Missing data presents a crucial challenge in data analysis,especially in high-dimensional datasets,where missing data often leads to biased conclusions and degraded model performance.In this study,we present a novel a...Missing data presents a crucial challenge in data analysis,especially in high-dimensional datasets,where missing data often leads to biased conclusions and degraded model performance.In this study,we present a novel autoencoder-based imputation framework that integrates a composite loss function to enhance robustness and precision.The proposed loss combines(i)a guided,masked mean squared error focusing on missing entries;(ii)a noise-aware regularization term to improve resilience against data corruption;and(iii)a variance penalty to encourage expressive yet stable reconstructions.We evaluate the proposed model across four missingness mechanisms,such as Missing Completely at Random,Missing at Random,Missing Not at Random,and Missing Not at Random with quantile censorship,under systematically varied feature counts,sample sizes,and missingness ratios ranging from 5%to 60%.Four publicly available real-world datasets(Stroke Prediction,Pima Indians Diabetes,Cardiovascular Disease,and Framingham Heart Study)were used,and the obtained results show that our proposed model consistently outperforms baseline methods,including traditional and deep learning-based techniques.An ablation study reveals the additive value of each component in the loss function.Additionally,we assessed the downstream utility of imputed data through classification tasks,where datasets imputed by the proposed method yielded the highest receiver operating characteristic area under the curve scores across all scenarios.The model demonstrates strong scalability and robustness,improving performance with larger datasets and higher feature counts.These results underscore the capacity of the proposed method to produce not only numerically accurate but also semantically useful imputations,making it a promising solution for robust data recovery in clinical applications.展开更多
Modern intrusion detection systems(MIDS)face persistent challenges in coping with the rapid evolution of cyber threats,high-volume network traffic,and imbalanced datasets.Traditional models often lack the robustness a...Modern intrusion detection systems(MIDS)face persistent challenges in coping with the rapid evolution of cyber threats,high-volume network traffic,and imbalanced datasets.Traditional models often lack the robustness and explainability required to detect novel and sophisticated attacks effectively.This study introduces an advanced,explainable machine learning framework for multi-class IDS using the KDD99 and IDS datasets,which reflects real-world network behavior through a blend of normal and diverse attack classes.The methodology begins with sophisticated data preprocessing,incorporating both RobustScaler and QuantileTransformer to address outliers and skewed feature distributions,ensuring standardized and model-ready inputs.Critical dimensionality reduction is achieved via the Harris Hawks Optimization(HHO)algorithm—a nature-inspired metaheuristic modeled on hawks’hunting strategies.HHO efficiently identifies the most informative features by optimizing a fitness function based on classification performance.Following feature selection,the SMOTE is applied to the training data to resolve class imbalance by synthetically augmenting underrepresented attack types.The stacked architecture is then employed,combining the strengths of XGBoost,SVM,and RF as base learners.This layered approach improves prediction robustness and generalization by balancing bias and variance across diverse classifiers.The model was evaluated using standard classification metrics:precision,recall,F1-score,and overall accuracy.The best overall performance was recorded with an accuracy of 99.44%for UNSW-NB15,demonstrating the model’s effectiveness.After balancing,the model demonstrated a clear improvement in detecting the attacks.We tested the model on four datasets to show the effectiveness of the proposed approach and performed the ablation study to check the effect of each parameter.Also,the proposed model is computationaly efficient.To support transparency and trust in decision-making,explainable AI(XAI)techniques are incorporated that provides both global and local insight into feature contributions,and offers intuitive visualizations for individual predictions.This makes it suitable for practical deployment in cybersecurity environments that demand both precision and accountability.展开更多
Reversible data hiding(RDH)enables secret data embedding while preserving complete cover image recovery,making it crucial for applications requiring image integrity.The pixel value ordering(PVO)technique used in multi...Reversible data hiding(RDH)enables secret data embedding while preserving complete cover image recovery,making it crucial for applications requiring image integrity.The pixel value ordering(PVO)technique used in multi-stego images provides good image quality but often results in low embedding capability.To address these challenges,this paper proposes a high-capacity RDH scheme based on PVO that generates three stego images from a single cover image.The cover image is partitioned into non-overlapping blocks with pixels sorted in ascending order.Four secret bits are embedded into each block’s maximum pixel value,while three additional bits are embedded into the second-largest value when the pixel difference exceeds a predefined threshold.A similar embedding strategy is also applied to the minimum side of the block,including the second-smallest pixel value.This design enables each block to embed up to 14 bits of secret data.Experimental results demonstrate that the proposed method achieves significantly higher embedding capacity and improved visual quality compared to existing triple-stego RDH approaches,advancing the field of reversible steganography.展开更多
Formamidinium lead iodide(FAPbI_(3))perovskite exhibits an impressive X-ray absorption coefficient and a large carrier mobility-lifetime product(μτ),making it as a highly promising candidate for X-ray detection appl...Formamidinium lead iodide(FAPbI_(3))perovskite exhibits an impressive X-ray absorption coefficient and a large carrier mobility-lifetime product(μτ),making it as a highly promising candidate for X-ray detection application.However,the presence of larger FA^(+)cation induces to an expansion of the Pb-I octahedral framework,which unfortunately affects both the stability and charge carrier mobility of the corresponding devices.To address this challenge,we develop a novel low-dimensional(HtrzT)PbI_(3) perovskite featuring a conjugated organic cation(1H-1,2,4-Triazole-3-thiol,HtrzT^(+))which matches well with theα-FAPbI_(3) lattices in two-dimensional plane.Benefiting from the matched lattice between(HtrzT)PbI_(3) andα-FAPbI_(3),the anchored lattice enhances the Pb-I bond strength and effectively mitigates the inherent tensile strain of theα-FAPbI_(3) crystal lattice.The X-ray detector based on(HtrzT)PbI_(3)(1.0)/FAPbI_(3) device achieves a remarkable sensitivity up to 1.83×10^(5)μC Gy_(air)^(−1) cm^(−2),along with a low detection limit of 27.6 nGy_(air) s^(−1),attributed to the release of residual stress,and the enhancement in carrier mobility-lifetime product.Furthermore,the detector exhibits outstanding stability under X-ray irradiation with tolerating doses equivalent to nearly 1.17×10^(6) chest imaging doses.展开更多
