past decade is reviewed, with its effects being discussed. Several challenging tasks and their solutions in the vibration-based fault detection of wind turbine drivetrains are proposed from the perspective of practicality for wind turbines, including the fault detection of planetary subassemblies in multistage wind turbine gearboxes, fault feature extraction under nonstationary conditions, fault information enhancement techniques and health indicator construction. Numerous naturally damaged cases representing the real operational features of industrial wind turbines are given, with a discussion of the failure mechanism of defective parts in wind turbine drivetrains as well. [ABSTRACT FROM AUTHOR]

Mechanical equipment is the heart of industry. For this reason, mechanical fault diagnosis has drawn considerable attention. In terms of the rich information hidden in fault vibration signals, the processing and analysis techniques of vibration signals have become a crucial research issue in the field of mechanical fault diagnosis. Based on the theory of sparse decomposition, Selesnick proposed a novel nonlinear signal processing method: resonance-based sparse signal decomposition (RSSD). Since being put forward, RSSD has become widely recognized, and many RSSD-based methods have been developed to guide mechanical fault diagnosis. This paper attempts to summarize and review the theoretical developments and application advances of RSSD in mechanical fault diagnosis, and to provide a more comprehensive reference for those interested in RSSD and mechanical fault diagnosis. Followed by a brief introduction of RSSD's theoretical foundation, based on different optimization directions, applications of RSSD in mechanical fault diagnosis are categorized into five aspects: original RSSD, parameter optimized RSSD, subband optimized RSSD, integrated optimized RSSD, and RSSD combined with other methods. On this basis, outstanding issues in current RSSD study are also pointed out, as well as corresponding instructional solutions. We hope this review will provide an insightful reference for researchers and readers who are interested in RSSD and mechanical fault diagnosis. [ABSTRACT FROM AUTHOR]

Reliable fault diagnosis and condition monitoring are essential for permanent magnet synchronous motor (PMSM) drive systems with high-reliability requirements. PMSMs can be subject to various types of damage during operation. Magnetic damage is a unique fault of PMSM and concerns the permanent magnet (PM) of the rotor. PM damage may be mechanical in nature or be related to the phenomenon of demagnetization. This article presents a machine learning (ML) based demagnetization fault diagnosis method for PMSM drives. The time-frequency domain analysis based on short-time Fourier transform (STFT) is applied in the process of PM fault feature extraction from the stator phase current signal. Moreover, two ML-based models are verified and compared in the process of the automatic fault detection of demagnetization fault. These models are k-nearest neighbors (KNN) and multiLayer perceptron (MLP). The influence of the input vector elements, key parameters and structures of the models used on their effectiveness is extensively analyzed. The results of the experimental verification confirm the very high effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

To improve the accuracy of shallow neural networks in processing complex signals and cable fault diagnosis, and to overcome the shortage of manual dependency and cable fault feature extraction, a deep learning method is introduced, and a time−frequency domain joint impedance spectrum is proposed for cable fault identification and localization based on a deep belief network (DBN). Firstly, based on the distribution parameter model of power cables, we model and analyze the cables under normal operation and different fault types, and we obtain the headend input impedance spectrum and the headend input time−frequency domain impedance spectrum of cables under various operating conditions. The headend input impedance amplitude and phase of normal operation and different fault cables are extracted as the original input samples of the cable fault type identification model; the real part of the headend input time–frequency domain impedance of the fault cables is extracted as the original input samples of the cable fault location model. Then, the unsupervised pre−training and supervised inverse fine−tuning methods are used for automatically learning, training, and extracting the cable fault state features from the original input samples, and the DBN−based cable fault type recognition model and location model are constructed and used to realize the type recognition and location of cable faults. Finally, the proposed method is validated by simulation, and the results show that the method has good fault feature extraction capability and high fault type recognition and localization accuracy. [ABSTRACT FROM AUTHOR]

