Tremor Estimation and Removal in Robot-Assisted Surgery Using Improved Enhanced Band-Limited Multiple Fourier Linear Combiner.

BACKGROUND: During a robot-assisted minimally invasive surgery, hand tremors in a surgeon's manipulation of the master manipulator can cause vibrations of the slave surgical instruments. METHODS: This letter addresses this problem by proposing an improved Enhanced Band-Limited Multiple Linear Fourier Combiner (E-BMFLC) algorithm for filtering the physiological tremor signals of a surgeon's hand. The proposed method uses the amplitude of the input signal to adapt the learning rate and a dense division of the combiner bands for the higher amplitude bands of the tremor signals. RESULTS: By using the proposed improved E-BMFLC algorithm, the compensation accuracy can be improved by 4.5%-8.9%, as well as a spatial position error of less than 1 mm. CONCLUSION: The results show that among all filtering methods, the improved E-BMFLC filtering method has the highest number of successful experiments and the lowest experimental time.

Enhanced forecasting of chlorophyll-a concentration in coastal waters through integration of Fourier analysis and Transformer networks.

The accurate prediction of chlorophyll-a (chl-a) concentration in coastal waters is essential to coastal economies and ecosystems as it serves as the key indicator of harmful algal blooms. Although powerful machine learning methods have made strides in forecasting chl-a concentrations, there remains a gap in effectively modeling the dynamic temporal patterns and dealing with data noise and unreliability. To wiggle out of quagmires, we introduce an innovative deep learning prediction model (termed ChloroFormer) by integrating Transformer networks with Fourier analysis within a decomposition architecture, utilizing coastal in-situ data from two distinct study areas. Our proposed model exhibits superior capabilities in capturing both short-term and middle-term dependency patterns in chl-a concentrations, surpassing the performance of six other deep learning models in multistep-ahead predictive accuracy. Particularly in scenarios involving extreme and frequent blooms, our proposed model shows exceptional predictive performance, especially in accurately forecasting peak chl-a concentrations. Further validation through Kolmogorov-Smirnov tests attests that our model not only replicates the actual dynamics of chl-a concentrations but also preserves the distribution of observation data, showcasing its robustness and reliability. The presented deep learning model addresses the critical need for accurate prediction on chl-a concentrations, facilitating the exploration of marine observations with complex dynamic temporal patterns, thereby supporting marine conservation and policy-making in coastal areas.

Cortical bone plate properties assessment using inversion of axially transmitted low frequency ultrasonic guided waves.

Over the past few decades, early osteoporosis detection using ultrasonic bone quality evaluation has gained prominence. Specifically, various studies focused on axial transmission using ultrasonic guided waves and have highlighted this technique's sensitivity to intrinsic properties of long cortical bones. This work aims to demonstrate the potential of low-frequency ultrasonic guided waves to infer the properties of the bone inside which they are propagating. A proprietary ultrasonic transducer, tailored to transmit ultrasonic guided waves under 500 kHz, was used for the data collection. The gathered data underwent two-dimensional fast Fourier transform processing to extract experimental dispersion curves. The proposed inversion scheme compares experimental dispersion curves with simulated dispersion curves calculated through the semi-analytical iso-geometric analysis (SAIGA) method. The numerical model integrates a bone phantom plate coupled with a soft tissue layer on its top surface, mimicking the experimental bone phantom plates. Subsequently, the mechanical properties of the bone phantom plates were estimated by reducing the misfit between the experimental and simulated dispersion curves. This inversion leaned heavily on the dispersive trajectories and amplitudes of ultrasonic guided wave modes. Results indicate a marginal discrepancy under 5% between the mechanical properties ascertained using the SAIGA-based inversion and those measured using bulk wave pulse-echo measurements.

Comparison of axial length and anterior segment parameters of patients with myopia measured using 2 fourier-domain optical coherent biometry devices.

