Single-pixel imaging(SPI)is a prominent scattering media imaging technique that allows image transmission via one-dimensional detection under structured illumination,with applications spanning from long-range imaging ...Single-pixel imaging(SPI)is a prominent scattering media imaging technique that allows image transmission via one-dimensional detection under structured illumination,with applications spanning from long-range imaging to microscopy.Recent advancements leveraging deep learning(DL)have significantly improved SPI performance,especially at low compression ratios.However,most DL-based SPI methods proposed so far rely heavily on extensive labeled datasets for supervised training,which are often impractical in real-world scenarios.Here,we propose an unsupervised learningenabled label-free SPI method for resilient information transmission through unknown dynamic scattering media.Additionally,we introduce a physics-informed autoencoder framework to optimize encoding schemes,further enhancing image quality at low compression ratios.Simulation and experimental results demonstrate that high-efficiency data transmission with structural similarity exceeding 0.9 is achieved through challenging turbulent channels.Moreover,experiments demonstrate that in a 5 m underwater dynamic turbulent channel,USAF target imaging quality surpasses traditional methods by over 13 dB.The compressive encoded transmission of 720×720 resolution video exceeding 30 seconds with great fidelity is also successfully demonstrated.These preliminary results suggest that our proposed method opens up a new paradigm for resilient information transmission through unknown dynamic scattering media and holds potential for broader applications within many other scattering media imaging technologies.展开更多
Automated cartoon character recognition is crucial for applications in content indexing,filtering,and copyright protection,yet it faces a significant challenge in animated media due to high intra-class visual variabil...Automated cartoon character recognition is crucial for applications in content indexing,filtering,and copyright protection,yet it faces a significant challenge in animated media due to high intra-class visual variability,where characters frequently alter their appearance.To address this problem,we introduce the novel Kral Sakir dataset,a public benchmark of 16,725 images specifically curated for the task of multi-label cartoon character classification under these varied conditions.This paper conducts a comprehensive benchmark study,evaluating the performance of state-of-the-art pretrained Convolutional Neural Networks(CNNs),including DenseNet,ResNet,and VGG,against a custom baseline model trained from scratch.Our experiments,evaluated using metrics of F1-Score,accuracy,and Area Under the ROC Curve(AUC),demonstrate that fine-tuning pretrained models is a highly effective strategy.The best-performing model,DenseNet121,achieved an F1-Score of 0.9890 and an accuracy of 0.9898,significantly outperforming our baseline CNN(F1-Score of 0.9545).The findings validate the power of transfer learning for this domain and establish a strong performance benchmark.The introduced dataset provides a valuable resource for future research into developing robust and accurate character recognition systems.展开更多
Holographic microscopy has emerged as a vital tool in biomedicine,enabling visualization of microscopic morphological features of tissues and cells in a label-free manner.Recently,deep learning(DL)-based image reconst...Holographic microscopy has emerged as a vital tool in biomedicine,enabling visualization of microscopic morphological features of tissues and cells in a label-free manner.Recently,deep learning(DL)-based image reconstruction models have demonstrated state-of-the-art performance in holographic image reconstruction.However,their utility in practice is still severely limited,as conventional training schemes could not properly handle out-of-distribution data.Here,we leverage backpropagation operation and reparameterization of the forward propagator to enable an adaptable image reconstruction model for histopathologic inspection.Only given with a training dataset of rectum tissue images captured from a single imaging configuration,our scheme consistently shows high reconstruction performance even with the input hologram of diverse tissue types at different pathological states captured under various imaging configurations.Using the proposed adaptation technique,we show that the diagnostic features of cancerous colorectal tissues,such as dirty necrosis,captured with 5×magnification and a numerical aperture(NA)of 0.1,can be reconstructed with high accuracy,whereas a given training dataset is strictly confined to normal rectum tissues acquired under the imaging configuration of 20×magnification and an NA of 0.4.Our results suggest that the DL-based image reconstruction approaches,with sophisticated adaptation techniques,could offer an extensively generalizable solution for inverse mapping problems in imaging.展开更多
In its 2023 global health statistics,the World Health Organization noted that noncommunicable diseases(NCDs)remain the leading cause of disease burden worldwide,with cardiovascular diseases(CVDs)resulting in more deat...In its 2023 global health statistics,the World Health Organization noted that noncommunicable diseases(NCDs)remain the leading cause of disease burden worldwide,with cardiovascular diseases(CVDs)resulting in more deaths than the three other major NCDs combined.In this study,we developed a method that can comprehensively detect which CVDs are present in a patient.Specifically,we propose a multi-label classification method that utilizes photoplethysmography(PPG)signals and physiological characteristics from public datasets to classify four types of CVDs and related conditions:hypertension,diabetes,cerebral infarction,and cerebrovascular disease.Our approach to multi-disease classification of cardiovascular diseases(CVDs)using PPG signals achieves the highest classification performance when encompassing the broadest range of disease categories,thereby offering a more comprehensive assessment of human health.We employ a multi-label classification strategy to simultaneously predict the presence or absence of multiple diseases.Specifically,we first apply the Savitzky-Golay(S-G)filter to the PPG signals to reduce noise and then transform into statistical features.We integrate processed PPG signals with individual physiological features as a multimodal input,thereby expanding the learned feature space.Notably,even with a simple machine learning method,this approach can achieve relatively high accuracy.The proposed method achieved a maximum F1-score of 0.91,minimum Hamming loss of 0.04,and an accuracy of 0.95.Thus,our method represents an effective and rapid solution for detecting multiple diseases simultaneously,which is beneficial for comprehensively managing CVDs.展开更多
This paper investigates the optimization of data sampling and target labeling techniques to enhance algorithmic trading strategies in cryptocurrency markets,focusing on Bitcoin(BTC)and Ethereum(ETH).Traditional data s...This paper investigates the optimization of data sampling and target labeling techniques to enhance algorithmic trading strategies in cryptocurrency markets,focusing on Bitcoin(BTC)and Ethereum(ETH).Traditional data sampling methods,such as time bars,often fail to capture the nuances of the continuously active and highly volatile cryptocurrency market and force traders to wait for arbitrary points in time.To address this,we propose an alternative approach using information-driven sampling methods,including the CUSUM filter,range bars,volume bars,and dollar bars,and evaluate their performance using tick-level data from January 2018 to June 2023.Additionally,we introduce the Triple Barrier method for target labeling,which offers a solution tailored for algorithmic trading as opposed to the widely used next-bar prediction.We empirically assess the effectiveness of these data sampling and labeling methods to craft profitable trading strategies.The results demonstrate that the innovative combination of CUSUM-filtered data with Triple Barrier labeling outperforms traditional time bars and next-bar prediction,achieving consistently positive trading performance even after accounting for transaction costs.Moreover,our system enables making trading decisions at any point in time on the basis of market conditions,providing an advantage over traditional methods that rely on fixed time intervals.Furthermore,the paper contributes to the ongoing debate on the applicability of Transformer models to time series classification in the context of algorithmic trading by evaluating various Transformer architectures—including the vanilla Transformer encoder,FEDformer,and Autoformer—alongside other deep learning architectures and classical machine learning models,revealing insights into their relative performance.展开更多
