RESUMEN

In this research work, Semantic-Preserved Generative Adversarial Network optimized by Piranha Foraging Optimization for Thyroid Nodule Classification in Ultrasound Images (SPGAN-PFO-TNC-UI) is proposed. Initially, ultrasound images are gathered from the DDTI dataset. Then the input image is sent to the pre-processing step. During pre-processing stage, the Multi-Window Savitzky-Golay Filter (MWSGF) is employed to reduce the noise and improve the quality of the ultrasound (US) images. The pre-processed output is supplied to the Generalized Intuitionistic Fuzzy C-Means Clustering (GIFCMC). Here, the ultrasound image's Region of Interest (ROI) is segmented. The segmentation output is supplied to the Fully Numerical Laplace Transform (FNLT) to extract the features, such as geometric features like solidity, orientation, roundness, main axis length, minor axis length, bounding box, convex area, and morphological features, like area, perimeter, aspect ratio, and AP ratio. The Semantic-Preserved Generative Adversarial Network (SPGAN) separates the image as benign or malignant nodules. Generally, SPGAN does not express any optimization adaptation methodologies for determining the best parameters to ensure the accurate classification of thyroid nodules. Therefore, the Piranha Foraging Optimization (PFO) algorithm is proposed to improve the SPGAN classifier and accurately identify the thyroid nodules. The metrics, like F-score, accuracy, error rate, precision, sensitivity, specificity, ROC, computing time is examined. The proposed SPGAN-PFO-TNC-UI method attains 30.54%, 21.30%, 27.40%, and 18.92% higher precision and 26.97%, 20.41%, 15.09%, and 18.27% lower error rate compared with existing techniques, like Thyroid detection and classification using DNN with Hybrid Meta-Heuristic and LSTM (TD-DL-HMH-LSTM), Quantum-Inspired convolutional neural networks for optimized thyroid nodule categorization (QCNN-OTNC), Thyroid nodules classification under Follow the Regularized Leader Optimization based Deep Neural Networks (CTN-FRL-DNN), Automatic classification of ultrasound thyroids images using vision transformers and generative adversarial networks (ACUTI-VT-GAN) respectively.

RESUMEN

This paper develops a new hybrid, automated, and non-invasive approach by combining hyper-spectral imaging, Savitzky-Golay (SG) Filter, Principal Components Analysis (PCA), Machine Learning (ML) classifiers/regressors, and stacking generalization methods to detect sugar in honey. First, the 32 different sugar concentration levels in honey were predicted using various ML regressors. Second, the six ranges of sugar were classified using various classifiers. Third, the 11 types of honey and 100% sugar were classified using classifiers. The stacking model (STM) obtained R2: 0.999, RMSE: 0.493 ml (v/v), RPD: 40.2, a 10-fold average R2: 0.996 and RMSE: 1.27 ml (v/v) for predicting 32 sugar concentrations. The STM achieved a Matthews Correlation Coefficient (MCC) of 99.7% and a Kappa score of 99.7%, a 10-fold average MCC of 98.9% and a Kappa score of 98.9% for classifying the six sugar ranges and 12 categories of honey types and a sugar.

Asunto(s)

RESUMEN

Vibration displacement is one of the key parameters in fault diagnosis of vibrating screens. Monitoring of acceleration signals of vibrating screens can be disturbed due to various factors such as on-site working conditions and equipment. In order to obtain accurate displacement signals of vibrating screen, the method for converting vibration acceleration to displacement based on improved Savitzky-Golay (S-G) filter is proposed. The Particle Swarm Optimization (PSO) algorithm is used to optimize the window length of the S-G filter with the fixed polynomial. The filters are cascaded to denoise the signals multiple times. The reasonable regularization parameter of the Smoothed Prior Approach (SPA) is calculated to remove the trend item from the acceleration signals. The vibration displacement is obtained by integrating the preprocessed acceleration data in the frequency domain. The results demonstrate that the objectivity of parameter selection of filter is improved, and the denoising effect is significant. The filtering effect of the filter is further improved after cascading. It becomes better as the number of stages of cascade increases. The vibration displacement can be obtained accurately by the proposed method. The vibration test platform is built to verify the correctness of the method.