BACKGROUND: This study assessed the agreement of ocular parameters of patients with myopia measured using Colombo intraocular lens (IOL) 2 and IOLMaster 700. METHODS: Eighty patients (male, 22; average age, 29.14 ± 7.36 years) with myopia (159 eyes) were included in this study in May 2023. The participants' axial length (AXL), central corneal thickness (CCT), lens thickness (LT), white-to-white distance (WTW), front flat (K1), steep (K2), mean (Km) corneal keratometry, astigmatism (Astig), J0 vector, and J45 vector were measured using the IOLMaster 700 and Colombo IOL 2. The measurements from both devices were compared using the generalized estimating equation, correlation analysis, and Bland-Altman plots. RESULTS: With the Colombo IOL 2, lower values for K2 and J0 (odds ratio [OR] = 0.587, p = 0.033; OR = 0.779, p < 0.0001, respectively), and larger values for WTW, Astig, and J45 (OR = 1.277, OR = 1.482, OR = 1.1, all p < 0.0001) were obtained. All ocular measurements by both instruments showed positive correlations, with AXL demonstrating the strongest correlation (r = 0.9996, p < 0.0001). The intraclass correlation coefficients for AXL and CCT measured by both instruments was 0.999 and 0.988 (both p < 0.0001), and Bland-Altman plot showed 95% limits of agreement (LoA) of -0.078 to 0.11 mm and - 9.989 to 13.486 µm, respectively. The maximum absolute 95% LoA for LT, WTW, K1, K2, and J0 were relatively high, achieving 0.829 mm, 0.717 mm, 0.983 D, 0.948 D, and 0.632 D, respectively. CONCLUSIONS: In young patients with myopia, CCT and AXL measurements obtained with the Colombo IOL 2 and IOLMaster 700 were comparable. However, WTW, LT, corneal refractive power, and astigmatism values could not be used interchangeably in clinical practice.

Correction of preferred orientation-induced distortion in cryo-electron microscopy maps.

Reconstruction maps of cryo-electron microscopy (cryo-EM) exhibit distortion when the cryo-EM dataset is incomplete, usually caused by unevenly distributed orientations. Prior efforts had been attempted to address this preferred orientation problem using tilt-collection strategy and modifications to grids or to air-water interfaces. However, these approaches often require time-consuming experiments, and the effect was always protein dependent. Here, we developed a procedure containing removing misaligned particles and an iterative reconstruction method based on signal-to-noise ratio of Fourier component to correct this distortion by recovering missing data using a purely computational algorithm. This procedure called signal-to-noise ratio iterative reconstruction method (SIRM) was applied on incomplete datasets of various proteins to fix distortion in cryo-EM maps and to a more isotropic resolution. In addition, SIRM provides a better reference map for further reconstruction refinements, resulting in an improved alignment, which ultimately improves map quality and benefits model building.

Improvement of image quality for bright-blood image in VISIBLE (volume isotropic simultaneous interleaved bright- and black-blood examination) by using k-space reordering and startup echoes.

PURPOSE: A volume isotropic simultaneous interleaved bright- and black-blood examination (VISIBLE) can simultaneously acquire images with suppressed vascular signals (black-blood images) and images without suppression (bright-blood images). We aimed to improve of the bright-blood images by adjusting the k-space filling and using startup echo. METHODS: The k-space arrangement of bright-blood images in the conventional VISIBLE followed a low-to-high frequency order, whereas that in the proposed VISIBLE sequence was in the reversed order, and a startup echo was added. The effects of startup echo on the signal-to-noise ratio (SNR) were evaluated using phantoms, considering both white matter (WM) and post-contrast blood. Data from copper sulfate phantoms were acquired in 1D Fourier transform mode using both the conventional and proposed methods of the two VISIBLE sequences. The signal behavior with each sequence was evaluated. Fourteen patients with a total of 21 metastases were included in the study. For each patient, VISIBLE images of both conventional and proposed methods were obtained consecutively after the contrast agent administration. Using clinical images, we conducted a comparison of the SNR and contrast-to-noise ratio (CNR) for tumors, normal WM, and blood vessels between the conventional and proposed VISIBLE sequences. RESULTS: There was no significant difference in SNRs for both black- and bright-blood images between the conventional sequence and the proposed sequence with different number of startup echoes, however, the SNR of the proposed sequence decreased with increasing number of startup echoes in both black- and bright-images. The signal behavior of the bright-blood image reached a "steady state" when the startup echo exceeded 20. The SNRs of blood vessels in the bright-blood images did not differ significantly between conventional and proposed VISIBLE sequences. The SNRs of WM in the bright-blood images was significantly larger in the conventional sequence than in the proposed sequence. The SNRs of tumors in bright blood images was significantly larger in the proposed sequence than in the conventional sequence. The CNRs between tumors and WM, vessels and WM in the bright-blood images were significantly higher in the proposed sequence than in the conventional sequence. CONCLUSION: The use of the startup echo in combination with the high-to-low frequency k-space ordering method resulted in improved CNR of the bright-blood images in the VISIBLE sequence.

