Semantic segmentation is a core task in computer vision that allows AI models to interact and understand their surrounding environment. Similarly to how humans subconsciously segment scenes, this ability is crucial fo...Semantic segmentation is a core task in computer vision that allows AI models to interact and understand their surrounding environment. Similarly to how humans subconsciously segment scenes, this ability is crucial for scene understanding. However, a challenge many semantic learning models face is the lack of data. Existing video datasets are limited to short, low-resolution videos that are not representative of real-world examples. Thus, one of our key contributions is a customized semantic segmentation version of the Walking Tours Dataset that features hour-long, high-resolution, real-world data from tours of different cities. Additionally, we evaluate the performance of open-vocabulary, semantic model OpenSeeD on our own custom dataset and discuss future implications.展开更多
Cascade index modulation(CIM) is a recently proposed improvement of orthogonal frequency division multiplexing with index modulation(OFDM-IM) and achieves better error performance.In CIM, at least two different IM ope...Cascade index modulation(CIM) is a recently proposed improvement of orthogonal frequency division multiplexing with index modulation(OFDM-IM) and achieves better error performance.In CIM, at least two different IM operations construct a super IM operation or achieve new functionality. First, we propose a OFDM with generalized CIM(OFDM-GCIM) scheme to achieve a joint IM of subcarrier selection and multiple-mode(MM)permutations by using a multilevel digital algorithm.Then, two schemes, called double CIM(D-CIM) and multiple-layer CIM(M-CIM), are proposed for secure communication, which combine new IM operation for disrupting the original order of bits and symbols with conventional OFDM-IM, to protect the legitimate users from eavesdropping in the wireless communications. A subcarrier-wise maximum likelihood(ML) detector and a low complexity log-likelihood ratio(LLR) detector are proposed for the legitimate users. A tight upper bound on the bit error rate(BER) of the proposed OFDM-GCIM, D-CIM and MCIM at the legitimate users are derived in closed form by employing the ML criteria detection. Computer simulations and numerical results show that the proposed OFDM-GCIM achieves superior error performance than OFDM-IM, and the error performance at the eavesdroppers demonstrates the security of D-CIM and M-CIM.展开更多
Understanding the characteristics and predicting the popularity of the newly published online videos can provide direct implications in various contexts such as service design, advertisement planning, network manageme...Understanding the characteristics and predicting the popularity of the newly published online videos can provide direct implications in various contexts such as service design, advertisement planning, network management and etc. In this paper, we collect a real-world large-scale dataset from a leading online video service provider in China, namely Youku. We first analyze the dynamics of content publication and content popularity for the online video service. Then, we propose a rich set of features and exploit various effective classification methods to estimate the future popularity level of an individual video in various scenarios. We show that the future popularity level of a video can be predicted even before the video's release, and by introducing the historical popularity information the prediction performance can be improved dramatically. In addition, we investigate the importance of each feature group and each feature in the popularity prediction, and further reveal the factors that may impact the video popularity. We also discuss how the early monitoring period influences the popularity level prediction. Our work provides an insight into the popularity of the newly published online videos, and demonstrates promising practical applications for content publishers,service providers, online advisers and network operators.展开更多
Cloud computing provides services to users through Internet.This open mode not only facilitates the access by users,but also brings potential security risks.In cloud computing,the risk of data leakage exists between u...Cloud computing provides services to users through Internet.This open mode not only facilitates the access by users,but also brings potential security risks.In cloud computing,the risk of data leakage exists between users and virtual machines.Whether direct or indirect data leakage,it can be regarded as illegal information flow.Methods,such as access control models can control the information flow,but not the covert information flow.Therefore,it needs to use the noninterference models to detect the existence of illegal information flow in cloud computing architecture.Typical noninterference models are not suitable to certificate information flow in cloud computing architecture.In this paper,we propose several information flow models for cloud architecture.One model is for transitive cloud computing architecture.The others are for intransitive cloud computing architecture.When concurrent access actions execute in the cloud architecture,we want that security domain and security domain do not affect each other,that there is no information flow between security domains.But in fact,there will be more or less indirect information flow between security domains.Our models are concerned with how much information is allowed to flow.For example,in the CIP model,the other domain can learn the sequence of actions.But in the CTA model,the other domain can’t learn the information.Which security model will be used in an architecture depends on the security requirements for that architecture.展开更多
Objective:Computer-aided diagnosis using deep learning algorithms has been initially applied in the field of mammography,but there is no large-scale clinical application.Methods:This study proposed to develop and veri...Objective:Computer-aided diagnosis using deep learning algorithms has been initially applied in the field of mammography,but there is no large-scale clinical application.Methods:This study proposed to develop and verify an artificial intelligence model based on mammography.Firstly,mammograms retrospectively collected from six centers were randomized to a training dataset and a validation dataset for establishing the model.Secondly,the model was tested by comparing 12 radiologists’performance with and without it.Finally,prospectively enrolled women with mammograms from six centers were diagnosed by radiologists with the model.The detection and diagnostic capabilities were evaluated using the freeresponse receiver operating characteristic(FROC)curve and ROC curve.Results:The sensitivity of model for detecting lesions after matching was 0.908 for false positive rate of 0.25 in unilateral images.The area under ROC curve(AUC)to distinguish the benign lesions from malignant lesions was0.855[95%confidence interval(95%CI):0.830,0.880].The performance of 12 radiologists with the model was higher than that of radiologists alone(AUC:0.852 vs.0.805,P=0.005).The mean reading time of with the model was shorter than that of reading alone(80.18 s vs.62.28 s,P=0.032).In prospective application,the sensitivity of detection reached 0.887 at false positive rate of 0.25;the AUC of radiologists with the model was 0.983(95%CI:0.978,0.988),with sensitivity,specificity,positive predictive value(PPV),and negative predictive value(NPV)of94.36%,98.07%,87.76%,and 99.09%,respectively.Conclusions:The artificial intelligence model exhibits high accuracy for detecting and diagnosing breast lesions,improves diagnostic accuracy and saves time.展开更多