RESUMEN

Objective. The T-wave in electrocardiogram (ECG) signal has the potential to enumerate various cardiac dysfunctions in the cardiovascular system. The primary objective of this research is to develop an efficient method for detecting T-waves in ECG signals, with potential applications in clinical diagnosis and continuous patient monitoring.Approach. In this work, we propose a novel algorithm for T-wave peak detection, which relies on a non-decimated stationary wavelet transform method (NSWT) and involves the cancellation of the QRS complex by utilizing its local extrema. The proposed scheme contains three stages: firstly, the technique is pre-processed using a two-stage median filter and Savitzky-Golay (SG) filter to remove the various artifacts from the ECG signal. Secondly, the NSWT technique is implemented using the bior 4.4 mother wavelet without downsampling, employing 24scale analysis, and involves the cancellation of QRS-complex using its local positions. After that, Sauvola technique is used to estimate the baseline and remove the P-wave peaks to enhance T-peaks for accurate detection in the ECG signal. Additionally, the moving average window and adaptive thresholding are employed to enhance and identify the location of the T-wave peaks. Thirdly, false positive T-peaks are corrected using the kurtosis coefficients method.Main results. The robustness and efficiency of the proposed technique have been corroborated by the QT database (QTDB). The results are also validated on a self-recorded database. In QTDB database, the sensitivity of 98.20%, positive predictivity of 99.82%, accuracy of 98.04%, and detection error rate of 1.95% have been achieved. The self-recorded dataset attains a sensitivity, positive predictivity, accuracy, and detection error rate of 99.94%, 99.96%, 99.90%, and 0.09% respectively.Significance. A T-wave peak detection based on NSWT and QRS complex cancellation, along with kurtosis analysis technique, demonstrates superior performance and enhanced detection accuracy compared to state-of-the-art techniques.

Asunto(s)

RESUMEN

Effective water quality prediction techniques are essential for the sustainable development of water resources and implementation of emergency response mechanisms. However, the water environment conditions are complex, and the presence of a large amount of noise in the water quality data makes it difficult to reveal the long-term trends or cycles of the data, affecting the acquisition of serial correlation in the data. In addition, the loss function based on the vertical Euclidean distance will produce a prediction lag problem, and it is difficult to make an accurate multi-step prediction of water quality series. This paper presents a multi-step water quality prediction model for watersheds that combines Savitzky-Golay (SG) filter with Transformer optimized networks. Among them, the SG filter highlights data trend change and improves sequence correlation by smoothing the potential noise of original data. The transformer network adopts a sequence-to-sequence framework, which contains a position encoding module and a self-attentive mechanism to perform multi-step prediction while effectively obtaining the sequence correlation. Moreover, the DIstortion Loss including shApe and TimE (DILATE) loss function is introduced into the model to solve the problem of prediction lag from two aspects of shape error and time error to improve the model's generalization ability. An example validates the model with the benchmark model at four monitoring stations in the Lanzhou section of the Yellow River basin in China. The results show that the predictions of the proposed model have the correct shape, temporal positioning, and the best accuracy in a multi-step prediction task for four sites. It can provide a decision-making basis for comprehensive water quality control and pollutant control in the basin.