With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comp...With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comprise heterogeneous networks where outdated systems coexist with the latest devices,spanning a range of devices from non-encrypted ones to fully encrypted ones.Given the limited visibility into payloads in this context,this study investigates AI-based attack detection methods that leverage encrypted traffic metadata,eliminating the need for decryption and minimizing system performance degradation—especially in light of these heterogeneous devices.Using the UNSW-NB15 and CICIoT-2023 dataset,encrypted and unencrypted traffic were categorized according to security protocol,and AI-based intrusion detection experiments were conducted for each traffic type based on metadata.To mitigate the problem of class imbalance,eight different data sampling techniques were applied.The effectiveness of these sampling techniques was then comparatively analyzed using two ensemble models and three Deep Learning(DL)models from various perspectives.The experimental results confirmed that metadata-based attack detection is feasible using only encrypted traffic.In the UNSW-NB15 dataset,the f1-score of encrypted traffic was approximately 0.98,which is 4.3%higher than that of unencrypted traffic(approximately 0.94).In addition,analysis of the encrypted traffic in the CICIoT-2023 dataset using the same method showed a significantly lower f1-score of roughly 0.43,indicating that the quality of the dataset and the preprocessing approach have a substantial impact on detection performance.Furthermore,when data sampling techniques were applied to encrypted traffic,the recall in the UNSWNB15(Encrypted)dataset improved by up to 23.0%,and in the CICIoT-2023(Encrypted)dataset by 20.26%,showing a similar level of improvement.Notably,in CICIoT-2023,f1-score and Receiver Operation Characteristic-Area Under the Curve(ROC-AUC)increased by 59.0%and 55.94%,respectively.These results suggest that data sampling can have a positive effect even in encrypted environments.However,the extent of the improvement may vary depending on data quality,model architecture,and sampling strategy.展开更多
The increasing complexity of China’s electricity market creates substantial challenges for settlement automation,data consistency,and operational scalability.Existing provincial settlement systems are fragmented,lack...The increasing complexity of China’s electricity market creates substantial challenges for settlement automation,data consistency,and operational scalability.Existing provincial settlement systems are fragmented,lack a unified data structure,and depend heavily on manual intervention to process high-frequency and retroactive transactions.To address these limitations,a graph-based unified settlement framework is proposed to enhance automation,flexibility,and adaptability in electricity market settlements.A flexible attribute-graph model is employed to represent heterogeneousmulti-market data,enabling standardized integration,rapid querying,and seamless adaptation to evolving business requirements.An extensible operator library is designed to support configurable settlement rules,and a suite of modular tools—including dataset generation,formula configuration,billing templates,and task scheduling—facilitates end-to-end automated settlement processing.A robust refund-clearing mechanism is further incorporated,utilizing sandbox execution,data-version snapshots,dynamic lineage tracing,and real-time changecapture technologies to enable rapid and accurate recalculations under dynamic policy and data revisions.Case studies based on real-world data from regional Chinese markets validate the effectiveness of the proposed approach,demonstrating marked improvements in computational efficiency,system robustness,and automation.Moreover,enhanced settlement accuracy and high temporal granularity improve price-signal fidelity,promote cost-reflective tariffs,and incentivize energy-efficient and demand-responsive behavior among market participants.The method not only supports equitable and transparent market operations but also provides a generalizable,scalable foundation for modern electricity settlement platforms in increasingly complex and dynamic market environments.展开更多
Automated essay scoring(AES)systems have gained significant importance in educational settings,offering a scalable,efficient,and objective method for evaluating student essays.However,developing AES systems for Arabic...Automated essay scoring(AES)systems have gained significant importance in educational settings,offering a scalable,efficient,and objective method for evaluating student essays.However,developing AES systems for Arabic poses distinct challenges due to the language’s complex morphology,diglossia,and the scarcity of annotated datasets.This paper presents a hybrid approach to Arabic AES by combining text-based,vector-based,and embeddingbased similarity measures to improve essay scoring accuracy while minimizing the training data required.Using a large Arabic essay dataset categorized into thematic groups,the study conducted four experiments to evaluate the impact of feature selection,data size,and model performance.Experiment 1 established a baseline using a non-machine learning approach,selecting top-N correlated features to predict essay scores.The subsequent experiments employed 5-fold cross-validation.Experiment 2 showed that combining embedding-based,text-based,and vector-based features in a Random Forest(RF)model achieved an R2 of 88.92%and an accuracy of 83.3%within a 0.5-point tolerance.Experiment 3 further refined the feature selection process,demonstrating that 19 correlated features yielded optimal results,improving R2 to 88.95%.In Experiment 4,an optimal data efficiency training approach was introduced,where training data portions increased from 5%to 50%.The study found that using just 10%of the data achieved near-peak performance,with an R2 of 85.49%,emphasizing an effective trade-off between performance and computational costs.These findings highlight the potential of the hybrid approach for developing scalable Arabic AES systems,especially in low-resource environments,addressing linguistic challenges while ensuring efficient data usage.展开更多
Objective expertise evaluation of individuals,as a prerequisite stage for team formation,has been a long-term desideratum in large software development companies.With the rapid advancements in machine learning methods...Objective expertise evaluation of individuals,as a prerequisite stage for team formation,has been a long-term desideratum in large software development companies.With the rapid advancements in machine learning methods,based on reliable existing data stored in project management tools’datasets,automating this evaluation process becomes a natural step forward.In this context,our approach focuses on quantifying software developer expertise by using metadata from the task-tracking systems.For this,we mathematically formalize two categories of expertise:technology-specific expertise,which denotes the skills required for a particular technology,and general expertise,which encapsulates overall knowledge in the software industry.Afterward,we automatically classify the zones of expertise associated with each task a developer has worked on using Bidirectional Encoder Representations from Transformers(BERT)-like transformers to handle the unique characteristics of project tool datasets effectively.Finally,our method evaluates the proficiency of each software specialist across already completed projects from both technology-specific and general perspectives.The method was experimentally validated,yielding promising results.展开更多