Background:In this investigation,we explore the literature regarding neuroregeneration from the 1700s to the present.The regeneration of central nervous system neurons or the regeneration of axons from cell bodies and...Background:In this investigation,we explore the literature regarding neuroregeneration from the 1700s to the present.The regeneration of central nervous system neurons or the regeneration of axons from cell bodies and their reconnection with other neurons remains a major hurdle.Injuries relating to war and accidents attracted medical professionals throughout early history to regenerate and reconnect nerves.Early literature till 1990 lacked specific molecular details and is likely provide some clues to conditions that promoted neuron and/or axon regeneration.This is an avenue for the application of natural language processing(NLP)to gain actionable intelligence.Post 1990 period saw an explosion of all molecular details.With the advent of genomic,transcriptomics,proteomics,and other omics-there is an emergence of big data sets and is another rich area for application of NLP.How the neuron and/or axon regeneration related keywords have changed over the years is a first step towards this endeavor.Methods:Specifically,this article curates over 600 published works in the field of neuroregeneration.We then apply a dynamic topic modeling algorithm based on the Latent Dirichlet allocation(LDA)algorithm to assess how topics cluster based on topics.Results:Based on how documents are assigned to topics,we then build a recommendation engine to assist researchers to access domain-specific literature based on how their search text matches to recommended document topics.The interface further includes interactive topic visualizations for researchers to understand how topics grow closer and further apart,and how intra-topic composition changes over time.Conclusions:We present a recommendation engine and interactive interface that enables dynamic topic modeling for neuronal regeneration.展开更多
Metaheuristic optimization methods are iterative search processes that aim to efficiently solve complexoptimization problems. These basically find the solution space very efficiently, often without utilizing the gradi...Metaheuristic optimization methods are iterative search processes that aim to efficiently solve complexoptimization problems. These basically find the solution space very efficiently, often without utilizing the gradientinformation, and are inspired by the bio-inspired and socially motivated heuristics. Metaheuristic optimizationalgorithms are increasingly applied to complex feature selection problems in high-dimensional medical datasets.Among these, Teaching-Learning-Based optimization (TLBO) has proven effective for continuous design tasks bybalancing exploration and exploitation phases. However, its binary version (BTLBO) suffers from limited exploitationability, often converging prematurely or getting trapped in local optima, particularly when applied to discrete featureselection tasks. Previous studies reported that BTLBO yields lower classification accuracy and higher feature subsetvariance compared to other hybrid methods in benchmark tests, motivating the development of hybrid approaches.This study proposes a novel hybrid algorithm, BTLBO-Cheetah Optimizer (BTLBO-CO), which integrates the globalexploration strength of BTLBO with the local exploitation efficiency of the Cheetah Optimization (CO) algorithm. Theobjective is to enhance the feature selection process for cancer classification tasks involving high-dimensional data. Theproposed BTLBO-CO algorithm was evaluated on six benchmark cancer datasets: 11 tumors (T), Lung Cancer (LUC),Leukemia (LEU), Small Round Blue Cell Tumor or SRBCT (SR), Diffuse Large B-cell Lymphoma or DLBCL (DL), andProstate Tumor (PT).The results demonstrate superior classification accuracy across all six datasets, achieving 93.71%,96.12%, 98.13%, 97.11%, 98.44%, and 98.84%, respectively.These results validate the effectiveness of the hybrid approachin addressing diverse feature selection challenges using a Support Vector Machine (SVM) classifier.展开更多
Positive data are very common in many scientific fields and applications;for these data,it is known that estimation and inference based on relative error criterion are superior to that of absolute error criterion.In p...Positive data are very common in many scientific fields and applications;for these data,it is known that estimation and inference based on relative error criterion are superior to that of absolute error criterion.In prediction problems,conformal prediction provides a useful framework to construct flexible prediction intervals based on hypothesis testing,which has been actively studied in the past decade.In view of the advantages of the relative error criterion for regression problems with positive responses,in this paper,we combine the relative error criterion(REC)with conformal prediction to develop a novel REC-based predictive inference method to construct prediction intervals for the positive response.The proposed method satisfies the finite sample global coverage guarantee and to some extent achieves the local validity.We conduct extensive simulation studies and two real data analysis to demonstrate the competitiveness of the new proposed method.展开更多
We performed spectral analyses on the ages of 89 well-dated major geological events of the last 260 Myr from the recent geologic literature. These events include times of marine and non-marine extinctions,major ocean-...We performed spectral analyses on the ages of 89 well-dated major geological events of the last 260 Myr from the recent geologic literature. These events include times of marine and non-marine extinctions,major ocean-anoxic events, continental flood-basalt eruptions, sea-level fluctuations, global pulses of intraplate magmatism, and times of changes in seafloor-spreading rates and plate reorganizations. The aggregate of all 89 events shows ten clusters in the last 260 Myr, spaced at an average interval of ~ 26.9 Myr, and Fourier analysis of the data yields a spectral peak at 27.5 Myr at the ≥96% confidence level. A shorter period of ~ 8.9 Myr may also be significant in modulating the timing of geologic events.Our results suggest that global geologic events are generally correlated, and seem to come in pulses with an underlying ~ 27.5-Myr cycle. These cyclic pulses of tectonics and climate change may be the result of geophysical processes related to the dynamics of plate tectonics and mantle plumes, or might alternatively be paced by astronomical cycles associated with the Earth’s motions in the Solar System and the Galaxy.展开更多
Demographic estimation becomes a problem of small area estimation when detaileddisaggregation leads to small cell counts.The usual difficulties of small area estimation are compounded when the available data sources c...Demographic estimation becomes a problem of small area estimation when detaileddisaggregation leads to small cell counts.The usual difficulties of small area estimation are compounded when the available data sources contain measurement errors.We present a Bayesianapproach to the problem of small area estimation with imperfect data sources.The overall modelcontains separate submodels for underlying demographic processes and for measurement processes.All unknown quantities in the model,including coverage ratios and demographic rates,are estimated jointly via Markov chain Monte Carlo methods.The approach is illustrated usingthe example of provincial fertility rates in Cambodia.展开更多
