Abdul Majeed A. The classification of EEG-based winking signals: a transfer learning and random forest pipeline

Brain Computer-Interface (BCI) technology plays a considerable role in the control of rehabilitation or peripheral devices for stroke patients. This is particularly due to their inability to control such devices from their inherent physical limitations after such an attack. More often than not, the control of such devices exploits electroencephalogram (EEG) signals. Nonetheless, it is worth noting that the extraction of the features and the classification of the signals is non-trivial for a successful BCI system. The use of Transfer Learning (TL) has been demonstrated to be a powerful tool in the extraction of essential features. However, the employment of such a method towards BCI applications, particularly in regard to EEG signals, are somewhat limited. The present study aims to evaluate the effectiveness of different TL models in extracting features for the classification of wink-based EEG signals. The extracted features are classified by means of fine-tuned Random Forest (RF) classifier. The raw EEG signals are transformed into a scalogram image via Continuous Wavelet Transform (CWT) before it was fed into the TL models, namely InceptionV3, Inception ResNetV2, Xception and MobileNet. The dataset was divided into training, validation, and test datasets, respectively, via a stratified ratio of 60:20:20. The hyperparameters of the RF models were optimised through the grid search approach, in which the five-fold cross-validation technique was adopted. The optimised RF classifier performance was compared with the conventional TL-based CNN classifier performance. It was demonstrated from the study that the best TL model identified is the Inception ResNetV2 along with an optimised RF pipeline, as it was able to yield a classification accuracy of 100% on both the training and validation dataset. Therefore, it could be established from the study that a comparable classification efficacy is attainable via the Inception ResNetV2 with an optimised RF pipeline. It is envisaged that the implementation of the proposed architecture to a BCI system would potentially facilitate post-stroke patients to lead a better life quality.

Changes in precipitation amounts and extremes across Xinjiang (northwest China) and their connection to climate indices

Xinjiang is a major part of China’s arid region and its water resource is extremely scarcity. The change in precipitation amounts and extremes is of significant importance for the reliable management of regional water resources in this region. Thus, this study explored the spatiotemporal changes in extreme precipitation using the Mann–Kendall (M–K) trend analysis, mutation test, and probability distribution functions, based on the observed daily precipitation data from 89 weather stations in Xinjiang, China during 1961–2018. We also examined the correlations between extreme precipitation and climate indices using the cross-wavelet analysis. The results indicated that the climate in Xinjiang is becoming wetter and the intensity and frequency of extreme precipitation has begun to strengthen, with these trends being more obvious after the 1990s. Extreme precipitation trends displayed spatial heterogeneity in Xinjiang. Extreme precipitation was mainly concentrated in mountainous areas, northern Xinjiang, and western Xinjiang. The significant increasing trend of extreme precipitation was also concentrated in the Tianshan Mountains and in northern Xinjiang. In addition, the climate indices, North Atlantic Oscillation, Atlantic Multidecadal Oscillation, Multivariate ENSO Index and Indian Ocean Dipole Index had obvious relationships with extreme precipitation in Xinjiang. The relationships between the extreme precipitation and climate indices were not clearly positive or negative, with many correlations advanced or delayed in phase. At the same time, extreme precipitation displayed periodic changes, with a frequency of approximately 1–3 or 4–7 years. These periodic changes were more obvious after the 1990s; however, the exact mechanisms involved in this require further study.

Time-frequency scattering accurately models auditory similarities between instrumental playing techniques

Instrumentalplaying techniques such as vibratos, glissandos, and trills often denote musical expressivity, both in classical and folk contexts. However, most existing approaches to music similarity retrieval fail to describe timbre beyond the so-called "ordinary" technique, use instrument identity as a proxy for timbre quality, and do not allow for customization to the perceptual idiosyncrasies of a new subject. In this article, we ask 31 human participants to organize 78 isolated notes into a set of timbre clusters. Analyzing their responses suggests that timbre perception operates within a more flexible taxonomy than those provided by instruments or playing techniques alone. In addition, we propose a machine listening model to recover the cluster graph of auditory similarities across instruments, mutes, and techniques. Our model relies on joint time-frequency scattering features to extract spectrotemporal modulations as acoustic features. Furthermore, it minimizes triplet loss in the cluster graph by means of the large-margin nearest neighbor (LMNN) metric learning algorithm. Over a dataset of 9346 isolated notes, we report a state-of-the-art average precision at rank five (AP@5) of 99.0%±1. An ablation study demonstrates that removing either the joint time-frequency scattering transform or the metric learning algorithm noticeably degrades performance.

