PLoS One. 2024 Oct 2;19(10):e0310818. doi: 10.1371/journal.pone.0310818. eCollection 2024.

ABSTRACT

Nowadays, video monitoring of farrowing and automatic video evaluation using Deep Learning have become increasingly important in farm animal science research and open up new possibilities for addressing specific research questions like the determination of husbandry relevant indicators. A robust detection performance of newborn piglets is essential for reliably monitoring the farrowing process and to access important information about the welfare status of the sow and piglets. Although object detection algorithms are increasingly being used in various scenarios in the field of livestock farming, their usability for detecting newborn piglets has so far been limited. Challenges such as frequent animal occlusions, high overlapping rates or strong heterogeneous animal postures increase the complexity and place new demands on the detection model. Typically, new data is manually annotated to improve model performance, but the annotation effort is expensive and time-consuming. To address this problem, we propose a Noisy Student approach to automatically generate annotation information and train an improved piglet detection model. By using a teacher-student model relationship we transform the image structure and generate pseudo-labels for the object classes piglet and tail. As a result, we improve the initial detection performance of the teacher model from 0.561, 0.838, 0.672 to 0.901, 0.944, 0.922 for the performance metrics Recall, Precision and F1-score, respectively. The results of this study can be used in two ways. Firstly, the results contribute directly to the improvement of piglet detection in the context of birth monitoring systems and the evaluation of the farrowing progress. Secondly, the approach presented can be transferred to other research questions and species, thereby reducing the problem of cost-intensive annotation processes and increase training efficiency. In addition, we provide a unique dataset for the detection and evaluation of newborn piglets and sow body parts to support researchers in the task of monitoring the farrowing process.

PMID:39356687 | DOI:10.1371/journal.pone.0310818

PLoS One. 2024 Oct 2;19(10):e0311228. doi: 10.1371/journal.pone.0311228. eCollection 2024.

ABSTRACT

Nanoparticles exhibit broad applications in materials mechanics, medicine, energy and other fields. The ordered arrangement of nanoparticles is very important to fully understand their properties and functionalities. However, in materials science, the acquisition of training images requires a large number of professionals and the labor cost is extremely high, so there are usually very few training samples in the field of materials. In this study, a segmentation method of nanoparticle topological structure based on synthetic data (SD) is proposed, which aims to solve the issue of small data in the field of materials. Our findings reveal that the combination of SD generated by rendering software with merely 15% Authentic Data (AD) shows better performance in training deep learning model. The trained U-Net model shows that Miou of 0.8476, accuracy of 0.9970, Kappa of 0.8207, and Dice of 0.9103, respectively. Compared with data enhancement alone, our approach yields a 1% improvement in the Miou metric. These results show that our proposed strategy can achieve better prediction performance without increasing the cost of data acquisition.

PMID:39356683 | DOI:10.1371/journal.pone.0311228

PLoS One. 2024 Oct 2;19(10):e0311416. doi: 10.1371/journal.pone.0311416. eCollection 2024.

ABSTRACT

To improve the prognosis of patients suffering from pulmonary diseases, such as lung cancer, early diagnosis and treatment are crucial. The analysis of CT images is invaluable for diagnosis, whereas high quality segmentation of the airway tree are required for intervention planning and live guidance during bronchoscopy. Recently, the Multi-domain Airway Tree Modeling (ATM'22) challenge released a large dataset, both enabling training of deep-learning based models and bringing substantial improvement of the state-of-the-art for the airway segmentation task. The ATM'22 dataset includes a large group of COVID'19 patients and a range of other lung diseases, however, relatively few patients with severe pathologies affecting the airway tree anatomy was found. In this study, we introduce a new public benchmark dataset (AeroPath), consisting of 27 CT images from patients with pathologies ranging from emphysema to large tumors, with corresponding trachea and bronchi annotations. Second, we present a multiscale fusion design for automatic airway segmentation. Models were trained on the ATM'22 dataset, tested on the AeroPath dataset, and further evaluated against competitive open-source methods. The same performance metrics as used in the ATM'22 challenge were used to benchmark the different considered approaches. Lastly, an open web application is developed, to easily test the proposed model on new data. The results demonstrated that our proposed architecture predicted topologically correct segmentations for all the patients included in the AeroPath dataset. The proposed method is robust and able to handle various anomalies, down to at least the fifth airway generation. In addition, the AeroPath dataset, featuring patients with challenging pathologies, will contribute to development of new state-of-the-art methods. The AeroPath dataset and the web application are made openly available.

