Savitzky-Golay Filter Research Articles

Coinciding Diabetic Retinopathy and Diabetic Macular Edema Grading With Rat Swarm Optimization Algorithm for Enhanced Capsule Generation Adversarial Network.

In the worldwide working-age population, visual disability and blindness are common conditions caused by diabetic retinopathy (DR) and diabetic macular edema (DME). Nowadays, due to diabetes, many people are affected by eye-related issues. Among these, DR and DME are the two foremost eye diseases, the severity of which may lead to some eye-related problems and blindness. Early detection of DR and DME is essential to preventing vision loss. Therefore, an enhanced capsule generation adversarial network (ECGAN) optimized with the rat swarm optimization (RSO) approach is proposed in this article to coincide with DR and DME grading (DR-DME-ECGAN-RSO-ISBI 2018 IDRiD). The input images are obtained from the ISBI 2018 unbalanced DR grading data set. Then, the input fundus images are preprocessed using the Savitzky-Golay (SG) filter filtering technique, which reduces noise from the input image. The preprocessed image is fed to the discrete shearlet transform (DST) for feature extraction. The extracting features of DR-DME are given to the ECGAN-RSO algorithm to categorize the grading of DR and DME disorders. The proposed approach is implemented in Python and achieves better accuracy by 7.94%, 36.66%, and 4.88% compared to the existing models, such as the combined DR with DME grading for the cross-disease attention network (DR-DME-CANet-ISBI 2018 IDRiD), category attention block for unbalanced grading of DR (DR-DME-HDLCNN-MGMO-ISBI 2018 IDRiD), combined DR-DME classification with a deep learning-convolutional neural network-based modified gray-wolf optimizer with variable weights (DR-DME-ANN-ISBI 2018 IDRiD).

Drilling Rate of Penetration Prediction Based on CBT-LSTM Neural Network

Due to the uncertainty of the subsurface environment and the complexity of parameters, particularly in feature extraction from input data and when seeking to understand bidirectional temporal information, the evaluation and prediction of the rate of penetration (ROP) in real-time drilling operations has remained a long-standing challenge. To address these issues, this study proposes an improved LSTM neural network model for ROP prediction (CBT-LSTM). This model integrates the capability of a two-dimensional convolutional neural network (2D-CNN) for multi-feature extraction, the advantages of bidirectional long short-term memory networks (BiLSTM) for processing bidirectional temporal information, and the dynamic weight adjustment of the time pattern attention mechanism (TPA) for extracting crucial information in BiLSTM, effectively capturing key features in temporal data. Initially, data are denoised using the Savitzky–Golay filter, and five correlation coefficient methods are employed to select input features, with principal component analysis (PCA) used to reduce model complexity. Subsequently, a sliding window approach transforms the time series into a two-dimensional structure to capture dynamic changes, constructing the model input. Finally, the ROP prediction model is established, and search methods are utilized to identify the optimal hyperparameter combinations. Compared with other neural networks, CBT-LSTM demonstrates superior performance metrics, with MAE, MAPE, RMSE, and R2 values of 0.0295, 0.0357, 9.3101%, and 0.9769, respectively, indicating the highest predictive capability. To validate the model’s robustness, noise was introduced into the training data, and results show stable performance. Furthermore, the model’s predictive results for other wells achieved R2 values of 0.95, confirming its strong generalization ability. This method provides a new solution for ROP prediction in real-time drilling operations, assisting drilling engineers in better planning their operations and reducing drilling cycles.

Deep Learning Ensemble for Flood Probability Analysis

Predicting flood events is complex due to uncertainties from limited gauge data, high data and computational demands of traditional physical models, and challenges in spatial and temporal scaling. This research innovatively uses only three remotely sensed and computed factors: rainfall, runoff and temperature. We also employ three deep learning models—Feedforward Neural Network (FNN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM)—along with a deep neural network ensemble (DNNE) using synthetic data to predict future flood probabilities, utilizing the Savitzky–Golay filter for smoothing. Using a hydrometeorological dataset from 1993–2022 for the Nile River basin, six flood predictors were derived. The FNN and LSTM models exhibited high accuracy and stable loss, indicating minimal overfitting, while the CNN showed slight overfitting. Performance metrics revealed that FNN achieved 99.63% accuracy and 0.999886 ROC AUC, CNN had 95.42% accuracy and 0.893218 ROC AUC, and LSTM excelled with 99.82% accuracy and 0.999967 ROC AUC. The DNNE outperformed individual models in reliability and consistency. Runoff and rainfall were the most influential predictors, while temperature had minimal impact.

