Training Dataset Research Articles

Improved Faster R-CNN Based on Multi-Scale Module for Detecting Weak Ground Targets in Remote Sensing Images

In order to optimize the detection capability of small and weak ground targets in remote sensing images, a remote sensing image ground weak target detection method based on multi-scale module improved Faster R-CNN is proposed. By adjusting the Region Proposal Network (RPN) and Region of Interest (RoI) pooling layers, the model is better suited for feature extraction and classification of small targets. Generate feature maps at multiple scales by introducing additional convolutional layers to process inputs at different resolutions, with each layer focusing on targets within a specific size range. These multi-scale features are integrated and input into RPN to provide richer target proposal characteristics. By using image transformation techniques such as scaling, cropping, and rotation, the training dataset is expanded to simulate different small target scenes, enhancing the model’s adaptability to changes in target size, direction, and environment. The experimental results show that the proposed method not only outperforms other models in accuracy, recall, and F1 score, but also maintains high consistency and stability across different datasets. Its significant advantage in mean accuracy (MAP) further proves its reliability and effectiveness in remote sensing applications.

Search for Young Stellar Objects within 4XMM-DR13 Using CatBoost and SPE

Classifying and summarizing large data sets from different sky survey projects is essential for various subsequent scientific research. By combining data from 4XMM-DR13, Sloan Digital Sky Survey (SDSS) DR18, and CatWISE, we formed an XMM-WISE-SDSS sample that included information in the X-ray, optical, and infrared bands. By cross matching this sample with data sets from known spectral classifications from SDSS and LAMOST, we obtained a training data set containing stars, galaxies, quasars, and young stellar objects (YSOs). Two machine learning methods, CatBoost and Self-Paced Ensemble (SPE), were used to train and construct machine learning models through training sets to classify the XMM-WISE-SDSS sample. Notably, the SPE classifier showed excellent performance in YSO classification, identifying 1102 YSO candidates from 160,545 sources, including 258 known YSOs. Then we further verify whether these candidates are YSOs by the spectra in LAMOST and the identification in the SIMBAD and VizieR databases. Finally there are 412 unidentified YSO candidates. The discovery of these new YSOs is an important addition to existing YSO samples and will deepen our understanding of star formation and evolution. Moreover we provided a classification catalog for the whole XMM-WISE-SDSS sample.

Classification and Comparison of Data Augmentation Techniques

Data augmentation is a technical method that generates additional data samples by applying different transformations and processes to the original training data. It aims to increase the size and diversity of the dataset, thus improving the models' generalization ability. This paper provides a detailed introduction to geometric transformations, data mixing, automated data augmentation methods, and generative adversarial methods. Geometric transformations manipulate the spatial configuration of data samples to create new variants that retain the original content. Data mixing techniques blend multiple data samples to produce novel training examples, promoting robustness and reducing overfitting. Automated data augmentation methods leverage search algorithms to discover optimal augmentation policies that improve model performance without manual intervention. Generative adversarial methods employ generative adversarial networks to synthesize realistic data samples that enrich the training dataset. These methods find broad application in domains including object detection, image classification, natural language processing, and speech recognition, significantly improving model performance. The paper explores the advantages and limitations of data augmentation techniques in practical applications and identifies future research directions and challenges. By systematically classifying and selecting appropriate data augmentation methods for specific application scenarios, this review provides a theoretical foundation and practical guidance for real-world applications.

Autoencoder-Driven Training Data Selection Based on Hidden Features for Improved Accuracy of ANN Short-Term Load Forecasting in ADMS

This paper presents a novel methodology for short-term load forecasting in the context of significant shifts in the daily load curve due to the rapid and extensive adoption of Distributed Energy Resources (DERs). The proposed solution, built upon the Similar Days Method (SDM) and Artificial Neural Network (ANN), introduces several novelties: (1) selection of similar days based on hidden representations of day data using Autoencoder (AE); (2) enhancement of model generalization by utilizing a broader set of training examples; (3) incorporating the relative importance of training examples derived from the similarity measure during training; and (4) mitigation of the influence of outliers by applying an ensemble of ANN models trained with different data splits. The presented AE configuration and procedure for selecting similar days generated a higher-quality training dataset, which led to more robust predictions by the ANN model for days with unexpected deviations. Experiments were conducted on actual load data from a Serbian electrical power system, and the results were compared to predictions obtained by the field-proven STLF tool. The experiments demonstrated an improved performance of the presented solution on test days when the existing STLF tool had poor predictions over the past year.