Asunto(s)

RESUMEN

The predictive maintenance of electrical machines is a critical issue for companies, as it can greatly reduce maintenance costs, increase efficiency, and minimize downtime. In this paper, the issue of predicting electrical machine failures by predicting possible anomalies in the data is addressed through time series analysis. The time series data are from a sensor attached to an electrical machine (motor) measuring vibration variations in three axes: X (axial), Y (radial), and Z (radial X). The dataset is used to train a hybrid convolutional neural network with long short-term memory (CNN-LSTM) architecture. By employing quantile regression at the network output, the proposed approach aims to manage the uncertainties present in the data. The application of the hybrid CNN-LSTM attention-based model, combined with the use of quantile regression to capture uncertainties, yielded superior results compared to traditional reference models. These results can benefit companies by optimizing their maintenance schedules and improving the overall performance of their electric machines.

RESUMEN

An elegant, well-established effective data filter concept, proposed originally by Abraham Savitzky and Marcel J.E. Golay, is undoubtedly a very effective tool, however not free from limitations and drawbacks. Despite the latter, over the years it has become a "monopolist" in many fields of spectra processing, claiming a "commercial" superiority over alternative approaches, which would potentially allow to obtain equivalent or in some cases even more reliable results. In order to show that basic operations performed on spectral datasets, like smoothing or differentiation, do not have to be equated to the application of the one particular single algorithm, several of such alternatives are briefly presented within this paper and discussed with regard to their practical realization. A special emphasis is put on the fast Fourier methodology (FFT), being widespread in the general domain of signal processing. Finally, a user-friendly Matlab routine, in which the outlined algorithms are implemented, is shared, so that one can select and apply the technique of spectral data processing more adequate for their individual requirements without the need to code it prior to use.

RESUMEN

Cosmic ray neutron sensors (CRNS) are increasingly used to determine field-scale soil moisture (SM). Uncertainty of the CRNS-derived soil moisture strongly depends on the CRNS count rate subject to Poisson distribution. State-of-the-art CRNS signal processing averages neutron counts over many hours, thereby accounting for soil moisture temporal dynamics at the daily but not sub-daily time scale. This study demonstrates CRNS signal processing methods to improve the temporal accuracy of the signal in order to observe sub-daily changes in soil moisture and improve the signal-to-noise ratio overall. In particular, this study investigates the effectiveness of the Moving Average (MA), Median filter (MF), Savitzky-Golay (SG) filter, and Kalman filter (KF) to reduce neutron count error while ensuring that the temporal SM dynamics are as good as possible. The study uses synthetic data from four stations for measuring forest ecosystem-atmosphere relations in Africa (Gorigo) and Europe (SMEAR II (Station for Measuring Forest Ecosystem-Atmosphere Relations), Rollesbroich, and Conde) with different soil properties, land cover and climate. The results showed that smaller window sizes (12 h) for MA, MF and SG captured sharp changes closely. Longer window sizes were more beneficial in the case of moderate soil moisture variations during long time periods. For MA, MF and SG, optimal window sizes were identified and varied by count rate and climate, i.e., estimated temporal soil moisture dynamics by providing a compromise between monitoring sharp changes and reducing the effects of outliers. The optimal window for these filters and the Kalman filter always outperformed the standard procedure of simple 24-h averaging. The Kalman filter showed its highest robustness in uncertainty reduction at three different locations, and it maintained relevant sharp changes in the neutron counts without the need to identify the optimal window size. Importantly, standard corrections of CRNS before filtering improved soil moisture accuracy for all filters. We anticipate the improved signal-to-noise ratio to benefit CRNS applications such as detection of rain events at sub-daily resolution, provision of SM at the exact time of a satellite overpass, and irrigation applications.

Asunto(s)