Detecting and sizing the Earth with PLATO: A feasibility study based on solar data

The PLAnetary Transits and Oscillations of stars (PLATO) mission will observe the same area of the sky continuously for at least two years in an effort to detect transit signals of an Earth-like planet orbiting a solar-like star. We aim to study how short-term solar-like variability caused by oscillations and granulation would affect PLATO's ability to detect and size Earth if PLATO were to observe the Solar System itself. We also compare different approaches to mitigate noise caused by short-term solar-like variability and perform realistic transit fitting of transit signals in PLATO-like light curves. We injected Earth-like transit signals onto real solar data taken by the Helioseismic and Magnetic Imager (HMI) instrument on board the Solar Dynamics Observatory (SDO). We isolated short-term stellar variability in the HMI observations by removing any variability with characteristic timescales longer than five hours using a smooth Savitzky-Golay filter. We then added a noise model for a variety of different stellar magnitudes computed by assuming an observation by all 24 normal cameras. We first compared four different commonly used treatments of correlated noise in the time domain by employing them in a transit fitting scheme. We then tried to recover pairs of transit signals using an algorithm similar to the transit least squares algorithm. Finally, we performed transit fits using realistic priors on planetary and stellar parameters and assessed how accurately the pair of two injected transits was recovered. We find that short-term solar-like variability affects the correct retrieval of Earth-like transit signals in PLATO data. Variability models accounting for variations with typical timescales at the order of one hour are sufficient to mitigate these effects. We find that when the limb-darkening coefficients of the host star are properly constrained, the impact parameter does not negatively affect the detectability of a transit signal or the retrieved transit parameters, except for high values ($b > 0.8$). For bright targets (8.5 - 10.5 mag), the transit signal of an Earth analogue can reliably be detected in PLATO data. For faint targets a detection is still likely, though the results of transit search algorithms have to be verified by transit-fitting algorithms to avoid false positive detections being flagged. For bright targets (V-mag leq 9.5), the radius of an Earth-like planet orbiting a solar-like star can be correctly determined at a precision of 3<!PCT!> or less, assuming that at least two transit events are observed and the characteristics of the host star are well understood.

Signal Acquisition and Algorithm Design for Bioimpedance-Based Heart Rate Estimation from the Wrist

Background: Heart rate (HR) is a critical biomarker that provides insights into overall health, stress levels, and the autonomic nervous system. Pulse wave signals contain valuable information about the cardiovascular system and heart status. However, signal acquisition in wearables poses challenges, particularly when using electrical sensors, due to factors like the distance from the heart, body movement, and suboptimal electrode placement. Methods: Electrical bioimpedance (EBI) measurements using bipolar and tetrapolar electrode systems were employed for pulse wave signal acquisition from the wrist in both perpendicular and distal configurations. Signal preprocessing techniques, including baseline removal via Hankel matrix methods, normalization, cross-correlation, and peak detection, were applied to improve signal quality. This study describes the combination of sensor-level signal acquisition and processing for accurate wearable HR estimation. Results: The bipolar system was shown to produce larger ΔZ(t), while the tetrapolar system demonstrated higher sensitivity. Distal placement of the electrodes yielded greater ΔZ(t) (up to 0.231 Ω) when targeting both wrist arteries. Bandpass filtering resulted in a better signal-to-noise ratio (SNR), achieving 3.6 dB for the best bipolar setup and 4.8 dB for the tetrapolar setup, compared to 2.6 and 3.3 dB SNR, respectively, with the Savitzky–Golay filter. The custom HR estimation algorithm presented in this paper demonstrated improved accuracy over a reference method, achieving an average error of 1.8 beats per minute for the best bipolar setup, with a mean absolute percentage error (MAPE) of 8%. Conclusions: The analysis supports the feasibility of using bipolar electrode setups on the wrist and highlights the importance of electrode positioning relative to the arteries. The proposed signal processing method, featuring a preprocessing pipeline and HR estimation algorithm, provides a proof-of-concept demonstration for HR estimation from EBI signals acquired at the wrist.