Defending against backdoor attack on deep neural networks based on multi-scale inactivation

Deep neural networks (DNNs) have excellent performance in various applications, especially for image classification tasks. However, DNNs also face the threat of backdoor attacks. Backdoor attacks embed a hidden backdoor into a model, after which the infected model can achieve correct classification on benign images, while incorrectly classify the images with the backdoor triggers as the target label. To obtain a clean model from a backdoor dataset, we propose a Kalman filtering based multi-scale inactivation scheme, which can effectively remove poison data in a poison dataset and obtain a clean model. Every sample in the suspicious training dataset will be judged by multi-scale inactivation and obtain a series of judging results, then data fusion is conducted using kalman filtering to determine whether it is a poison sample. To further improve the performance, a trigger localization and target determination based scheme is proposed. Extensive experiments are conducted to demonstrate the superior effectiveness of the proposed method. The results show that the proposed methods can remove poison samples effectively, and achieve greater than 99% recall rate, and the attack success rate of the retrained clean model is smaller than 1%.

Accelerating Optimal Synthesis of Atomically Thin MoS2: A Constrained Bayesian Optimization Guided Brachistochrone Approach

AbstractA machine learning (ML) guided approach is presented for the accelerated optimization of chemical vapor deposition (CVD) synthesis of 2D materials toward the highest quality, starting from low‐quality or unsuccessful synthesis conditions. Using 26 sets of these synthesis conditions as the initial training dataset, our method systematically guides experimental synthesis towards optoelectronic‐grade monolayer MoS2 flakes. A‐exciton linewidth (σA) as narrow as 38 meV could be achieved in 2D MoS2 flakes after only an additional 35 trials (reflecting 15% of the full factorial design dataset for training purposes). In practical terms, this reflects a decrease of the possible experimental time to optimize the parameters from up to one year to about two months. This remarkable efficiency was achieved by formulating a constrained sequencing optimization problem solved via a combination of constraint learning and Bayesian Optimization with the narrowness of σA as the single target metric. By employing graph‐based semi‐supervised learning with data acquired through a multi‐criteria sampling method, the constraint model effectively delineates and refines the feasible design space for monolayer flake production. Additionally, the Gaussian Process regression effectively captures the relationships between synthesis parameters and outcomes, offering high predictive capability along with a measure of prediction uncertainty. This method is scalable to a higher number of synthesis parameters and target metrics and is transferrable to other materials and types of reactors. This study envisions that this method will be fundamental for CVD and similar techniques in the future.

A lactate metabolism-related gene signature to diagnose osteoarthritis based on machine learning combined with experimental validation.

Lactate is gradually proved as the essential regulator in intercellular signal transduction, energy metabolism reprogramming, and histone modification. This study aims to clarify the diagnosis value of lactate metabolism-related genes in osteoarthritis (OA). Lactate metabolism-related genes were retrieved from the MSigDB. GSE51588 was downloaded from the Gene Expression Omnibus (GEO) as the training dataset. GSE114007, GSE117999, and GSE82107 datasets were adopted for external validation. Genomic difference detection, protein-protein interaction network analysis, LASSO, SVM-RFE, Boruta, and univariate logistic regression (LR) analyses were used for feature selection. Multivariate LR, Random Forest (RF), Support Vector Machine (SVM), and XGBoost (XGB) were used to develop the multiple-gene diagnosis models. 12 control and 12 OA samples were collected from the local hospital for re-verification. The transfection assays were conducted to explore the regulatory ability of the gene to the apoptosis and vitality of chondrocytes. Through the bioinformatical analyses and machine learning algorithms, SLC2A1 and NDUFB9 of the 273 lactate metabolism-related genes were identified as the significant diagnosis biomarkers. The LR, RF, SVM, and XGB models performed impressively in the cohorts (AUC > 0.7). The local clinical samples indicated that SLC2A1 and NDUFB9 were both down-regulated in the OA samples (both P < 0.05). The knockdown of NDUFB9 inhibited the viability and promoted the apoptosis of the CHON-001 cells treated with IL-1beta (both P < 0.05). A lactate metabolism-related gene signature was constructed to diagnose OA, which was validated in multiple independent cohorts, local clinical samples, and cellular functional experiments.