The rapid growth of biomedical data,particularly multi-omics data including genomes,transcriptomics,proteomics,metabolomics,and epigenomics,medical research and clinical decision-making confront both new opportunities...The rapid growth of biomedical data,particularly multi-omics data including genomes,transcriptomics,proteomics,metabolomics,and epigenomics,medical research and clinical decision-making confront both new opportunities and obstacles.The huge and diversified nature of these datasets cannot always be managed using traditional data analysis methods.As a consequence,deep learning has emerged as a strong tool for analysing numerous omics data due to its ability to handle complex and non-linear relationships.This paper explores the fundamental concepts of deep learning and how they are used in multi-omics medical data mining.We demonstrate how autoencoders,variational autoencoders,multimodal models,attention mechanisms,transformers,and graph neural networks enable pattern analysis and recognition across all omics data.Deep learning has been found to be effective in illness classification,biomarker identification,gene network learning,and therapeutic efficacy prediction.We also consider critical problems like as data quality,model explainability,whether findings can be repeated,and computational power requirements.We now consider future elements of combining omics with clinical and imaging data,explainable AI,federated learning,and real-time diagnostics.Overall,this study emphasises the need of collaborating across disciplines to advance deep learning-based multi-omics research for precision medicine and comprehending complicated disorders.展开更多
High-throughput transcriptomics has evolved from bulk RNA-seq to single-cell and spatial profiling,yet its clinical translation still depends on effective integration across diverse omics and data modalities.Emerging ...High-throughput transcriptomics has evolved from bulk RNA-seq to single-cell and spatial profiling,yet its clinical translation still depends on effective integration across diverse omics and data modalities.Emerging foundation models and multimodal learning frameworks are enabling scalable and transferable representations of cellular states,while advances in interpretability and real-world data integration are bridging the gap between discovery and clinical application.This paper outlines a concise roadmap for AI-driven,transcriptome-centered multi-omics integration in precision medicine(Figure 1).展开更多
Gastrointestinal tumors require personalized treatment strategies due to their heterogeneity and complexity.Multimodal artificial intelligence(AI)addresses this challenge by integrating diverse data sources-including ...Gastrointestinal tumors require personalized treatment strategies due to their heterogeneity and complexity.Multimodal artificial intelligence(AI)addresses this challenge by integrating diverse data sources-including computed tomography(CT),magnetic resonance imaging(MRI),endoscopic imaging,and genomic profiles-to enable intelligent decision-making for individualized therapy.This approach leverages AI algorithms to fuse imaging,endoscopic,and omics data,facilitating comprehensive characterization of tumor biology,prediction of treatment response,and optimization of therapeutic strategies.By combining CT and MRI for structural assessment,endoscopic data for real-time visual inspection,and genomic information for molecular profiling,multimodal AI enhances the accuracy of patient stratification and treatment personalization.The clinical implementation of this technology demonstrates potential for improving patient outcomes,advancing precision oncology,and supporting individualized care in gastrointestinal cancers.Ultimately,multimodal AI serves as a transformative tool in oncology,bridging data integration with clinical application to effectively tailor therapies.展开更多
We investigate the null tests of cosmic accelerated expansion by using the baryon acoustic oscillation(BAO)data measured by the dark energy spectroscopic instrument(DESI)and reconstruct the dimensionless Hubble parame...We investigate the null tests of cosmic accelerated expansion by using the baryon acoustic oscillation(BAO)data measured by the dark energy spectroscopic instrument(DESI)and reconstruct the dimensionless Hubble parameter E(z)from the DESI BAO Alcock-Paczynski(AP)data using Gaussian process to perform the null test.We find strong evidence of accelerated expansion from the DESI BAO AP data.By reconstructing the deceleration parameter q(z) from the DESI BAO AP data,we find that accelerated expansion persisted until z■0.7 with a 99.7%confidence level.Additionally,to provide insights into the Hubble tension problem,we propose combining the reconstructed E(z) with D_(H)/r_(d) data to derive a model-independent result r_(d)h=99.8±3.1 Mpc.This result is consistent with measurements from cosmic microwave background(CMB)anisotropies using the ΛCDM model.We also propose a model-independent method for reconstructing the comoving angular diameter distance D_(M)(z) from the distance modulus μ,using SNe Ia data and combining this result with DESI BAO data of D_(M)/r_(d) to constrain the value of r_(d).We find that the value of r_(d),derived from this model-independent method,is smaller than that obtained from CMB measurements,with a significant discrepancy of at least 4.17σ.All the conclusions drawn in this paper are independent of cosmological models and gravitational theories.展开更多
Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using d...Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using deep learning algorithms further enhances performance;nevertheless,it is challenging due to the nature of small-scale and imbalanced PD datasets.This paper proposed a convolutional neural network-based deep support vector machine(CNN-DSVM)to automate the feature extraction process using CNN and extend the conventional SVM to a DSVM for better classification performance in small-scale PD datasets.A customized kernel function reduces the impact of biased classification towards the majority class(healthy candidates in our consideration).An improved generative adversarial network(IGAN)was designed to generate additional training data to enhance the model’s performance.For performance evaluation,the proposed algorithm achieves a sensitivity of 97.6%and a specificity of 97.3%.The performance comparison is evaluated from five perspectives,including comparisons with different data generation algorithms,feature extraction techniques,kernel functions,and existing works.Results reveal the effectiveness of the IGAN algorithm,which improves the sensitivity and specificity by 4.05%–4.72%and 4.96%–5.86%,respectively;and the effectiveness of the CNN-DSVM algorithm,which improves the sensitivity by 1.24%–57.4%and specificity by 1.04%–163%and reduces biased detection towards the majority class.The ablation experiments confirm the effectiveness of individual components.Two future research directions have also been suggested.展开更多