Determination of steady-state for continuous powder mixing: Analysis of mixture properties and signal processing

Continuous powder mixing offers many advantages over batch processes, but its industrial implementation requires control of transient phases due to startup or variations in operating conditions. Detecting the steady-state by observing the mixture properties, obtained through in-line analysis of the mixture composition, is challenging due to the significant fluctuations in these properties. However, there is no quantitative method for identifying the steady-state for continuous powder mixing. We therefore propose in this work a methodology for steady-state detection by comparing several methods of mixture property analysis and signal processing. We show that conventional methods of mixture property analysis cannot reliably and accurately detect steady-state. We conclude that the best methodology is to perform signal processing on the content of the key component in the mixture. To do this, the signal of the content of the key component is first smoothed by the Savitzky-Golay filter. Then, the standard deviation of the filtered signal is compared with a tuning parameter to detect the beginning of steady-state. This method could be used to determine the mixing conditions leading to the smallest startup time, hence avoiding costly waste.

Intelligent filtering of field data

In the oil and gas industry, the measured parameters during oil and gas production are often affected by noise, which contributes to complex and non-monotonic dynamics. This makes manual analysis and interpretation extremely difficult. Therefore, this article aims to develop an algorithm capable of identifying and removing noise (signal changes without a clear cause) in the production parameters of well operation. The article examines data smoothing methods, including moving average, exponential smoothing, Kalman filter, Wiener filter, Savitzky-Golay filter, Fourier transform, and wavelet transform. The authors identified advantages and limitations. An alternative approach is proposed, combining machine learning methods with standard data filtering tools. The developed algorithm restores the true dynamics of well performance metrics and filters out and smooths noise related to technical malfunctions. The novelty of the algorithm lies in using an LSTM neural network to extract the trend component from noisy dynamics, taking into account events occurring at the well itself as well as events happening at surrounding wells.

Rapid determination of the geographical origin of kimchi by Fourier transform near-infrared spectroscopy coupled with chemometric techniques.

Determining the geographical origin of kimchi holds significance because of the considerable variation in quality and price among kimchi products from different regions. This study explored the feasibility of employing Fourier transform near-infrared spectroscopy in conjunction with supervised chemometric techniques to differentiate domestic and imported kimchi products. A total of 30 domestic and 30 imported kimchi products were used to build datasets. Three categories of preprocessing methods such as scattering correction (multiplicative signal correction and standard normal variate), spectral derivatives (the first derivative and the second derivative), and data smoothing (Savitzky-Golay filtering and Norris derivative filtering) were used. K-nearest neighbors, support vector machine, random forest, and partial least squares-discriminant analysis were employed. By appropriately preprocessing spectral data, these four methods successfully distinguished between the two sample groups based on their origin. Notably, the k-nearest neighbors method exhibited exceptional performance, accurately classifying the sample groups irrespective of the preprocessing method employed and swiftly achieving this classification. In comparison, classification and regression tree as well as naïve Bayes methods were outperformed by the aforementioned four classification techniques. Particularly, the efficiency and accuracy of the k-nearest neighbors method make it the most recommended chemometric tool for determining the geographical origins of kimchi.