PMID:39356679 | DOI:10.1371/journal.pone.0311416

IEEE J Biomed Health Inform. 2024 Oct 2;PP. doi: 10.1109/JBHI.2024.3472609. Online ahead of print.

ABSTRACT

Contrast-enhanced ultrasound (CEUS) has been extensively employed as an imaging modality in thyroid nodule diagnosis due to its capacity to visualise the distribution and circulation of micro-vessels in organs and lesions in a non-invasive manner. However, current CEUS-based thyroid nodule diagnosis methods suffered from: 1) the blurred spatial boundaries between nodules and other anatomies in CEUS videos, and 2) the insufficient representations of the local structural information of nodule tissues by the features extracted only from CEUS videos. In this paper, we propose a novel dual-branch network with a cross-modality-attention mechanism for thyroid nodule diagnosis by integrating the information from tow related modalities, i.e., CEUS videos and ultrasound image. The mechanism has two parts: US-attention-from-CEUS transformer (UAC-T) and CEUS-attention-from-US transformer (CAU-T). As such, this network imitates the manner of human radiologists by decomposing the diagnosis into two correlated tasks: 1) the spatio-temporal features extracted from CEUS are hierarchically embedded into the spatial features extracted from US with UAC-T for the nodule segmentation; 2) the US spatial features are used to guide the extraction of the CEUS spatio-temporal features with CAU-T for the nodule classification. The two tasks are intertwined in the dual-branch end-to-end network and optimized with the multi-task learning (MTL) strategy. The proposed method is evaluated on our collected thyroid US-CEUS dataset. Experimental results show that our method achieves the classification accuracy of 86.92%, specificity of 66.41%, and sensitivity of 97.01%, outperforming the state-of-the-art methods. As a general contribution in the field of multi-modality diagnosis of diseases, the proposed method has provided an effective way to combine static information with its related dynamic information, improving the quality of deep learning based diagnosis with an additional benefit of explainability.

PMID:39356606 | DOI:10.1109/JBHI.2024.3472609

Crit Rev Food Sci Nutr. 2024 Oct 2:1-28. doi: 10.1080/10408398.2024.2405840. Online ahead of print.

ABSTRACT

Food fraud has serious consequences including reputational damage to businesses, health and safety risks and lack of consumer confidence. New technologies targeted at ensuring food authenticity has emerged and however, the penetration and diffusion of sophisticated analytical technologies are faced with challenges in the industry. This review is focused on investigating the emerging technologies and strategies for mitigating food fraud and exploring the key barriers to their application. The review discusses three key areas of focus for food fraud mitigation that include systematic approaches, analytical techniques and package-level anti-counterfeiting technologies. A notable gap exists in converting laboratory based sophisticated technologies and tools in high-paced, live industrial applications. New frontiers such as handheld laser-induced breakdown spectroscopy (LIBS) and smart-phone spectroscopy have emerged for rapid food authentication. Multifunctional devices with hyphenating sensing mechanisms together with deep learning strategies to compare food fingerprints can be a great leap forward in the industry. Combination of different technologies such as spectroscopy and separation techniques will also be superior where quantification of adulterants are preferred. With the advancement of automation these technologies will be able to be deployed as in-line scanning devices in industrial settings to detect food fraud across multiple points in food supply chains.

PMID:39356551 | DOI:10.1080/10408398.2024.2405840

J Nephrol. 2024 Oct 2. doi: 10.1007/s40620-024-02094-4. Online ahead of print.