A plastic correction algorithm for full-field elasto-plastic finite element simulations: critical assessment of predictive capabilities and improvement by machine learning

AbstractThis paper introduces a new local plastic correction algorithm that is aimed at accelerating elasto-plastic finite element (FE) simulations for structural problems exhibiting localised plasticity (around e.g. notches, geometrical defects). The proposed method belongs to the category of generalised multi-axial Neuber-type methods, which process the results of an elastic prediction point-wise in order to calculate an approximation of the full elasto-plastic solution. The proposed algorithm relies on a rule of local proportionality, which, in the context of J2 plasticity, allows us to express the plastic correction problem in terms of the amplitude of the full mechanical tensors only. This lightweight correction problem can be solved for numerically using a fully implicit time integrator that shares similarities with the radial return algorithm. The numerical capabilities of the proposed algorithm are demonstrated for a notched structure and a specimen containing a distribution of spherical pores, subjected to monotonic and cyclic loading. As a second point of innovation, we show that the proposed local plastic correction algorithm can be further accelerated by employing a simple meta-modelling strategy, with virtually no added errors. At last, we develop and investigate the merits of a deep-learning-based corrective layer designed to reduce the approximation error of the plastic corrector. A convolutional architecture is used to analyse the neighbourhoods of material points and outputs a scalar correction to the point-wise Neuber-type predictions. This optional brick of the proposed plastic correction methodology relies on the availability of a set of full elasto-plastic finite element solutions to be used as a training data-set.

Spatio-temporal reconstruction of droplet impingement dynamics by means of color-coded glare points and deep learning

Abstract The present work introduces a deep learning approach for the three-dimensional reconstruction of the spatio-temporal dynamics of the gas-liquid interface on the basis of monocular images obtained via optical measurement techniques.&amp;#xD;The method is tested an evaluated at the example of liquid droplets impacting on structured solid substrates.&amp;#xD;The droplet dynamics are captured through high-speed imaging in an extended shadowgraphy setup with additional glare points from lateral light sources that encode further three-dimensional information of the gas-liquid interface in the images.&amp;#xD;A neural network is trained for the physically correct reconstruction of the droplet dynamics on a labelled dataset generated by synthetic image rendering on the basis of gas-liquid interface shapes obtained from direct numerical simulation.&amp;#xD;The employment of synthetic image rendering allows for the efficient generation of training data and circumvents the introduction of errors resulting from the inherent discrepancy of the droplet shapes between experiment and simulation. &amp;#xD;The accurate reconstruction of the three-dimensional shape of the gas-liquid interface during droplet impingement on the basis of images obtained in the experiment demonstrates the practicality of the presented approach.&amp;#xD;The introduction of glare points from lateral light sources in the experiments is shown to improve the reconstruction accuracy, which indicates that the neural network learns to leverage the additional three-dimensional information encoded in the images for a more accurate depth estimation.&amp;#xD;By the successful reconstruction of obscured areas in the input images, it is demonstrated that the neural network has the capability to learn a physically correct interpolation of missing data from the numerical simulation.&amp;#xD;Furthermore, the physically reasonable reconstruction of unknown gas-liquid interface shapes for drop impact regimes that were not contained in the training dataset indicates that the neural network learned a versatile model of the involved two-phase flow phenomena during droplet impingement.