Metagenomic and FT-ICR MS insights into the mechanism for the arsenic biogeochemical cycling in groundwater.

Arsenic (As) is a groundwater contaminant of global concern. The degradation of dissolved organic matter (DOM) can provide a reducing environment for As release. However, the interaction of DOM with local microbial communities and how different sources and types of DOM influence the biotransformation of As in aquifers is uncertain. This study used optical spectroscopy, Fourier transform ion cyclotron resonance mass spectrometry (FT-ICR MS), metagenomics, and structural equation modeling (SEM) to demonstrate the how the biotransformation of As in aquifers is promoted. The results indicated that the DOM in high-As groundwater is dominated by highly unsaturated low-oxygen(O) compounds that are quite humic and stable. Metagenomics analysis indicated Acinetobacter, Pseudoxanthomonas, and Pseudomonas predominate in high-As environments; these genera all contain As detoxification genes and are members of the same phylum (Proteobacteria). SEM analyses indicated the presence of Proteobacteria is positively related to highly unsaturated low-O compounds in the groundwater and conditions that promote arsenite release. The results illustrate how the biogeochemical transformation of As in groundwater systems is affected by DOM from different sources and with different characteristics.

Identification and Removal of Pollen Spectral Interference in the Classification of Hazardous Substances Based on Excitation Emission Matrix Fluorescence Spectroscopy.

Sensitively detecting hazardous and suspected bioaerosols is crucial for safeguarding public health. The potential impact of pollen on identifying bacterial species through fluorescence spectra should not be overlooked. Before the analysis, the spectrum underwent preprocessing steps, including normalization, multivariate scattering correction, and Savitzky-Golay smoothing. Additionally, the spectrum was transformed using difference, standard normal variable, and fast Fourier transform techniques. A random forest algorithm was employed for the classification and identification of 31 different types of samples. The fast Fourier transform improved the classification accuracy of the sample excitation-emission matrix fluorescence spectrum data by 9.2%, resulting in an accuracy of 89.24%. The harmful substances, including Staphylococcus aureus, ricin, beta-bungarotoxin, and Staphylococcal enterotoxin B, were clearly distinguished. The spectral data transformation and classification algorithm effectively eliminated the interference of pollen on other components. Furthermore, a classification and recognition model based on spectral feature transformation was established, demonstrating excellent application potential in detecting hazardous substances and protecting public health. This study provided a solid foundation for the application of rapid detection methods for harmful bioaerosols.

Metaheuristic integrated machine learning classification of colon cancer using STFT LASSO and EHO feature extraction from microarray gene expressions.

The microarray gene expression data poses a tremendous challenge due to their curse of dimensionality problem. The sheer volume of features far surpasses available samples, leading to overfitting and reduced classification accuracy. Thus the dimensionality of microarray gene expression data must be reduced with efficient feature extraction methods to reduce the volume of data and extract meaningful information to enhance the classification accuracy and interpretability. In this research, we discover the uniqueness of applying STFT (Short Term Fourier Transform), LASSO (Least Absolute Shrinkage and Selection Operator), and EHO (Elephant Herding Optimisation) for extracting significant features from lung cancer and reducing the dimensionality of the microarray gene expression database. The classification of lung cancer is performed using the following classifiers: Gaussian Mixture Model (GMM), Particle Swarm Optimization (PSO) with GMM, Detrended Fluctuation Analysis (DFA), Naive Bayes classifier (NBC), Firefly with GMM, Support Vector Machine with Radial Basis Kernel (SVM-RBF) and Flower Pollination Optimization (FPO) with GMM. The EHO feature extraction with the FPO-GMM classifier attained the highest accuracy in the range of 96.77, with an F1 score of 97.5, MCC of 0.92 and Kappa of 0.92. The reported results underline the significance of utilizing STFT, LASSO, and EHO for feature extraction in reducing the dimensionality of microarray gene expression data. These methodologies also help in improved and early diagnosis of lung cancer with enhanced classification accuracy and interpretability.