This paper introduces a novel ensemble Deep learning(DL)-based Multi-Label Retinal Disease Classification(MLRDC)system,known for its high accuracy and efficiency.Utilising a stacking ensemble approach,and integrating ...This paper introduces a novel ensemble Deep learning(DL)-based Multi-Label Retinal Disease Classification(MLRDC)system,known for its high accuracy and efficiency.Utilising a stacking ensemble approach,and integrating DenseNet201,EfficientNetB4,EfficientNetB3 and EfficientNetV2S models,exceptional performance in retinal disease classification is achieved.The proposed MLRDC model,leveraging DL as the meta-model,outperforms individual base detectors,with DenseNet201 and EfficientNetV2S achieving an accuracy of 96.5%,precision of 98.6%,recall of 97.1%,and F1 score of 97.8%.Weighted multilabel classifiers in the ensemble exhibit an average accuracy of 90.6%,precision of 98.3%,recall of 91.2%,and F1 score of 94.6%,whereas unweighted models achieve an average accuracy of 90%,precision of 98.6%,recall of 93.1%,and F1 score of 95.7%.Employing Logistic Regression(LR)as the meta-model,the proposed MLRDC system achieves an accuracy of 93.5%,precision of 98.2%,recall of 93.9%,and F1 score of 96%,with a minimal loss of 0.029.These results highlight the superiority of the proposed model over benchmark state-of-the-art ensembles,emphasising its practical applicability in medical image classification.展开更多
The rise of deep learning has brought about transformative advancements in both scientific research and engineering applications.The 2024 Nobel Prizes,particularly in Physics and Chemistry,highlighted the revolutionar...The rise of deep learning has brought about transformative advancements in both scientific research and engineering applications.The 2024 Nobel Prizes,particularly in Physics and Chemistry,highlighted the revolutionary impact of deep learning,with AlphaFold’s breakthrough in protein structure prediction exemplifying its potential.This review explores the historical evolution of deep learning,from its foundational theories in neural networks and connectionism to its modern applications in various fields.Focus is given to its use in geotechnical engineering,particularly in geological disaster prediction,tunnel safety monitoring,and structural design optimization.The integration of deep learning models such as Convolutional Neural Networks(CNNs),Recurrent Neural Networks(RNNs),and Transformers has enabled significant progress in analyzing complex,unstructured data,offering innovative solutions to longstanding engineering challenges.The review also examines the opportunities and challenges faced by the field,advocating for interdisciplinary collaboration and open data sharing to further unlock deep learning’s potential in advancing both scientific and engineering disciplines.As deep learning continues to evolve,it promises to drive further innovation,shaping the future of engineering practices and scientific discovery.展开更多
The unsupervised vehicle re-identification task aims at identifying specific vehicles in surveillance videos without utilizing annotation information.Due to the higher similarity in appearance between vehicles compare...The unsupervised vehicle re-identification task aims at identifying specific vehicles in surveillance videos without utilizing annotation information.Due to the higher similarity in appearance between vehicles compared to pedestrians,pseudo-labels generated through clustering are ineffective in mitigating the impact of noise,and the feature distance between inter-class and intra-class has not been adequately improved.To address the aforementioned issues,we design a dual contrastive learning method based on knowledge distillation.During each iteration,we utilize a teacher model to randomly partition the entire dataset into two sub-domains based on clustering pseudo-label categories.By conducting contrastive learning between the two student models,we extract more discernible vehicle identity cues to improve the problem of imbalanced data distribution.Subsequently,we propose a context-aware pseudo label refinement strategy that leverages contextual features by progressively associating granularity information from different bottleneck blocks.To produce more trustworthy pseudo-labels and lessen noise interference during the clustering process,the context-aware scores are obtained by calculating the similarity between global features and contextual ones,which are subsequently added to the pseudo-label encoding process.The proposed method has achieved excellent performance in overcoming label noise and optimizing data distribution through extensive experimental results on publicly available datasets.展开更多
Medical image segmentation,i.e.,labeling structures of interest in medical images,is crucial for disease diagnosis and treatment in radiology.In reversible data hiding in medical images(RDHMI),segmentation consists of...Medical image segmentation,i.e.,labeling structures of interest in medical images,is crucial for disease diagnosis and treatment in radiology.In reversible data hiding in medical images(RDHMI),segmentation consists of only two regions:the focal and nonfocal regions.The focal region mainly contains information for diagnosis,while the nonfocal region serves as the monochrome background.The current traditional segmentation methods utilized in RDHMI are inaccurate for complex medical images,and manual segmentation is time-consuming,poorly reproducible,and operator-dependent.Implementing state-of-the-art deep learning(DL)models will facilitate key benefits,but the lack of domain-specific labels for existing medical datasets makes it impossible.To address this problem,this study provides labels of existing medical datasets based on a hybrid segmentation approach to facilitate the implementation of DL segmentation models in this domain.First,an initial segmentation based on a 33 kernel is performed to analyze×identified contour pixels before classifying pixels into focal and nonfocal regions.Then,several human expert raters evaluate and classify the generated labels into accurate and inaccurate labels.The inaccurate labels undergo manual segmentation by medical practitioners and are scored based on a hierarchical voting scheme before being assigned to the proposed dataset.To ensure reliability and integrity in the proposed dataset,we evaluate the accurate automated labels with manually segmented labels by medical practitioners using five assessment metrics:dice coefficient,Jaccard index,precision,recall,and accuracy.The experimental results show labels in the proposed dataset are consistent with the subjective judgment of human experts,with an average accuracy score of 94%and dice coefficient scores between 90%-99%.The study further proposes a ResNet-UNet with concatenated spatial and channel squeeze and excitation(scSE)architecture for semantic segmentation to validate and illustrate the usefulness of the proposed dataset.The results demonstrate the superior performance of the proposed architecture in accurately separating the focal and nonfocal regions compared to state-of-the-art architectures.Dataset information is released under the following URL:https://www.kaggle.com/lordamoah/datasets(accessed on 31 March 2025).展开更多
Cyclohexene is an important raw material in the production of nylon.Selective hydrogenation of benzene is a key method for preparing cyclohexene.However,the Ru catalysts used in current industrial processes still face...Cyclohexene is an important raw material in the production of nylon.Selective hydrogenation of benzene is a key method for preparing cyclohexene.However,the Ru catalysts used in current industrial processes still face challenges,including high metal usage,high process costs,and low cyclohexene yield.This study utilizes existing literature data combined with machine learning methods to analyze the factors influencing benzene conversion,cyclohexene selectivity,and yield in the benzene hydrogenation to cyclohexene reaction.It constructs predictive models based on XGBoost and Random Forest algorithms.After analysis,it was found that reaction time,Ru content,and space velocity are key factors influencing cyclohexene yield,selectivity,and benzene conversion.Shapley Additive Explanations(SHAP)analysis and feature importance analysis further revealed the contribution of each variable to the reaction outcomes.Additionally,we randomly generated one million variable combinations using the Dirichlet distribution to attempt to predict high-yield catalyst formulations.This paper provides new insights into the application of machine learning in heterogeneous catalysis and offers some reference for further research.展开更多