RESUMEN

Bitcoin is a volatile financial asset that runs on a decentralized peer-to-peer Blockchain network. Investors need accurate price forecasts to minimize losses and maximize profits. Extreme volatility, speculative nature, and dependence on intrinsic and external factors make Bitcoin price forecast challenging. This research proposes a reliable forecasting framework by reducing the inherent noise in Bitcoin time series and by examining the predictive power of three distinct types of predictors, namely fundamental indicators, technical indicators, and univariate lagged prices. We begin with a three-step hybrid feature selection procedure to identify the variables with the highest predictive ability, then use Hampel and Savitzky-Golay filters to impute outliers and remove signal noise from the Bitcoin time series. Next, we use several deep neural networks tuned by Bayesian Optimization to forecast short-term prices for the next day, three days, five days, and seven days ahead intervals. We found that the Deep Artificial Neural Network model created using technical indicators as input data outperformed other benchmark models like Long Short Term Memory, Bi-directional LSTM (BiLSTM), and Convolutional Neural Network (CNN)-BiLSTM. The presented results record a high accuracy and outperform all existing models available in the past literature with an absolute percentage error as low as 0.28% for the next day forecast and 2.25% for the seventh day for the latest out of sample period ranging from Jan 1, 2021, to Nov 1, 2021. With contributions in feature selection, data-preprocessing, and hybridizing deep learning models, this work contributes to researchers and traders in fundamental and technical domains.

RESUMEN

The problem of entrainment is central to circadian biology. In this regard, Drosophila has been an important model system. Owing to the simplicity of its nervous system and the availability of powerful genetic tools, the system has shed significant light on the molecular and neural underpinnings of entrainment. However, much remains to be learned regarding the molecular and physiological mechanisms underlying this important phenomenon. Under cyclic light/dark conditions, Drosophila melanogaster displays crepuscular patterns of locomotor activity with one peak anticipating dawn and the other anticipating dusk. These peaks are characterized through an estimation of their phase relative to the environmental light cycle and the extent of their anticipation of light transitions. In Drosophila chronobiology, estimations of phases are often subjective, and anticipation indices vary significantly between studies. Though there is increasing interest in building flexible analysis tools in the field, none incorporates objective measures of Drosophila activity peaks in combination with the analysis of fly activity/sleep in the same program. To this end, we have developed PHASE, a MATLAB-based program that is simple and easy to use and (i) supports the visualization and analysis of activity and sleep under entrainment, (ii) allows analysis of both activity and sleep parameters within user-defined windows within a diurnal cycle, (iii) uses a smoothing filter for the objective identification of peaks of activity (and therefore can be used to quantitatively characterize them), and (iv) offers a series of analyses for the assessment of behavioral anticipation of environmental transitions.

Asunto(s)

RESUMEN

This paper presents a collection of electroencephalogram (EEG) data recorded from 40 subjects (female: 14, male: 26, mean age: 21.5 years). The dataset was recorded from the subjects while performing various tasks such as Stroop color-word test, solving arithmetic questions, identification of symmetric mirror images, and a state of relaxation. The experiment was primarily conducted to monitor the short-term stress elicited in an individual while performing the aforementioned cognitive tasks. The individual tasks were carried out for 25 s and were repeated to record three trials. The EEG was recorded using a 32-channel Emotiv Epoc Flex gel kit. The EEG data were then segmented into non-overlapping epochs of 25 s depending on the various tasks performed by the subjects. The EEG data were further processed to remove the baseline drifts by subtracting the average trend obtained using the Savitzky-Golay filter. Furthermore, the artifacts were also removed from the EEG data by applying wavelet thresholding. The dataset proposed in this paper can aid and support the research activities in the field of brain-computer interface and can also be used in the identification of patterns in the EEG data elicited due to stress.

RESUMEN

An improved Savitzky-Golay (S-G) filtering algorithm was developed to denoise the absorption spectroscopy of nitrogen oxide (NO2). A deep learning (DL) network was introduced to the traditional S-G filtering algorithm to adjust the window size and polynomial order in real time. The self-adjusting and follow-up actions of DL network can effectively solve the blindness of selecting the input filter parameters in digital signal processing. The developed adaptive S-G filter algorithm is compared with the multi-signal averaging filtering (MAF) algorithm to demonstrate its performance. The optimized S-G filtering algorithm is used to detect NO2 in a mid-quantum-cascade-laser (QCL) based gas sensor system. A sensitivity enhancement factor of 5 is obtained, indicating that the newly developed algorithm can generate a high-quality gas absorption spectrum for applications such as atmospheric environmental monitoring and exhaled breath detection.