Enhanced tissue slide imaging in the complex domain via cross-explainable GAN for Fourier ptychographic microscopy.

Achieving microscopy with large space-bandwidth products plays a key role in diagnostic imaging and is widely significant in the overall field of clinical practice. Among quantitative microscopy techniques, Fourier Ptychography (FP) provides a wide field of view and high-resolution images, suitable to the histopathological field, but onerous in computational terms. Artificial intelligence can be a solution in this sense. In particular, this research delves into the application of Generative Adversarial Networks (GAN) for the dual-channel complex FP image enhancement of human kidney samples. The study underscores the GANs' efficacy in promoting biological architectures in FP domain, thereby still guaranteeing high resolution and visibility of detailed microscopic structures. We demonstrate successful GAN-based enhanced reconstruction through two strategies: cross-explainability and expert survey. The cross-explainability is evaluated through the comparison of explanation maps for both real and imaginary components underlining its robustness. This comparison further shows that their interplay is pivotal for accurate reconstruction without hallucinations. Secondly, the enhanced reconstruction accuracy and effectiveness in a clinical workflow are confirmed through a two-step survey conducted with nephrologists.

Transformation of sedimentary dissolved organic matter in electrokinetic remediation catalogued by FT-ICR mass spectrometry.

In electrokinetic remediation (EKR), the sedimentary dissolved organic matter (DOM) could impede remediation by scavenging reactive species and generating unintended byproducts. Yet its transformation and mechanisms remained largely unknown. This study conducted molecular-level characterization of the water-extractable DOM (WEOM) in EKR using negative-ion electrospray ionization coupled to 21 tesla Fourier transform ion cyclotron resonance mass spectrometry (21 T FT-ICR MS). The results suggested that ∼55 % of the ∼7,000 WEOM compounds identified were reactive, and EKR lowered their diversity, molecular weight distribution, and double-bond equivalent (DBE) through a combination of electrochemical and microbial redox reactions. Heteroatom-containing WEOM (CHON and CHOS) were abundant (∼ 35% of the total WEOM), with CHOS generally being more reactive than CHON. Low electric potential (1 V/cm) promoted the growth of dealkylation and desulfurization bacteria, and led to anodic CO2 mineralization, anodic cleavage of -SO and -SO3, and cathodic cleavage of -SH2; high electric potential (2 V/cm) only enriched desulfurization bacteria, and differently, led to anodic oxygenation and cathodic hydrogenation of unsaturated and phenolic compounds, in addition to cathodic cleavage of -SH2. The long-term impact of these changes on soil quality and nitrogen-sulfur-carbon flux may be need to studied to identify unknown risks and new applications of EKR.

Reduced B0/B1 + sensitivity in velocity-selective inversion arterial spin labeling using adiabatic refocusing pulses.