As urbanization continues to accelerate,the challenges associated with managing transportation in metropolitan areas become increasingly complex.The surge in population density contributes to traffic congestion,impact...As urbanization continues to accelerate,the challenges associated with managing transportation in metropolitan areas become increasingly complex.The surge in population density contributes to traffic congestion,impacting travel experiences and posing safety risks.Smart urban transportation management emerges as a strategic solution,conceptualized here as a multidimensional big data problem.The success of this strategy hinges on the effective collection of information from diverse,extensive,and heterogeneous data sources,necessitating the implementation of full⁃stack Information and Communication Technology(ICT)solutions.The main idea of the work is to investigate the current technologies of Intelligent Transportation Systems(ITS)and enhance the safety of urban transportation systems.Machine learning models,trained on historical data,can predict traffic congestion,allowing for the implementation of preventive measures.Deep learning architectures,with their ability to handle complex data representations,further refine traffic predictions,contributing to more accurate and dynamic transportation management.The background of this research underscores the challenges posed by traffic congestion in metropolitan areas and emphasizes the need for advanced technological solutions.By integrating GPS and GIS technologies with machine learning algorithms,this work aims to pay attention to the development of intelligent transportation systems that not only address current challenges but also pave the way for future advancements in urban transportation management.展开更多
BACKGROUND The accurate prediction of lymph node metastasis(LNM)is crucial for managing locally advanced(T3/T4)colorectal cancer(CRC).However,both traditional histopathology and standard slide-level deep learning ofte...BACKGROUND The accurate prediction of lymph node metastasis(LNM)is crucial for managing locally advanced(T3/T4)colorectal cancer(CRC).However,both traditional histopathology and standard slide-level deep learning often fail to capture the sparse and diagnostically critical features of metastatic potential.AIM To develop and validate a case-level multiple-instance learning(MIL)framework mimicking a pathologist's comprehensive review and improve T3/T4 CRC LNM prediction.METHODS The whole-slide images of 130 patients with T3/T4 CRC were retrospectively collected.A case-level MIL framework utilising the CONCH v1.5 and UNI2-h deep learning models was trained on features from all haematoxylin and eosinstained primary tumour slides for each patient.These pathological features were subsequently integrated with clinical data,and model performance was evaluated using the area under the curve(AUC).RESULTS The case-level framework demonstrated superior LNM prediction over slide-level training,with the CONCH v1.5 model achieving a mean AUC(±SD)of 0.899±0.033 vs 0.814±0.083,respectively.Integrating pathology features with clinical data further enhanced performance,yielding a top model with a mean AUC of 0.904±0.047,in sharp contrast to a clinical-only model(mean AUC 0.584±0.084).Crucially,a pathologist’s review confirmed that the model-identified high-attention regions correspond to known high-risk histopathological features.CONCLUSION A case-level MIL framework provides a superior approach for predicting LNM in advanced CRC.This method shows promise for risk stratification and therapy decisions,requiring further validation.展开更多
The solar cycle(SC),a phenomenon caused by the quasi-periodic regular activities in the Sun,occurs approximately every 11 years.Intense solar activity can disrupt the Earth’s ionosphere,affecting communication and na...The solar cycle(SC),a phenomenon caused by the quasi-periodic regular activities in the Sun,occurs approximately every 11 years.Intense solar activity can disrupt the Earth’s ionosphere,affecting communication and navigation systems.Consequently,accurately predicting the intensity of the SC holds great significance,but predicting the SC involves a long-term time series,and many existing time series forecasting methods have fallen short in terms of accuracy and efficiency.The Time-series Dense Encoder model is a deep learning solution tailored for long time series prediction.Based on a multi-layer perceptron structure,it outperforms the best previously existing models in accuracy,while being efficiently trainable on general datasets.We propose a method based on this model for SC forecasting.Using a trained model,we predict the test set from SC 19 to SC 25 with an average mean absolute percentage error of 32.02,root mean square error of 30.3,mean absolute error of 23.32,and R^(2)(coefficient of determination)of 0.76,outperforming other deep learning models in terms of accuracy and training efficiency on sunspot number datasets.Subsequently,we use it to predict the peaks of SC 25 and SC 26.For SC 25,the peak time has ended,but a stronger peak is predicted for SC 26,of 199.3,within a range of 170.8-221.9,projected to occur during April 2034.展开更多
Unmanned Aerial Vehicles(UAVs)have become integral components in smart city infrastructures,supporting applications such as emergency response,surveillance,and data collection.However,the high mobility and dynamic top...Unmanned Aerial Vehicles(UAVs)have become integral components in smart city infrastructures,supporting applications such as emergency response,surveillance,and data collection.However,the high mobility and dynamic topology of Flying Ad Hoc Networks(FANETs)present significant challenges for maintaining reliable,low-latency communication.Conventional geographic routing protocols often struggle in situations where link quality varies and mobility patterns are unpredictable.To overcome these limitations,this paper proposes an improved routing protocol based on reinforcement learning.This new approach integrates Q-learning with mechanisms that are both link-aware and mobility-aware.The proposed method optimizes the selection of relay nodes by using an adaptive reward function that takes into account energy consumption,delay,and link quality.Additionally,a Kalman filter is integrated to predict UAV mobility,improving the stability of communication links under dynamic network conditions.Simulation experiments were conducted using realistic scenarios,varying the number of UAVs to assess scalability.An analysis was conducted on key performance metrics,including the packet delivery ratio,end-to-end delay,and total energy consumption.The results demonstrate that the proposed approach significantly improves the packet delivery ratio by 12%–15%and reduces delay by up to 25.5%when compared to conventional GEO and QGEO protocols.However,this improvement comes at the cost of higher energy consumption due to additional computations and control overhead.Despite this trade-off,the proposed solution ensures reliable and efficient communication,making it well-suited for large-scale UAV networks operating in complex urban environments.展开更多