Resource-optimized cnns for real-time rice disease detection with ARM cortex-M microprocessors

This study explores the application of Artificial Intelligence (AI), specifically Convolutional Neural Networks (CNNs), for detecting rice plant diseases using ARM Cortex-M microprocessors. Given the significant role of rice as a staple food, particularly in Malaysia where the rice self-sufficiency ratio dropped from 65.2% in 2021 to 62.6% in 2022, there is a pressing need for advanced disease detection methods to enhance agricultural productivity and sustainability. The research utilizes two extensive datasets for model training and validation: the first dataset includes 5932 images across four rice disease classes, and the second comprises 10,407 images across ten classes. These datasets facilitate comprehensive disease detection analysis, leveraging MobileNetV2 and FD-MobileNet models optimized for the ARM Cortex-M4 microprocessor. The performance of these models is rigorously evaluated in terms of accuracy and computational efficiency. MobileNetV2, for instance, demonstrates a high accuracy rate of 97.5%, significantly outperforming FD-MobileNet, especially in detecting complex disease patterns such as tungro with a 93% accuracy rate. Despite FD-MobileNet’s lower resource consumption, its accuracy is limited to 90% across varied testing conditions. Resource optimization strategies highlight that even slight adjustments, such as a 0.5% reduction in RAM usage and a 1.14% decrease in flash memory, can result in a notable 9% increase in validation accuracy. This underscores the critical balance between computational resource management and model performance, particularly in resource-constrained settings like those provided by microcontrollers. In summary, the deployment of CNNs on microcontrollers presents a viable solution for real-time, on-site plant disease detection, demonstrating potential improvements in detection accuracy and operational efficiency. This study advances the field of smart agriculture by integrating cutting-edge AI with practical agricultural needs, aiming to address the challenges of food security in vulnerable regions.

Sentiment Analysis of User Reviews on BSI Mobile and Action Mobile Applications on the Google Play Store Using Multinomial Naive Bayes Algorithm

Mobile banking services are designed to facilitate customer transactions. Bank Syariah Indonesia (BSI) and Bank Aceh also provide these online services through their respective applications, BSI Mobile and Action Mobile. The mobile banking apps aim to simplify customer transactions, which can be conducted remotely via several features, from transfers, payments, and purchases to zakat payments, by simply connecting to the internet. Therefore, this research aims to classify the sentiment of user reviews for BSI Mobile and Action Mobile applications on Google Play Store to understand the users' experiences. The Multinomial Naïve Bayes algorithm is used in this study, where the algorithm analyzes and classifies the user reviews into positive and negative sentiment categories. The study involves several stages, such as text preprocessing, sentiment visualization, splitting the data into an 80:20 ratio for training and testing datasets, and training the model using the Multinomial Naïve Bayes algorithm. The results of this study show that the Multinomial Naïve Bayes algorithm performs well in analyzing user sentiment for BSI Mobile and Action Mobile, achieving an accuracy of 78.7%, precision of 76.5%, recall of 86.2%, and an F1-score of 80.6% for BSI Mobile, and an accuracy of 85.6%, precision of 75%, recall of 75%, and an F1-score of 75% for Action Mobile. Additionally, the sentiment classification results reveal that 52.8% of BSI Mobile user reviews are positive and 47.2% are negative, while for Action Mobile, 35.1% are positive and 64.9% are negative. For BSI Mobile, 21,497 reviews express a positive sentiment with dominant keywords such as "updated," "good," "balance," "transaction," and "thank." Meanwhile, for Action Mobile, 274 reviews express a negative sentiment with dominant keywords such as "transaction," "application," "network," "register," "please," and "update."

Comparative Analysis of the Response Accuracies of Large Language Models in the Korean National Dental Hygienist Examination Across Korean and English Questions.

Large language models such as Gemini, GPT-3.5, and GPT-4 have demonstrated significant potential in the medical field. Their performance in medical licensing examinations globally has highlighted their capabilities in understanding and processing specialized medical knowledge. This study aimed to evaluate and compare the performance of Gemini, GPT-3.5, and GPT-4 in the Korean National Dental Hygienist Examination. The accuracy of answering the examination questions in both Korean and English was assessed. This study used a dataset comprising questions from the Korean National Dental Hygienist Examination over 5 years (2019-2023). A two-way analysis of variance (ANOVA) test was employed to investigate the impacts of model type and language on the accuracy of the responses. Questions were input into each model under standardized conditions, and responses were classified as correct or incorrect based on predefined criteria. GPT-4 consistently outperformed the other models, achieving the highest accuracy rates across both language versions annually. In particular, it showed superior performance in English, suggesting advancements in its training algorithms for language processing. However, all models demonstrated variable accuracies in subjects with localized characteristics, such as health and medical law. These findings indicate that GPT-4 holds significant promise for application in medical education and standardized testing, especially in English. However, the variability in performance across different subjects and languages underscores the need for ongoing improvements and the inclusion of more diverse and localized training datasets to enhance the models' effectiveness in multilingual and multicultural contexts.