PURPOSE: To mitigate the B0/B1 + sensitivity of velocity-selective inversion (VSI) pulse trains for velocity-selective arterial spin labeling (VSASL) by implementing adiabatic refocusing. This approach aims to achieve artifact-free VSI-based perfusion imaging through single-pair label-control subtractions, reducing the need for the currently required four-pair dynamic phase-cycling (DPC) technique when using a velocity-insensitive control. METHODS: We introduce a Fourier-transform VSI (FT-VSI) train that incorporates sinc-modulated hard excitation pulses with MLEV-8-modulated adiabatic hyperbolic secant refocusing pairs. We compare performance between this train and the standard composite refocusing train, including with and without DPC, for dual-module VSI VSASL. We evaluate (1) simulated velocity-selective profiles and subtraction fidelity across a broad B0/B1 + range, (2) subtraction fidelity in phantoms, and (3) image quality, artifact presence, and gray-matter perfusion heterogeneity (as measured by the spatial coefficient of variation) in healthy human subjects. RESULTS: Adiabatic refocusing significantly improves FT-VSI robustness to B0/B1 + inhomogeneity for a single label-control subtraction. Subtraction fidelity is dramatically improved in both simulation and phantoms compared with composite refocusing without DPC, and is similar compared with DPC methods. In humans, marked artifacts seen with the non-DPC composite refocusing approach are eliminated, corroborated by significantly reduced gray-matter heterogeneity (via lower spatial coefficient of variation values). CONCLUSION: A novel VSASL labeling train using adiabatic refocusing pulses for VSI was found to reduce artifacts related to B0/B1 + inhomogeneity, thereby providing an alternative to DPC and its associated limitations, which include increased vulnerability to physiological noise and motion, reduced functional MRI applicability, and suboptimal data censoring.

Development and Assessment of Multiple Illumination Color Fourier Ptychographic Microscopy for High Throughput Sample Digitization.

In this study, we proposed a multiplexed color illumination strategy to improve the data acquisition efficiency of Fourier ptychography microscopy (FPM). Instead of sequentially lighting up one single channel LED, our method turns on multiple white light LEDs for each image acquisition via a color camera. Thus, each raw image contains multiplexed spectral information. An FPM prototype was developed, which was equipped with a 4×/0.13 NA objective lens to achieve a spatial resolution equivalent to that of a 20×/0.4 NA objective lens. Both two- and four-LED illumination patterns were designed and applied during the experiments. A USAF 1951 resolution target was first imaged under these illumination conditions, based on which MTF curves were generated to assess the corresponding imaging performance. Next, H&E tissue samples and analyzable metaphase chromosome cells were used to evaluate the clinical utility of our strategy. The results show that the single and multiplexed (two- or four-LED) illumination results achieved comparable imaging performance on all the three channels of the MTF curves. Meanwhile, the reconstructed tissue or cell images successfully retain the definition of cell nuclei and cytoplasm and can better preserve the cell edges as compared to the results from the conventional microscopes. This study initially validates the feasibility of multiplexed color illumination for the future development of high-throughput FPM scanning systems.

A new methodology for determining the central pressure waveform from peripheral measurement using Fourier-based machine learning.

Radial applanation tonometry is a well-established technique for hemodynamic monitoring and is becoming popular in affordable non-invasive wearable healthcare electronics. To assess the central aortic pressure using radial-based measurements, there is an essential need to develop mathematical approaches to estimate the central pressure waveform. In this study, we propose a new Fourier-based machine learning (F-ML) methodology to transfer non-invasive radial pressure measurements to the central pressure waveform. To test the method, collection of tonometry recordings of the radial and carotid pressure measurements are used from the Framingham Heart Study (2640 individuals, 55 % women) with mean (range) age of 66 (40-91) years. Method-derived estimates are significantly correlated with the measured ones for three major features of the pressure waveform (systolic blood pressure, r=0.97, p < 0.001; diastolic blood pressure, r=0.99, p < 0.001; and mean blood pressure, r=0.99, p < 0.001). In all cases, the Bland-Altman analysis shows negligible bias in the estimations and error is bounded to 5.4 mmHg. Findings also suggest that the F-ML approach reconstructs the shape of the central pressure waveform accurately with the average normalized root mean square error of 5.5 % in the testing population which is blinded to all stages of machine learning development. The results show that the F-ML transfer function outperforms the conventional generalized transfer function, particularly in terms of reconstructing the shape of the central pressure waveform morphology. The proposed F-ML transfer function can provide accurate estimates for the central pressure waveform, and ultimately expand the usage of non-invasive devices for central hemodynamic assessment.

Advanced qEEG analyses discriminate between dementia subtypes.