First-principles calculations based on density functional theory(DFT)have had a significant impact on chemistry,physics,and materials science,enabling in-depth exploration of the structural and electronic properties o...First-principles calculations based on density functional theory(DFT)have had a significant impact on chemistry,physics,and materials science,enabling in-depth exploration of the structural and electronic properties of a wide variety of materials.Among different implementations of DFT,the plane-wave method is widely used for periodic systems because of its high accuracy.However,this method typically requires a large number of basis functions for large systems,leading to high computational costs.Localized basis sets,such as the muffin-tin orbital(MTO)method,have been introduced to provide a more efficient description of electronic structure with a reduced basis set,albeit at the cost of reduced computational accuracy.In this work,we propose an optimization strategy using machine-learning techniques to automate MTO basis-set parameters,thereby improving the accuracy and efficiency of MTO-based calculations.Default MTO parameter settings primarily focus on lattice structure and give less consideration to element-specific differences.In contrast,our optimized parameters incorporate both structural and elemental information.Based on these converged parameters,we successfully recovered missing bands for CrTe_(2).For the other three materials—Si,GaAs,and CrI_(3)—we achieved band improvements of up to 2 e V.Furthermore,the generalization of the machine-learned method is validated by perturbation,strain,and elemental substitution,resulting in improved band structures.Additionally,lattice-constant optimization for Ga As using the converged parameters yields closer agreement with experiment.展开更多
The rapid advancement of machine learning based tight-binding Hamiltonian(MLTB)methods has opened new avenues for efficient and accurate electronic structure simulations,particularly in large-scale systems and long-ti...The rapid advancement of machine learning based tight-binding Hamiltonian(MLTB)methods has opened new avenues for efficient and accurate electronic structure simulations,particularly in large-scale systems and long-time scenarios.This review begins with a concise overview of traditional tight-binding(TB)models,including both(semi-)empirical and first-principles approaches,establishing the foundation for understanding MLTB developments.We then present a systematic classification of existing MLTB methodologies,grouped into two major categories:direct prediction of TB Hamiltonian elements and inference of empirical parameters.A comparative analysis with other ML-based electronic structure models is also provided,highlighting the advancement of MLTB approaches.Finally,we explore the emerging MLTB application ecosystem,highlighting how the integration of MLTB models with a diverse suite of post-processing tools from linear-scaling solvers to quantum transport frameworks and molecular dynamics interfaces is essential for tackling complex scientific problems across different domains.The continued advancement of this integrated paradigm promises to accelerate materials discovery and open new frontiers in the predictive simulation of complex quantum phenomena.展开更多
Background:Stomach cancer(SC)is one of the most lethal malignancies worldwide due to late-stage diagnosis and limited treatment.The transcriptomic,epigenomic,and proteomic,etc.,omics datasets generated by high-through...Background:Stomach cancer(SC)is one of the most lethal malignancies worldwide due to late-stage diagnosis and limited treatment.The transcriptomic,epigenomic,and proteomic,etc.,omics datasets generated by high-throughput sequencing technology have become prominent in biomedical research,and they reveal molecular aspects of cancer diagnosis and therapy.Despite the development of advanced sequencing technology,the presence of high-dimensionality in multi-omics data makes it challenging to interpret the data.Methods:In this study,we introduce RankXLAN,an explainable ensemble-based multi-omics framework that integrates feature selection(FS),ensemble learning,bioinformatics,and in-silico validation for robust biomarker detection,potential therapeutic drug-repurposing candidates’identification,and classification of SC.To enhance the interpretability of the model,we incorporated explainable artificial intelligence(SHapley Additive exPlanations analysis),as well as accuracy,precision,F1-score,recall,cross-validation,specificity,likelihood ratio(LR)+,LR−,and Youden index results.Results:The experimental results showed that the top four FS algorithms achieved improved results when applied to the ensemble learning classification model.The proposed ensemble model produced an area under the curve(AUC)score of 0.994 for gene expression,0.97 for methylation,and 0.96 for miRNA expression data.Through the integration of bioinformatics and ML approach of the transcriptomic and epigenomic multi-omics dataset,we identified potential marker genes,namely,UBE2D2,HPCAL4,IGHA1,DPT,and FN3K.In-silico molecular docking revealed a strong binding affinity between ANKRD13C and the FDA-approved drug Everolimus(binding affinity−10.1 kcal/mol),identifying ANKRD13C as a potential therapeutic drug-repurposing target for SC.Conclusion:The proposed framework RankXLAN outperforms other existing frameworks for serum biomarker identification,therapeutic target identification,and SC classification with multi-omics datasets.展开更多
Graph Federated Learning(GFL)has shown great potential in privacy protection and distributed intelligence through distributed collaborative training of graph-structured data without sharing raw information.However,exi...Graph Federated Learning(GFL)has shown great potential in privacy protection and distributed intelligence through distributed collaborative training of graph-structured data without sharing raw information.However,existing GFL approaches often lack the capability for comprehensive feature extraction and adaptive optimization,particularly in non-independent and identically distributed(NON-IID)scenarios where balancing global structural understanding and local node-level detail remains a challenge.To this end,this paper proposes a novel framework called GFL-SAR(Graph Federated Collaborative Learning Framework Based on Structural Amplification and Attention Refinement),which enhances the representation learning capability of graph data through a dual-branch collaborative design.Specifically,we propose the Structural Insight Amplifier(SIA),which utilizes an improved Graph Convolutional Network(GCN)to strengthen structural awareness and improve modeling of topological patterns.In parallel,we propose the Attentive Relational Refiner(ARR),which employs an enhanced Graph Attention Network(GAT)to perform fine-grained modeling of node relationships and neighborhood features,thereby improving the expressiveness of local interactions and preserving critical contextual information.GFL-SAR effectively integrates multi-scale features from every branch via feature fusion and federated optimization,thereby addressing existing GFL limitations in structural modeling and feature representation.Experiments on standard benchmark datasets including Cora,Citeseer,Polblogs,and Cora_ML demonstrate that GFL-SAR achieves superior performance in classification accuracy,convergence speed,and robustness compared to existing methods,confirming its effectiveness and generalizability in GFL tasks.展开更多
Wearable sensors integrated with deep learning techniques have the potential to revolutionize seamless human-machine interfaces for real-time health monitoring,clinical diagnosis,and robotic applications.Nevertheless,...Wearable sensors integrated with deep learning techniques have the potential to revolutionize seamless human-machine interfaces for real-time health monitoring,clinical diagnosis,and robotic applications.Nevertheless,it remains a critical challenge to simultaneously achieve desirable mechanical and electrical performance along with biocompatibility,adhesion,self-healing,and environmental robustness with excellent sensing metrics.Herein,we report a multifunctional,anti-freezing,selfadhesive,and self-healable organogel pressure sensor composed of cobalt nanoparticle encapsulated nitrogen-doped carbon nanotubes(CoN CNT)embedded in a polyvinyl alcohol-gelatin(PVA/GLE)matrix.Fabricated using a binary solvent system of water and ethylene glycol(EG),the CoN CNT/PVA/GLE organogel exhibits excellent flexibility,biocompatibility,and temperature tolerance with remarkable environmental stability.Electrochemical impedance spectroscopy confirms near-stable performance across a broad humidity range(40%-95%RH).Freeze-tolerant conductivity under sub-zero conditions(-20℃)is attributed to the synergistic role of CoN CNT and EG,preserving mobility and network integrity.The Co N CNT/PVA/GLE organogel sensor exhibits high sensitivity of 5.75 k Pa^(-1)in the detection range from 0 to 20 k Pa,ideal for subtle biomechanical motion detection.A smart human-machine interface for English letter recognition using deep learning achieved 98%accuracy.The organogel sensor utility was extended to detect human gestures like finger bending,wrist motion,and throat vibration during speech.展开更多
基金supported by the Natural Science Foundation of China Project(No.62525102).