ABSTRACT

BACKGROUND: Pre-transplant procurement biopsy interpretation is challenging, also because of the low number of renal pathology experts. Artificial intelligence (AI) can assist by aiding pathologists with kidney donor biopsy assessment. Herein we present the "Galileo" AI tool, designed specifically to assist the on-call pathologist with interpreting pre-implantation kidney biopsies.

METHODS: A multicenter cohort of whole slide images acquired from core-needle and wedge biopsies of the kidney was collected. A deep learning algorithm was trained to detect the main findings evaluated in the pre-implantation setting (normal glomeruli, globally sclerosed glomeruli, ischemic glomeruli, arterioles and arteries). The model obtained on the Aiforia Create platform was validated on an external dataset by three independent pathologists to evaluate the performance of the algorithm.

RESULTS: Galileo demonstrated a precision, sensitivity, F1 score and total area error of 81.96%, 94.39%, 87.74%, 2.81% and 74.05%, 71.03%, 72.5%, 2% in the training and validation sets, respectively. Galileo was significantly faster than pathologists, requiring 2 min overall in the validation phase (vs 25, 22 and 31 min by 3 separate human readers, p < 0.001). Galileo-assisted detection of renal structures and quantitative information was directly integrated in the final report.

CONCLUSIONS: The Galileo AI-assisted tool shows promise in speeding up pre-implantation kidney biopsy interpretation, as well as in reducing inter-observer variability. This tool may represent a starting point for further improvements based on hard endpoints such as graft survival.

PMID:39356416 | DOI:10.1007/s40620-024-02094-4

EJNMMI Phys. 2024 Oct 2;11(1):80. doi: 10.1186/s40658-024-00680-w.

ABSTRACT

BACKGROUND: Deep learning (DL)-based denoising has been proven to improve image quality and quantitation accuracy of low dose (LD) SPECT. However, conventional DL-based methods used SPECT images with mixed frequency components. This work aims to develop an integrated multi-frequency denoising network to further enhance LD myocardial perfusion (MP) SPECT denoising.

METHODS: Fifty anonymized patients who underwent routine 99mTc-sestamibi stress SPECT/CT scans were retrospectively recruited. Three LD datasets were obtained by reducing the 10 s acquisition time of full dose (FD) SPECT to be 5, 2 and 1 s per projection based on the list mode data for a total of 60 projections. FD and LD projections were Fourier transformed to magnitude and phase images, which were then separated into two or three frequency bands. Each frequency band was then inversed Fourier transformed back to the image domain. We proposed a 3D integrated attention-guided multi-frequency conditional generative adversarial network (AttMFGAN) and compared with AttGAN, and separate AttGAN for multi-frequency bands denoising (AttGAN-MF).The multi-frequency FD and LD projections of 35, 5 and 10 patients were paired for training, validation and testing. The LD projections to be tested were separated to multi-frequency components and input to corresponding networks to get the denoised components, which were summed to get the final denoised projections. Voxel-based error indices were measured on the cardiac region on the reconstructed images. The perfusion defect size (PDS) was also analyzed.

RESULTS: AttGAN-MF and AttMFGAN have superior performance on all physical and clinical indices as compared to conventional AttGAN. The integrated AttMFGAN is better than AttGAN-MF. Multi-frequency denoising with two frequency bands have generally better results than corresponding three-frequency bands methods.

CONCLUSIONS: AttGAN-MF and AttMFGAN are promising to further improve LD MP SPECT denoising.

PMID:39356406 | DOI:10.1186/s40658-024-00680-w

Environ Monit Assess. 2024 Oct 2;196(11):1002. doi: 10.1007/s10661-024-13164-2.