A Recurrent Deep Network for Gait Phase Identification from EMG Signals During Exoskeleton-Assisted Walking

Lower limb exoskeletons represent a relevant tool for rehabilitating gait in patients with lower limb movement disorders. Partial assistance exoskeletons adaptively provide the joint torque needed, on top of that produced by the patient, for a correct and stable gait, helping the patient to recover an autonomous gait. Thus, the device needs to identify the different phases of the gait cycle to produce precisely timed commands that drive its joint motors appropriately. In this study, EMG signals have been used for gait phase detection considering that EMG activations lead limb kinematics by at least 120 ms. We propose a deep learning model based on bidirectional LSTM to identify stance and swing gait phases from EMG data. We built a dataset of EMG signals recorded at 1500 Hz from four muscles from the dominant leg in a population of 26 healthy subjects walking overground (WO) and walking on a treadmill (WT) using a lower limb exoskeleton. The data were labeled with the corresponding stance or swing gait phase based on limb kinematics provided by inertial motion sensors. The model was studied in three different scenarios, and we explored its generalization abilities and evaluated its applicability to the online processing of EMG data. The training was always conducted on 500-sample sequences from WO recordings of 23 subjects. Testing always involved WO and WT sequences from the remaining three subjects. First, the model was trained and tested on 500 Hz EMG data, obtaining an overall accuracy on the WO and WT test datasets of 92.43% and 91.16%, respectively. The simulation of online operation required 127 ms to preprocess and classify one sequence. Second, the trained model was evaluated against a test set built on 1500 Hz EMG data. The accuracies were lower, yet the processing times were 11 ms faster. Third, we partially retrained the model on a subset of the 1500 Hz training dataset, achieving 87.17% and 89.64% accuracy on the 1500 Hz WO and WT test sets, respectively. Overall, the proposed deep learning model appears to be a valuable candidate for entering the control pipeline of a lower limb rehabilitation exoskeleton in terms of both the achieved accuracy and processing times.

Construction and interpretation of machine learning-based prognostic models for survival prediction among intestinal-type and diffuse-type gastric cancer patients

BackgroundGastric cancer is one of the most common malignant tumors worldwide, with high incidence and mortality rates, and it has a complex etiology and complex pathological features. Depending on the tumor type, gastric cancer can be classified as intestinal-type and diffuse-type gastric cancer, each with distinct pathogenic mechanisms and clinical presentations. In recent years, machine learning techniques have been widely applied in the medical field, offering new perspectives for the diagnosis, treatment, and prognosis of gastric cancer patients.MethodsThis study recruited 2158 gastric cancer patients and constructed prognostic prediction models for both intestinal-type and diffuse-type gastric cancer. Clinical pathological data were collected from patients, and machine learning algorithms were used for feature selection and model construction. The performance of the models was validated with training and testing datasets. The Shapley additive explanations (SHAP) values were used to interpret the model predictions and identify the main factors that influence patient survival.ResultsIn the prognostic model for intestinal-type gastric cancer, the gradient boosting decision tree (GBDT) model demonstrated the best performance, with key features including pTNM, CA125, tumor size, CA199, and PALB. Similarly, in the prognostic model for diffuse-type gastric cancer, the GBDT model was utilized, with key features comprising pTNM, Borrmann type IV disease, lymphocyte (LYM), lactate dehydrogenase (LDH), potassium (K), perineural invasion (PNI), tumor size, and whole stomach location. Risk stratification analysis revealed that the prognosis of high-risk patients was significantly worse than that of low-risk patients.ConclusionMachine learning shows great potential in predicting survival outcomes of gastric cancer patients, providing strong support for the development of personalized treatment plans.