文摘Single-pixel imaging(SPI)is a prominent scattering media imaging technique that allows image transmission via one-dimensional detection under structured illumination,with applications spanning from long-range imaging to microscopy.Recent advancements leveraging deep learning(DL)have significantly improved SPI performance,especially at low compression ratios.However,most DL-based SPI methods proposed so far rely heavily on extensive labeled datasets for supervised training,which are often impractical in real-world scenarios.Here,we propose an unsupervised learningenabled label-free SPI method for resilient information transmission through unknown dynamic scattering media.Additionally,we introduce a physics-informed autoencoder framework to optimize encoding schemes,further enhancing image quality at low compression ratios.Simulation and experimental results demonstrate that high-efficiency data transmission with structural similarity exceeding 0.9 is achieved through challenging turbulent channels.Moreover,experiments demonstrate that in a 5 m underwater dynamic turbulent channel,USAF target imaging quality surpasses traditional methods by over 13 dB.The compressive encoded transmission of 720×720 resolution video exceeding 30 seconds with great fidelity is also successfully demonstrated.These preliminary results suggest that our proposed method opens up a new paradigm for resilient information transmission through unknown dynamic scattering media and holds potential for broader applications within many other scattering media imaging technologies.
文摘Automated cartoon character recognition is crucial for applications in content indexing,filtering,and copyright protection,yet it faces a significant challenge in animated media due to high intra-class visual variability,where characters frequently alter their appearance.To address this problem,we introduce the novel Kral Sakir dataset,a public benchmark of 16,725 images specifically curated for the task of multi-label cartoon character classification under these varied conditions.This paper conducts a comprehensive benchmark study,evaluating the performance of state-of-the-art pretrained Convolutional Neural Networks(CNNs),including DenseNet,ResNet,and VGG,against a custom baseline model trained from scratch.Our experiments,evaluated using metrics of F1-Score,accuracy,and Area Under the ROC Curve(AUC),demonstrate that fine-tuning pretrained models is a highly effective strategy.The best-performing model,DenseNet121,achieved an F1-Score of 0.9890 and an accuracy of 0.9898,significantly outperforming our baseline CNN(F1-Score of 0.9545).The findings validate the power of transfer learning for this domain and establish a strong performance benchmark.The introduced dataset provides a valuable resource for future research into developing robust and accurate character recognition systems.
基金supported by the Samsung Research Funding and Incubation Center of Samsung Electronics(Grant No.SRFC-IT2002-03)the Samsung Electronics Co.,Ltd.(Grant No.IO220908-02403-01)+2 种基金the National Research Foundation of Korea(NRF)grant funded by the Korean government(MSIT)(Grant Nos.NRF-RS-2021-NR060086 and NRF-RS-2023-00251628)the Bio&Medical Technology Development Program of the National Research Foundation funded by the Korean government(MSIT)(Grant No RS-2024-00397673)the KAIST-CERAGEM Next Generation Healthcare Research Center.
文摘Holographic microscopy has emerged as a vital tool in biomedicine,enabling visualization of microscopic morphological features of tissues and cells in a label-free manner.Recently,deep learning(DL)-based image reconstruction models have demonstrated state-of-the-art performance in holographic image reconstruction.However,their utility in practice is still severely limited,as conventional training schemes could not properly handle out-of-distribution data.Here,we leverage backpropagation operation and reparameterization of the forward propagator to enable an adaptable image reconstruction model for histopathologic inspection.Only given with a training dataset of rectum tissue images captured from a single imaging configuration,our scheme consistently shows high reconstruction performance even with the input hologram of diverse tissue types at different pathological states captured under various imaging configurations.Using the proposed adaptation technique,we show that the diagnostic features of cancerous colorectal tissues,such as dirty necrosis,captured with 5×magnification and a numerical aperture(NA)of 0.1,can be reconstructed with high accuracy,whereas a given training dataset is strictly confined to normal rectum tissues acquired under the imaging configuration of 20×magnification and an NA of 0.4.Our results suggest that the DL-based image reconstruction approaches,with sophisticated adaptation techniques,could offer an extensively generalizable solution for inverse mapping problems in imaging.
基金supporting of the National Science and Technology Council NSTC(grant nos.NSTC 112-2221-E-019-023,NSTC 113-2221-E-019-039)Taiwan University of Science and Technology.
文摘In its 2023 global health statistics,the World Health Organization noted that noncommunicable diseases(NCDs)remain the leading cause of disease burden worldwide,with cardiovascular diseases(CVDs)resulting in more deaths than the three other major NCDs combined.In this study,we developed a method that can comprehensively detect which CVDs are present in a patient.Specifically,we propose a multi-label classification method that utilizes photoplethysmography(PPG)signals and physiological characteristics from public datasets to classify four types of CVDs and related conditions:hypertension,diabetes,cerebral infarction,and cerebrovascular disease.Our approach to multi-disease classification of cardiovascular diseases(CVDs)using PPG signals achieves the highest classification performance when encompassing the broadest range of disease categories,thereby offering a more comprehensive assessment of human health.We employ a multi-label classification strategy to simultaneously predict the presence or absence of multiple diseases.Specifically,we first apply the Savitzky-Golay(S-G)filter to the PPG signals to reduce noise and then transform into statistical features.We integrate processed PPG signals with individual physiological features as a multimodal input,thereby expanding the learned feature space.Notably,even with a simple machine learning method,this approach can achieve relatively high accuracy.The proposed method achieved a maximum F1-score of 0.91,minimum Hamming loss of 0.04,and an accuracy of 0.95.Thus,our method represents an effective and rapid solution for detecting multiple diseases simultaneously,which is beneficial for comprehensively managing CVDs.
基金support of the University of Warsaw under’New Ideas 3B’competition in POB Ⅲ implemented under the’Excellence Initiative-Research University’Programme.
文摘This paper investigates the optimization of data sampling and target labeling techniques to enhance algorithmic trading strategies in cryptocurrency markets,focusing on Bitcoin(BTC)and Ethereum(ETH).Traditional data sampling methods,such as time bars,often fail to capture the nuances of the continuously active and highly volatile cryptocurrency market and force traders to wait for arbitrary points in time.To address this,we propose an alternative approach using information-driven sampling methods,including the CUSUM filter,range bars,volume bars,and dollar bars,and evaluate their performance using tick-level data from January 2018 to June 2023.Additionally,we introduce the Triple Barrier method for target labeling,which offers a solution tailored for algorithmic trading as opposed to the widely used next-bar prediction.We empirically assess the effectiveness of these data sampling and labeling methods to craft profitable trading strategies.The results demonstrate that the innovative combination of CUSUM-filtered data with Triple Barrier labeling outperforms traditional time bars and next-bar prediction,achieving consistently positive trading performance even after accounting for transaction costs.Moreover,our system enables making trading decisions at any point in time on the basis of market conditions,providing an advantage over traditional methods that rely on fixed time intervals.Furthermore,the paper contributes to the ongoing debate on the applicability of Transformer models to time series classification in the context of algorithmic trading by evaluating various Transformer architectures—including the vanilla Transformer encoder,FEDformer,and Autoformer—alongside other deep learning architectures and classical machine learning models,revealing insights into their relative performance.