BACKGROUND: Dementia is caused by neurodegenerative conditions and characterized by cognitive decline. Diagnostic accuracy for dementia subtypes, such as Alzheimer's Disease (AD), Dementia with Lewy Bodies (DLB) and Parkinson's Disease with dementia (PDD), remains challenging. METHODS: Here, different methods of quantitative electroencephalography (qEEG) analyses were employed to assess their effectiveness in distinguishing dementia subtypes from healthy controls under eyes closed (EC) and eyes open (EO) conditions. RESULTS: Classic Fast-Fourier Transform (FFT) and autoregressive (AR) power analyses differentiated between all conditions for the 4-8 Hz theta range. Only individuals with dementia with Lewy Bodies (DLB) differed from healthy subjects for the wider 4-15 Hz frequency range, encompassing the actual dominant frequency of all individuals. FFT results for this range yielded wider significant discriminators vs AR, also detecting differences between AD and DLB. Analyses of the inclusive dominant / peak frequency range (4-15 Hz) indicated slowing and reduced variability, also discriminating between synucleinopathies vs controls and AD. Dissociation of periodic oscillations and aperiodic components of AR spectra using Fitting-Oscillations-&-One-Over-F (FOOOF) modelling delivered a reliable and subtype-specific slowing of brain oscillatory peaks during EC and EO for all groups. Distinct and robust differences were particularly strong for aperiodic parameters, suggesting their potential diagnostic power in detecting specific changes resulting from age and cognitive status. CONCLUSION: Our findings indicate that qEEG methods can reliably detect dementia subtypes. Spectral analyses comprising an integrated, multi-parameter EEG approach discriminating between periodic and aperiodic components under EC and EO conditions may enhance diagnostic accuracy in the future.

Pillar data-acquisition strategies for cryo-electron tomography of beam-sensitive biological samples.

For cryo-electron tomography (cryo-ET) of beam-sensitive biological specimens, a planar sample geometry is typically used. As the sample is tilted, the effective thickness of the sample along the direction of the electron beam increases and the signal-to-noise ratio concomitantly decreases, limiting the transfer of information at high tilt angles. In addition, the tilt range where data can be collected is limited by a combination of various sample-environment constraints, including the limited space in the objective lens pole piece and the possible use of fixed conductive braids to cool the specimen. Consequently, most tilt series are limited to a maximum of ±70°, leading to the presence of a missing wedge in Fourier space. The acquisition of cryo-ET data without a missing wedge, for example using a cylindrical sample geometry, is hence attractive for volumetric analysis of low-symmetry structures such as organelles or vesicles, lysis events, pore formation or filaments for which the missing information cannot be compensated by averaging techniques. Irrespective of the geometry, electron-beam damage to the specimen is an issue and the first images acquired will transfer more high-resolution information than those acquired last. There is also an inherent trade-off between higher sampling in Fourier space and avoiding beam damage to the sample. Finally, the necessity of using a sufficient electron fluence to align the tilt images means that this fluence needs to be fractionated across a small number of images; therefore, the order of data acquisition is also a factor to consider. Here, an n-helix tilt scheme is described and simulated which uses overlapping and interleaved tilt series to maximize the use of a pillar geometry, allowing the entire pillar volume to be reconstructed as a single unit. Three related tilt schemes are also evaluated that extend the continuous and classic dose-symmetric tilt schemes for cryo-ET to pillar samples to enable the collection of isotropic information across all spatial frequencies. A fourfold dose-symmetric scheme is proposed which provides a practical compromise between uniform information transfer and complexity of data acquisition.

Epilepsy detection based on multi-head self-attention mechanism.

CNN has demonstrated remarkable performance in EEG signal detection, yet it still faces limitations in terms of global perception. Additionally, due to individual differences in EEG signals, the generalization ability of epilepsy detection models is week. To address this issue, this paper presents a cross-patient epilepsy detection method utilizing a multi-head self-attention mechanism. This method first utilizes Short-Time Fourier Transform (STFT) to transform the original EEG signals into time-frequency features, then models local information using Convolutional Neural Network (CNN), subsequently captures global dependency relationships between features using the multi-head self-attention mechanism of Transformer, and finally performs epilepsy detection using these features. Meanwhile, this model employs a light multi-head attention mechanism module with an alternating structure, which can comprehensively extract multi-scale features while significantly reducing computational costs. Experimental results on the CHB-MIT dataset show that the proposed model achieves accuracy, sensitivity, specificity, F1 score, and AUC of 92.89%, 96.17%, 92.99%, 94.41%, and 96.77%, respectively. Compared to the existing methods, the method proposed in this paper obtains better performance along with better generalization.