Objective To evaluate the association between serum uric acid(SUA)and kidney function decline.Methods Data was obtained from the China Health and Retirement Longitudinal Study on the Chinese middle-aged and older popu...Objective To evaluate the association between serum uric acid(SUA)and kidney function decline.Methods Data was obtained from the China Health and Retirement Longitudinal Study on the Chinese middle-aged and older population for analysis.The kidney function decline was defined as an annual estimated glomerular filtration rate(e GFR)decrease by>3 mL/min per 1.73 m^(2).Multivariable logistic regression was applied to determine the association between SUA and kidney function decline.The shape of the association was investigated by restricted cubic splines.Results A total of 7,346 participants were included,of which 1,004 individuals(13.67%)developed kidney function decline during the follow-up of 4 years.A significant dose-response relation was recorded between SUA and the kidney function decline(OR 1.14,95%CI 1.03-1.27),as the risk of kidney function decline increased by 14%per 1 mg/d L increase in SUA.In the subgroup analyses,such a relation was only recorded among women(OR 1.22,95%CI 1.03-1.45),those aged<60 years(OR 1.22,95%CI 1.05-1.42),and those without hypertension and without diabetes(OR 1.22,95%CI 1.06-1.41).Although the dose-response relation was not observed in men,the high level of SUA was related to kidney function decline(OR 1.83,95%CI 1.05-3.17).The restricted cubic spline analysis indicated that SUA>5 mg/dL was associated with a significantly higher risk of kidney function decline.Conclusion The SUA level was associated with kidney function decline.An elevation of SUA should therefore be addressed to prevent possible kidney impairment and dysfunction.展开更多
The sole use of single modality data often fails to capture the complex heterogeneity among patients,including the variability in resistance to anti-HER2 therapy and outcomes of combined treatment regimens,for the tre...The sole use of single modality data often fails to capture the complex heterogeneity among patients,including the variability in resistance to anti-HER2 therapy and outcomes of combined treatment regimens,for the treatment of HER2-positive gastric cancer(GC).This modality deficit has not been fully considered in many studies.Furthermore,the application of artificial intelligence in predicting the treatment response,particularly in complex diseases such as GC,is still in its infancy.Therefore,this study aimed to use a comprehensive analytic approach to accurately predict treatment responses to anti-HER2 therapy or anti-HER2 combined immunotherapy in patients with HER2-positive GC.We collected multi-modal data,comprising radiology,pathology,and clinical information from a cohort of 429 patients:310 treated with anti-HER2 therapy and 119 treated with a combination of anti-HER2 and anti-PD-1/PD-L1 inhibitors immunotherapy.We introduced a deep learning model,called the Multi-Modal model(MuMo),that integrates these data to make precise treatment response predictions.MuMo achieved an area under the curve score of 0.821 for anti-HER2 therapy and 0.914 for combined immunotherapy.Moreover,patients classified as low-risk by MuMo exhibited significantly prolonged progression-free survival and overall survival(log-rank test,P<0.05).These findings not only highlight the significance of multi-modal data analysis in enhancing treatment evaluation and personalized medicine for HER2-positive gastric cancer,but also the potential and clinical value of our model.展开更多
In this paper,we study compressed data separation(CDS)problem,i.e.,sparse data separation from a few linear random measurements.We propose the nonconvex ℓ_(q)-split analysis with ℓ_(∞)-constraint and 0<q≤1.We cal...In this paper,we study compressed data separation(CDS)problem,i.e.,sparse data separation from a few linear random measurements.We propose the nonconvex ℓ_(q)-split analysis with ℓ_(∞)-constraint and 0<q≤1.We call the algorithm ℓ_(q)-split-analysis Dantzig selector(ℓ_(q)-split-analysis DS).We show that the two distinct subcomponents that are approximately sparse in terms of two different dictionaries could be stably approximated via the ℓ_(q)-split-analysis DS,provided that the measurement matrix satisfies either a classical D-RIP(Restricted Isometry Property with respect to Dictionaries and ℓ_(2) norm)or a relatively new(D,q)-RIP(RIP with respect to Dictionaries and ℓ_(q)-quasi norm)condition and the two different dictionaries satisfy a mutual coherence condition between them.For the Gaussian random measurements,the measurement number needed for the(D,q)-RIP condition is far less than those needed for the D-RIP condition and the(D,1)-RIP condition when q is small enough.展开更多
The healthcare industry faces core challenges,including increasingly complex operational processes and entities,the rapid development of medical knowledge,and the rising demand for interdisciplinary expertise.The comp...The healthcare industry faces core challenges,including increasingly complex operational processes and entities,the rapid development of medical knowledge,and the rising demand for interdisciplinary expertise.The complexity of medical processes is evident in every aspect,from patient appointments,diagnoses,and treatments to follow-up tasks,all of which involve intricate data processing and decision-making procedures.展开更多
.Holographic imaging poses significant challenges when facing real-time disturbances introduced by dynamic environments.The existing deep-learning methods for holographic imaging often depend solely on the specific co....Holographic imaging poses significant challenges when facing real-time disturbances introduced by dynamic environments.The existing deep-learning methods for holographic imaging often depend solely on the specific condition based on the given data distributions,thus hindering their generalization across multiple scenes.One critical problem is how to guarantee the alignment between any given downstream tasks and pretrained models.We analyze the physical mechanism of image degradation caused by turbulence and innovatively propose a swin transformer-based method,termed train-with-coherence-swin(TWC-Swin)transformer,which uses spatial coherence(SC)as an adaptable physical prior information to precisely align image restoration tasks in the arbitrary turbulent scene.The light-processing system(LPR)we designed enables manipulation of SC and simulation of any turbulence.Qualitative and quantitative evaluations demonstrate that the TWC-Swin method presents superiority over traditional convolution frameworks and realizes image restoration under various turbulences,which suggests its robustness,powerful generalization capabilities,and adaptability to unknown environments.Our research reveals the significance of physical prior information in the optical intersection and provides an effective solution for model-to-tasks alignment schemes,which will help to unlock the full potential of deep learning for all-weather optical imaging across terrestrial,marine,and aerial domains.展开更多