文摘This paper introduces a novel ensemble Deep learning(DL)-based Multi-Label Retinal Disease Classification(MLRDC)system,known for its high accuracy and efficiency.Utilising a stacking ensemble approach,and integrating DenseNet201,EfficientNetB4,EfficientNetB3 and EfficientNetV2S models,exceptional performance in retinal disease classification is achieved.The proposed MLRDC model,leveraging DL as the meta-model,outperforms individual base detectors,with DenseNet201 and EfficientNetV2S achieving an accuracy of 96.5%,precision of 98.6%,recall of 97.1%,and F1 score of 97.8%.Weighted multilabel classifiers in the ensemble exhibit an average accuracy of 90.6%,precision of 98.3%,recall of 91.2%,and F1 score of 94.6%,whereas unweighted models achieve an average accuracy of 90%,precision of 98.6%,recall of 93.1%,and F1 score of 95.7%.Employing Logistic Regression(LR)as the meta-model,the proposed MLRDC system achieves an accuracy of 93.5%,precision of 98.2%,recall of 93.9%,and F1 score of 96%,with a minimal loss of 0.029.These results highlight the superiority of the proposed model over benchmark state-of-the-art ensembles,emphasising its practical applicability in medical image classification.
基金support provided by the Hebei Province Full-Time Recruitment of National High-Level Innovative Talents Research Project(Grant No.2023HBQZYCSB004).
文摘The rise of deep learning has brought about transformative advancements in both scientific research and engineering applications.The 2024 Nobel Prizes,particularly in Physics and Chemistry,highlighted the revolutionary impact of deep learning,with AlphaFold’s breakthrough in protein structure prediction exemplifying its potential.This review explores the historical evolution of deep learning,from its foundational theories in neural networks and connectionism to its modern applications in various fields.Focus is given to its use in geotechnical engineering,particularly in geological disaster prediction,tunnel safety monitoring,and structural design optimization.The integration of deep learning models such as Convolutional Neural Networks(CNNs),Recurrent Neural Networks(RNNs),and Transformers has enabled significant progress in analyzing complex,unstructured data,offering innovative solutions to longstanding engineering challenges.The review also examines the opportunities and challenges faced by the field,advocating for interdisciplinary collaboration and open data sharing to further unlock deep learning’s potential in advancing both scientific and engineering disciplines.As deep learning continues to evolve,it promises to drive further innovation,shaping the future of engineering practices and scientific discovery.
基金supported by the National Natural Science Foundation of China under Grant Nos.62461037,62076117 and 62166026the Jiangxi Provincial Natural Science Foundation under Grant Nos.20224BAB212011,20232BAB202051,20232BAB212008 and 20242BAB25078the Jiangxi Provincial Key Laboratory of Virtual Reality under Grant No.2024SSY03151.
文摘The unsupervised vehicle re-identification task aims at identifying specific vehicles in surveillance videos without utilizing annotation information.Due to the higher similarity in appearance between vehicles compared to pedestrians,pseudo-labels generated through clustering are ineffective in mitigating the impact of noise,and the feature distance between inter-class and intra-class has not been adequately improved.To address the aforementioned issues,we design a dual contrastive learning method based on knowledge distillation.During each iteration,we utilize a teacher model to randomly partition the entire dataset into two sub-domains based on clustering pseudo-label categories.By conducting contrastive learning between the two student models,we extract more discernible vehicle identity cues to improve the problem of imbalanced data distribution.Subsequently,we propose a context-aware pseudo label refinement strategy that leverages contextual features by progressively associating granularity information from different bottleneck blocks.To produce more trustworthy pseudo-labels and lessen noise interference during the clustering process,the context-aware scores are obtained by calculating the similarity between global features and contextual ones,which are subsequently added to the pseudo-label encoding process.The proposed method has achieved excellent performance in overcoming label noise and optimizing data distribution through extensive experimental results on publicly available datasets.
基金supported by the National Natural Science Foundation of China(Grant Nos.62072250,61772281,61702235,U1636117,U1804263,62172435,61872203 and 61802212)the Zhongyuan Science and Technology Innovation Leading Talent Project of China(Grant No.214200510019)+3 种基金the Suqian Municipal Science and Technology Plan Project in 2020(S202015)the Plan for Scientific Talent of Henan Province(Grant No.2018JR0018)the Opening Project of Guangdong Provincial Key Laboratory of Information Security Technology(Grant No.2020B1212060078)the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)Fund.
文摘Medical image segmentation,i.e.,labeling structures of interest in medical images,is crucial for disease diagnosis and treatment in radiology.In reversible data hiding in medical images(RDHMI),segmentation consists of only two regions:the focal and nonfocal regions.The focal region mainly contains information for diagnosis,while the nonfocal region serves as the monochrome background.The current traditional segmentation methods utilized in RDHMI are inaccurate for complex medical images,and manual segmentation is time-consuming,poorly reproducible,and operator-dependent.Implementing state-of-the-art deep learning(DL)models will facilitate key benefits,but the lack of domain-specific labels for existing medical datasets makes it impossible.To address this problem,this study provides labels of existing medical datasets based on a hybrid segmentation approach to facilitate the implementation of DL segmentation models in this domain.First,an initial segmentation based on a 33 kernel is performed to analyze×identified contour pixels before classifying pixels into focal and nonfocal regions.Then,several human expert raters evaluate and classify the generated labels into accurate and inaccurate labels.The inaccurate labels undergo manual segmentation by medical practitioners and are scored based on a hierarchical voting scheme before being assigned to the proposed dataset.To ensure reliability and integrity in the proposed dataset,we evaluate the accurate automated labels with manually segmented labels by medical practitioners using five assessment metrics:dice coefficient,Jaccard index,precision,recall,and accuracy.The experimental results show labels in the proposed dataset are consistent with the subjective judgment of human experts,with an average accuracy score of 94%and dice coefficient scores between 90%-99%.The study further proposes a ResNet-UNet with concatenated spatial and channel squeeze and excitation(scSE)architecture for semantic segmentation to validate and illustrate the usefulness of the proposed dataset.The results demonstrate the superior performance of the proposed architecture in accurately separating the focal and nonfocal regions compared to state-of-the-art architectures.Dataset information is released under the following URL:https://www.kaggle.com/lordamoah/datasets(accessed on 31 March 2025).
基金Supported by CAS Basic and Interdisciplinary Frontier Scientific Research Pilot Project(XDB1190300,XDB1190302)Youth Innovation Promotion Association CAS(Y2021056)+1 种基金Joint Fund of the Yulin University and the Dalian National Laboratory for Clean Energy(YLU-DNL Fund 2022007)The special fund for Science and Technology Innovation Teams of Shanxi Province(202304051001007)。
文摘Cyclohexene is an important raw material in the production of nylon.Selective hydrogenation of benzene is a key method for preparing cyclohexene.However,the Ru catalysts used in current industrial processes still face challenges,including high metal usage,high process costs,and low cyclohexene yield.This study utilizes existing literature data combined with machine learning methods to analyze the factors influencing benzene conversion,cyclohexene selectivity,and yield in the benzene hydrogenation to cyclohexene reaction.It constructs predictive models based on XGBoost and Random Forest algorithms.After analysis,it was found that reaction time,Ru content,and space velocity are key factors influencing cyclohexene yield,selectivity,and benzene conversion.Shapley Additive Explanations(SHAP)analysis and feature importance analysis further revealed the contribution of each variable to the reaction outcomes.Additionally,we randomly generated one million variable combinations using the Dirichlet distribution to attempt to predict high-yield catalyst formulations.This paper provides new insights into the application of machine learning in heterogeneous catalysis and offers some reference for further research.
