Fault diagnosis(FD)is essential for ensuring the reliable operation of chillers and preventing energy waste.Feature selection(FS)is a critical prerequisite for effective FD.However,current FS methods have two major ga...Fault diagnosis(FD)is essential for ensuring the reliable operation of chillers and preventing energy waste.Feature selection(FS)is a critical prerequisite for effective FD.However,current FS methods have two major gaps.First,most approaches rely on single-source ranking information(SSRI)to evaluate features individually,which results in non-robust outcomes across different models and datasets due to the one-sided nature of SSRI.Second,thermodynamic mechanism features are often overlooked,leading to incomplete initial feature libraries,making it challenging to select optimal features and achieve better diagnostic performance.To address these issues,a robust ensemble FS method based on multi-source ranking information(MSRI)is proposed.By employing an efficient strategy based on maximizing relevance while proper redundancy,the MSRI method fully leverages Mutual Information,Information Gain,Gain Ratio,Gini index,Chi-squared,and Relief-F from both qualitative and quantitative perspectives.Additionally,comprehensive consideration of thermodynamic mechanism features ensures a complete initial feature library.From a methodological standpoint,a general framework for constructing the MSRI-based FS method is provided.The proposed method is applied to chiller FD and tested across ten widely-used machine learning models.Thirteen optimized features are selected from the original set of forty-two,achieving an average diagnostic accuracy of 98.40%and an average F-measure above 94.94%,demonstrating the effectiveness and generalizability of the MSRI method.Compared to the SSRI approach,the MSRI method shows superior robustness,with the standard deviation of diagnostic accuracy reduced by 0.03 to 0.07 and an improvement in diagnostic accuracy ranging from 2.53%to 6.12%.Moreover,the MSRI method reduced computation time by 98.62%compared to wrapper methods,without sacrificing accuracy.展开更多
Due to the development of cloud computing and machine learning,users can upload their data to the cloud for machine learning model training.However,dishonest clouds may infer user data,resulting in user data leakage.P...Due to the development of cloud computing and machine learning,users can upload their data to the cloud for machine learning model training.However,dishonest clouds may infer user data,resulting in user data leakage.Previous schemes have achieved secure outsourced computing,but they suffer from low computational accuracy,difficult-to-handle heterogeneous distribution of data from multiple sources,and high computational cost,which result in extremely poor user experience and expensive cloud computing costs.To address the above problems,we propose amulti-precision,multi-sourced,andmulti-key outsourcing neural network training scheme.Firstly,we design a multi-precision functional encryption computation based on Euclidean division.Second,we design the outsourcing model training algorithm based on a multi-precision functional encryption with multi-sourced heterogeneity.Finally,we conduct experiments on three datasets.The results indicate that our framework achieves an accuracy improvement of 6%to 30%.Additionally,it offers a memory space optimization of 1.0×2^(24) times compared to the previous best approach.展开更多
Rock mass quality serves as a vital index for predicting the stability and safety status of rock tunnel faces.In tunneling practice,the rock mass quality is often assessed via a combination of qualitative and quantita...Rock mass quality serves as a vital index for predicting the stability and safety status of rock tunnel faces.In tunneling practice,the rock mass quality is often assessed via a combination of qualitative and quantitative parameters.However,due to the harsh on-site construction conditions,it is rather difficult to obtain some of the evaluation parameters which are essential for the rock mass quality prediction.In this study,a novel improved Swin Transformer is proposed to detect,segment,and quantify rock mass characteristic parameters such as water leakage,fractures,weak interlayers.The site experiment results demonstrate that the improved Swin Transformer achieves optimal segmentation results and achieving accuracies of 92%,81%,and 86%for water leakage,fractures,and weak interlayers,respectively.A multisource rock tunnel face characteristic(RTFC)dataset includes 11 parameters for predicting rock mass quality is established.Considering the limitations in predictive performance of incomplete evaluation parameters exist in this dataset,a novel tree-augmented naive Bayesian network(BN)is proposed to address the challenge of the incomplete dataset and achieved a prediction accuracy of 88%.In comparison with other commonly used Machine Learning models the proposed BN-based approach proved an improved performance on predicting the rock mass quality with the incomplete dataset.By utilizing the established BN,a further sensitivity analysis is conducted to quantitatively evaluate the importance of the various parameters,results indicate that the rock strength and fractures parameter exert the most significant influence on rock mass quality.展开更多