ABSTRACT

This research introduces syN-BEATS, a novel ensemble deep learning model tailored for effective pollutant forecasting under conditions of limited data availability. Based on the N-BEATS architecture, syN-BEATS integrates various configurations with differing numbers of stacks and blocks, effectively combining weak and strong learning approaches. Our experiments show that syN-BEATS outperforms standard models, especially when using Bayesian optimization to fine-tune ensemble weights. The model consistently achieves low relative root mean square errors, proving its capacity for precise pollutant forecasting despite data constraints. A key aspect of this study is the use of data from only one meteorological and one air quality monitoring station per region, simulating environments with restricted monitoring capabilities. By applying this approach in regions with diverse climates and air quality levels, we thoroughly assess the model's flexibility and resilience under different environmental conditions. The results highlight syN-BEATS' ability to support the development of effective health alert systems that can detect specific airborne pollutants, even in areas with limited monitoring infrastructure. This advancement is crucial for enhancing environmental monitoring and public health management in under-resourced areas.

PMID:39356366 | DOI:10.1007/s10661-024-13164-2

J Magn Reson Imaging. 2024 Oct 2. doi: 10.1002/jmri.29621. Online ahead of print.

NO ABSTRACT

PMID:39355970 | DOI:10.1002/jmri.29621

J Undergrad Neurosci Educ. 2024 Aug 31;22(3):A185-A196. doi: 10.59390/PAHQ2595. eCollection 2024 Spring.

ABSTRACT

Game-based learning is a promising approach that can promote engagement and deep learning of course content in a fun setting. This article describes the development, implementation, and evaluation of a card game designed to help students develop greater familiarity and comfort with complex neuroscience vocabulary. To play Forbidden Neurds, students within a team take turns acting as the Lead Neurd, who must get the team to guess a Neuroscience word without using any of the Forbidden words listed on the card. The game is designed to help students develop a deeper understanding of neuroscience terminology, identify relationships between terms, identify gaps in their understanding, and reinforce learning. The game was evaluated in a 200-level fundamentals of neuroscience course at a small public liberal arts university. Students showed increased content knowledge through pre-post testing, and a post-game self-reported survey showed that playing Forbidden Neurds enabled students to assess, increase, and apply content knowledge. Gameplay also helped students develop greater communication, critical thinking, and teamwork skills. In addition, students reported experiencing greater engagement through this fun learning activity. This game could act as an adaptable and effective learning tool across a range of neuroscience courses.

PMID:39355667 | PMC:PMC11441429 | DOI:10.59390/PAHQ2595

Rev Cardiovasc Med. 2024 Sep 19;25(9):335. doi: 10.31083/j.rcm2509335. eCollection 2024 Sep.

ABSTRACT

BACKGROUND: Congenital heart diseases (CHDs), particularly atrial and ventricular septal defects, pose significant health risks and common challenges in detection via echocardiography. Doctors often employ the cardiac structural information during the diagnostic process. However, prior CHD research has not determined the influence of including cardiac structural information during the labeling process and the application of data augmentation techniques.

METHODS: This study utilizes advanced artificial intelligence (AI)-driven object detection frameworks, specifically You Look Only Once (YOLO)v5, YOLOv7, and YOLOv9, to assess the impact of including cardiac structural information and data augmentation techniques on the identification of septal defects in echocardiographic images.

RESULTS: The experimental results reveal that different labeling strategies substantially affect the performance of the detection models. Notably, adjustments in bounding box dimensions and the inclusion of cardiac structural details in the annotations are key factors influencing the accuracy of the model. The application of deep learning techniques in echocardiography enhances the precision of detecting septal heart defects.

CONCLUSIONS: This study confirms that careful annotation of imaging data is crucial for optimizing the performance of object detection algorithms in medical imaging. These findings suggest potential pathways for refining AI applications in diagnostic cardiology studies.

PMID:39355611 | PMC:PMC11440387 | DOI:10.31083/j.rcm2509335

Front Microbiol. 2024 Sep 6;15:1438942. doi: 10.3389/fmicb.2024.1438942. eCollection 2024.

ABSTRACT

BACKGROUND: Clinical studies have demonstrated that microbes play a crucial role in human health and disease. The identification of microbe-disease interactions can provide insights into the pathogenesis and promote the diagnosis, treatment, and prevention of disease. Although a large number of computational methods are designed to screen novel microbe-disease associations, the accurate and efficient methods are still lacking due to data inconsistence, underutilization of prior information, and model performance.