文摘As urbanization continues to accelerate,the challenges associated with managing transportation in metropolitan areas become increasingly complex.The surge in population density contributes to traffic congestion,impacting travel experiences and posing safety risks.Smart urban transportation management emerges as a strategic solution,conceptualized here as a multidimensional big data problem.The success of this strategy hinges on the effective collection of information from diverse,extensive,and heterogeneous data sources,necessitating the implementation of full⁃stack Information and Communication Technology(ICT)solutions.The main idea of the work is to investigate the current technologies of Intelligent Transportation Systems(ITS)and enhance the safety of urban transportation systems.Machine learning models,trained on historical data,can predict traffic congestion,allowing for the implementation of preventive measures.Deep learning architectures,with their ability to handle complex data representations,further refine traffic predictions,contributing to more accurate and dynamic transportation management.The background of this research underscores the challenges posed by traffic congestion in metropolitan areas and emphasizes the need for advanced technological solutions.By integrating GPS and GIS technologies with machine learning algorithms,this work aims to pay attention to the development of intelligent transportation systems that not only address current challenges but also pave the way for future advancements in urban transportation management.
基金Supported by Chongqing Medical Scientific Research Project(Joint Project of Chongqing Health Commission and Science and Technology Bureau),No.2023MSXM060.
文摘BACKGROUND The accurate prediction of lymph node metastasis(LNM)is crucial for managing locally advanced(T3/T4)colorectal cancer(CRC).However,both traditional histopathology and standard slide-level deep learning often fail to capture the sparse and diagnostically critical features of metastatic potential.AIM To develop and validate a case-level multiple-instance learning(MIL)framework mimicking a pathologist's comprehensive review and improve T3/T4 CRC LNM prediction.METHODS The whole-slide images of 130 patients with T3/T4 CRC were retrospectively collected.A case-level MIL framework utilising the CONCH v1.5 and UNI2-h deep learning models was trained on features from all haematoxylin and eosinstained primary tumour slides for each patient.These pathological features were subsequently integrated with clinical data,and model performance was evaluated using the area under the curve(AUC).RESULTS The case-level framework demonstrated superior LNM prediction over slide-level training,with the CONCH v1.5 model achieving a mean AUC(±SD)of 0.899±0.033 vs 0.814±0.083,respectively.Integrating pathology features with clinical data further enhanced performance,yielding a top model with a mean AUC of 0.904±0.047,in sharp contrast to a clinical-only model(mean AUC 0.584±0.084).Crucially,a pathologist’s review confirmed that the model-identified high-attention regions correspond to known high-risk histopathological features.CONCLUSION A case-level MIL framework provides a superior approach for predicting LNM in advanced CRC.This method shows promise for risk stratification and therapy decisions,requiring further validation.
基金supported by the Academic Research Projects of Beijing Union University(ZK20202204)the National Natural Science Foundation of China(12250005,12073040,12273059,11973056,12003051,11573037,12073041,11427901,11572005,11611530679 and 12473052)+1 种基金the Strategic Priority Research Program of the China Academy of Sciences(XDB0560000,XDA15052200,XDB09040200,XDA15010700,XDB0560301,and XDA15320102)the Chinese Meridian Project(CMP).
文摘The solar cycle(SC),a phenomenon caused by the quasi-periodic regular activities in the Sun,occurs approximately every 11 years.Intense solar activity can disrupt the Earth’s ionosphere,affecting communication and navigation systems.Consequently,accurately predicting the intensity of the SC holds great significance,but predicting the SC involves a long-term time series,and many existing time series forecasting methods have fallen short in terms of accuracy and efficiency.The Time-series Dense Encoder model is a deep learning solution tailored for long time series prediction.Based on a multi-layer perceptron structure,it outperforms the best previously existing models in accuracy,while being efficiently trainable on general datasets.We propose a method based on this model for SC forecasting.Using a trained model,we predict the test set from SC 19 to SC 25 with an average mean absolute percentage error of 32.02,root mean square error of 30.3,mean absolute error of 23.32,and R^(2)(coefficient of determination)of 0.76,outperforming other deep learning models in terms of accuracy and training efficiency on sunspot number datasets.Subsequently,we use it to predict the peaks of SC 25 and SC 26.For SC 25,the peak time has ended,but a stronger peak is predicted for SC 26,of 199.3,within a range of 170.8-221.9,projected to occur during April 2034.
基金funded by Hung Yen University of Technology and Education under grand number UTEHY.L.2025.62.
文摘Unmanned Aerial Vehicles(UAVs)have become integral components in smart city infrastructures,supporting applications such as emergency response,surveillance,and data collection.However,the high mobility and dynamic topology of Flying Ad Hoc Networks(FANETs)present significant challenges for maintaining reliable,low-latency communication.Conventional geographic routing protocols often struggle in situations where link quality varies and mobility patterns are unpredictable.To overcome these limitations,this paper proposes an improved routing protocol based on reinforcement learning.This new approach integrates Q-learning with mechanisms that are both link-aware and mobility-aware.The proposed method optimizes the selection of relay nodes by using an adaptive reward function that takes into account energy consumption,delay,and link quality.Additionally,a Kalman filter is integrated to predict UAV mobility,improving the stability of communication links under dynamic network conditions.Simulation experiments were conducted using realistic scenarios,varying the number of UAVs to assess scalability.An analysis was conducted on key performance metrics,including the packet delivery ratio,end-to-end delay,and total energy consumption.The results demonstrate that the proposed approach significantly improves the packet delivery ratio by 12%–15%and reduces delay by up to 25.5%when compared to conventional GEO and QGEO protocols.However,this improvement comes at the cost of higher energy consumption due to additional computations and control overhead.Despite this trade-off,the proposed solution ensures reliable and efficient communication,making it well-suited for large-scale UAV networks operating in complex urban environments.
基金supported by the National Key Research and Development Program of China(Grant Nos.2023YFA1406600 and 2021YFA1202200)。
文摘First-principles calculations based on density functional theory(DFT)have had a significant impact on chemistry,physics,and materials science,enabling in-depth exploration of the structural and electronic properties of a wide variety of materials.Among different implementations of DFT,the plane-wave method is widely used for periodic systems because of its high accuracy.However,this method typically requires a large number of basis functions for large systems,leading to high computational costs.Localized basis sets,such as the muffin-tin orbital(MTO)method,have been introduced to provide a more efficient description of electronic structure with a reduced basis set,albeit at the cost of reduced computational accuracy.In this work,we propose an optimization strategy using machine-learning techniques to automate MTO basis-set parameters,thereby improving the accuracy and efficiency of MTO-based calculations.Default MTO parameter settings primarily focus on lattice structure and give less consideration to element-specific differences.In contrast,our optimized parameters incorporate both structural and elemental information.Based on these converged parameters,we successfully recovered missing bands for CrTe_(2).For the other three materials—Si,GaAs,and CrI_(3)—we achieved band improvements of up to 2 e V.Furthermore,the generalization of the machine-learned method is validated by perturbation,strain,and elemental substitution,resulting in improved band structures.Additionally,lattice-constant optimization for Ga As using the converged parameters yields closer agreement with experiment.