When employing penetration ammunition to strike multi-story buildings,the detection methods using acceleration sensors suffer from signal aliasing,while magnetic detection methods are susceptible to interference from ...When employing penetration ammunition to strike multi-story buildings,the detection methods using acceleration sensors suffer from signal aliasing,while magnetic detection methods are susceptible to interference from ferromagnetic materials,thereby posing challenges in accurately determining the number of layers.To address this issue,this research proposes a layer counting method for penetration fuze that incorporates multi-source information fusion,utilizing both the temporal convolutional network(TCN)and the long short-term memory(LSTM)recurrent network.By leveraging the strengths of these two network structures,the method extracts temporal and high-dimensional features from the multi-source physical field during the penetration process,establishing a relationship between the multi-source physical field and the distance between the fuze and the target plate.A simulation model is developed to simulate the overload and magnetic field of a projectile penetrating multiple layers of target plates,capturing the multi-source physical field signals and their patterns during the penetration process.The analysis reveals that the proposed multi-source fusion layer counting method reduces errors by 60% and 50% compared to single overload layer counting and single magnetic anomaly signal layer counting,respectively.The model's predictive performance is evaluated under various operating conditions,including different ratios of added noise to random sample positions,penetration speeds,and spacing between target plates.The maximum errors in fuze penetration time predicted by the three modes are 0.08 ms,0.12 ms,and 0.16 ms,respectively,confirming the robustness of the proposed model.Moreover,the model's predictions indicate that the fitting degree for large interlayer spacings is superior to that for small interlayer spacings due to the influence of stress waves.展开更多
The power Internet of Things(IoT)is a significant trend in technology and a requirement for national strategic development.With the deepening digital transformation of the power grid,China’s power system has initiall...The power Internet of Things(IoT)is a significant trend in technology and a requirement for national strategic development.With the deepening digital transformation of the power grid,China’s power system has initially built a power IoT architecture comprising a perception,network,and platform application layer.However,owing to the structural complexity of the power system,the construction of the power IoT continues to face problems such as complex access management of massive heterogeneous equipment,diverse IoT protocol access methods,high concurrency of network communications,and weak data security protection.To address these issues,this study optimizes the existing architecture of the power IoT and designs an integrated management framework for the access of multi-source heterogeneous data in the power IoT,comprising cloud,pipe,edge,and terminal parts.It further reviews and analyzes the key technologies involved in the power IoT,such as the unified management of the physical model,high concurrent access,multi-protocol access,multi-source heterogeneous data storage management,and data security control,to provide a more flexible,efficient,secure,and easy-to-use solution for multi-source heterogeneous data access in the power IoT.展开更多
Long runout landslides involve a massive amount of energy and can be extremely hazardous owing to their long movement distance,high mobility and strong destructive power.Numerical methods have been widely used to pred...Long runout landslides involve a massive amount of energy and can be extremely hazardous owing to their long movement distance,high mobility and strong destructive power.Numerical methods have been widely used to predict the landslide runout but a fundamental problem remained is how to determine the reliable numerical parameters.This study proposes a framework to predict the runout of potential landslides through multi-source data collaboration and numerical analysis of historical landslide events.Specifically,for the historical landslide cases,the landslide-induced seismic signal,geophysical surveys,and possible in-situ drone/phone videos(multi-source data collaboration)can validate the numerical results in terms of landslide dynamics and deposit features and help calibrate the numerical(rheological)parameters.Subsequently,the calibrated numerical parameters can be used to numerically predict the runout of potential landslides in the region with a similar geological setting to the recorded events.Application of the runout prediction approach to the 2020 Jiashanying landslide in Guizhou,China gives reasonable results in comparison to the field observations.The numerical parameters are determined from the multi-source data collaboration analysis of a historical case in the region(2019 Shuicheng landslide).The proposed framework for landslide runout prediction can be of great utility for landslide risk assessment and disaster reduction in mountainous regions worldwide.展开更多