METHODS: In this study, we proposed an improved deep learning-based framework, named GIMMDA, to identify latent microbe-disease associations, which is based on graph autoencoder and inductive matrix completion. By co-training the information from microbe and disease space, the new representations of microbes and diseases are used to reconstruct microbe-disease association in the end-to-end framework. In particular, a similarity fusion strategy is conducted to improve prediction performance.

RESULTS: The experimental results show that the performance of GIMMDA is competitive with that of existing state-of-the-art methods on 3 datasets (i.e., HMDAD, Disbiome, and multiMDA). In particular, it performs best with the area under the receiver operating characteristic curve (AUC) of 0.9735, 0.9156, 0.9396 on abovementioned 3 datasets, respectively. And the result also confirms that different similarity fusions can improve the prediction performance. Furthermore, case studies on two diseases, i.e., asthma and obesity, validate the effectiveness and reliability of our proposed model.

CONCLUSION: The proposed GIMMDA model show a strong capability in predicting microbe-disease associations. We expect that GPUDMDA will help identify potential microbe-related diseases in the future.

PMID:39355422 | PMC:PMC11443509 | DOI:10.3389/fmicb.2024.1438942

Front Microbiol. 2024 Sep 17;15:1446097. doi: 10.3389/fmicb.2024.1446097. eCollection 2024.

ABSTRACT

Bacteriophages are the most prolific organisms on Earth, yet many of their genomes and assemblies from metagenomic sources lack protein sequences with identified functions. While most bacteriophage proteins are structural proteins, categorized as Phage Virion Proteins (PVPs), a considerable number remain unclassified. Complicating matters further, traditional lab-based methods for PVP identification can be tedious. To expedite the process of identifying PVPs, machine-learning models are increasingly being employed. Existing tools have developed models for predicting PVPs from protein sequences as input. However, none of these efforts have built software allowing for both genomic and metagenomic data as input. In addition, there is currently no framework available for easily curating data and creating new types of machine learning models. In response, we introduce PhageScanner, an open-source platform that streamlines data collection for genomic and metagenomic datasets, model training and testing, and includes a prediction pipeline for annotating genomic and metagenomic data. PhageScanner also features a graphical user interface (GUI) for visualizing annotations on genomic and metagenomic data. We further introduce a BLAST-based classifier that outperforms ML-based models and an efficient Long Short-Term Memory (LSTM) classifier. We then showcase the capabilities of PhageScanner by predicting PVPs in six previously uncharacterized bacteriophage genomes. In addition, we create a new model that predicts phage-encoded toxins within bacteriophage genomes, thus displaying the utility of the framework.

PMID:39355420 | PMC:PMC11442244 | DOI:10.3389/fmicb.2024.1446097

Front Psychiatry. 2024 Sep 17;15:1422020. doi: 10.3389/fpsyt.2024.1422020. eCollection 2024.

ABSTRACT

BACKGROUND: Previous studies have classified major depression and healthy control groups based on vocal acoustic features, but the classification accuracy needs to be improved. Therefore, this study utilized deep learning methods to construct classification and prediction models for major depression and healthy control groups.

METHODS: 120 participants aged 16-25 participated in this study, included 64 MDD group and 56 HC group. We used the Covarep open-source algorithm to extract a total of 1200 high-level statistical functions for each sample. In addition, we used Python for correlation analysis, and neural network to establish the model to distinguish whether participants experienced depression, predict the total depression score, and evaluate the effectiveness of the classification and prediction model.

RESULTS: The classification modelling of the major depression and the healthy control groups by relevant and significant vocal acoustic features was 0.90, and the Receiver Operating Characteristic (ROC) curves analysis results showed that the classification accuracy was 84.16%, the sensitivity was 95.38%, and the specificity was 70.9%. The depression prediction model of speech characteristics showed that the predicted score was closely related to the total score of 17 items of the Hamilton Depression Scale(HAMD-17) (r=0.687, P<0.01); and the Mean Absolute Error(MAE) between the model's predicted score and total HAMD-17 score was 4.51.