Bayesian inverse problem for a fractional diffusion model of cell migration.

In the present work, both direct and inverse problems are considered for a Fisher-type fractional diffusion equation, which is proposed to describe the phenomenon of cell migration. For the direct problem, a solution is given via the Fourier method and the Laplace transform. On the other hand, we solved the inverse problem from a Bayesian statistical framework using a set of data that are the result of a cell migration experiment on a wound closure assay. We estimated the parameters of the mathematical model via Markov Chain Monte Carlo methods.

Integrating gated recurrent unit in graph neural network to improve infectious disease prediction: an attempt.

Objective: This study focuses on enhancing the precision of epidemic time series data prediction by integrating Gated Recurrent Unit (GRU) into a Graph Neural Network (GNN), forming the GRGNN. The accuracy of the GNN (Graph Neural Network) network with introduced GRU (Gated Recurrent Units) is validated by comparing it with seven commonly used prediction methods. Method: The GRGNN methodology involves multivariate time series prediction using a GNN (Graph Neural Network) network improved by the integration of GRU (Gated Recurrent Units). Additionally, Graphical Fourier Transform (GFT) and Discrete Fourier Transform (DFT) are introduced. GFT captures inter-sequence correlations in the spectral domain, while DFT transforms data from the time domain to the frequency domain, revealing temporal node correlations. Following GFT and DFT, outbreak data are predicted through one-dimensional convolution and gated linear regression in the frequency domain, graph convolution in the spectral domain, and GRU (Gated Recurrent Units) in the time domain. The inverse transformation of GFT and DFT is employed, and final predictions are obtained after passing through a fully connected layer. Evaluation is conducted on three datasets: the COVID-19 datasets of 38 African countries and 42 European countries from worldometers, and the chickenpox dataset of 20 Hungarian regions from Kaggle. Metrics include Average Root Mean Square Error (ARMSE) and Average Mean Absolute Error (AMAE). Result: For African COVID-19 dataset and Hungarian Chickenpox dataset, GRGNN consistently outperforms other methods in ARMSE and AMAE across various prediction step lengths. Optimal results are achieved even at extended prediction steps, highlighting the model's robustness. Conclusion: GRGNN proves effective in predicting epidemic time series data with high accuracy, demonstrating its potential in epidemic surveillance and early warning applications. However, further discussions and studies are warranted to refine its application and judgment methods, emphasizing the ongoing need for exploration and research in this domain.

Two-Dimensional Deep Learning Frameworks for Drug-Induced Cardiotoxicity Detection.

The identification of drug-induced cardiotoxicity remains a pressing challenge with far-reaching clinical and economic ramifications, often leading to patient harm and resource-intensive drug recalls. Current methodologies, including in vivo and in vitro models, have severe limitations in accurate identification of cardiotoxic substances. Pioneering a paradigm shift from these conventional techniques, our study presents two deep learning-based frameworks, STFT-CNN and SST-CNN, to assess cardiotoxicity with markedly improved accuracy and reliability. Leveraging the power of induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs) as a more human-relevant cell model, we record mechanical beating signals through impedance measurements. These temporal signals were converted into enriched two-dimensional representations through advanced transformation techniques, specifically short-time Fourier transform (STFT) and synchro-squeezing transform (SST). These transformed data are fed into the proposed frameworks for comprehensive analysis, including drug type classification, concentration classification, cardiotoxicity classification, and new drug identification. Compared to traditional models like recurrent neural network (RNN) and 1-dimensional convolutional neural network (1D-CNN), SST-CNN delivered an impressive test accuracy of 98.55% in drug type classification and 99% in distinguishing cardiotoxic and noncardiotoxic drugs. Its feasibility is further highlighted with a stellar 98.5% average accuracy for classification of various concentrations, and the superiority of our proposed frameworks underscores their promise in revolutionizing drug safety assessments. With a potential for scalability, they represent a major leap in drug safety assessments, offering a pathway to more robust, efficient, and human-relevant cardiotoxicity evaluations.