Analog hardware used for signal envelope extraction in low-power interfaces for acoustic event detection, owing to its low complexity and power consumption, suffers from low sensitivity and performs poorly under low signal to noise ratios (SNR) found in undersea environments. To overcome those problems, in this paper, we propose a novel passive electromechanical solution for the signal feature extraction in low frequency acoustic range (200–1000 Hz), in the form of a piezoelectric vibration transducer, and a rectifier with a mechanically switched inductor. A simulation study of the novel solution is presented, and a proof-of-concept device is developed and experimentally characterized. We demonstrate its applicability and show the advantages of the passive electromechanical device in comparison to the active electrical solution in terms of operation with lower input signals (<20 mV compared to 40 mV), and higher robustness in low SNR conditions (output voltage loss for −10 dB ≤ SNR < 40 dB of 1 mV, compared to 10 mV). In addition to the signal processing performance improvements, compared to our previous work, the utilization of the presented novel passive feature extractor would also decrease power consumption of a detector's channel by over 76%, enabling life-time extension and/or increased quality of detection with larger number of channels. To the best of our knowledge, this is the first solution presented in the literature that demonstrates the possibility of using a passive electromechanical feature extractor in a low-power analog wake-up event detector interface. [ABSTRACT FROM AUTHOR]

The vibration monitoring of ball bearings of a rotating machinery is a crucial aspect for smooth functioning and sustainability of plants. The wireless vibration monitoring using conventional Nyquist sampling techniques is costly in terms of power consumption, as it generates lots of data that need to be processed. To overcome this issue, compressive sensing (CS) can be employed, which directly acquires the signal in compressed form and hence reduces power consumption. The compressive measurements so generated can easily be transmitted to the base station and the original signal can be recovered there using CS reconstruction algorithms to diagnose the faults. However, the CS reconstruction is very costly in terms of computational time and power. Hence, this conventional CS framework is not suitable for diagnosing the machinery faults in real time. In this paper, a bearing condition monitoring framework is presented based on compressed signal processing (CSP). The CSP is a newer research area of CS, in which inference problems are solved without reconstructing the original signal back from compressive measurements. By omitting the reconstruction efforts, the proposed method significantly improves the time and power cost. This leads to faster processing of compressive measurements for solving the required inference problems for machinery condition monitoring. This gives a way to diagnose the machinery faults in real-time. A comparison of proposed scheme with the conventional method shows that the proposed scheme lowers the computational efforts while simultaneously achieving the comparable fault classification accuracy. [ABSTRACT FROM AUTHOR]

This paper proposes a methodology to process and interpret the complex signals acquired from the health monitoring of civil structures via scale-space empirical wavelet transform (EWT). The FREEVIB method, a widely used instantaneous modal parameters identification method, determines the structural characteristics from the individual components separated by EWT first. The scale-space EWT turns the detecting of the frequency boundaries into the scale-space representation of the Fourier spectrum. As well, to find meaningful modes becomes a clustering problem on the length of minima scale-space curves. The Otsu's algorithm is employed to determine the threshold for the clustering analysis. To retain the time-varying features, the EWT-extracted mono-components are analyzed by the FREEVIB method to obtain the instantaneous modal parameters and the linearity characteristics of the structures. Both simulated and real SHM signals from civil structures are used to validate the effectiveness of the present method. The results demonstrate that the proposed methodology is capable of separating the signal components, even those closely spaced ones in frequency domain, with high accuracy, and extracting the structural features reliably. [ABSTRACT FROM AUTHOR]