In recent years,deep neural network has achieved great success in solving many natural language processing tasks.Particularly,substantial progress has been made on neural text generation,which takes the linguistic and...In recent years,deep neural network has achieved great success in solving many natural language processing tasks.Particularly,substantial progress has been made on neural text generation,which takes the linguistic and non-linguistic input,and generates natural language text.This survey aims to provide an up-to-date synthesis of core tasks in neural text generation and the architectures adopted to handle these tasks,and draw attention to the challenges in neural text generation.We first outline the mainstream neural text generation frameworks,and then introduce datasets,advanced models and challenges of four core text generation tasks in detail,including AMR-to-text generation,data-to-text generation,and two text-to-text generation tasks(i.e.,text summarization and paraphrase generation).Finally,we present future research directions for neural text generation.This survey can be used as a guide and reference for researchers and practitioners in this area.展开更多
Entity Linking(EL)aims to automatically link the mentions in unstructured documents to corresponding entities in a knowledge base(KB),which has recently been dominated by global models.Although many global EL methods ...Entity Linking(EL)aims to automatically link the mentions in unstructured documents to corresponding entities in a knowledge base(KB),which has recently been dominated by global models.Although many global EL methods attempt to model the topical coherence among all linked entities,most of them failed in exploiting the correlations among manifold knowledge helpful for linking,such as the semantics of mentions and their candidates,the neighborhood information of candidate entities in KB and the fine-grained type information of entities.As we will show in the paper,interactions among these types of information are very useful for better characterizing the topic features of entities and more accurately estimating the topical coherence among all the referred entities within the same document.In this paper,we present a novel HEterogeneous Graph-based Entity Linker(HEGEL)for global entity linking,which builds an informative heterogeneous graph for every document to collect various linking clues.Then HEGEL utilizes a novel heterogeneous graph neural network(HGNN)to integrate the different types of manifold information and model the interactions among them.Experiments on the standard benchmark datasets demonstrate that HEGEL can well capture the global coherence and outperforms the prior state-of-the-art EL methods.展开更多
Multivariate time series segmentation is an important problem in data mining and it has arisen in more and more practical applications in recent years.The task of time series segmentation is to partition a time series...Multivariate time series segmentation is an important problem in data mining and it has arisen in more and more practical applications in recent years.The task of time series segmentation is to partition a time series into segments by detecting the abrupt changes or anomalies in the time series.Multivariate time series segmentation can provide meaningful information for further data analysis,prediction and policy decision.A time series can be considered as a piecewise continuous function,it is natural to take its total variation norm as a prior information of this time series.In this paper,by minimizing the negative log-likelihood function of a time series,we propose a total variation based model for multivariate time series segmentation.An iterative process is applied to solve the proposed model and a search combined the dynamic programming method is designed to determine the breakpoints.The experimental results show that the proposed method is efficient for multivariate time series segmentation and it is competitive to the existing methods for multivariate time series segmentation.展开更多
Deep learning has been widely used for plant disease recognition in smart agriculture and has proven to be a powerful tool for image classification and pattern recognition.However,it has limited interpretability for d...Deep learning has been widely used for plant disease recognition in smart agriculture and has proven to be a powerful tool for image classification and pattern recognition.However,it has limited interpretability for deep features.With the transfer of expert knowledge,handcrafted features provide a new way for personalized diagnosis of plant diseases.However,irrelevant and redundant features lead to high dimensionality.In this study,we proposed a swarm intelligence algorithm for feature selection[salp swarm algorithm for feature selection(SSAFS)]in image-based plant disease detection.SSAFS is employed to determine the ideal combination of handcrafted features to maximize classification success while minimizing the number of features.To verify the effectiveness of the developed SSAFS algorithm,we conducted experimental studies using SSAFS and 5 metaheuristic algorithms.Several evaluation metrics were used to evaluate and analyze the performance of these methods on 4 datasets from the UCI machine learning repository and 6 plant phenomics datasets from PlantVillage.Experimental results and statistical analyses validated the outstanding performance of SSAFS compared to existing state-of-the-art algorithms,confirming the superiority of SSAFS in exploring the feature space and identifying the most valuable features for diseased plant image classification.This computational tool will allow us to explore an optimal combination of handcrafted features to improve plant disease recognition accuracy and processing time.展开更多
With the rapid development of artificial intelligence,large language models(LLMs)have shown promising capabilities in mimicking human-level language comprehen-sion and reasoning.This has sparked significant interest i...With the rapid development of artificial intelligence,large language models(LLMs)have shown promising capabilities in mimicking human-level language comprehen-sion and reasoning.This has sparked significant interest in applying LLMs to enhance various aspects of healthcare,ranging from medical education to clinical decision support.However,medicine involves multifaceted data modalities and nuanced reasoning skills,presenting challenges for integrating LLMs.This review introduces the fundamental applications of general-purpose and specialized LLMs,demon-strating their utilities in knowledge retrieval,research support,clinical workflow automation,and diagnostic assistance.Recognizing the inherent multimodality of medicine,the review emphasizes the multimodal LLMs and discusses their ability to process diverse data types like medical imaging and electronic health records to augment diagnostic accuracy.To address LLMs'limitations regarding personalization and complex clinical reasoning,the review further explores the emerging develop-ment of LLM-powered autonomous agents for healthcare.Moreover,it summarizes the evaluation methodologies for assessing LLMs'reliability and safety in medical contexts.LLMs have transformative potential in medicine;however,there is a pivotal need for continuous optimizations and ethical oversight before these models can be effectively integrated into clinical practice.展开更多
文摘Semantic segmentation is a core task in computer vision that allows AI models to interact and understand their surrounding environment. Similarly to how humans subconsciously segment scenes, this ability is crucial for scene understanding. However, a challenge many semantic learning models face is the lack of data. Existing video datasets are limited to short, low-resolution videos that are not representative of real-world examples. Thus, one of our key contributions is a customized semantic segmentation version of the Walking Tours Dataset that features hour-long, high-resolution, real-world data from tours of different cities. Additionally, we evaluate the performance of open-vocabulary, semantic model OpenSeeD on our own custom dataset and discuss future implications.