The science analysis of the data from the High Energy X-ray Telescope(HE) on the Hard X-ray Modulation Telescope(HXMT) satellite is organized in three stages:calibration,screening and extraction of high-level scientif...The science analysis of the data from the High Energy X-ray Telescope(HE) on the Hard X-ray Modulation Telescope(HXMT) satellite is organized in three stages:calibration,screening and extraction of high-level scientific products.At the first stage,the raw PHA value of each event is converted to PI value accounting for temporal changes in gain and energy offset.At the second stage,the calibrated events are screened by applying cleaning criteria.At the third stage,scientific products,i.e.spectra,light curves and redistribution matrix files,are extracted.This work will introduce the three stages as well as the screening criteria and the data combining method.展开更多
The Active Particle-induced X-ray Spectrometer （APXS） is an important payload mounted on the Yutu rover, which is part of the Chang＇e-3 mission. The sci- entific objective of APXS is to perform in-situ analysis of ...The Active Particle-induced X-ray Spectrometer （APXS） is an important payload mounted on the Yutu rover, which is part of the Chang＇e-3 mission. The sci- entific objective of APXS is to perform in-situ analysis of the chemical composition of lunar soil and rock samples. The radioactive sources, 55Fe and 109Cd, decay and produce a-particles and X-rays. When X-rays and a-particles interact with atoms in the surface material, they knock electrons out of their orbits, which release energy by emitting X-rays that can be measured by a silicon drift detector （SDD）. The elements and their concentrations can be determined by analyzing their peak energies and in- tensities. APXS has analyzed both the calibration target and lunar soil once during the first lunar day and again during the second lunar day. The total detection time lasted about 266 min and more than 2000 frames of data records have been acquired. APXS has three operating modes： calibration mode, distance sensing mode and detection mode. In detection mode, work distance can be calculated from the X-ray counting rate collected by SDD. Correction for the effect of temperature has been performed to convert the channel number for each spectrum to X-ray energy. Dead time correction is used to eliminate the systematic error in quantifying the activity of an X-ray pulse in a sample and derive the real count rate. We report APXS data and initial results during the first and second lunar days for the Yutu rover. In this study, we analyze the data from the calibration target and lunar soil on the first lunar day. Seven major elements, including Mg, A1, Si, K, Ca, Ti and Fe, have been identified. Comparing the peak areas and ratios of calibration basalt and lunar soil the landing site was found to be depleted in K, and have lower Mg and A1 but higher Ca, Ti, and Fe. In the future, we will obtain the elemental concentrations of lunar soil at the Chang＇e-3 landing site using APXS data.展开更多
The three-dimensional(3 D) structures of pores directly affect the CH4 flow.Therefore,it is very important to analyze the3 D spatial structure of pores and to simulate the CH4 flow with the connected pores as the carr...The three-dimensional(3 D) structures of pores directly affect the CH4 flow.Therefore,it is very important to analyze the3 D spatial structure of pores and to simulate the CH4 flow with the connected pores as the carrier.The result shows that the equivalent radius of pores and throats are 1-16 μm and 1.03-8.9 μm,respectively,and the throat length is 3.28-231.25 μm.The coordination number of pores concentrates around three,and the intersection point between the connectivity function and the X-axis is 3-4 μm,which indicate the macro-pores have good connectivity.During the single-channel flow,the pressure decreases along the direction of CH4 flow,and the flow velocity of CH4 decreases from the pore center to the wall.Under the dual-channel and the multi-channel flows,the pressure also decreases along the CH4 flow direction,while the velocity increases.The mean flow pressure gradually decreases with the increase of the distance from the inlet slice.The change of mean flow pressure is relatively stable in the direction horizontal to the bedding plane,while it is relatively large in the direction perpendicular to the bedding plane.The mean flow velocity in the direction horizontal to the bedding plane(Y-axis) is the largest,followed by that in the direction horizontal to the bedding plane(X-axis),and the mean flow velocity in the direction perpendicular to the bedding plane is the smallest.展开更多
The X-ray powder diffraction data of the compound GdAlSi was studied by means of X-ray diffraction technique and refined by Rietveld method. The compound GdAlSi has tetragonal α-ThSi_2-type structure, space group I4_...The X-ray powder diffraction data of the compound GdAlSi was studied by means of X-ray diffraction technique and refined by Rietveld method. The compound GdAlSi has tetragonal α-ThSi_2-type structure, space group I4_1/amd (No.141), Z=4, the lattice parameters a=041234 (1) nm, c=1.44202(1) nm. The Smith and Snyder figure of merit [5] F_N is F_ 30=2521(36). The R-factors of Rietveld refinement are R_p=0.098 and R_ wp=0.128. The X-ray powder diffraction data are given. The field dependence of the magnetization measured at room temperature and the temperature variation of the inverse magnetic susceptibility of the compound GdAlSi were also presented.展开更多
Matrix swelling effect will cause the change of microstructure of coal reservoir and its permeability,which is the key factor affecting the engineering effect of CO_(2)-ECBM technology.The Sihe and Yuwu collieries are...Matrix swelling effect will cause the change of microstructure of coal reservoir and its permeability,which is the key factor affecting the engineering effect of CO_(2)-ECBM technology.The Sihe and Yuwu collieries are taken as research objects.Firstly,visualization reconstruction of coal reservoir is realized.Secondly,the evolution of the pore/fracture structures under different swelling contents is discussed.Then,the influence of matrix phase with different swelling contents on permeability is discussed.Finally,the mechanism of swelling effect during the CO_(2)-ECBM process is further discussed.The results show that the intra-matrix pores and matrix-edge fractures are the focus of this study,and the contacting area between matrix and pore/fracture is the core area of matrix swelling.The number of matrix particles decreases with the increase of size,and the distribution of which is isolated with small size and interconnected with large size.The swelling effect of matrix particles with larger size has a great influence on the pore/fracture structures.The number of connected pores/fractures is limited and only interconnected in a certain direction.With the increase of matrix swelling content,the number,porosity,width,fractal dimension,surface area and volume of pores/fractures decrease,and their negative contribution to absolute permeability increases from 0.368% to 0.633% and 0.868%-1.404%,respectively.With the increase of swelling content,the number of intra-matrix pores gradually decreases and the pore radius becomes shorter during the CO_(2)-ECBM process.The matrix continuously expands to the connected fractures,and the width of connected fractures gradually shorten.Under the influence of matrix swelling,the bending degree of fluid flow increases gradually,so the resistance of fluid migration increases and the permeability gradually decreases.This study shows that the matrix swelling effect is the key factor affecting CBM recovery,and the application of this effect in CO_(2)-ECBM process can be discussed.展开更多