TSAE-UNet: A Novel Network for Multi-Scene and Multi-Temporal Water Body Detection Based on Spatiotemporal Feature Extraction

The application of remote sensing technology in water body detection has become increasingly widespread, offering significant value for environmental monitoring, hydrological research, and disaster early warning. However, the existing methods face challenges in multi-scene and multi-temporal water body detection, including the diverse variations in water body shapes and sizes that complicate detection; the complexity of land cover types, which easily leads to false positives and missed detections; the high cost of acquiring high-resolution images, limiting long-term applications; and the lack of effective handling of multi-temporal data, making it difficult to capture the dynamic changes in water bodies. To address these challenges, this study proposes a novel network for multi-scene and multi-temporal water body detection based on spatiotemporal feature extraction, named TSAE-UNet. TSAE-UNet integrates convolutional neural networks (CNN), depthwise separable convolutions, ConvLSTM, and attention mechanisms, significantly improving the accuracy and robustness of water body detection by capturing multi-scale features and establishing long-term dependencies. The Otsu method was employed to quickly process Sentinel-1A and Sentinel-2 images, generating a high-quality training dataset. In the first experiment, five rectangular areas of approximately 37.5 km2 each were selected to validate the water body detection performance of the TSAE-UNet model across different scenes. The second experiment focused on Jining City, Shandong Province, China, analyzing the monthly water body changes from 2020 to 2022 and the quarterly changes in 2022. The experimental results demonstrate that TSAE-UNet excels in multi-scene and long-term water body detection, achieving a precision of 0.989, a recall of 0.983, an F1 score of 0.986, and an IoU of 0.974, significantly outperforming FCN, PSPNet, DeepLabV3+, ADCNN, and MECNet.

Comprehensive Approach to TB Diagnosis Powered by Machine Learning in Endemic Countries

Abstract Introduction/Objective Tuberculosis (TB), a leading cause of mortality worldwide, is primarily diagnosed through methods that face numerous challenges, including lengthy result times and diagnostic inaccuracy, particularly in the context of drug-resistant strains and latent infections. This study proposes a novel approach that integrates multiple diagnostic modalities with machine learning to enhance TB diagnosis accuracy. Methods/Case Report The Machine learning model was tailored for the classification of radiological images, specifically CT scans, using original DICOM images to preserve valuable voxel information. The study involved a curated dataset of CT scans from Pakistan, TB-positive (smear+/Culture+ n=72; smear+/culture- n= 3; smear-/Culture+ n=16; smear-/Culture- n=14; clinical and radiological diagnosis only n= 12) and healthy (n=103) scans from COVID-CTSet were included in the training to assess the specificity of the model. Data preprocessing included noise reduction, histogram matching, and data augmentation techniques to ensure a robust training dataset. The methodology also incorporated using k-fold cross validation and a custom learning rate scheduling strategy to optimize the model’s training process. To further test its robustness, the model was evaluated by swapping random patches and analyzing 60 mm patches from the entire CT scan for local feature categorization. Results (if a Case Study enter NA) The model has demonstrated outstanding performance, with sensitivity and specificity exceeding 95% on our internal dataset (n=117) and aligning well with clinical, smear, culture, and anti-TB antibody findings. It also showed promising results on the external NIH TB Portal’s dataset (n= 1,460). The model is robust to variations in CT scanner image quality and noise profiles, maintaining strong generalization across datasets. Even when analyzing random 60mm patches, effectively classifying all local features Conclusion Our study enhances tuberculosis diagnostic methods in endemic regions by blending machine learning with conventional diagnostic techniques. This approach improves TB detection, particularly the early and accurate identification in areas impacted by drug-resistant strains and asymptomatic latent infections. By integrating radiological and clinico-pathological data, we aim to develop a comprehensive diagnostic score. Moving forward, we plan to further integrate this method into clinical decision support systems and adapt the approach to other infectious diseases.

Integration of machine learning and CFD for modeling mass transfer in water treatment using membrane separation process

This study aims to assess the efficacy of machine learning models in predicting solute concentration (C) distribution in a membrane separation process, using the input parameters which are spatial coordinates. Computational fluid dynamics (CFD) was employed with machine learning for simulation of process. The models evaluated include Kernel Ridge Regression (KRR), Radius nearest neighbor regression (RNN), K-nearest neighbors (KNN), LASSO, and Multi-Layer Perceptron (MLP). Additionally, Harris Hawks Optimization (HHO) was utilized to fine-tune the hyperparameters of these models. Leading the way is the MLP model, which achieves a remarkable test R2 value of 0.98637 together with very low RMSE and MAE values. Strongness and generalization capacity are shown by its consistent performance on test and training datasets. To conclude, the effectiveness of using machine learning regression methods more especially, KRR, KNN, RNN, LASSO, and MLP in estimating concentration from spatial coordinates was demonstrated in this work. For separation science via membranes where predictive modeling of spatial data is essential, the results offer important new perspectives by developing hybrid model.