Effectively managing extensive,multi-source,and multi-level real-scene 3D models for responsive retrieval scheduling and rapid visualization in the Web environment is a significant challenge in the current development...Effectively managing extensive,multi-source,and multi-level real-scene 3D models for responsive retrieval scheduling and rapid visualization in the Web environment is a significant challenge in the current development of real-scene 3D applications in China.In this paper,we address this challenge by reorganizing spatial and temporal information into a 3D geospatial grid.It introduces the Global 3D Geocoding System(G_(3)DGS),leveraging neighborhood similarity and uniqueness for efficient storage,retrieval,updating,and scheduling of these models.A combination of G_(3)DGS and non-relational databases is implemented,enhancing data storage scalability and flexibility.Additionally,a model detail management scheduling strategy(TLOD)based on G_(3)DGS and an importance factor T is designed.Compared with mainstream commercial and open-source platforms,this method significantly enhances the loadable capacity of massive multi-source real-scene 3D models in the Web environment by 33%,improves browsing efficiency by 48%,and accelerates invocation speed by 40%.展开更多
Dempster-Shafer evidence theory is broadly employed in the research of multi-source information fusion.Nevertheless,when fusing highly conflicting evidence it may pro-duce counterintuitive outcomes.To address this iss...Dempster-Shafer evidence theory is broadly employed in the research of multi-source information fusion.Nevertheless,when fusing highly conflicting evidence it may pro-duce counterintuitive outcomes.To address this issue,a fusion approach based on a newly defined belief exponential diver-gence and Deng entropy is proposed.First,a belief exponential divergence is proposed as the conflict measurement between evidences.Then,the credibility of each evidence is calculated.Afterwards,the Deng entropy is used to calculate information volume to determine the uncertainty of evidence.Then,the weight of evidence is calculated by integrating the credibility and uncertainty of each evidence.Ultimately,initial evidences are amended and fused using Dempster’s rule of combination.The effectiveness of this approach in addressing the fusion of three typical conflict paradoxes is demonstrated by arithmetic exam-ples.Additionally,the proposed approach is applied to aerial tar-get recognition and iris dataset-based classification to validate its efficacy.Results indicate that the proposed approach can enhance the accuracy of target recognition and effectively address the issue of fusing conflicting evidences.展开更多
The rapid development of short video platforms poses new challenges for traditional recommendation systems.Recommender systems typically depend on two types of user behavior feedback to construct user interest profile...The rapid development of short video platforms poses new challenges for traditional recommendation systems.Recommender systems typically depend on two types of user behavior feedback to construct user interest profiles:explicit feedback(interactive behavior),which significantly influences users’short-term interests,and implicit feedback(viewing time),which substantially affects their long-term interests.However,the previous model fails to distinguish between these two feedback methods,leading it to predict only the overall preferences of users based on extensive historical behavior sequences.Consequently,it cannot differentiate between users’long-term and shortterm interests,resulting in low accuracy in describing users’interest states and predicting the evolution of their interests.This paper introduces a video recommendationmodel calledCAT-MFRec(CrossAttention Transformer-Mixed Feedback Recommendation)designed to differentiate between explicit and implicit user feedback within the DIEN(Deep Interest Evolution Network)framework.This study emphasizes the separate learning of the two types of behavioral feedback,effectively integrating them through the cross-attention mechanism.Additionally,it leverages the long sequence dependence capabilities of Transformer technology to accurately construct user interest profiles and predict the evolution of user interests.Experimental results indicate that CAT-MF Rec significantly outperforms existing recommendation methods across various performance indicators.This advancement offers new theoretical and practical insights for the development of video recommendations,particularly in addressing complex and dynamic user behavior patterns.展开更多
The good estimation consistency of Invariant Extended Kalman Filter(InEKF)is mainly attributed to its excellent trajectory-independent property.However,when the InEKF is applied to multi-source inertial-based navigati...The good estimation consistency of Invariant Extended Kalman Filter(InEKF)is mainly attributed to its excellent trajectory-independent property.However,when the InEKF is applied to multi-source inertial-based navigation that coexists left-invariant and right-invariant observations,the observation matrix would be unavoidably trajectory-dependent and might lead to the degradation of estimation performance.This paper for the first time performs theoretical analyses on the covariance switch between the left error and the right error in multi-source inertial-based navigation.Furthermore,detailed realizations of the covariance switch-based InEKF are formulated in this work,which are lacked in previous works.Numerical simulations and experiments demonstrate that the covariance switch significantly reduces the attitude errors during the transient phase in contrast with the original method using the incompatible error definition.展开更多