The application of continuous wavelet transform based on spectrophotometric method and high-performance liquid chromatography for simultaneous determination of anti-glaucoma drugs in eye drop

In this study, a fast, low-cost, accurate, and precise spectrophotometric method based on the continuous wavelet transform (CWT) was assayed to determine dorzolamide (DOR) and timolol (TIM) in an eye drop sample simultaneously. Different wavelet families were investigated to select the best family for analyzing the DOR and TIM. The Mexican hat wavelet (MHW) family with the wavelength of 281 nm and Gaussian wavelet family (gaus2) in the wavelength of 267 nm were found for the simultaneous analysis of DOR and TIM, respectively. Mean recovery values of synthetic mixtures were found 97.44%±2.63 and 99.18%±4.00 for DOR and TIM, respectively. The root mean square errors (RMSE) of DOR and TIM were achieved 0.5550 and 0.3306, respectively. Eye drop as a real sample was analyzed by spectrophotometry coupled with the CWT technique, as well as high-performance liquid chromatography (HPLC) as a reference method. The obtained results were compared with each other by the one-way analysis of variance (ANOVA) test and there was no significant difference between them.

Continuous wavelet transform analysis of ERG in patients with diabetic retinopathy

PURPOSE

Diabetic retinopathy (DR) is one of the leading causes of blindness worldwide. Non-proliferative diabetic retinopathy (NPDR) is a stage of the disease that contains morphological and functional disruption of the retinal vasculature and dysfunction of retinal neurons. This study aimed to compare time and time-frequency-domain analysis in the evaluation of electroretinograms (ERGs) in subjects with NPDR.

METHOD

The ERG responses were recorded in 16 eyes from 12 patients with NPDR and 24 eyes from 12 healthy subjects as the control group. The implicit time, amplitude, and time-frequency-domain parameters of photopic and scotopic ERGs were analyzed.

RESULTS

The implicit times of b-waves in the dark-adapted 10.0 (P = 0.0513) and light-adapted 3.0 (P = 0.0414) were significantly increased in the NPDR group. The amplitudes of a- and b-wave showed a significantly decreased dark-adapted 10.0 (P = 0.0212; P = 0.0133) and light-adapted 3.0 (P = 0.0517; P = 0.0021) ERG of the NPDR group. The Cohen's d effect size had higher values in the amplitude of dark-adapted 10.0 b-wave (|d|= 1.8058) and amplitude of light-adapted 3.0 b-wave (|d|= 1.9662). The CWT results showed that the frequency ranges of the dominant components in dark-adapted 10.0 and light-adapted 3.0 ERG were decreased in the NPDR group compared to the healthy group (P < 0.05). The times associated with the NDPR group's dominant components were increased compared to normal eyes in both dark-adapted 10.0 and light-adapted 3.0 ERG (P < 0.05). All Cohen's d effect sizes of the implicit times and dominant frequency components were on a large scale (|d|> 1).

CONCLUSION

These findings suggest that the time and time-frequency parameters of both photopic and scotopic ERGs can be good indicators for DR. However, time-frequency-domain analysis could present more information might be helpful in the assessment of the DR severity.

Understanding the complexity of the structures in alcohol solutions by temperature-dependent near-infrared spectroscopy

For understanding the structures and the hydrogen bonding in alcohol solutions, the changes of the structures and hydrogen bonding with temperature were studied by temperature-dependent near-infrared (NIR) spectroscopy. The spectral features of eight alcohol species including the monomer, dimer and linear or cyclic aggregates (trimer, tetramer and polymer) were found from the resolution-enhanced spectra calculated by continuous wavelet transform. The changes of the eight species with concentration and temperature were analyzed using the intensity variation of the corresponding spectral features and two-dimensional correlation NIR spectroscopy. The aggregates were found to form at a very low concentration and the stability of the seven aggregates with temperature was found in an order of cyclic tetramer > linear polymer > linear tetramer > cyclic trimer > linear trimer > cyclic polymer > dimer. Furthermore, the formation of the aggregates was found to be affected by the chain length. The increase of the chain length is beneficial for the formation of cyclic tetramer and polymer due to the hydrophobic effect, but is an adverse effect for the formation of linear polymer.