In environment sound classification, log Mel band energies (MBEs) are considered as the most successful and commonly used features for classification. The underlying algorithm, fast Fourier transform (FFT), is valid under certain restrictions. In this study, we address these limitations of Fourier transform and propose a new method to extract log Mel band energies using amplitude modulation and frequency modulation. We present a comparative study between traditionally used log Mel band energy features extracted by Fourier transform and log Mel band energy features extracted by our new approach. This approach is based on extracting log Mel band energies from estimation of instantaneous frequency (IF) and instantaneous amplitude (IA), which are used to construct a spectrogram. The estimation of IA and IF is made by associating empirical mode decomposition (EMD) with the Teager–Kaiser energy operator (TKEO) and the discrete energy separation algorithm. Later, Mel filter bank is applied to the estimated spectrogram to generate EMD-TKEO-based MBEs, or simply, EMD-MBEs. In addition, we employ the EMD method to remove signal trends from the original signal and generate another type of MBE, called S-MBEs, using FFT and a Mel filter bank. Four different datasets were utilised and convolutional neural networks (CNN) were trained using features extracted from Fourier transform-based MBEs (FFT-MBEs), EMD-MBEs, and S-MBEs. In addition, CNNs were trained with an aggregation of all three feature extraction techniques and a combination of FFT-MBEs and EMD-MBEs. Individually, FFT-MBEs achieved higher accuracy compared to EMD-MBEs and S-MBEs. In general, the system trained with the combination of all three features performed slightly better compared to the system trained with the three features separately. [ABSTRACT FROM AUTHOR]

Epilepsy is a chronic neurological disorder caused by abnormal neuronal activity that is diagnosed visually by analyzing electroencephalography (EEG) signals. Background: Surgical operations are the only option for epilepsy treatment when patients are refractory to treatment, which highlights the role of classifying focal and generalized epilepsy syndrome. Therefore, developing a model to be used for diagnosing focal and generalized epilepsy automatically is important. Methods: A classification model based on longitudinal bipolar montage (LB), discrete wavelet transform (DWT), feature extraction techniques, and statistical analysis in feature selection for RNN combined with long short-term memory (LSTM) is proposed in this work for identifying epilepsy. Initially, normal and epileptic LB channels were decomposed into three levels, and 15 various features were extracted. The selected features were extracted from each segment of the signals and fed into LSTM for the classification approach. Results: The proposed algorithm achieved a 96.1% accuracy, a 96.8% sensitivity, and a 97.4% specificity in distinguishing normal subjects from subjects with epilepsy. This optimal model was used to analyze the channels of subjects with focal and generalized epilepsy for diagnosing purposes, relying on statistical parameters. Conclusions: The proposed approach is promising, as it can be used to detect epilepsy with satisfactory classification performance and diagnose focal and generalized epilepsy. [ABSTRACT FROM AUTHOR]

In the era of technological advances and innovations in transportation technologies, application of driving simulators for the investigation and assessment of the driving process provides a safe and suitable testing environment. Although driving simulators are crucial for further improvements in transportation, it is important to resolve one of their main disadvantages–simulator sickness. Therefore, suitable methods for the assessment of simulator sickness are required. The main aim of this paper was to present a non-invasive method for assessing simulator sickness by recording gastric myoelectrical activity–electrogastrography. Open-source hardware for electrogastrography together with recordings obtained in 13 healthy volunteers is presented, and the main aspects of signal processing for artifact cancellation and feature extraction were discussed. Based on the obtained results, it was concluded that slow-wave electrical gastric activity can be recorded during driving simulation by following adequate recommendations and that proposed features could be beneficial in describing non-ordinary electrogastrography signals. [ABSTRACT FROM AUTHOR]

Accurate and timely bearing fault diagnosis is crucial to decrease the probability of unexpected failures of rotating machinery and improve the efficiency of its scheduled maintenance. Since convolutional neural networks (CNN) have poor feature extraction capability for sensor data with 1D format, CNN combined with signal processing algorithm is often adopted for fault diagnosis. This increases manual conversion work and expertise dependence while reducing the feasibility and robustness of the corresponding fault diagnosis method. In this paper, a novel sensor data-driven fault diagnosis method is proposed by fusing S-transform (ST) algorithm and CNN, namely ST-CNN. First of all, a ST layer is designed based on S-transform algorithm. In the ST layer, sensor data is automatically converted into 2D time-frequency matrix without manual conversion work. Then, a new ST-CNN model is constructed, and the time-frequency coefficient matrixes are inputted into the constructed ST-CNN model. After the training process of the ST-CNN model is completed, the classification layer such as softmax performs the fault diagnosis. Finally, the diagnosis performance of the proposed method is evaluated by using two public available datasets of bearings. The experimental results show that the proposed method performs the higher and more robust diagnosis performance than other existing methods. [ABSTRACT FROM AUTHOR]