Accurately and efficiently predicting the permeability of porous media is essential for addressing a wide range of hydrogeological issues.However,the complexity of porous media often limits the effectiveness of indivi...Accurately and efficiently predicting the permeability of porous media is essential for addressing a wide range of hydrogeological issues.However,the complexity of porous media often limits the effectiveness of individual prediction methods.This study introduces a novel Particle Swarm Optimization-based Permeability Integrated Prediction model(PSO-PIP),which incorporates a particle swarm optimization algorithm enhanced with dy-namic clustering and adaptive parameter tuning(KGPSO).The model integrates multi-source data from the Lattice Boltzmann Method(LBM),Pore Network Modeling(PNM),and Finite Difference Method(FDM).By assigning optimal weight coefficients to the outputs of these methods,the model minimizes deviations from actual values and enhances permeability prediction performance.Initially,the computational performances of the LBM,PNM,and FDM are comparatively analyzed on datasets consisting of sphere packings and real rock samples.It is observed that these methods exhibit computational biases in certain permeability ranges.The PSOPIP model is proposed to combine the strengths of each computational approach and mitigate their limitations.The PSO-PIP model consistently produces predictions that are highly congruent with actual permeability values across all prediction intervals,significantly enhancing prediction accuracy.The outcomes of this study provide a new tool and perspective for the comprehensive,rapid,and accurate prediction of permeability in porous media.展开更多
Airway management plays a crucial role in providing adequate oxygenation and ventilation to patients during various medical procedures and emergencies.When patients have a limited mouth opening due to factors such as ...Airway management plays a crucial role in providing adequate oxygenation and ventilation to patients during various medical procedures and emergencies.When patients have a limited mouth opening due to factors such as trauma,inflammation,or anatomical abnormalities airway management becomes challenging.A commonly utilized method to overcome this challenge is the use of video laryngoscopy(VL),which employs a specialized device equipped with a camera and a light source to allow a clear view of the larynx and vocal cords.VL overcomes the limitations of direct laryngoscopy in patients with limited mouth opening,enabling better visualization and successful intubation.Various types of VL blades are available.We devised a novel flangeless video laryngoscope for use in patients with a limited mouth opening and then tested it on a manikin.展开更多
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
Objective: The purpose of this study was to evaluate health education using videos and leaflets for preconception care (PCC) awareness among adolescent females up to six months after the health education. Methods: The...Objective: The purpose of this study was to evaluate health education using videos and leaflets for preconception care (PCC) awareness among adolescent females up to six months after the health education. Methods: The subjects were female university students living in the Kinki area. A longitudinal survey was conducted on 67 members in the intervention group, who received the health education, and 52 members in the control group, who did not receive the health education. The primary outcome measures were knowledge of PCC and the subscales of the Health Promotion Lifestyle Profile. Surveys were conducted before, after, and six months after the intervention in the intervention group, and an initial survey and survey six months later were conducted in the control group. Cochran’s Q test, Bonferroni’s multiple comparison test, and McNemar’s test were used to analyze the knowledge of PCC data. The Health Awareness, Nutrition, and Stress Management subscales of the Health Promotion Lifestyle Profile were analyzed by paired t-test, and comparisons between the intervention and control groups were performed using the two-way repeated measures analysis of variance. Results: In the intervention group of 67 people, the number of subjects who answered “correct” for five of the nine items concerning knowledge of PCC increased immediately after the health education (P = 0.006) but decreased for five items from immediately after the health education to six months later (P = 0.043). In addition, the number of respondents who answered “correct” for “low birth weight infants and future lifestyle-related diseases” (P = 0.016) increased after six months compared with before the health education. For the 52 subjects in the control group, there was no change in the number of subjects who answered “correct” for eight out of the nine items after six months. There was also no increase in scores for the Health Promotion Lifestyle Profile after six months for either the intervention or control group. Conclusion: Providing health education about PCC using videos and leaflets to adolescent females was shown to enhance the knowledge of PCC immediately after the education.展开更多