Accuracy of coeffcient A_(isp) is related to the reference phase chosen during analysis. The cri- terion of choosing reference phase which may minimize the error of A_(isp) was deduced. The optimum results could be ob...Accuracy of coeffcient A_(isp) is related to the reference phase chosen during analysis. The cri- terion of choosing reference phase which may minimize the error of A_(isp) was deduced. The optimum results could be obtained by using the method of least squares if the number of sam- pies for analysis is more than the phase in samples. The procedure presented here is satisfacto- ryfor ordinary phase analysis.展开更多
文摘Missing data presents a crucial challenge in data analysis,especially in high-dimensional datasets,where missing data often leads to biased conclusions and degraded model performance.In this study,we present a novel autoencoder-based imputation framework that integrates a composite loss function to enhance robustness and precision.The proposed loss combines(i)a guided,masked mean squared error focusing on missing entries;(ii)a noise-aware regularization term to improve resilience against data corruption;and(iii)a variance penalty to encourage expressive yet stable reconstructions.We evaluate the proposed model across four missingness mechanisms,such as Missing Completely at Random,Missing at Random,Missing Not at Random,and Missing Not at Random with quantile censorship,under systematically varied feature counts,sample sizes,and missingness ratios ranging from 5%to 60%.Four publicly available real-world datasets(Stroke Prediction,Pima Indians Diabetes,Cardiovascular Disease,and Framingham Heart Study)were used,and the obtained results show that our proposed model consistently outperforms baseline methods,including traditional and deep learning-based techniques.An ablation study reveals the additive value of each component in the loss function.Additionally,we assessed the downstream utility of imputed data through classification tasks,where datasets imputed by the proposed method yielded the highest receiver operating characteristic area under the curve scores across all scenarios.The model demonstrates strong scalability and robustness,improving performance with larger datasets and higher feature counts.These results underscore the capacity of the proposed method to produce not only numerically accurate but also semantically useful imputations,making it a promising solution for robust data recovery in clinical applications.
基金funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R104)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Modern intrusion detection systems(MIDS)face persistent challenges in coping with the rapid evolution of cyber threats,high-volume network traffic,and imbalanced datasets.Traditional models often lack the robustness and explainability required to detect novel and sophisticated attacks effectively.This study introduces an advanced,explainable machine learning framework for multi-class IDS using the KDD99 and IDS datasets,which reflects real-world network behavior through a blend of normal and diverse attack classes.The methodology begins with sophisticated data preprocessing,incorporating both RobustScaler and QuantileTransformer to address outliers and skewed feature distributions,ensuring standardized and model-ready inputs.Critical dimensionality reduction is achieved via the Harris Hawks Optimization(HHO)algorithm—a nature-inspired metaheuristic modeled on hawks’hunting strategies.HHO efficiently identifies the most informative features by optimizing a fitness function based on classification performance.Following feature selection,the SMOTE is applied to the training data to resolve class imbalance by synthetically augmenting underrepresented attack types.The stacked architecture is then employed,combining the strengths of XGBoost,SVM,and RF as base learners.This layered approach improves prediction robustness and generalization by balancing bias and variance across diverse classifiers.The model was evaluated using standard classification metrics:precision,recall,F1-score,and overall accuracy.The best overall performance was recorded with an accuracy of 99.44%for UNSW-NB15,demonstrating the model’s effectiveness.After balancing,the model demonstrated a clear improvement in detecting the attacks.We tested the model on four datasets to show the effectiveness of the proposed approach and performed the ablation study to check the effect of each parameter.Also,the proposed model is computationaly efficient.To support transparency and trust in decision-making,explainable AI(XAI)techniques are incorporated that provides both global and local insight into feature contributions,and offers intuitive visualizations for individual predictions.This makes it suitable for practical deployment in cybersecurity environments that demand both precision and accountability.
基金funded by University of Transport and Communications(UTC)under grant number T2025-CN-004.
文摘Reversible data hiding(RDH)enables secret data embedding while preserving complete cover image recovery,making it crucial for applications requiring image integrity.The pixel value ordering(PVO)technique used in multi-stego images provides good image quality but often results in low embedding capability.To address these challenges,this paper proposes a high-capacity RDH scheme based on PVO that generates three stego images from a single cover image.The cover image is partitioned into non-overlapping blocks with pixels sorted in ascending order.Four secret bits are embedded into each block’s maximum pixel value,while three additional bits are embedded into the second-largest value when the pixel difference exceeds a predefined threshold.A similar embedding strategy is also applied to the minimum side of the block,including the second-smallest pixel value.This design enables each block to embed up to 14 bits of secret data.Experimental results demonstrate that the proposed method achieves significantly higher embedding capacity and improved visual quality compared to existing triple-stego RDH approaches,advancing the field of reversible steganography.
基金supports from the National Natural Science Foundation of China(22375220,U2001214,22471302)the Guangdong Basic and Applied Basic Research Foundation(2024B1515020101)Open Project Fund from State Key Laboratory of Optoelectronic Materials and Technologies(OEMT-2024-KF-08).
文摘Formamidinium lead iodide(FAPbI_(3))perovskite exhibits an impressive X-ray absorption coefficient and a large carrier mobility-lifetime product(μτ),making it as a highly promising candidate for X-ray detection application.However,the presence of larger FA^(+)cation induces to an expansion of the Pb-I octahedral framework,which unfortunately affects both the stability and charge carrier mobility of the corresponding devices.To address this challenge,we develop a novel low-dimensional(HtrzT)PbI_(3) perovskite featuring a conjugated organic cation(1H-1,2,4-Triazole-3-thiol,HtrzT^(+))which matches well with theα-FAPbI_(3) lattices in two-dimensional plane.Benefiting from the matched lattice between(HtrzT)PbI_(3) andα-FAPbI_(3),the anchored lattice enhances the Pb-I bond strength and effectively mitigates the inherent tensile strain of theα-FAPbI_(3) crystal lattice.The X-ray detector based on(HtrzT)PbI_(3)(1.0)/FAPbI_(3) device achieves a remarkable sensitivity up to 1.83×10^(5)μC Gy_(air)^(−1) cm^(−2),along with a low detection limit of 27.6 nGy_(air) s^(−1),attributed to the release of residual stress,and the enhancement in carrier mobility-lifetime product.Furthermore,the detector exhibits outstanding stability under X-ray irradiation with tolerating doses equivalent to nearly 1.17×10^(6) chest imaging doses.