Asunto(s)

RESUMEN

Face recognition is a well-researched domain however many issues for instance expression changes, illumination variations, and presence of occlusion in the face images seriously affect the performance of such systems. A recent survey shows that COVID-19 will also have a considerable and long-term impact on biometric face recognition systems. The work has presented two novel Savitzky-Golay differentiator (SGD) and gradient-based Savitzky-Golay differentiator (GSGD) feature extraction techniques to elevate issues related to face recognition systems. The SGD and GSGD feature descriptors are able to extract discriminative information present in different parts of the face image. In this paper, an efficient and robust person identification using symbolic data modeling approach and similarity analysis measure is devised and employed for feature representation and classification tasks to address the aforementioned issues of face recognition. Extensive experiments and comparisons of the proposed descriptors experimental results indicated that the proposed approaches can achieve optimal performance of 96-97, 92-96, 100, 84-93, and 87-96% on LFW, ORL, AR, IJB-A datasets, and newly devised VISA database, respectively.

RESUMEN

The performance of vehicle safety systems depends very much on the accuracy of the signals coming from vehicle sensors. Among them, the wheel speed is of vital importance. This paper describes a new method to obtain the wheel speed by using Sin-Cos encoders. The methodology is based on the use of the Savitzky-Golay filters to optimally determine the coefficients of the polynomials that best fit the measured signals and their time derivatives. The whole process requires a low computational cost, which makes it suitable for real-time applications. This way it is possible to provide the safety system with an accurate measurement of both the angular speed and acceleration of the wheels. The proposed method has been compared to other conventional approaches. The results obtained in simulations and real tests show the superior performance of the proposed method, particularly for medium and low wheel angular speeds.

RESUMEN

The article discusses an important issue in connection with the technique of mobile Global Navigation Satellite System (GNSS) measurements of railway track coordinates, which is digital filtering performed to precisely determine railway track axes. For this purpose, a measuring technique is proposed which bases on the use of a measuring platform with a number of appropriately distributed GNSS receivers, where two of them determine the directional base vector of the platform. The receivers used in the research had high measuring frequency in the Real Time Kinematic (RTK) operating mode and enabled correction of the obtained results in post-processing. A key problem discussed in the article is the method for assessing the quality of the measurement results obtained from GNSS receivers, and their preparation for further processing making use of geometrically constrained parameters of the base vector and specialized digital filtering, among other elements, to precisely determining the track axis. The obtained results confirm the applicability of the used method of GNSS signal processing.

RESUMEN

The Savitzky-Golay filter (SGF) is a time-domain technique that determines a trend line for a signal. The direct application of SGF for damage localization and quantification is investigated in this paper. Therefore, a single-stage trend line-based damage detection method employing SGF is proposed in which the damage is located and quantified at the bridge under moving load. A simply supported beam under moving sprung mass is numerically simulated to verify the proposed method. Four different velocities and five different single- and multi-damage scenarios are considered. The acceleration data along the beam are obtained, manually polluted with noise and their trend lines are then determined using SGF. The results show that the proposed method can accurately locate and quantify the damage using these trend lines. It is proved that the proposed method is insensitive to the noise and velocity variation in which having a constant velocity is a hard task before and after damage. Additionally, defining a normalization factor and fitting a Gaussian curve to this factor provide an estimation for the baseline and therefore, it categorizes the proposed method as baseline-free method.

RESUMEN

This paper covers a brief review of both the advantages and disadvantages of the implementation of various smoothing filters in the analysis of electroencephalography (EEG) data for the purpose of potential medical diagnostics. The EEG data are very prone to the occurrence of various internal and external artifacts and signal distortions. In this paper, three types of smoothing filters were compared: smooth filter, median filter and Savitzky-Golay filter. The authors of this paper compared those filters and proved their usefulness, as they made the analyzed data more legible for diagnostic purposes. The obtained results were promising, however, the studies on finding perfect filtering methods are still in progress.