基金supported by National Natural Science Foundation of China (No. 61971149, 62071504, 62271208)in part by the Special Projects in Key Fields for General Universities of Guangdong Province (No. 2020ZDZX3025, 2021ZDZX056)+1 种基金in part by the Guangdong Basic and Applied Basic Research Foundation (No. 2021A1515011657)in part by the Featured Innovation Projects of Guangdong Province of China (No. 2021KTSCX049)。
文摘Cascade index modulation(CIM) is a recently proposed improvement of orthogonal frequency division multiplexing with index modulation(OFDM-IM) and achieves better error performance.In CIM, at least two different IM operations construct a super IM operation or achieve new functionality. First, we propose a OFDM with generalized CIM(OFDM-GCIM) scheme to achieve a joint IM of subcarrier selection and multiple-mode(MM)permutations by using a multilevel digital algorithm.Then, two schemes, called double CIM(D-CIM) and multiple-layer CIM(M-CIM), are proposed for secure communication, which combine new IM operation for disrupting the original order of bits and symbols with conventional OFDM-IM, to protect the legitimate users from eavesdropping in the wireless communications. A subcarrier-wise maximum likelihood(ML) detector and a low complexity log-likelihood ratio(LLR) detector are proposed for the legitimate users. A tight upper bound on the bit error rate(BER) of the proposed OFDM-GCIM, D-CIM and MCIM at the legitimate users are derived in closed form by employing the ML criteria detection. Computer simulations and numerical results show that the proposed OFDM-GCIM achieves superior error performance than OFDM-IM, and the error performance at the eavesdroppers demonstrates the security of D-CIM and M-CIM.
文摘Understanding the characteristics and predicting the popularity of the newly published online videos can provide direct implications in various contexts such as service design, advertisement planning, network management and etc. In this paper, we collect a real-world large-scale dataset from a leading online video service provider in China, namely Youku. We first analyze the dynamics of content publication and content popularity for the online video service. Then, we propose a rich set of features and exploit various effective classification methods to estimate the future popularity level of an individual video in various scenarios. We show that the future popularity level of a video can be predicted even before the video's release, and by introducing the historical popularity information the prediction performance can be improved dramatically. In addition, we investigate the importance of each feature group and each feature in the popularity prediction, and further reveal the factors that may impact the video popularity. We also discuss how the early monitoring period influences the popularity level prediction. Our work provides an insight into the popularity of the newly published online videos, and demonstrates promising practical applications for content publishers,service providers, online advisers and network operators.
基金Natural Science Research Project of Jiangsu Province Universities and Colleges(No.17KJD520005,Congdong Lv).
文摘Cloud computing provides services to users through Internet.This open mode not only facilitates the access by users,but also brings potential security risks.In cloud computing,the risk of data leakage exists between users and virtual machines.Whether direct or indirect data leakage,it can be regarded as illegal information flow.Methods,such as access control models can control the information flow,but not the covert information flow.Therefore,it needs to use the noninterference models to detect the existence of illegal information flow in cloud computing architecture.Typical noninterference models are not suitable to certificate information flow in cloud computing architecture.In this paper,we propose several information flow models for cloud architecture.One model is for transitive cloud computing architecture.The others are for intransitive cloud computing architecture.When concurrent access actions execute in the cloud architecture,we want that security domain and security domain do not affect each other,that there is no information flow between security domains.But in fact,there will be more or less indirect information flow between security domains.Our models are concerned with how much information is allowed to flow.For example,in the CIP model,the other domain can learn the sequence of actions.But in the CTA model,the other domain can’t learn the information.Which security model will be used in an architecture depends on the security requirements for that architecture.
基金supported by Beijing Municipal Science&Technology Commission(No.Z181100001918001)Beijing Municipal Administration of Hospitals Clinical Medicine Development of Special Funding Support(No.ZYLX201803)+1 种基金Beijing Hospitals Authority Ascent Plan(No.DFL20191103)Beijing Municipal Administration of Hospitals Incubating Program(No.PX2018041)。
文摘Objective:Computer-aided diagnosis using deep learning algorithms has been initially applied in the field of mammography,but there is no large-scale clinical application.Methods:This study proposed to develop and verify an artificial intelligence model based on mammography.Firstly,mammograms retrospectively collected from six centers were randomized to a training dataset and a validation dataset for establishing the model.Secondly,the model was tested by comparing 12 radiologists’performance with and without it.Finally,prospectively enrolled women with mammograms from six centers were diagnosed by radiologists with the model.The detection and diagnostic capabilities were evaluated using the freeresponse receiver operating characteristic(FROC)curve and ROC curve.Results:The sensitivity of model for detecting lesions after matching was 0.908 for false positive rate of 0.25 in unilateral images.The area under ROC curve(AUC)to distinguish the benign lesions from malignant lesions was0.855[95%confidence interval(95%CI):0.830,0.880].The performance of 12 radiologists with the model was higher than that of radiologists alone(AUC:0.852 vs.0.805,P=0.005).The mean reading time of with the model was shorter than that of reading alone(80.18 s vs.62.28 s,P=0.032).In prospective application,the sensitivity of detection reached 0.887 at false positive rate of 0.25;the AUC of radiologists with the model was 0.983(95%CI:0.978,0.988),with sensitivity,specificity,positive predictive value(PPV),and negative predictive value(NPV)of94.36%,98.07%,87.76%,and 99.09%,respectively.Conclusions:The artificial intelligence model exhibits high accuracy for detecting and diagnosing breast lesions,improves diagnostic accuracy and saves time.