Classification of ischemic and non-ischemic cardiac events in Holter recordings based on the continuous wavelet transform

Holter recordings are widely used to detect cardiac events that occur transiently, such as ischemic events. Much effort has been made to detect early ischemia, thus preventing myocardial infarction. However, after detection, classification of ischemia has still not been fully solved. The main difficulty relies on the false positives produced because of non-ischemic events, such as changes in the heart rate, the intraventricular conduction or the cardiac electrical axis. In this work, the classification of ischemic and non-ischemic events from the long-term ST database has been improved, using novel spectral parameters based on the continuous wavelet transform (CWT) together with temporal parameters (such as ST level and slope, T wave width and peak, R wave peak, QRS complex width). This was achieved by using a nearest neighbour classifier of six neighbours. Results indicated a sensitivity and specificity of 84.1% and 92.9% between ischemic and non-ischemic events, respectively, resulting a 10% increase of the sensitivity found in the literature. Extracted features based on the CWT applied on the ECG in the frequency band 0.5-4 Hz provided a substantial improvement in classifying ischemic and non-ischemic events, when comparing with the same classifier using only temporal parameters. Graphical Abstract In this work it is improved the classification of ischemic and non-ischemic events. The main difficulty of ischemic detectors relies on the false positives produced because of non-ischemic events. After a preprocessing stage, temporal and spectral parameters are extracted from events of the Long Term ST Database. The novel parameters proposed in this work are extracted from the Continuous Wavelet Transform. A nearest Neighbor Classifier is used, obtaining a sensitivity and specificity of 84.1% and 92.9%, respectively.

Temporal evolution characteristics of PM2.5 concentration based on continuous wavelet transform

Fine particulate matter (PM2.5) is an important haze index, and the researches on the evolutionary characteristics of the PM2.5 concentration will provide a fundamental and guiding prerequisite for the haze prediction. However, the past researchers were usually based on the overall time-domain evolution information of PM2.5. Since the temporal evolution of PM2.5 concentration is nonstationary, previous studies might neglect some important localization features that the evolution has various predominant periods at different scales. Therefore, we applied the wavelet transform to study the localized intermittent oscillations of PM2.5. First, we analyze the daily average PM2.5 concentration collected from the automatic monitoring stations. The result reveals that the predominant oscillation period does vary with time. There exist multiple oscillation periods on the scale of 14-32 d, 62-104 d, 105-178 d and 216-389 d and the 298d is the first dominant period in the entire evolutionary process. Moreover, we want to figure out whether the temporal characteristics of PM2.5 in the days with heavy haze also have localized intermittent periodicities. We select the hourly average PM2.5 concentration in 120 h when the haze pollution is serious. We find that the principal period has experienced two abrupt shifts and the energy at the 63-hour scale is the most powerful. The results in these two independent analyses come into the same conclusion that the multiscale features shown in the temporal evolution of PM2.5 cannot be ignored and may play an important role in the further haze prediction.

DeepFHR: intelligent prediction of fetal Acidemia using fetal heart rate signals based on convolutional neural network

Background

Fetal heart rate (FHR) monitoring is a screening tool used by obstetricians to evaluate the fetal state. Because of the complexity and non-linearity, a visual interpretation of FHR signals using common guidelines usually results in significant subjective inter-observer and intra-observer variability. Objective: Therefore, computer aided diagnosis (CAD) systems based on advanced artificial intelligence (AI) technology have recently been developed to assist obstetricians in making objective medical decisions.

Methods

In this work, we present an 8-layer deep convolutional neural network (CNN) framework to automatically predict fetal acidemia. After signal preprocessing, the input 2-dimensional (2D) images are obtained using the continuous wavelet transform (CWT), which provides a better way to observe and capture the hidden characteristic information of the FHR signals in both the time and frequency domains. Unlike the conventional machine learning (ML) approaches, this work does not require the execution of complex feature engineering, i.e., feature extraction and selection. In fact, 2D CNN model can self-learn useful features from the input data with the prerequisite of not losing informative features, representing the tremendous advantage of deep learning (DL) over ML.