State of Health Estimation of Lithium-Ion Battery Using Multi-Health Features Based on Savitzky–Golay Filter and Fitness-Distance Balance- and Lévy Roulette-Enhanced Coyote Optimization Algorithm-Optimized Long Short-Term Memory

Accurate and reliable state of health (SOH) estimation is extremely crucial for the safe and stable operation of lithium-ion batteries (LIBs). In this paper, a method based on Lévy roulette- and fitness-distance balance-enhanced coyote optimization algorithm-optimized long short-term memory (LRFDBCOA-LSTM) is employed for SOH estimation of LIB. Firstly, six health features are extracted from battery charging and discharging data, and Savitzky–Golay is used to filter the feature data to improve correlation between feature and SOH. Then, Lévy roulette and fitness-distance balance (FDB) strategies are used to improve the coyote optimization algorithm (COA), i.e., LRFDBCOA. Meanwhile, the improved algorithm is used to optimize the internal parameters of long short-term memory (LSTM) neural network. Finally, the effectiveness of the proposed model is comprehensively validated using five evaluation indicators based on battery data obtained under three different testing conditions. The experimental results manifest that after algorithm improvement and network parameter optimization, the performance of the model is significantly improved. In addition, the method has high estimation accuracy, strong generalization, and strong robustness for SOH estimation with a maximum R2 of 0.9896 and minimum R2 of no less than 0.9711.

Automated prediction of phosphorus concentration in soils using reflectance spectroscopy and machine learning algorithms

A method is presented for predicting total phosphorus concentration in soils from Santander de Quilichao, Colombia, using a UV-VIS V-750 Spectrophotometer and machine learning techniques. A total of 152 soil samples, prepared with varying proportions of P2O5 fertilizer and soil, were analyzed, obtaining reflectance spectra in the 200 to 900 nm range with 3501 wavelengths. Additionally, 152 laboratory results of total phosphorus concentration were used to train the prediction model. The spectra were filtered using a Savitzky-Golay filter. Key wavelengths were identified using Variable Importance in Projection - Partial Least Squares (VIP-PLS) and Random Forest (RF), reducing the spectral bands to 1085. Principal Component Analysis (PCA) further reduced data dimensionality. A feedforward artificial neural network was then trained to predict phosphorus concentration. This method is faster than traditional lab tests by leveraging advanced data analysis and machine learning, offering results in less time. While sample preparation remains consistent with standard spectroscopic analysis, the value added by the proposed method lies in its data processing and interpretation. Currently applied to a single soil type, future improvements will include more soil types and other macronutrients, enhancing nutrient management in agriculture. Accurate macronutrient measurements aid in better fertilizer uses planning.• Filtering spectra and determining relevant wavelengths using VIP-PLS and RF.• Dimensionality reduction with PCA.• Training feedforward artificial neural networks.

A method for predicting remaining useful life using enhanced Savitzky–Golay filter and improved deep learning framework

Ensuring operational integrity in large-scale equipment hinges on effective fault prediction and health management. Prognostics and health management (PHM) face the challenge of accurately predicting remaining useful life (RUL) using multivariate sensor data. Traditional methods often require extensive prior knowledge for indicator construction and processing. Deep learning offers a promising alternative. This study presents a multi-channel multi-scale deep learning approach. Initially, an improved Savitzky‒Golay filter (ISG) addresses challenges posed by large and rapidly changing data volumes, enhancing data preprocessing. Subsequently, a framework integrates convolutional neural networks (CNNs) with long short-term memory (LSTM) to capture hierarchical signal information and make integrated predictions. The CNN extracts spatial features from multi-channel input data, while the LSTM captures temporal dependencies. By fusing outputs from both components, the framework enhances predictive accuracy and robustness for complex operational datasets. Experimental validation on the C-MAPSS dataset tests various fusion methods and CNN depths, determining parameters and evaluating filtering effectiveness. Comparative analyses show promising performance, particularly under dynamic conditions. While not optimal for predicting multiple fault types, it outperforms classical algorithms, especially in single fault type prediction tasks.

Utilizing X-ray diffraction in conjunction with competitive adaptive reweighted sampling (CARS) and principal component analysis for the discrimination of medicinal pearl powder and nacre powder.