Objectives:Short video addiction has emerged as a significant public health issue in recent years,with a growing trend toward severity.However,research on the causes and impacts of short video addiction remains limite...Objectives:Short video addiction has emerged as a significant public health issue in recent years,with a growing trend toward severity.However,research on the causes and impacts of short video addiction remains limited,and understanding of the variable“TikTok brain”is still in its infancy.Therefore,based on the Stimulus-Organism-Behavior-Consequence(SOBC)framework,we proposed six research hypotheses and constructed a model to explore the relationships between short video usage intensity,TikTok brain,short video addiction,and decreased attention control.Methods:Given that students are considered a high-risk group for excessive short video use,we collected 1086 valid participants from Chinese student users,including 609 males(56.1%)and 477 females(43.9%),with an average participant age of 19.84 years,to test the hypotheses.Results:(1)Short video usage intensity was positively related to short video addiction,TikTok brain,and decreased attention control;(2)TikTok brain was positively related to short video addiction and decreased attention control;and(3)Short video addiction was positively related to decreased attention control.Conclusions:These findings suggest that although excessive use of short video applications brings negative consequences,users still spend significant amounts of time on these platforms,indicating a need for strict self-regulation of usage time.展开更多
Video classification is an important task in video understanding and plays a pivotal role in intelligent monitoring of information content.Most existing methods do not consider the multimodal nature of the video,and t...Video classification is an important task in video understanding and plays a pivotal role in intelligent monitoring of information content.Most existing methods do not consider the multimodal nature of the video,and the modality fusion approach tends to be too simple,often neglecting modality alignment before fusion.This research introduces a novel dual stream multimodal alignment and fusion network named DMAFNet for classifying short videos.The network uses two unimodal encoder modules to extract features within modalities and exploits a multimodal encoder module to learn interaction between modalities.To solve the modality alignment problem,contrastive learning is introduced between two unimodal encoder modules.Additionally,masked language modeling(MLM)and video text matching(VTM)auxiliary tasks are introduced to improve the interaction between video frames and text modalities through backpropagation of loss functions.Diverse experiments prove the efficiency of DMAFNet in multimodal video classification tasks.Compared with other two mainstream baselines,DMAFNet achieves the best results on the 2022 WeChat Big Data Challenge dataset.展开更多
Dance video is an innovative form that integrates dance art with imaging technology,enriching the expression of dance through techniques such as photography,videography,and special effects.This paper explores the defi...Dance video is an innovative form that integrates dance art with imaging technology,enriching the expression of dance through techniques such as photography,videography,and special effects.This paper explores the definition,current development,artistic expression,social impact,and future trends of dance video.Through narrative construction,visual impact,emotional resonance,technological innovation,and cultural expression,dance video enhances the narrative and visual appeal of dance.In the future,dance video will focus more on the integration of virtual reality(VR)and augmented reality(AR)technologies.However,it also faces challenges such as rapid technological updates,maintaining artistic originality,and balancing commercial interests.展开更多
It has been over a decade since the first coded aperture video compressive sensing(CS)system was reported.The underlying principle of this technology is to employ a high-frequency modulator in the optical path to modu...It has been over a decade since the first coded aperture video compressive sensing(CS)system was reported.The underlying principle of this technology is to employ a high-frequency modulator in the optical path to modulate a recorded high-speed scene within one integration time.The superimposed image captured in this manner is modulated and compressed,since multiple modulation patterns are imposed.Following this,reconstruction algorithms are utilized to recover the desired high-speed scene.One leading advantage of video CS is that a single captured measurement can be used to reconstruct a multi-frame video,thereby enabling a low-speed camera to capture high-speed scenes.Inspired by this,a number of variants of video CS systems have been built,mainly using different modulation devices.Meanwhile,in order to obtain high-quality reconstruction videos,many algorithms have been developed,from optimization-based iterative algorithms to deep-learning-based ones.Recently,emerging deep learning methods have been dominant due to their high-speed inference and high-quality reconstruction,highlighting the possibility of deploying video CS in practical applications.Toward this end,this paper reviews the progress that has been achieved in video CS during the past decade.We further analyze the efforts that need to be made—in terms of both hardware and algorithms—to enable real applications.Research gaps are put forward and future directions are summarized to help researchers and engineers working on this topic.展开更多