Results

Based on the test open-access database (CTU-UHB), after comprehensive experimentation, we achieved better classification performance using the optimal CNN configuration compared to other state-of-the-art methods: the averaged ten-fold cross-validation of the accuracy, sensitivity, specificity, quality index defined as the geometric mean of the sensitivity and specificity, and the area under the curve yielded results of 98.34, 98.22, 94.87, 96.53 and 97.82%, respectively

Conclusions

Once the proposed CNN model is successfully trained, the corresponding CAD system can be served as an effective tool to predict fetal asphyxia objectively and accurately.

A spectrophotometric method for simultaneous determination of trace ions of copper, cobalt, and nickel in the zinc sulfate solution by ultraviolet-visible spectrometry

In the zinc sulfate solution, the concentration ratio of zinc to metal ion impurities can be up to 10⁵, which causes impurity ion signals to be severely masked by the zinc signal. In particular, nickel exhibits a strong nonlinearity. Conventional spectroscopic methods are commonly used to detect multi-component analytes with similar concentrations and require the detection component to be linear to satisfy Beer-Lambert law. In order to solve high concentration ratio and nonlinear problems, a spectrophotometric method combining the extended Kalman filter and derivative methods is proposed to simultaneously determine copper, cobalt and nickel in the zinc sulfate solution by ultraviolet-visible spectroscopy. The derivative method developed by using continuous wavelet transform with a Haar wavelet function was applied to detect copper and cobalt in regions with wavelengths greater than 500nm, in which the absorbance of zinc and nickel changed to a fixed value, where linear regression graphs for copper and cobalt were established at zero-crossing wavelengths. Extended Kalman filter spectrophotometry is a filtering algorithm for nonlinear systems, so it was proposed to iteratively detect nickel concentration. The detection range was found to be 0.5-5mg/L for copper, 0.3-3mg/L for cobalt, and 0.6-6mg/L. The predicted root mean square error was 0.097 for copper, 0.049 for cobalt, and 0.206 for nickel. The average relative deviations of copper, cobalt, and nickel in 10 sets of mixed solutions were 3.19%, 2.23%, and 4.56%, respectively. The spectrophotometric method studied is suitable for real-time detection and control of trace amounts of copper, cobalt, and nickel in purification process of zinc hydrometallurgy, and can be applied to more fields.

An efficient automatic arousals detection algorithm in single channel EEG

BACKGROUND AND OBJECTIVE

Electroencephalographic arousal is a transient waveform that instantaneously happens in sleep as an inherent component. It has distinctive amplitude and frequency features. However, it is visually difficult to distinguish arousal from the background of the electroencephalogram. This visual scoring is important for brain researches, sleep studies, sleep stage scorings and assessment of sleep disorders. The scoring process is a time-consuming and difficult clinical procedure which is evaluated by sleep experts. It may also have subjective consequences due to the variability of personal expertise of physicians. Conversely, this scoring process can be significantly accelerated with computer-aided automated algorithms. Moreover, reproducible and objective results can be obtained. In this work, we propose a novel algorithm for the automatic detection of electroencephalographic arousals in sleep polysomnographic recordings.

METHODS

The approach uses a well-known time-frequency localization method, the continuous wavelet transform, to identify relevant arousal patterns. Special emphasis was carried out to produce a robust, reliable, fast and artifact tolerant algorithm. In the first part, the electroencephalographic scalogram, the squared magnitude of the continuous wavelet transform, was obtained. The mean and variance of the scalogram coefficients were determined as novel features. Support vector machine was applied as a classifier. Half of the recordings were used for training with five-fold cross-validation and a high accuracy training rate was obtained. Then, the rest of the recordings were used for testing.

RESULTS

As a result, the overall sensitivity, specificity, accuracy, and positive predictive value of the algorithm are 94.67%, 99.33%, 98.2%, and 97.93%, respectively.

CONCLUSION

In this paper, we have shown that the electroencephalographic arousal pattern can be characterized by the scalogram in the wavelet domain. The proposed algorithm works with high accuracy, reproducibility and gives objective results without case-specific sensitivity.