基金supported by the Advanced Materials-National Science and Technology Major Project(Grant No.2025ZD0618401)the National Natural Science Foundation of China(Grant No.12504285)+1 种基金the Natural Science Foundation of Jiangsu Province(Grant No.BK20250472)NFSG grant from BITS-Pilani,Dubai campus。
文摘The rapid advancement of machine learning based tight-binding Hamiltonian(MLTB)methods has opened new avenues for efficient and accurate electronic structure simulations,particularly in large-scale systems and long-time scenarios.This review begins with a concise overview of traditional tight-binding(TB)models,including both(semi-)empirical and first-principles approaches,establishing the foundation for understanding MLTB developments.We then present a systematic classification of existing MLTB methodologies,grouped into two major categories:direct prediction of TB Hamiltonian elements and inference of empirical parameters.A comparative analysis with other ML-based electronic structure models is also provided,highlighting the advancement of MLTB approaches.Finally,we explore the emerging MLTB application ecosystem,highlighting how the integration of MLTB models with a diverse suite of post-processing tools from linear-scaling solvers to quantum transport frameworks and molecular dynamics interfaces is essential for tackling complex scientific problems across different domains.The continued advancement of this integrated paradigm promises to accelerate materials discovery and open new frontiers in the predictive simulation of complex quantum phenomena.
基金the Deanship of Research and Graduate Studies at King Khalid University,KSA,for funding this work through the Large Research Project under grant number RGP2/164/46.
文摘Background:Stomach cancer(SC)is one of the most lethal malignancies worldwide due to late-stage diagnosis and limited treatment.The transcriptomic,epigenomic,and proteomic,etc.,omics datasets generated by high-throughput sequencing technology have become prominent in biomedical research,and they reveal molecular aspects of cancer diagnosis and therapy.Despite the development of advanced sequencing technology,the presence of high-dimensionality in multi-omics data makes it challenging to interpret the data.Methods:In this study,we introduce RankXLAN,an explainable ensemble-based multi-omics framework that integrates feature selection(FS),ensemble learning,bioinformatics,and in-silico validation for robust biomarker detection,potential therapeutic drug-repurposing candidates’identification,and classification of SC.To enhance the interpretability of the model,we incorporated explainable artificial intelligence(SHapley Additive exPlanations analysis),as well as accuracy,precision,F1-score,recall,cross-validation,specificity,likelihood ratio(LR)+,LR−,and Youden index results.Results:The experimental results showed that the top four FS algorithms achieved improved results when applied to the ensemble learning classification model.The proposed ensemble model produced an area under the curve(AUC)score of 0.994 for gene expression,0.97 for methylation,and 0.96 for miRNA expression data.Through the integration of bioinformatics and ML approach of the transcriptomic and epigenomic multi-omics dataset,we identified potential marker genes,namely,UBE2D2,HPCAL4,IGHA1,DPT,and FN3K.In-silico molecular docking revealed a strong binding affinity between ANKRD13C and the FDA-approved drug Everolimus(binding affinity−10.1 kcal/mol),identifying ANKRD13C as a potential therapeutic drug-repurposing target for SC.Conclusion:The proposed framework RankXLAN outperforms other existing frameworks for serum biomarker identification,therapeutic target identification,and SC classification with multi-omics datasets.
基金supported by National Natural Science Foundation of China(62466045)Inner Mongolia Natural Science Foundation Project(2021LHMS06003)Inner Mongolia University Basic Research Business Fee Project(114).
文摘Graph Federated Learning(GFL)has shown great potential in privacy protection and distributed intelligence through distributed collaborative training of graph-structured data without sharing raw information.However,existing GFL approaches often lack the capability for comprehensive feature extraction and adaptive optimization,particularly in non-independent and identically distributed(NON-IID)scenarios where balancing global structural understanding and local node-level detail remains a challenge.To this end,this paper proposes a novel framework called GFL-SAR(Graph Federated Collaborative Learning Framework Based on Structural Amplification and Attention Refinement),which enhances the representation learning capability of graph data through a dual-branch collaborative design.Specifically,we propose the Structural Insight Amplifier(SIA),which utilizes an improved Graph Convolutional Network(GCN)to strengthen structural awareness and improve modeling of topological patterns.In parallel,we propose the Attentive Relational Refiner(ARR),which employs an enhanced Graph Attention Network(GAT)to perform fine-grained modeling of node relationships and neighborhood features,thereby improving the expressiveness of local interactions and preserving critical contextual information.GFL-SAR effectively integrates multi-scale features from every branch via feature fusion and federated optimization,thereby addressing existing GFL limitations in structural modeling and feature representation.Experiments on standard benchmark datasets including Cora,Citeseer,Polblogs,and Cora_ML demonstrate that GFL-SAR achieves superior performance in classification accuracy,convergence speed,and robustness compared to existing methods,confirming its effectiveness and generalizability in GFL tasks.
基金supported by the Basic Science Research Program(2023R1A2C3004336,RS-202300243807)&Regional Leading Research Center(RS-202400405278)through the National Research Foundation of Korea(NRF)grant funded by the Korea Government(MSIT)。
文摘Wearable sensors integrated with deep learning techniques have the potential to revolutionize seamless human-machine interfaces for real-time health monitoring,clinical diagnosis,and robotic applications.Nevertheless,it remains a critical challenge to simultaneously achieve desirable mechanical and electrical performance along with biocompatibility,adhesion,self-healing,and environmental robustness with excellent sensing metrics.Herein,we report a multifunctional,anti-freezing,selfadhesive,and self-healable organogel pressure sensor composed of cobalt nanoparticle encapsulated nitrogen-doped carbon nanotubes(CoN CNT)embedded in a polyvinyl alcohol-gelatin(PVA/GLE)matrix.Fabricated using a binary solvent system of water and ethylene glycol(EG),the CoN CNT/PVA/GLE organogel exhibits excellent flexibility,biocompatibility,and temperature tolerance with remarkable environmental stability.Electrochemical impedance spectroscopy confirms near-stable performance across a broad humidity range(40%-95%RH).Freeze-tolerant conductivity under sub-zero conditions(-20℃)is attributed to the synergistic role of CoN CNT and EG,preserving mobility and network integrity.The Co N CNT/PVA/GLE organogel sensor exhibits high sensitivity of 5.75 k Pa^(-1)in the detection range from 0 to 20 k Pa,ideal for subtle biomechanical motion detection.A smart human-machine interface for English letter recognition using deep learning achieved 98%accuracy.The organogel sensor utility was extended to detect human gestures like finger bending,wrist motion,and throat vibration during speech.