Automatic kidney stone identification: an adaptive feature-weighted LSTM model based on urine and blood routine analysis.

Kidney stones are the most common urinary system diseases, and early identification is of great significance. The purpose of this study was to use routine urine and blood detection indices to build a deep learning (DL) model to identify the presence of kidney stones in the early stage. A retrospective analysis was conducted on patients with kidney stones who were treated at West China Hospital of Sichuan University from January 2020 to June 2023. A total of 1130 individuals presenting with kidney stones and 1230 healthy subjects were enrolled. The first blood and urine laboratory data of participants at our hospital were collected, and the data were divided into a training dataset (80%) and a verification dataset (20%). Additionally, a long short-term memory (LSTM)-based adaptive feature weighting model was trained for the early identification of kidney stones, and the results were compared with those of other models. The performance of the model was evaluated by the area under the subject working characteristic curve (AUC). The important predictive factors are determined by ranking the characteristic importance of the predictive factors. A total of 17 variables were screened; among the top 4 characteristics according to the weight coefficient in this model, urine WBC, urine occult blood, qualitative urinary protein, and microcyte percentage had high predictive value for kidney stones in patients. The accuracy of the kidney stone (KS-LSTM) learning model was 89.5%, and the AUC was 0.95. Compared with other models, it has better performance. The results show that the KS-LSTM model based on routine urine and blood tests can accurately identify the presence of kidney stones. And provide valuable assistance for clinicians to identify kidney stones in the early stage.

A method for extracting Martian terrain features based on unsupervised contrastive learning

Intelligent recognition of Martian surface terrain is of great significance to autonomous exploration of Mars rovers. Feature extraction methods for Martian terrain images are currently mainly divided into two categories: traditional shallow visual feature extraction and deep feature extraction based on supervised learning. Loss of image information and the need for a large amount of labeled data are key issues to be addressed. A method for Martian terrain feature recognition based on unsupervised contrastive learning is proposed. By establishing an image dictionary dataset, two sets of neural networks, "query" and "encoding", are used to compare a single image with other images in the "dictionary" dataset, and the network is trained using the similarity functional as the loss function, thereby realizing feature recognition of Martian terrain images. The proposed method also has the ability to recognize new types of terrain images outside the training dataset, and has outstanding superiority in subsequent recognition and classification. Computer simulation verification shows that the recognition accuracy of the proposed method is and the 85.4%recognition accuracy of new types of terrain images is 84.5%.

Thermal, mechanical, and electrical properties of Si-stacked nanosheet transistors using machine learning interatomic potentials

Thermal and mechanical properties play a key role in optimizing the performance of nanoelectronic devices. In this study, the lattice thermal conductivity (κL) and elastic constants of Si nanosheets at different sheet thicknesses were determined using recently developed machine learning interatomic potentials (MLIPs). A Si nanosheet with a minimum thickness of 10 atomic layers was used for model training to predict the properties of sheets with greater thicknesses. The training dataset was efficiently constructed using stochastic sampling of the potential energy surface (PES). Density functional theory (DFT) calculations were used to extract&#xD;the MLIP, which served as the basis for further analysis. The Moment Tensor Potential (MTP) method was used to obtain the MLIP in this study. The results showed that, at sub-6 nm sheet thickness, the thermal conductivity dropped to ∼ 7 % of its bulk value, whereas some stiffness tensor components dropped to ∼ 3 % of the bulk values. These findings contribute to the understanding of heat transport and mechanical behavior of ultrathin Si nanosheets, which is crucial for designing and optimizing nanoelectronic devices. The technological implications of the extracted parameters on nanosheet field-effect transistor (NS-FET) performance at advanced technology nodes were evaluated using TCAD device simulations.