基金supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.RS-2023-00235509Development of security monitoring technology based network behavior against encrypted cyber threats in ICT convergence environment).
文摘With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comprise heterogeneous networks where outdated systems coexist with the latest devices,spanning a range of devices from non-encrypted ones to fully encrypted ones.Given the limited visibility into payloads in this context,this study investigates AI-based attack detection methods that leverage encrypted traffic metadata,eliminating the need for decryption and minimizing system performance degradation—especially in light of these heterogeneous devices.Using the UNSW-NB15 and CICIoT-2023 dataset,encrypted and unencrypted traffic were categorized according to security protocol,and AI-based intrusion detection experiments were conducted for each traffic type based on metadata.To mitigate the problem of class imbalance,eight different data sampling techniques were applied.The effectiveness of these sampling techniques was then comparatively analyzed using two ensemble models and three Deep Learning(DL)models from various perspectives.The experimental results confirmed that metadata-based attack detection is feasible using only encrypted traffic.In the UNSW-NB15 dataset,the f1-score of encrypted traffic was approximately 0.98,which is 4.3%higher than that of unencrypted traffic(approximately 0.94).In addition,analysis of the encrypted traffic in the CICIoT-2023 dataset using the same method showed a significantly lower f1-score of roughly 0.43,indicating that the quality of the dataset and the preprocessing approach have a substantial impact on detection performance.Furthermore,when data sampling techniques were applied to encrypted traffic,the recall in the UNSWNB15(Encrypted)dataset improved by up to 23.0%,and in the CICIoT-2023(Encrypted)dataset by 20.26%,showing a similar level of improvement.Notably,in CICIoT-2023,f1-score and Receiver Operation Characteristic-Area Under the Curve(ROC-AUC)increased by 59.0%and 55.94%,respectively.These results suggest that data sampling can have a positive effect even in encrypted environments.However,the extent of the improvement may vary depending on data quality,model architecture,and sampling strategy.
基金funded by the Science and Technology Project of State Grid Corporation of China(5108-202355437A-3-2-ZN).
文摘The increasing complexity of China’s electricity market creates substantial challenges for settlement automation,data consistency,and operational scalability.Existing provincial settlement systems are fragmented,lack a unified data structure,and depend heavily on manual intervention to process high-frequency and retroactive transactions.To address these limitations,a graph-based unified settlement framework is proposed to enhance automation,flexibility,and adaptability in electricity market settlements.A flexible attribute-graph model is employed to represent heterogeneousmulti-market data,enabling standardized integration,rapid querying,and seamless adaptation to evolving business requirements.An extensible operator library is designed to support configurable settlement rules,and a suite of modular tools—including dataset generation,formula configuration,billing templates,and task scheduling—facilitates end-to-end automated settlement processing.A robust refund-clearing mechanism is further incorporated,utilizing sandbox execution,data-version snapshots,dynamic lineage tracing,and real-time changecapture technologies to enable rapid and accurate recalculations under dynamic policy and data revisions.Case studies based on real-world data from regional Chinese markets validate the effectiveness of the proposed approach,demonstrating marked improvements in computational efficiency,system robustness,and automation.Moreover,enhanced settlement accuracy and high temporal granularity improve price-signal fidelity,promote cost-reflective tariffs,and incentivize energy-efficient and demand-responsive behavior among market participants.The method not only supports equitable and transparent market operations but also provides a generalizable,scalable foundation for modern electricity settlement platforms in increasingly complex and dynamic market environments.
基金funded by Deanship of Graduate studies and Scientific Research at Jouf University under grant No.(DGSSR-2024-02-01264).
文摘Automated essay scoring(AES)systems have gained significant importance in educational settings,offering a scalable,efficient,and objective method for evaluating student essays.However,developing AES systems for Arabic poses distinct challenges due to the language’s complex morphology,diglossia,and the scarcity of annotated datasets.This paper presents a hybrid approach to Arabic AES by combining text-based,vector-based,and embeddingbased similarity measures to improve essay scoring accuracy while minimizing the training data required.Using a large Arabic essay dataset categorized into thematic groups,the study conducted four experiments to evaluate the impact of feature selection,data size,and model performance.Experiment 1 established a baseline using a non-machine learning approach,selecting top-N correlated features to predict essay scores.The subsequent experiments employed 5-fold cross-validation.Experiment 2 showed that combining embedding-based,text-based,and vector-based features in a Random Forest(RF)model achieved an R2 of 88.92%and an accuracy of 83.3%within a 0.5-point tolerance.Experiment 3 further refined the feature selection process,demonstrating that 19 correlated features yielded optimal results,improving R2 to 88.95%.In Experiment 4,an optimal data efficiency training approach was introduced,where training data portions increased from 5%to 50%.The study found that using just 10%of the data achieved near-peak performance,with an R2 of 85.49%,emphasizing an effective trade-off between performance and computational costs.These findings highlight the potential of the hybrid approach for developing scalable Arabic AES systems,especially in low-resource environments,addressing linguistic challenges while ensuring efficient data usage.
基金supported by the project“Romanian Hub for Artificial Intelligence-HRIA”,Smart Growth,Digitization and Financial Instruments Program,2021–2027,MySMIS No.334906.
文摘Objective expertise evaluation of individuals,as a prerequisite stage for team formation,has been a long-term desideratum in large software development companies.With the rapid advancements in machine learning methods,based on reliable existing data stored in project management tools’datasets,automating this evaluation process becomes a natural step forward.In this context,our approach focuses on quantifying software developer expertise by using metadata from the task-tracking systems.For this,we mathematically formalize two categories of expertise:technology-specific expertise,which denotes the skills required for a particular technology,and general expertise,which encapsulates overall knowledge in the software industry.Afterward,we automatically classify the zones of expertise associated with each task a developer has worked on using Bidirectional Encoder Representations from Transformers(BERT)-like transformers to handle the unique characteristics of project tool datasets effectively.Finally,our method evaluates the proficiency of each software specialist across already completed projects from both technology-specific and general perspectives.The method was experimentally validated,yielding promising results.