Emotion recognition based on multi-channel electroencephalograph (EEG) signals is becoming increasingly attractive. However, the conventional methods ignore the spatial characteristics of EEG signals, which also contain salient information related to emotion states. In this paper, a deep learning framework based on a multiband feature matrix (MFM) and a capsule network (CapsNet) is proposed. In the framework, the frequency domain, spatial characteristics, and frequency band characteristics of the multi-channel EEG signals are combined to construct the MFM. Then, the CapsNet model is introduced to recognize emotion states according to the input MFM. Experiments conducted on the dataset for emotion analysis using EEG, physiological, and video signals (DEAP) indicate that the proposed method outperforms most of the common models. The experimental results demonstrate that the three characteristics contained in the MFM were complementary and the capsule network was more suitable for mining and utilizing the three correlation characteristics. [ABSTRACT FROM AUTHOR]

Due to the existing relationship between microstructural properties and magnetic ones of the ferromagnetic materials, the application potential of the magnetic Barkhausen noise (BN) method to non-destructive testing is constantly growing. However, the stochastic nature of the Barkhausen effect requires the use of advanced signal processing methods. Recently, the need to apply time-frequency (TF) transformations to the processing of BN signals arose. However, various TF methods have been used in the majority of cases for qualitative signal conditioning and no extensive analysis of TF-based information has been conducted so far. Therefore, in this paper, the wide analysis of BN TF representation was carried out. Considering the properties of TF transformations, the Short-Time Fourier Transform (STFT) was used. A procedure for definition of the envelopes of the TF characteristic was proposed. To verify the quality of extracted features, an analysis was performed on the basis of BN signals acquired during stress loading experiments of steel elements. First, the preliminary experiments were processed for various parameters of the measuring system and calculation procedures. The feature extraction procedure was performed for different modes of TF representations. Finally, the distributions of TF features over the loading stages are presented and their information content was validated using commonly used features derived from time T and frequency F domains. [ABSTRACT FROM AUTHOR]

Various lengths of time window have been used in feature extraction for electroencephalogram (EEG) signal processing in previous studies. However, the effect of time window length on feature extraction for the downstream tasks such as emotion recognition has not been well examined. To this end, we investigate the effect of different time window (TW) lengths on human emotion recognition to find the optimal TW length for extracting electroencephalogram (EEG) emotion signals. Both power spectral density (PSD) features and differential entropy (DE) features are used to evaluate the effectiveness of different TW lengths based on the SJTU emotion EEG dataset (SEED). Different lengths of TW are then processed with an EEG feature-processing approach, namely experiment-level batch normalization (ELBN). The processed features are used to perform emotion recognition tasks in the six classifiers, the results of which are then compared with the results without ELBN. The recognition accuracies indicate that a 2-s TW length has the best performance on emotion recognition and is the most suitable to be used in EEG feature extraction for emotion recognition. The deployment of ELBN in the 2-s TW can further improve the emotion recognition performances by 21.63% and 5.04% when using an SVM based on PSD and DE features, respectively. These results provide a solid reference for the selection of TW length in analyzing EEG signals for applications in intelligent systems. [ABSTRACT FROM AUTHOR]

A systematic review on electroencephalographic (EEG)-based feature extraction strategies to diagnosis and therapy of attention deficit hyperactivity disorder (ADHD) in children is presented. The analysis is realized at an executive function level to improve the research of neurocorrelates of heterogeneous disorders such as ADHD. The Quality Assessment Tool for Quantitative Studies (QATQS) and field-weighted citation impact metric (Scopus) were used to assess the methodological rigor of the studies and their impact on the scientific community, respectively. One hundred and one articles, concerning the diagnostics and therapy of ADHD children aged from 8 to 14, were collected. Event-related potential components were mainly exploited for executive functions related to the cluster inhibition, whereas band power spectral density is the most considered EEG feature for executive functions related to the cluster working memory. This review identifies the most used (also by rigorous and relevant articles) EEG signal processing strategies for executive function assessment in ADHD. [ABSTRACT FROM AUTHOR]