文摘Background:In this investigation,we explore the literature regarding neuroregeneration from the 1700s to the present.The regeneration of central nervous system neurons or the regeneration of axons from cell bodies and their reconnection with other neurons remains a major hurdle.Injuries relating to war and accidents attracted medical professionals throughout early history to regenerate and reconnect nerves.Early literature till 1990 lacked specific molecular details and is likely provide some clues to conditions that promoted neuron and/or axon regeneration.This is an avenue for the application of natural language processing(NLP)to gain actionable intelligence.Post 1990 period saw an explosion of all molecular details.With the advent of genomic,transcriptomics,proteomics,and other omics-there is an emergence of big data sets and is another rich area for application of NLP.How the neuron and/or axon regeneration related keywords have changed over the years is a first step towards this endeavor.Methods:Specifically,this article curates over 600 published works in the field of neuroregeneration.We then apply a dynamic topic modeling algorithm based on the Latent Dirichlet allocation(LDA)algorithm to assess how topics cluster based on topics.Results:Based on how documents are assigned to topics,we then build a recommendation engine to assist researchers to access domain-specific literature based on how their search text matches to recommended document topics.The interface further includes interactive topic visualizations for researchers to understand how topics grow closer and further apart,and how intra-topic composition changes over time.Conclusions:We present a recommendation engine and interactive interface that enables dynamic topic modeling for neuronal regeneration.
基金funded by the Deanship of Research andGraduate Studies at King Khalid University through the Large Research Project under grant number RGP2/417/46.
文摘Metaheuristic optimization methods are iterative search processes that aim to efficiently solve complexoptimization problems. These basically find the solution space very efficiently, often without utilizing the gradientinformation, and are inspired by the bio-inspired and socially motivated heuristics. Metaheuristic optimizationalgorithms are increasingly applied to complex feature selection problems in high-dimensional medical datasets.Among these, Teaching-Learning-Based optimization (TLBO) has proven effective for continuous design tasks bybalancing exploration and exploitation phases. However, its binary version (BTLBO) suffers from limited exploitationability, often converging prematurely or getting trapped in local optima, particularly when applied to discrete featureselection tasks. Previous studies reported that BTLBO yields lower classification accuracy and higher feature subsetvariance compared to other hybrid methods in benchmark tests, motivating the development of hybrid approaches.This study proposes a novel hybrid algorithm, BTLBO-Cheetah Optimizer (BTLBO-CO), which integrates the globalexploration strength of BTLBO with the local exploitation efficiency of the Cheetah Optimization (CO) algorithm. Theobjective is to enhance the feature selection process for cancer classification tasks involving high-dimensional data. Theproposed BTLBO-CO algorithm was evaluated on six benchmark cancer datasets: 11 tumors (T), Lung Cancer (LUC),Leukemia (LEU), Small Round Blue Cell Tumor or SRBCT (SR), Diffuse Large B-cell Lymphoma or DLBCL (DL), andProstate Tumor (PT).The results demonstrate superior classification accuracy across all six datasets, achieving 93.71%,96.12%, 98.13%, 97.11%, 98.44%, and 98.84%, respectively.These results validate the effectiveness of the hybrid approachin addressing diverse feature selection challenges using a Support Vector Machine (SVM) classifier.
文摘Positive data are very common in many scientific fields and applications;for these data,it is known that estimation and inference based on relative error criterion are superior to that of absolute error criterion.In prediction problems,conformal prediction provides a useful framework to construct flexible prediction intervals based on hypothesis testing,which has been actively studied in the past decade.In view of the advantages of the relative error criterion for regression problems with positive responses,in this paper,we combine the relative error criterion(REC)with conformal prediction to develop a novel REC-based predictive inference method to construct prediction intervals for the positive response.The proposed method satisfies the finite sample global coverage guarantee and to some extent achieves the local validity.We conduct extensive simulation studies and two real data analysis to demonstrate the competitiveness of the new proposed method.
基金Research was partly funded by an NYU Research Challenge Fund Grant。
文摘We performed spectral analyses on the ages of 89 well-dated major geological events of the last 260 Myr from the recent geologic literature. These events include times of marine and non-marine extinctions,major ocean-anoxic events, continental flood-basalt eruptions, sea-level fluctuations, global pulses of intraplate magmatism, and times of changes in seafloor-spreading rates and plate reorganizations. The aggregate of all 89 events shows ten clusters in the last 260 Myr, spaced at an average interval of ~ 26.9 Myr, and Fourier analysis of the data yields a spectral peak at 27.5 Myr at the ≥96% confidence level. A shorter period of ~ 8.9 Myr may also be significant in modulating the timing of geologic events.Our results suggest that global geologic events are generally correlated, and seem to come in pulses with an underlying ~ 27.5-Myr cycle. These cyclic pulses of tectonics and climate change may be the result of geophysical processes related to the dynamics of plate tectonics and mantle plumes, or might alternatively be paced by astronomical cycles associated with the Earth’s motions in the Solar System and the Galaxy.
文摘Demographic estimation becomes a problem of small area estimation when detaileddisaggregation leads to small cell counts.The usual difficulties of small area estimation are compounded when the available data sources contain measurement errors.We present a Bayesianapproach to the problem of small area estimation with imperfect data sources.The overall modelcontains separate submodels for underlying demographic processes and for measurement processes.All unknown quantities in the model,including coverage ratios and demographic rates,are estimated jointly via Markov chain Monte Carlo methods.The approach is illustrated usingthe example of provincial fertility rates in Cambodia.