文摘The rapid growth of biomedical data,particularly multi-omics data including genomes,transcriptomics,proteomics,metabolomics,and epigenomics,medical research and clinical decision-making confront both new opportunities and obstacles.The huge and diversified nature of these datasets cannot always be managed using traditional data analysis methods.As a consequence,deep learning has emerged as a strong tool for analysing numerous omics data due to its ability to handle complex and non-linear relationships.This paper explores the fundamental concepts of deep learning and how they are used in multi-omics medical data mining.We demonstrate how autoencoders,variational autoencoders,multimodal models,attention mechanisms,transformers,and graph neural networks enable pattern analysis and recognition across all omics data.Deep learning has been found to be effective in illness classification,biomarker identification,gene network learning,and therapeutic efficacy prediction.We also consider critical problems like as data quality,model explainability,whether findings can be repeated,and computational power requirements.We now consider future elements of combining omics with clinical and imaging data,explainable AI,federated learning,and real-time diagnostics.Overall,this study emphasises the need of collaborating across disciplines to advance deep learning-based multi-omics research for precision medicine and comprehending complicated disorders.
文摘High-throughput transcriptomics has evolved from bulk RNA-seq to single-cell and spatial profiling,yet its clinical translation still depends on effective integration across diverse omics and data modalities.Emerging foundation models and multimodal learning frameworks are enabling scalable and transferable representations of cellular states,while advances in interpretability and real-world data integration are bridging the gap between discovery and clinical application.This paper outlines a concise roadmap for AI-driven,transcriptome-centered multi-omics integration in precision medicine(Figure 1).
基金Supported by Xuhui District Health Commission,No.SHXH202214.
文摘Gastrointestinal tumors require personalized treatment strategies due to their heterogeneity and complexity.Multimodal artificial intelligence(AI)addresses this challenge by integrating diverse data sources-including computed tomography(CT),magnetic resonance imaging(MRI),endoscopic imaging,and genomic profiles-to enable intelligent decision-making for individualized therapy.This approach leverages AI algorithms to fuse imaging,endoscopic,and omics data,facilitating comprehensive characterization of tumor biology,prediction of treatment response,and optimization of therapeutic strategies.By combining CT and MRI for structural assessment,endoscopic data for real-time visual inspection,and genomic information for molecular profiling,multimodal AI enhances the accuracy of patient stratification and treatment personalization.The clinical implementation of this technology demonstrates potential for improving patient outcomes,advancing precision oncology,and supporting individualized care in gastrointestinal cancers.Ultimately,multimodal AI serves as a transformative tool in oncology,bridging data integration with clinical application to effectively tailor therapies.
基金supported in part by the National Key Research and Development Program of China (Grant No.2020YFC2201504)the National Natural Science Foundation of China (Grant Nos.12588101 and 12535002)。
文摘We investigate the null tests of cosmic accelerated expansion by using the baryon acoustic oscillation(BAO)data measured by the dark energy spectroscopic instrument(DESI)and reconstruct the dimensionless Hubble parameter E(z)from the DESI BAO Alcock-Paczynski(AP)data using Gaussian process to perform the null test.We find strong evidence of accelerated expansion from the DESI BAO AP data.By reconstructing the deceleration parameter q(z) from the DESI BAO AP data,we find that accelerated expansion persisted until z■0.7 with a 99.7%confidence level.Additionally,to provide insights into the Hubble tension problem,we propose combining the reconstructed E(z) with D_(H)/r_(d) data to derive a model-independent result r_(d)h=99.8±3.1 Mpc.This result is consistent with measurements from cosmic microwave background(CMB)anisotropies using the ΛCDM model.We also propose a model-independent method for reconstructing the comoving angular diameter distance D_(M)(z) from the distance modulus μ,using SNe Ia data and combining this result with DESI BAO data of D_(M)/r_(d) to constrain the value of r_(d).We find that the value of r_(d),derived from this model-independent method,is smaller than that obtained from CMB measurements,with a significant discrepancy of at least 4.17σ.All the conclusions drawn in this paper are independent of cosmological models and gravitational theories.
基金The work described in this paper was fully supported by a grant from Hong Kong Metropolitan University(RIF/2021/05).
文摘Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using deep learning algorithms further enhances performance;nevertheless,it is challenging due to the nature of small-scale and imbalanced PD datasets.This paper proposed a convolutional neural network-based deep support vector machine(CNN-DSVM)to automate the feature extraction process using CNN and extend the conventional SVM to a DSVM for better classification performance in small-scale PD datasets.A customized kernel function reduces the impact of biased classification towards the majority class(healthy candidates in our consideration).An improved generative adversarial network(IGAN)was designed to generate additional training data to enhance the model’s performance.For performance evaluation,the proposed algorithm achieves a sensitivity of 97.6%and a specificity of 97.3%.The performance comparison is evaluated from five perspectives,including comparisons with different data generation algorithms,feature extraction techniques,kernel functions,and existing works.Results reveal the effectiveness of the IGAN algorithm,which improves the sensitivity and specificity by 4.05%–4.72%and 4.96%–5.86%,respectively;and the effectiveness of the CNN-DSVM algorithm,which improves the sensitivity by 1.24%–57.4%and specificity by 1.04%–163%and reduces biased detection towards the majority class.The ablation experiments confirm the effectiveness of individual components.Two future research directions have also been suggested.
基金Supported by the National Natural Science Foundation of China(11303027,11503029)the Strategic Priority Research Program on Space Science of the Chinese Academy of Sciences(XDA04010300)
文摘The science analysis of the data from the High Energy X-ray Telescope(HE) on the Hard X-ray Modulation Telescope(HXMT) satellite is organized in three stages:calibration,screening and extraction of high-level scientific products.At the first stage,the raw PHA value of each event is converted to PI value accounting for temporal changes in gain and energy offset.At the second stage,the calibrated events are screened by applying cleaning criteria.At the third stage,scientific products,i.e.spectra,light curves and redistribution matrix files,are extracted.This work will introduce the three stages as well as the screening criteria and the data combining method.