High order derivative to investigate the complexity of the near infrared spectra of aqueous solutions

Derivative calculation is a powerful method for resolution enhancement in spectral analysis. A high order derivative method based on continuous wavelet transform (CWT) is discussed in the analysis of near infrared (NIR) spectra. The results for a simulated spectrum obtained from conventional numerical differentiation (NM), Fourier transform (FT), Savitzky-Golay (SG) and CWT method were compared. CWT method was found to be as efficient as FT and SG, but easier for high order derivative computation, and the fourth order derivative was proved to be a good choice for resolution enhancement as well as reduction of noise and sidelobe effects. For the NIR spectra of water-ethanol mixtures, the complexity of the spectra can be observed from the fourth derivative, including the spectral features of OH and CH with various intermolecular interactions. Fitting the derivative spectra of the mixtures by those of pure water and ethanol, the obtained coefficients for ethanol show a linear relation with the content but that for water exhibit a non-linear relation, which reveals the influence of ethanol on water structure in the mixture. Furthermore, the information of the water-ethanol clusters was found in the residual spectra after the fitting. Therefore, high order derivative can be an efficient way to improve the resolution of NIR spectra for understanding the interactions in aqueous solutions.

Time-frequency analysis for bearing fault diagnosis using multiple Q-factor Gabor wavelets

Rolling element bearings are key and also vulnerable machine elements in rotating machinery. Fault diagnosis of rolling element bearings is significant for guaranteeing machinery safety and functionality. To accurately extract bearing diagnostic information, a time-frequency analysis method based on continuous wavelet transform (CWT) and multiple Q-factor Gabor wavelets (MQGWs) (termed CMQGWT) is introduced in this paper. In the CMQGWT method, Gabor wavelets with multiple Q-factors are adopted and sets of the continuous wavelet coefficients for each Q-factor are combined to generate time-frequency map. By this way, the resolution of the CWT time-frequency map can be greatly increased and the diagnostic information can be accurately identified. Numerical simulation is carried out and verified the effectiveness of the proposed method. Case studies and comparisons with the continuous Morlet wavelet transform (CMWT) and the tunable Q-factor wavelet transform (TQWT) demonstrate the effectiveness and superiority of the CMQGWT for bearing diagnostic information extraction and fault identification.

Hyperspectral inversion of heavy metal content in reclaimed soil from a mining wasteland based on different spectral transformation and modeling methods

Conventional methods for investigating heavy metal contamination in soil are time consuming and expensive. We explored reflectance spectroscopy as an alternative method for assessing heavy metals. Four spectral transformation methods, first-order differential (FDR), second-order differential (SDR), continuum removal (CR) and continuous wavelet transform (CWT), are used for the original spectral data. Spectral preprocessing effectively eliminated the noise and baseline drifting and also highlighted the locations of the spectral feature bands. Partial least squares regression (PLSR) and radial basis function neural network (RBF) were used to study the hyperspectral inversion of four heavy metals (Cr, As, Ni, Cd). The inversion models of four heavy metals were established in the bands with the highest correlation coefficient. The inversion effects were evaluated by the coefficient of determination (R²), root mean square error (RMSE) and residual predictive deviation (RPD) indexes. The R values of the correlation coefficient were significantly improved after smoothing and spectral transformation compared to the original waveband. The method combining continuous wavelet transform (CWT) with radial basis function neural network (RBF) had the best inversion effect on the four heavy metals. When compared to partial least squares regression (PLSR), the RMSE values were reduced by approximately 2. The CWT-RBF method can be used as a means of inversion of heavy metals in mining wasteland reclaimed land.

A comparative study of different aspects in manipulating ratio spectra used for the analysis of cefradine in the presence of its alkaline degradation product

Six stability-indicating UV-spectrophotometric methods manipulating ratio spectra were utilized for the analysis of cefradine in presence of its alkaline degradate. These methods are different forms of transformations; ratio difference, mean centering, derivative ratio using numerical differentiation, derivative ratio using Savitsky-Golay filter, continuous wavelet transform and derivative continuous wavelet transform. Water was used as a solvent and the linearity ranges were 6-26 μg/mL. Determination of accuracy and precision for the suggested procedures were executed. Assessment of specificity was run through analyzing laboratory prepared mixtures containing cefradine and its alkaline degradate. The suggested methods were useful for cefradine estimation in tablets. Statistically, the outputs obtained from the recommended and published methods reveal no significant differences.