Asunto(s)

RESUMEN

In today's world, cardiovascular diseases are prevalent becoming the leading cause of death; more than half of the cardiovascular diseases are due to Coronary Heart Disease (CHD) which generates the demand of predicting them timely so that people can take precautions or treatment before it becomes fatal. For serving this purpose a Modified Artificial Plant Optimization (MAPO) algorithm has been proposed which can be used as an optimal feature selector along with other machine learning algorithms to predict the heart rate using the fingertip video dataset which further predicts the presence or absence of Coronary Heart Disease in an individual at the moment. Initially, the video dataset has been pre-processed, noise is filtered and then MAPO is applied to predict the heart rate with a Pearson correlation and Standard Error Estimate of 0.9541 and 2.418 respectively. The predicted heart rate is used as a feature in other two datasets and MAPO is again applied to optimize the features of both datasets. Different machine learning algorithms are then applied to the optimized dataset to predict values for presence of current heart disease. The result shows that MAPO reduces the dimensionality to the most significant information with comparable accuracies for different machine learning models with maximum dimensionality reduction of 81.25%. MAPO has been compared with other optimizers and outperforms them with better accuracy.

Asunto(s)

RESUMEN

In this paper, a novel hybrid method combining adaptive chirp mode pursuit (ACMP) with an adaptive multiscale Savitzky-Golay filter (AMSGF) based on adaptive moving average (AMA) is proposed for offline denoising micro-electromechanical system (MEMS) gyroscope signal. The denoising scheme includes preliminary denoising and further denoising. At the preliminary denoising stage, the original gyroscope signal is decomposed into signal modes one by one using ACMP with modified stopping criterion based on mutual information. Useful information is extracted while most noise is discarded in the residue at this stage. Then, AMSGF is proposed to further denoise the signal modes. Sample variance based on AMA is used to adjust the window size of AMSGF adaptively. Practical MEMS gyroscope signal denoising results under different motion conditions show the superior performance of the proposed method over empirical mode decomposition (EMD)-based denoising, discrete wavelet threshold denoising, and variational mode decomposition (VMD)-based denoising. Moreover, AMSGF is proven to gain a better denoising effect than some other common smoothing methods.

RESUMEN

Electrocardiogram (ECG) sensing is an important application for the diagnosis of cardiovascular diseases. Recently, driven by the emerging technology of wearable electronics, massive wearable ECG sensors are developed, which however brings additional sources of noise contamination on ECG signals from these wearable ECG sensors. In this paper, we propose a new low-distortion adaptive Savitzky-Golay (LDASG) filtering method for ECG denoising based on discrete curvature estimation, which demonstrates better performance than the state of the art of ECG denoising. The standard Savitzky-Golay (SG) filter has a remarkable performance of data smoothing. However, it lacks adaptability to signal variations and thus often induces signal distortion for high-variation signals such as ECG. In our method, the discrete curvature estimation is adapted to represent the signal variation for the purpose of mitigating signal distortion. By adaptively designing the proper SG filter according to the discrete curvature for each data sample, the proposed method still retains the intrinsic advantage of SG filters of excellent data smoothing and further tackles the challenge of denoising high signal variations with low signal distortion. In our experiment, we compared our method with the EMD-wavelet based method and the non-local means (NLM) denoising method in the performance of both noise elimination and signal distortion reduction. Particularly, for the signal distortion reduction, our method decreases in MSE by 33.33% when compared to EMD-wavelet and by 50% when compared to NLM, and decreases in PRD by 18.25% when compared to EMD-wavelet and by 25.24% when compared to NLM. Our method shows high potential and feasibility in wide applications of ECG denoising for both clinical use and consumer electronics.

Asunto(s)