LIMITATION: This study's results may have been influenced by anxiety comorbidities.

CONCLUSION: The vocal acoustic features can not only effectively classify the major depression and the healthy control groups, but also accurately predict the severity of depressive symptoms.

PMID:39355380 | PMC:PMC11442283 | DOI:10.3389/fpsyt.2024.1422020

Clin Pract Epidemiol Ment Health. 2024 Jul 26;20:e17450179315688. doi: 10.2174/0117450179315688240607052117. eCollection 2024.

ABSTRACT

INTRODUCTION: This study aims to investigate the potential of machine learning in predicting mental health conditions among college students by analyzing existing literature on mental health diagnoses using various machine learning algorithms.

METHODS: The research employed a systematic literature review methodology to investigate the application of deep learning techniques in predicting mental health diagnoses among students from 2011 to 2024. The search strategy involved key terms, such as "deep learning," "mental health," and related terms, conducted on reputable repositories like IEEE, Xplore, ScienceDirect, SpringerLink, PLOS, and Elsevier. Papers published between January, 2011, and May, 2024, specifically focusing on deep learning models for mental health diagnoses, were considered. The selection process adhered to PRISMA guidelines and resulted in 30 relevant studies.

RESULTS: The study highlights Convolutional Neural Networks (CNN), Random Forest (RF), Support Vector Machine (SVM), Deep Neural Networks, and Extreme Learning Machine (ELM) as prominent models for predicting mental health conditions. Among these, CNN demonstrated exceptional accuracy compared to other models in diagnosing bipolar disorder. However, challenges persist, including the need for more extensive and diverse datasets, consideration of heterogeneity in mental health condition, and inclusion of longitudinal data to capture temporal dynamics.

CONCLUSION: This study offers valuable insights into the potential and challenges of machine learning in predicting mental health conditions among college students. While deep learning models like CNN show promise, addressing data limitations and incorporating temporal dynamics are crucial for further advancements.

PMID:39355197 | PMC:PMC11443461 | DOI:10.2174/0117450179315688240607052117

Front Artif Intell. 2024 Sep 4;7:1387936. doi: 10.3389/frai.2024.1387936. eCollection 2024.

ABSTRACT

Training Deep Neural Networks (DNNs) places immense compute requirements on the underlying hardware platforms, expending large amounts of time and energy. An important factor contributing to the long training times is the increasing dataset complexity required to reach state-of-the-art performance in real-world applications. To address this challenge, we explore the use of input mixing, where multiple inputs are combined into a single composite input with an associated composite label for training. The goal is for training on the mixed input to achieve a similar effect as training separately on each the constituent inputs that it represents. This results in a lower number of inputs (or mini-batches) to be processed in each epoch, proportionally reducing training time. We find that naive input mixing leads to a considerable drop in learning performance and model accuracy due to interference between the forward/backward propagation of the mixed inputs. We propose two strategies to address this challenge and realize training speedups from input mixing with minimal impact on accuracy. First, we reduce the impact of inter-input interference by exploiting the spatial separation between the features of the constituent inputs in the network's intermediate representations. We also adaptively vary the mixing ratio of constituent inputs based on their loss in previous epochs. Second, we propose heuristics to automatically identify the subset of the training dataset that is subject to mixing in each epoch. Across ResNets of varying depth, MobileNetV2 and two Vision Transformer networks, we obtain upto 1.6 × and 1.8 × speedups in training for the ImageNet and Cifar10 datasets, respectively, on an Nvidia RTX 2080Ti GPU, with negligible loss in classification accuracy.

PMID:39355147 | PMC:PMC11443600 | DOI:10.3389/frai.2024.1387936

Front Cell Dev Biol. 2024 Sep 17;12:1379984. doi: 10.3389/fcell.2024.1379984. eCollection 2024.