Quantifying Movement in Preterm Infants Using Photoplethysmography

Long-term recordings of movement in preterm infants might reveal important clinical information. However, measurement of movement is limited because of time-consuming and subjective analysis of video or reluctance to attach additional sensors to the infant. We evaluated whether photoplethysmogram (PPG), routinely used for oximetry in preterm infants in the neonatal intensive care unit (NICU), can provide reliable long-term measurements of movement. In 18 infants [mean post-conceptional age (PCA) 31.10 weeks, range 29-34.29 weeks], we designed and tested a wavelet-based algorithm that detects movement signals from the PPG. The algorithm's performance was optimized relative to subjective assessments of movement using video and accelerometers attached to two limbs and force sensors embedded within the mattress (five infants, three raters). We then applied the optimized algorithm to infants receiving routine care in the NICU without additional sensors. The algorithm revealed a decline in brief movements (< 5 s) with increasing PCA (13 infants, r = - 0.87, p < 0.001, PCA range 27.3-33.9 weeks). Our findings suggest that quantitative relationships between motor activity and clinical outcomes in preterm infants can be studied using routine photoplethysmography.

Use of continuous wavelet transform approach for simultaneous quantitative determination of multicomponent mixture by UV-Vis spectrophotometry

In the present paper, a multicomponent analysis approach based on spectrophotometry method was developed for simultaneous determination of Guaifenesin (GU), Chlorpheniramine (CHL) and Pseudoephedrine (PSE) without any separation steps. The method under study is signal processing method based on Continuous Wavelet Transform (CWT) coupled with zero cross point technique. In this paper, CWT method was tested by synthetic ternary mixtures and was applied to the commercial cough syrup as a real sample and assessed by applying the standard addition technique. For demonstrate the accuracy of the results, other applications of signal processing, such as Derivative Transform (DT), Partial Least Squares (PLS) regression and Principal Components Regression (PCR) were used as comparative methods. Afterwards, the obtained results from analyzing the cough syrup by all methods were compared to the High-Performance Liquid Chromatography (HPLC) as a reference method. One-way analysis of variance test at 95% confidence level showed no significant differences between CWT and other applications.

Intra-annual groundwater levels and water temperature patterns in raised bogs affected by human impact in mountain areas in Poland

Over the last century, the vast majority of peatlands in Europe have experienced substantial transformation as a result of drainage works that led to an imbalance in the natural hydrologic regime as well as changes in vegetation composition. The ongoing study aims to reconstruct the natural hydrologic regime of peatlands and restore their typical vegetation communities. In this study, we examine the variability of groundwater levels and groundwater temperature in raised bogs located in the Bieszczady Mts. in southern Poland. Both groundwater table levels and groundwater temperature serve to characterise the hydrology of peatlands, which in turn is critical for plant growth and rates of relevant biochemical processes. Our objective is to determine the predominant scale of intra-annual variability in time series and identify their potential sources by assessing the adaptive response of peat bogs to key changes in weather conditions. For this purpose, data obtained from 9 monitoring wells located in peat bogs, with a varying degree of degradation, were used. Fluctuations in time series and potential linkages between selected variables were analysed in the frequency domain using the continuous wavelet transform. The results show that peat bogs exhibit a relatively high stability of groundwater table levels and groundwater temperature despite meaningful changes in weather conditions. The most visible response of peat bogs to weather conditions was observed in summer and autumn. Our study demonstrates that degraded peat bogs experience the largest decrease in groundwater table levels and more frequent fluctuations. In contrast, groundwater temperature remained stable throughout the year at all the studied bog sites.