Nacre powder, often utilized to counterfeit medicinal pearl powder due to their similar chemical composition and appearance, poses a challenge in product authentication. This study introduces a rapid and efficient method for distinguishing between medicinal pearl powder and nacre powder using X-ray diffraction in conjunction with principal component analysis (PCA). The X-ray diffraction pattern underwent preprocessing techniques including smoothing denoising (Savitzky-Golay filter, 5-point) and second-order derivative analysis. Subsequently, PCA was employed for dimensionality reduction modeling. The CARS method was applied to select optimal variables for model refinement, determining the data preprocessing approach and key modeling variables. This method demonstrates the capability to accurately differentiate between pearl powder, nacre powder, and even counterfeit samples containing up to 90% pearl powder. With a high accuracy rate, swift operational speed, and potential for automation, this approach shows promise for practical implementation in the realm of pearl powder quality control.

A Novel Method for Online Diagnostic Analysis of Partial Discharge in Instrument Transformers and Surge Arresters from the Correlation of HFCT and IEC Methods

In this work, a new methodology is proposed for the online and non-invasive extraction of partial discharge (PD) pulses from raw measurement data obtained using a simplified setup. This method enables the creation of sub-windows with optimized size, each containing a single candidate PD pulse. The proposed approach integrates mathematical morphological filtering (MMF) with kurtosis, a first-order Savitzky-Golay smoothing filter, the Otsu method for thresholding, and a specific technique to associate each sub-window with the phase angle of the applied voltage waveform, enabling the construction of phase-resolved PD (PRPD) patterns. The methodology was validated against a commercial PD detection device adhering to the IEC (International Electrotechnical Commission) standard. Experimental results demonstrated that the proposed method, utilizing an off-the-shelf 8-bit resolution data acquisition system and a low-cost high-frequency current transformer (HFCT) sensor, effectively diagnoses and characterizes PD activity in high-voltage equipment, such as surge arresters and instrument transformers, even in noisy environments. It was able to characterize PD activity using only a few cycles of the applied voltage waveform and identify low amplitude PD pulses with low signal-to-noise ratio signals. Other contribution of this work is the diagnosis and fault signature obtained from a real surge arrester (SA) with a nominal voltage of 192 kV, corroborated by destructive disassembly and internal inspection of the tested equipment. This work provides a cost-effective and accurate tool for real-time PD monitoring, which can be embedded in hardware for continuous evaluation of electrical equipment integrity.

Low-Cost Electronic Nose for Robusta and Arabica Coffee Classification Using 1-D Convolutional Neural Networks

Abstract The use of an electronic nose (e-nose) employing MQ-series sensors has become increasingly popular due to its cost-effectiveness. However, the impact of varying sampling durations on its performance, particularly in distinguishing between Robusta and Arabica coffee, has not been extensively studied. This research investigates how different sampling durations affect the e-nose’s classification accuracy. The study utilizes a 1D Convolutional Neural Network (1D-CNN) and a Support Vector Machine (SVM), with both models enhanced by a Savitzky-Golay filter to reduce noise and improve data quality. Feature selection techniques are applied to address data complexity and improve model performance. The experimental results indicate that the 1D-CNN model achieves optimal accuracy of up to 100% at a sampling duration of 200 seconds, while the SVM reaches approximately 92% accuracy under the same conditions. Notably, for applications requiring faster processing times, the SVM proves to be more effective, achieving 70% accuracy at a 20-second sampling interval, compared to 60% for the 1D-CNN. The study demonstrates that integrating MQ sensors in e-nose systems can yield effective classification results for coffee varieties, even with shorter sampling times. These findings have the potential to influence the development of cost-effective e-nose devices, making them more accessible to small and medium-sized industrial enterprises.

Improving Radio Signal from Baghdad University Radio Telescope Using the Savitzky-Golay Filter

Astronomical radio observations from a small radio telescope suffer from various types of noise. Hence, astronomers continuously search for new techniques to eliminate or reduce such noise and obtain more accurate results. This research investigates the impact of implementing the Savitzky-Golay filter on enhancing radio observation signals retrieved from the Baghdad University Radio Telescope (BURT). Observations from BURT were carried out for different Galactic coordinates, and then a MATLAB code was written and used to implement the Savitzky-Golay filter for the collected data. This process provides an assessment of the ability of the filter to reduce noise and improve the quality of the signal. The results of this research clearly showed that applying the Savitzky-Golay filter reduces the noise and enhances the signal of astronomical radio observations. However, the filter should be used appropriately to preserve the original features of the signal. In conclusion, the filter is considered an efficient tool for enhancing the radio signal by reducing the noise and smoothing the signal. Therefore, the filter provides a substantial contribution and improvement to the field of radio astronomy.