基金Supported by the National Natural Science Foundation of China
文摘The Active Particle-induced X-ray Spectrometer （APXS） is an important payload mounted on the Yutu rover, which is part of the Chang＇e-3 mission. The sci- entific objective of APXS is to perform in-situ analysis of the chemical composition of lunar soil and rock samples. The radioactive sources, 55Fe and 109Cd, decay and produce a-particles and X-rays. When X-rays and a-particles interact with atoms in the surface material, they knock electrons out of their orbits, which release energy by emitting X-rays that can be measured by a silicon drift detector （SDD）. The elements and their concentrations can be determined by analyzing their peak energies and in- tensities. APXS has analyzed both the calibration target and lunar soil once during the first lunar day and again during the second lunar day. The total detection time lasted about 266 min and more than 2000 frames of data records have been acquired. APXS has three operating modes： calibration mode, distance sensing mode and detection mode. In detection mode, work distance can be calculated from the X-ray counting rate collected by SDD. Correction for the effect of temperature has been performed to convert the channel number for each spectrum to X-ray energy. Dead time correction is used to eliminate the systematic error in quantifying the activity of an X-ray pulse in a sample and derive the real count rate. We report APXS data and initial results during the first and second lunar days for the Yutu rover. In this study, we analyze the data from the calibration target and lunar soil on the first lunar day. Seven major elements, including Mg, A1, Si, K, Ca, Ti and Fe, have been identified. Comparing the peak areas and ratios of calibration basalt and lunar soil the landing site was found to be depleted in K, and have lower Mg and A1 but higher Ca, Ti, and Fe. In the future, we will obtain the elemental concentrations of lunar soil at the Chang＇e-3 landing site using APXS data.
基金financially supported by the National Key Research and Development Plan(No.2018YFB0605601)the National Natural Science Foundation of China(No.41972168)。
文摘The three-dimensional(3 D) structures of pores directly affect the CH4 flow.Therefore,it is very important to analyze the3 D spatial structure of pores and to simulate the CH4 flow with the connected pores as the carrier.The result shows that the equivalent radius of pores and throats are 1-16 μm and 1.03-8.9 μm,respectively,and the throat length is 3.28-231.25 μm.The coordination number of pores concentrates around three,and the intersection point between the connectivity function and the X-axis is 3-4 μm,which indicate the macro-pores have good connectivity.During the single-channel flow,the pressure decreases along the direction of CH4 flow,and the flow velocity of CH4 decreases from the pore center to the wall.Under the dual-channel and the multi-channel flows,the pressure also decreases along the CH4 flow direction,while the velocity increases.The mean flow pressure gradually decreases with the increase of the distance from the inlet slice.The change of mean flow pressure is relatively stable in the direction horizontal to the bedding plane,while it is relatively large in the direction perpendicular to the bedding plane.The mean flow velocity in the direction horizontal to the bedding plane(Y-axis) is the largest,followed by that in the direction horizontal to the bedding plane(X-axis),and the mean flow velocity in the direction perpendicular to the bedding plane is the smallest.
文摘The X-ray powder diffraction data of the compound GdAlSi was studied by means of X-ray diffraction technique and refined by Rietveld method. The compound GdAlSi has tetragonal α-ThSi_2-type structure, space group I4_1/amd (No.141), Z=4, the lattice parameters a=041234 (1) nm, c=1.44202(1) nm. The Smith and Snyder figure of merit [5] F_N is F_ 30=2521(36). The R-factors of Rietveld refinement are R_p=0.098 and R_ wp=0.128. The X-ray powder diffraction data are given. The field dependence of the magnetization measured at room temperature and the temperature variation of the inverse magnetic susceptibility of the compound GdAlSi were also presented.
基金This work was financially supported by the National Natural Science Foundation of China(No.42102217)the University Synergy Innovation Program of Anhui Province(No.GXXT-2021-018)+3 种基金the Natural Science Research Project of Anhui University(No.KJ2020A0315No.KJ2020A0317)the Natural Science Foundation of Anhui Province(No.2108085MD134)the Foundation of State Key Laboratory of Petroleum Resources and Prospecting,China University of Petroleum,Beijing(No.PRP/open-2005).
文摘Matrix swelling effect will cause the change of microstructure of coal reservoir and its permeability,which is the key factor affecting the engineering effect of CO_(2)-ECBM technology.The Sihe and Yuwu collieries are taken as research objects.Firstly,visualization reconstruction of coal reservoir is realized.Secondly,the evolution of the pore/fracture structures under different swelling contents is discussed.Then,the influence of matrix phase with different swelling contents on permeability is discussed.Finally,the mechanism of swelling effect during the CO_(2)-ECBM process is further discussed.The results show that the intra-matrix pores and matrix-edge fractures are the focus of this study,and the contacting area between matrix and pore/fracture is the core area of matrix swelling.The number of matrix particles decreases with the increase of size,and the distribution of which is isolated with small size and interconnected with large size.The swelling effect of matrix particles with larger size has a great influence on the pore/fracture structures.The number of connected pores/fractures is limited and only interconnected in a certain direction.With the increase of matrix swelling content,the number,porosity,width,fractal dimension,surface area and volume of pores/fractures decrease,and their negative contribution to absolute permeability increases from 0.368% to 0.633% and 0.868%-1.404%,respectively.With the increase of swelling content,the number of intra-matrix pores gradually decreases and the pore radius becomes shorter during the CO_(2)-ECBM process.The matrix continuously expands to the connected fractures,and the width of connected fractures gradually shorten.Under the influence of matrix swelling,the bending degree of fluid flow increases gradually,so the resistance of fluid migration increases and the permeability gradually decreases.This study shows that the matrix swelling effect is the key factor affecting CBM recovery,and the application of this effect in CO_(2)-ECBM process can be discussed.
文摘Accuracy of coeffcient A_(isp) is related to the reference phase chosen during analysis. The cri- terion of choosing reference phase which may minimize the error of A_(isp) was deduced. The optimum results could be obtained by using the method of least squares if the number of sam- pies for analysis is more than the phase in samples. The procedure presented here is satisfacto- ryfor ordinary phase analysis.