Improved analysis of ground vibrations produced by man-made sources

Man-made sources of ground vibration must be carefully monitored in urban areas in order to ensure that structural damage and discomfort to residents is prevented or minimised. The research presented in this paper provides a comparative evaluation of various methods used to analyse a series of tri-axial ground vibration measurements generated by rail, road, and explosive blasting. The first part of the study is focused on comparing various techniques to estimate the dominant frequency, including time-frequency analysis. The comparative evaluation of the various methods to estimate the dominant frequency revealed that, depending on the method used, there can be significant variation in the estimates obtained. A new and improved analysis approach using the continuous wavelet transform was also presented, using the time-frequency distribution to estimate the localised dominant frequency and peak particle velocity. The technique can be used to accurately identify the level and frequency content of a ground vibration signal as it varies with time, and identify the number of times the threshold limits of damage are exceeded.

Application of wavelet and Fuorier transforms as powerful alternatives for derivative spectrophotometry in analysis of binary mixtures: A comparative study

Two signal processing methods, namely, Continuous Wavelet Transform (CWT) and the second was Discrete Fourier Transform (DFT) were introduced as alternatives to the classical Derivative Spectrophotometry (DS) in analysis of binary mixtures. To show the advantages of these methods, a comparative study was performed on a binary mixture of Naltrexone (NTX) and Bupropion (BUP). The methods were compared by analyzing laboratory prepared mixtures of the two drugs. By comparing performance of the three methods, it was proved that CWT and DFT methods are more efficient and advantageous in analysis of mixtures with overlapped spectra than DS. The three signal processing methods were adopted for the quantification of NTX and BUP in pure and tablet forms. The adopted methods were validated according to the ICH guideline where accuracy, precision and specificity were found to be within appropriate limits.

Different spectrophotometric methods applied for the analysis of simeprevir in the presence of its oxidative degradation product: Acomparative study

Five simple spectrophotometric methods were developed for the determination of simeprevir in the presence of its oxidative degradation product namely, ratio difference, mean centering, derivative ratio using the Savitsky-Golay filters, second derivative and continuous wavelet transform. These methods are linear in the range of 2.5-40μg/mL and validated according to the ICH guidelines. The obtained results of accuracy, repeatability and precision were found to be within the acceptable limits. The specificity of the proposed methods was tested using laboratory prepared mixtures and assessed by applying the standard addition technique. Furthermore, these methods were statistically comparable to RP-HPLC method and good results were obtained. So, they can be used for the routine analysis of simeprevir in quality-control laboratories.

Unsupervised detection and removal of muscle artifacts from scalp EEG recordings using canonical correlation analysis, wavelets and random forests

OBJECTIVE

This paper proposes supervised and unsupervised algorithms for automatic muscle artifact detection and removal from long-term EEG recordings, which combine canonical correlation analysis (CCA) and wavelets with random forests (RF).

METHODS

The proposed algorithms first perform CCA and continuous wavelet transform of the canonical components to generate a number of features which include component autocorrelation values and wavelet coefficient magnitude values. A subset of the most important features is subsequently selected using RF and labelled observations (supervised case) or synthetic data constructed from the original observations (unsupervised case). The proposed algorithms are evaluated using realistic simulation data as well as 30min epochs of non-invasive EEG recordings obtained from ten patients with epilepsy.

RESULTS

We assessed the performance of the proposed algorithms using classification performance and goodness-of-fit values for noisy and noise-free signal windows. In the simulation study, where the ground truth was known, the proposed algorithms yielded almost perfect performance. In the case of experimental data, where expert marking was performed, the results suggest that both the supervised and unsupervised algorithm versions were able to remove artifacts without affecting noise-free channels considerably, outperforming standard CCA, independent component analysis (ICA) and Lagged Auto-Mutual Information Clustering (LAMIC).

CONCLUSION

The proposed algorithms achieved excellent performance for both simulation and experimental data. Importantly, for the first time to our knowledge, we were able to perform entirely unsupervised artifact removal, i.e. without using already marked noisy data segments, achieving performance that is comparable to the supervised case.

SIGNIFICANCE

Overall, the results suggest that the proposed algorithms yield significant future potential for improving EEG signal quality in research or clinical settings without the need for marking by expert neurophysiologists, EMG signal recording and user visual inspection.