文摘Objective To evaluate the association between serum uric acid(SUA)and kidney function decline.Methods Data was obtained from the China Health and Retirement Longitudinal Study on the Chinese middle-aged and older population for analysis.The kidney function decline was defined as an annual estimated glomerular filtration rate(e GFR)decrease by>3 mL/min per 1.73 m^(2).Multivariable logistic regression was applied to determine the association between SUA and kidney function decline.The shape of the association was investigated by restricted cubic splines.Results A total of 7,346 participants were included,of which 1,004 individuals(13.67%)developed kidney function decline during the follow-up of 4 years.A significant dose-response relation was recorded between SUA and the kidney function decline(OR 1.14,95%CI 1.03-1.27),as the risk of kidney function decline increased by 14%per 1 mg/d L increase in SUA.In the subgroup analyses,such a relation was only recorded among women(OR 1.22,95%CI 1.03-1.45),those aged<60 years(OR 1.22,95%CI 1.05-1.42),and those without hypertension and without diabetes(OR 1.22,95%CI 1.06-1.41).Although the dose-response relation was not observed in men,the high level of SUA was related to kidney function decline(OR 1.83,95%CI 1.05-3.17).The restricted cubic spline analysis indicated that SUA>5 mg/dL was associated with a significantly higher risk of kidney function decline.Conclusion The SUA level was associated with kidney function decline.An elevation of SUA should therefore be addressed to prevent possible kidney impairment and dysfunction.
基金supported by the National Natural Science Foundation of China(91959205 to L.S.,U22A20327 to L.S.,82203881 to Y.C.,82272627 to XT.Z.,7232018 to Y.S.,12090022 to B.D.,11831002 to B.D.,81801778 to L.Z.)Beijing Natural Science Foundation(7222021 to Y.C.,Z200015 to XT.Z.)+1 种基金Beijing Hospitals Authority Youth Programme(QML20231115 to Y.C.)Clinical Medicine Plus X-Young Scholars Project of Peking University(PKU2023LCXQ041 to Y.C.and L.Z.).
文摘The sole use of single modality data often fails to capture the complex heterogeneity among patients,including the variability in resistance to anti-HER2 therapy and outcomes of combined treatment regimens,for the treatment of HER2-positive gastric cancer(GC).This modality deficit has not been fully considered in many studies.Furthermore,the application of artificial intelligence in predicting the treatment response,particularly in complex diseases such as GC,is still in its infancy.Therefore,this study aimed to use a comprehensive analytic approach to accurately predict treatment responses to anti-HER2 therapy or anti-HER2 combined immunotherapy in patients with HER2-positive GC.We collected multi-modal data,comprising radiology,pathology,and clinical information from a cohort of 429 patients:310 treated with anti-HER2 therapy and 119 treated with a combination of anti-HER2 and anti-PD-1/PD-L1 inhibitors immunotherapy.We introduced a deep learning model,called the Multi-Modal model(MuMo),that integrates these data to make precise treatment response predictions.MuMo achieved an area under the curve score of 0.821 for anti-HER2 therapy and 0.914 for combined immunotherapy.Moreover,patients classified as low-risk by MuMo exhibited significantly prolonged progression-free survival and overall survival(log-rank test,P<0.05).These findings not only highlight the significance of multi-modal data analysis in enhancing treatment evaluation and personalized medicine for HER2-positive gastric cancer,but also the potential and clinical value of our model.
基金Supported by the National Key Research and Development Program of China(Grant No.2021YFA1003500)the NSFC(Grant Nos.U21A20426,11971427,12071426 and 11901518)。
文摘In this paper,we study compressed data separation(CDS)problem,i.e.,sparse data separation from a few linear random measurements.We propose the nonconvex ℓ_(q)-split analysis with ℓ_(∞)-constraint and 0<q≤1.We call the algorithm ℓ_(q)-split-analysis Dantzig selector(ℓ_(q)-split-analysis DS).We show that the two distinct subcomponents that are approximately sparse in terms of two different dictionaries could be stably approximated via the ℓ_(q)-split-analysis DS,provided that the measurement matrix satisfies either a classical D-RIP(Restricted Isometry Property with respect to Dictionaries and ℓ_(2) norm)or a relatively new(D,q)-RIP(RIP with respect to Dictionaries and ℓ_(q)-quasi norm)condition and the two different dictionaries satisfy a mutual coherence condition between them.For the Gaussian random measurements,the measurement number needed for the(D,q)-RIP condition is far less than those needed for the D-RIP condition and the(D,1)-RIP condition when q is small enough.
基金supported by the National Natural Science Foundation of China(U22A20327,12090022,11831002,81801778,and 82203881)Beijing Natural Science Foundation(7222021)+1 种基金Beijing Hospitals Authority Youth Programme(QML20231115)Clinical Medicine Plus X-Young Scholars Project of Peking University(PKU2023LCXQ041).
文摘The healthcare industry faces core challenges,including increasingly complex operational processes and entities,the rapid development of medical knowledge,and the rising demand for interdisciplinary expertise.The complexity of medical processes is evident in every aspect,from patient appointments,diagnoses,and treatments to follow-up tasks,all of which involve intricate data processing and decision-making procedures.
基金supported by the National Natural Science Foundation of China(Grants Nos.12174338 and 11874321)
文摘.Holographic imaging poses significant challenges when facing real-time disturbances introduced by dynamic environments.The existing deep-learning methods for holographic imaging often depend solely on the specific condition based on the given data distributions,thus hindering their generalization across multiple scenes.One critical problem is how to guarantee the alignment between any given downstream tasks and pretrained models.We analyze the physical mechanism of image degradation caused by turbulence and innovatively propose a swin transformer-based method,termed train-with-coherence-swin(TWC-Swin)transformer,which uses spatial coherence(SC)as an adaptable physical prior information to precisely align image restoration tasks in the arbitrary turbulent scene.The light-processing system(LPR)we designed enables manipulation of SC and simulation of any turbulence.Qualitative and quantitative evaluations demonstrate that the TWC-Swin method presents superiority over traditional convolution frameworks and realizes image restoration under various turbulences,which suggests its robustness,powerful generalization capabilities,and adaptability to unknown environments.Our research reveals the significance of physical prior information in the optical intersection and provides an effective solution for model-to-tasks alignment schemes,which will help to unlock the full potential of deep learning for all-weather optical imaging across terrestrial,marine,and aerial domains.