ABSTRACT

Alzheimer's disease (AD) is the leading neurodegenerative pathology in aged individuals, but many questions remain on its pathogenesis, and a cure is still not available. Recent research efforts have generated measurements of multiple omics in individuals that were healthy or diagnosed with AD. Although machine learning approaches are well-suited to handle the complexity of omics data, the models typically lack interpretability. Additionally, while the genetic landscape of AD is somewhat more established, the proteomic landscape of the diseased brain is less well-understood. Here, we establish a deep learning method that takes advantage of an ensemble of autoencoders (AEs) - EnsembleOmicsAE-to reduce the complexity of proteomics data into a reduced space containing a small number of latent features. We combine brain proteomic data from 559 individuals across three AD cohorts and demonstrate that the ensemble autoencoder models generate stable latent features which are well-suited for downstream biological interpretation. We present an algorithm to calculate feature importance scores based on the iterative scrambling of individual input features (i.e., proteins) and show that the algorithm identifies signaling modules (AE signaling modules) that are significantly enriched in protein-protein interactions. The molecular drivers of AD identified within the AE signaling modules derived with EnsembleOmicsAE were missed by linear methods, including integrin signaling and cell adhesion. Finally, we characterize the relationship between the AE signaling modules and the age of death of the patients and identify a differential regulation of vimentin and MAPK signaling in younger compared with older AD patients.

PMID:39355118 | PMC:PMC11442384 | DOI:10.3389/fcell.2024.1379984

Front Nucl Med. 2024 Jan 11;3:1362018. doi: 10.3389/fnume.2023.1362018. eCollection 2023.

NO ABSTRACT

PMID:39355037 | PMC:PMC11440866 | DOI:10.3389/fnume.2023.1362018

Environ Monit Assess. 2024 Oct 1;196(10):994. doi: 10.1007/s10661-024-13162-4.

ABSTRACT

Tehran, the most crowded city in Iran, suffers from severe air pollution, particularly during the cold months. This research endeavored to examine the statistical relationships between criteria air pollutants (CO, NO2, SO2, O3, PM10, and PM2.5) and meteorological elements (temperature, rainfall, wind speed, relative humidity, air pressure, sunshine hours, solar radiation, and cloudiness), as well as assess and compare the efficacy of six different algorithms (multiple linear regression (MLR), generalized additive model (GAM), classification and regression trees (CART), random forest (RF), gradient boosting machine (GBM), and deep learning (DL)) in modeling pollutants and climatic factors responsible for variations in Tehran's air pollution levels from 2001 to 2021 using R 4.3.2 software. The results of this study showed that O3 was strongly affected by weather conditions, while other pollutants were mainly influenced by each other than by meteorological parameters and more extensive research is required to pinpoint the precise impact of human activity on these pollutant levels in Tehran. Also based on the predictive model performance evaluation and concerning the principle of parsimony, in half of the cases, the MLR outperformed other models, despite its seeming simplicity and principal assumptions dependence. In other situations, the GAM was a good substitute.

PMID:39352511 | DOI:10.1007/s10661-024-13162-4

J Chem Phys. 2024 Oct 7;161(13):134102. doi: 10.1063/5.0226764.

ABSTRACT

The contribution of nuclear quantum effects (NQEs) to the properties of various hydrogen-bound systems, including biomolecules, is increasingly recognized. Despite the development of many acceleration techniques, the computational overhead of incorporating NQEs in complex systems is sizable, particularly at low temperatures. In this work, we leverage deep learning and multiscale coarse-graining techniques to mitigate the computational burden of path integral molecular dynamics (PIMD). In particular, we employ a machine-learned potential to accurately represent corrections to classical potentials, thereby significantly reducing the computational cost of simulating NQEs. We validate our approach using four distinct systems: Morse potential, Zundel cation, single water molecule, and bulk water. Our framework allows us to accurately compute position-dependent static properties, as demonstrated by the excellent agreement obtained between the machine-learned potential and computationally intensive PIMD calculations, even in the presence of strong NQEs. This approach opens the way to the development of transferable machine-learned potentials capable of accurately reproducing NQEs in a wide range of molecular systems.

PMID:39352405 | DOI:10.1063/5.0226764