An Improved LandTrendr Algorithm for Forest Disturbance Detection Using Optimized Temporal Trajectories of the Spectrum: A Case Study in Yunnan Province, China

Forest disturbance mapping plays an important role in furthering our understanding of forest dynamics. The Landsat-based detection of Trends in Disturbance and Recovery (LandTrendr) algorithm is widely used in forest disturbance mapping. However, it neglects the quality of the temporal trajectory and its change trends for forest disturbance mapping. Therefore, the aim of this paper is to improve LandTrendr (iLandTrendr) for forest disturbance mapping by optimizing its temporal trajectories and the post-processing of detection results. Specifically, the temporal trajectory of complex forest disturbance types was optimized using the Savitzky–Golay (SG) filter with constraints. That is, the smooth value generated from the SG filter for the disturbance year was replaced by the satellite observations when the nonlinear abrupt signals were included in the multi-temporal data. The forest disturbance detected by LandTrendr was further modified using the consistency of spectral variation trends. A case study using iLandTrendr to detect forest disturbance in Yunnan Province was conducted. Compared to the LandTrendr method, which has an overall accuracy (OA) of 35.88%, iLandTrendr generated forest disturbance mapping with an OA of 89.32%, which was significantly higher. The total mapped area of disturbance was 1,985,820.9 km2, accounting for 49.69% of the total area. The disturbances were predominately caused by natural factors, such as wildfires, pests and diseases, and forest degradation, accounting for 85.31% of the total disturbed area. iLandTrendr can quickly and accurately detect the occurrence year of complex forest disturbance types and can be extended for the forest disturbance mapping of a large area.

Enhancing pressure transient analysis in reservoir characterization through deep learning neural networks

Deep learning neural networks exhibit remarkable efficiency in numerous tasks within machine learning applications across various disciplines, including reservoir engineering. Traditional pressure transient analysis (PTA) methodologies, however, are challenged by limitations such as human error in accurately estimating critical reservoir parameters like permeability and wellbore damage (skin). In this study, we evaluate the efficiency and accuracy of various machine learning models in pressure transient analysis (PTA) tasks. Our investigation initially focused on integrating Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to enhance the precision in estimating reservoir parameters and identifying reservoir models. However, through comprehensive testing and validation using simulated well-test data and out-of-distribution samples, we discovered that tree-based models, specifically XGBoost and Random Forest, exhibit superior performance, particularly in generalization tasks. These models outperform CNN-LSTM and 1D-CNN models, demonstrating enhanced robustness and accuracy in handling diverse and unseen data, thereby addressing traditional challenges in pressure transient analysis more effectively. Moreover, Savitzky–Golay Filters were used to handle the noise problems of data, and this method proved effective for data with noise levels up to a standard deviation of 2. Compared with other models, the XGBoost model has a better performance in reservoir model identification with an out-of-distribution accuracy of 92%. On the other hand, Random Forest showed a remarkable result in the task of reservoir parameter estimation, especially for the permeability and skin with out-of-distribution R2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$R^2$$\\end{document} of 98% and 97%, respectively. The findings of this study can help for a better understanding of the different deep learning models and their applications in pressure transient analysis. Specifically, the superior performance of the tree-based models in overcoming traditional pressure transient analysis challenges demonstrates their potential to enhance reservoir characterization predictions. Employing these advanced machine learning techniques can significantly reduce human error, increase the accuracy of parameter estimation, and improve the analysis process, thereby aiding strategic decision-making in reservoir management

Smoothing of the Noisy Lithium-ion Battery Surface Temperature Data Based on Savitzky–Golay (SG) Filter