基金the National Natural Science Foundation of China(Grant No.61772036)the Key Laboratory of Science,Technology and Standard in Press Industry(Key Laboratory of Intelligent Press Media Technology)。
文摘In recent years,deep neural network has achieved great success in solving many natural language processing tasks.Particularly,substantial progress has been made on neural text generation,which takes the linguistic and non-linguistic input,and generates natural language text.This survey aims to provide an up-to-date synthesis of core tasks in neural text generation and the architectures adopted to handle these tasks,and draw attention to the challenges in neural text generation.We first outline the mainstream neural text generation frameworks,and then introduce datasets,advanced models and challenges of four core text generation tasks in detail,including AMR-to-text generation,data-to-text generation,and two text-to-text generation tasks(i.e.,text summarization and paraphrase generation).Finally,we present future research directions for neural text generation.This survey can be used as a guide and reference for researchers and practitioners in this area.
基金supported in part by the National Key R&D Program of China(No.2020AAA0106600)the Key Laboratory of Science,Technology and Standard in Press Industry(Key Laboratory of Intelligent Press Media Technology)
文摘Entity Linking(EL)aims to automatically link the mentions in unstructured documents to corresponding entities in a knowledge base(KB),which has recently been dominated by global models.Although many global EL methods attempt to model the topical coherence among all linked entities,most of them failed in exploiting the correlations among manifold knowledge helpful for linking,such as the semantics of mentions and their candidates,the neighborhood information of candidate entities in KB and the fine-grained type information of entities.As we will show in the paper,interactions among these types of information are very useful for better characterizing the topic features of entities and more accurately estimating the topical coherence among all the referred entities within the same document.In this paper,we present a novel HEterogeneous Graph-based Entity Linker(HEGEL)for global entity linking,which builds an informative heterogeneous graph for every document to collect various linking clues.Then HEGEL utilizes a novel heterogeneous graph neural network(HGNN)to integrate the different types of manifold information and model the interactions among them.Experiments on the standard benchmark datasets demonstrate that HEGEL can well capture the global coherence and outperforms the prior state-of-the-art EL methods.
基金This work is supported by the National Natural Science Foundation of China Nos.11971215,11871210,and 11971214the Key Laboratory of Applied Mathematics and Complex Systems of Lanzhou University.
文摘Multivariate time series segmentation is an important problem in data mining and it has arisen in more and more practical applications in recent years.The task of time series segmentation is to partition a time series into segments by detecting the abrupt changes or anomalies in the time series.Multivariate time series segmentation can provide meaningful information for further data analysis,prediction and policy decision.A time series can be considered as a piecewise continuous function,it is natural to take its total variation norm as a prior information of this time series.In this paper,by minimizing the negative log-likelihood function of a time series,we propose a total variation based model for multivariate time series segmentation.An iterative process is applied to solve the proposed model and a search combined the dynamic programming method is designed to determine the breakpoints.The experimental results show that the proposed method is efficient for multivariate time series segmentation and it is competitive to the existing methods for multivariate time series segmentation.
基金supported by the Nat-ural Science Foundation of Jiangsu Province(No.BK20211210)the Fundamental Research Funds for the Central Universities(KYCXJC2022005)+1 种基金the startup award of new professors at Nanjing Agricultural University(No.106/804001)supported by the Natural Science Foundation of Zhejiang province(No.LY20F020003).
文摘Deep learning has been widely used for plant disease recognition in smart agriculture and has proven to be a powerful tool for image classification and pattern recognition.However,it has limited interpretability for deep features.With the transfer of expert knowledge,handcrafted features provide a new way for personalized diagnosis of plant diseases.However,irrelevant and redundant features lead to high dimensionality.In this study,we proposed a swarm intelligence algorithm for feature selection[salp swarm algorithm for feature selection(SSAFS)]in image-based plant disease detection.SSAFS is employed to determine the ideal combination of handcrafted features to maximize classification success while minimizing the number of features.To verify the effectiveness of the developed SSAFS algorithm,we conducted experimental studies using SSAFS and 5 metaheuristic algorithms.Several evaluation metrics were used to evaluate and analyze the performance of these methods on 4 datasets from the UCI machine learning repository and 6 plant phenomics datasets from PlantVillage.Experimental results and statistical analyses validated the outstanding performance of SSAFS compared to existing state-of-the-art algorithms,confirming the superiority of SSAFS in exploring the feature space and identifying the most valuable features for diseased plant image classification.This computational tool will allow us to explore an optimal combination of handcrafted features to improve plant disease recognition accuracy and processing time.
基金supported by the National Natural Science Foundation of China(91959205,U22A20327,82203881,12090022,11831002,and 81801778)Beijing Natural Science Foundation(7222021)+2 种基金Beijing Hospitals Authority Youth Programme(QML20231115)Clinical Medicine Plus X-Young Scholars Project of Peking University(PKU2023LCXQ041)Guangdong Provincial Key Laboratory of Precision Medicine for Gastrointestinal Cancer(2020B121201004).
文摘With the rapid development of artificial intelligence,large language models(LLMs)have shown promising capabilities in mimicking human-level language comprehen-sion and reasoning.This has sparked significant interest in applying LLMs to enhance various aspects of healthcare,ranging from medical education to clinical decision support.However,medicine involves multifaceted data modalities and nuanced reasoning skills,presenting challenges for integrating LLMs.This review introduces the fundamental applications of general-purpose and specialized LLMs,demon-strating their utilities in knowledge retrieval,research support,clinical workflow automation,and diagnostic assistance.Recognizing the inherent multimodality of medicine,the review emphasizes the multimodal LLMs and discusses their ability to process diverse data types like medical imaging and electronic health records to augment diagnostic accuracy.To address LLMs'limitations regarding personalization and complex clinical reasoning,the review further explores the emerging develop-ment of LLM-powered autonomous agents for healthcare.Moreover,it summarizes the evaluation methodologies for assessing LLMs'reliability and safety in medical contexts.LLMs have transformative potential in medicine;however,there is a pivotal need for continuous optimizations and ethical oversight before these models can be effectively integrated into clinical practice.