Spectrophotometric determination of meclizine hydrochloride and pyridoxine hydrochloride in laboratory prepared mixtures and in their pharmaceutical preparation

In this paper, three rapid, simple, accurate and precise spectrophotometric methods were developed for the determination of meclizine hydrochloride in the presence of pyridoxine hydrochloride without previous separation. The methods under study are dual wavelength (DWL), ratio difference (RD) and continuous wavelet transform (CWT). On the other hand, pyridoxine hydrochloride (PYH) was determined directly at 291nm. The methods obey Beer's law in the range of (5-50μg/mL) for both compounds. All the methods were validated according to the ICH guidelines where the accuracy was found to be 98.29, 99.59, 100.42 and 100.62% for DWL, RD, CWT and PYH; respectively. Moreover the precision of the methods were calculated in terms of %RSD and it was found to be 0.545, 0.372, 1.287 and 0.759 for DWL, RD,CWT and PYH; respectively. The selectivity of the proposed methods was tested using laboratory prepared mixtures and assessed by applying the standard addition technique. So, they can be used for the routine analysis of pyridoxine hydrochloride and meclizine hydrochloride in quality-control laboratories.

Investigating the Structural Change in Protein Aqueous Solution Using Temperature-Dependent Near-Infrared Spectroscopy and Continuous Wavelet Transform

The circulatory protein, human serum albumin (HSA), is widely used as a model protein for the study of protein structure. In this work, the structures of human serum albumin in aqueous solutions are studied using temperature-dependent near-infrared (NIR) spectroscopy with the aid of continuous wavelet transform (CWT). Near-infrared spectra of human serum albumin solutions with different concentrations were measured over a temperature range of 30-85 ℃. Then, continuous wavelet transform was performed on the spectra to enhance the resolution. As a result of the resolution enhancement, spectral bands around 4361, 4521, 4600 and 4260 cm^-1 were extracted from the overlapping low-resolution signals. The four bands can be assigned to the protein structures of α-helix, β-sheet, an intermediate state and side chains, respectively. The variations in intensity of the bands around 4361 and 4521 cm^-1 with temperature show that the increase of temperature leads to the loss of α-helical structure but the formation of β-sheet, and the denaturation temperature of human serum albumin is about 55 ℃. The variation of the band around 4600 cm^-1 indicates that the temperature-induced unfolding process of human serum albumin occurs through a stable intermediate state, and a significant change in the microenvironment of the side chains about 63 ℃ is observed from the variation of the band around 4260 cm^-1. On the other hand, the transformed spectra in the region of 8000-5600 cm^-1 provide an explicit evidence for the structural changes of water during the process of protein denaturation, and the unfolding process of HSA can be reflected by these changes.

Improved protein-protein interactions prediction via weighted sparse representation model combining continuous wavelet descriptor and PseAA composition

Background

Protein-protein interactions (PPIs) are essential to most biological processes. Since bioscience has entered into the era of genome and proteome, there is a growing demand for the knowledge about PPI network. High-throughput biological technologies can be used to identify new PPIs, but they are expensive, time-consuming, and tedious. Therefore, computational methods for predicting PPIs have an important role. For the past years, an increasing number of computational methods such as protein structure-based approaches have been proposed for predicting PPIs. The major limitation in principle of these methods lies in the prior information of the protein to infer PPIs. Therefore, it is of much significance to develop computational methods which only use the information of protein amino acids sequence.

Results

Here, we report a highly efficient approach for predicting PPIs. The main improvements come from the use of a novel protein sequence representation by combining continuous wavelet descriptor and Chou’s pseudo amino acid composition (PseAAC), and from adopting weighted sparse representation based classifier (WSRC). This method, cross-validated on the PPIs datasets of Saccharomyces cerevisiae, Human and H. pylori, achieves an excellent results with accuracies as high as 92.50%, 95.54% and 84.28% respectively, significantly better than previously proposed methods. Extensive experiments are performed to compare the proposed method with state-of-the-art Support Vector Machine (SVM) classifier.

Conclusions

The outstanding results yield by our model that the proposed feature extraction method combing two kinds of descriptors have strong expression ability and are expected to provide comprehensive and effective information for machine learning-based classification models. In addition, the prediction performance in the comparison experiments shows the well cooperation between the combined feature and WSRC. Thus, the proposed method is a very efficient method to predict PPIs and may be a useful supplementary tool for future proteomics studies.