As the charging current and surrounding temperatures rise concurrently in an electric vehicle's (EV) battery pack, the battery temperature increases abruptly beyond safe limits. The battery is susceptible to triggering thermal runaway at higher temperatures, leading to battery damage and even an explosion. The control system depends on these measurement data from the sensors to prevent dangerous situations and maximize the performance and cycle life of batteries. However, traditional noisy temperature measurement sensors in a real application, such as thermistors and thermocouples, are extensively used. In this paper, the experimental setup, the heat pipe-based battery thermal management system (BTMS) was designed and experimented with high input power. The battery was sandwiched with heat pipes, and heated at 30, 40, 50, and 60 W. The Savitzky-Golay filter technique is applied to the noisy temperature data of the surface temperature of the lithium-ion batteries (LIBs) used to estimate the condition of the battery. According to this study, the start-up time parameter in battery thermal management can be controlled by the Savitzky-Golay filter. This will attenuate random temperature fluctuations of battery temperature noise and avoid the cooling system from being falsely triggered. The results are measured by the signal-to-noise (SNR) to demonstrate the ability of the Savitzky-Golay filter to eliminate noise

Authentication of the shelf-life of NPH injectable insulins samples using NIR and MS spectral fingerprints

Insulin is essential for regulating glucose levels, and its hormonal deficiency leads to diabetes. Treatment involves the use of different types of insulin tailored to individual needs. Properly stored and transported Neutral Protamine Hagedorn (NPH) insulin remains effective and stable, highlighting the importance of quality control to ensure its efficacy and patient safety. This study aims to develop an analytical method to evaluate the shelf-life of NPH injectable insulin samples while preserving packaging integrity. The approach consisted of analyzing intact insulin samples, with and without expired shelf-life dates, using near-infrared spectroscopy (NIR) obtained from two instruments: a benchtop and a portable device. These measurements were coupled with chemometric methods, specifically single-class classification algorithms. The classifiers considered were Data Driven-Soft Independent Modeling of Class Analogy (DD-SIMCA) and One-Class Partial Least Squares (OC-PLS). For benchtop NIR, the DD-SIMCA method, with Savitzky-Golay smoothing preprocessing (41-point window) and baseline offset (BO), achieved excellent results, reaching 100% sensitivity, specificity, and efficiency in both training and test sets. As for portable NIR, the most effective methods were DD-SIMCA and OC-PLS, using datasets preprocessed with Savitzky-Golay smoothing with first derivative, second-order polynomial (SGD-1st-2nd), and 9-point windows combined with Standard Normal Variate (SNV), and Savitzky-Golay smoothing filters (SGS) using second-order polynomial and 7-point windows combined with baseline offset (BO) and Multiplicative Scattering Correction (MSC). The results were corroborated by mass spectrometry, correlating the structural changes of degraded insulin with NIR data. The proposed methodology is a promising tool for non-destructive, rapid, and cost-effective authentication of the preservation state of NPH insulin, aligning with green chemistry principles and allowing for in-situ evaluation, thereby preserving medication integrity.

Innovative strategies for protein content determination in dried laver (Porphyra spp.): Evaluation of preprocessing methods and machine learning algorithms through short-wave infrared imaging

In this study, we explored the application of Short-Wave Infrared (SWIR) hyperspectral imaging combined with Competitive Adaptive Reweighted Sampling (CARS) and advanced regression models for the non-destructive assessment of protein content in dried laver. Utilizing a spectral range of 900–1700 nm, we aimed to refine the quality control process by selecting informative wavelengths through CARS and applying various preprocessing techniques (standard normal variate [SNV], Savitzky-Golay filtering [SG], Orthogonal Signal Correction [OSC], and StandardScaler [SS]) to enhance the model's accuracy. The SNV-OSC-StandardScaler- Support vector regression (SVR) model trained on CARS-selected wavelengths significantly outperformed the other configurations, achieving a prediction determination coefficient (Rp2) of 0.9673, root mean square error of prediction of 0.4043, and residual predictive deviation of 5.533. These results highlight SWIR hyperspectral imaging's potential as a rapid and precise tool for assessing dried laver quality, aiding food industry quality control and dried laver market growth.