Personal video recorders (PVRs) have altered the way users consume television (TV) content by allowing users to record programs and watch them at their convenience, overcoming the constraints of live broadcasting. How...Personal video recorders (PVRs) have altered the way users consume television (TV) content by allowing users to record programs and watch them at their convenience, overcoming the constraints of live broadcasting. However, standalone PVRs are limited by their individual storage capacities, restricting the number of programs they can store. While online catch-up TV services such as Hulu and Netflix mitigate this limitation by offering on-demand access to broadcast programs shortly after their initial broadcast, they require substantial storage and network resources, leading to significant infrastructural costs for service providers. To address these challenges, we propose a collaborative TV content recording system that leverages distributed PVRs, combining their storage into a virtual shared pool without additional costs. Our system aims to support all concurrent playback requests without service interruption while ensuring program availability comparable to that of local devices. The main contributions of our proposed system are fourfold. First, by sharing storage and upload bandwidth among PVRs, our system significantly expands the overall recording capacity and enables simultaneous recording of multiple programs without the physical constraints of standalone devices. Second, by utilizing erasure coding efficiently, our system reduces the storage space required for each program, allowing more programs to be recorded compared to traditional replication. Third, we propose an adaptive redundancy scheme to control the degree of redundancy of each program based on its evolving playback demand, ensuring high-quality playback by providing sufficient bandwidth for popular programs. Finally, we introduce a contribution-based incentive policy that encourages PVRs to actively participate by contributing resources, while discouraging excessive consumption of the combined storage pool. Through extensive experiments, we demonstrate the effectiveness of our proposed collaborative TV program recording system in terms of storage efficiency and performance.展开更多
Video camouflaged object detection(VCOD)has become a fundamental task in computer vision that has attracted significant attention in recent years.Unlike image camouflaged object detection(ICOD),VCOD not only requires ...Video camouflaged object detection(VCOD)has become a fundamental task in computer vision that has attracted significant attention in recent years.Unlike image camouflaged object detection(ICOD),VCOD not only requires spatial cues but also needs motion cues.Thus,effectively utilizing spatiotemporal information is crucial for generating accurate segmentation results.Current VCOD methods,which typically focus on exploring motion representation,often ineffectively integrate spatial and motion features,leading to poor performance in diverse scenarios.To address these issues,we design a novel spatiotemporal network with an encoder-decoder structure.During the encoding stage,an adjacent space-time memory module(ASTM)is employed to extract high-level temporal features(i.e.,motion cues)from the current frame and its adjacent frames.In the decoding stage,a selective space-time aggregation module is introduced to efficiently integrate spatial and temporal features.Additionally,a multi-feature fusion module is developed to progressively refine the rough prediction by utilizing the information provided by multiple types of features.Furthermore,we incorporate multi-task learning into the proposed network to obtain more accurate predictions.Experimental results show that the proposed method outperforms existing cutting-edge baselines on VCOD benchmarks.展开更多
基金the National Natural Science Foundation of China(No.52478087)China Postdoctoral Science Foundation(No.2024M750799,No.2024T170238)+4 种基金China Scholarship Council(No.202308410494)Zhongyuan Outstanding Youth Talent Program(No.2022 Year)Youth Scientist Project in Henan Province(No.225200810087)the Program for Science&Technology Innovation Talents in Universities of Henan Province(No.22HASTIT025)the Program for Innovative Research Team(in Science and Technology)in University of Henan Province(No.22IRTSTHN006).
文摘Fault diagnosis(FD)is essential for ensuring the reliable operation of chillers and preventing energy waste.Feature selection(FS)is a critical prerequisite for effective FD.However,current FS methods have two major gaps.First,most approaches rely on single-source ranking information(SSRI)to evaluate features individually,which results in non-robust outcomes across different models and datasets due to the one-sided nature of SSRI.Second,thermodynamic mechanism features are often overlooked,leading to incomplete initial feature libraries,making it challenging to select optimal features and achieve better diagnostic performance.To address these issues,a robust ensemble FS method based on multi-source ranking information(MSRI)is proposed.By employing an efficient strategy based on maximizing relevance while proper redundancy,the MSRI method fully leverages Mutual Information,Information Gain,Gain Ratio,Gini index,Chi-squared,and Relief-F from both qualitative and quantitative perspectives.Additionally,comprehensive consideration of thermodynamic mechanism features ensures a complete initial feature library.From a methodological standpoint,a general framework for constructing the MSRI-based FS method is provided.The proposed method is applied to chiller FD and tested across ten widely-used machine learning models.Thirteen optimized features are selected from the original set of forty-two,achieving an average diagnostic accuracy of 98.40%and an average F-measure above 94.94%,demonstrating the effectiveness and generalizability of the MSRI method.Compared to the SSRI approach,the MSRI method shows superior robustness,with the standard deviation of diagnostic accuracy reduced by 0.03 to 0.07 and an improvement in diagnostic accuracy ranging from 2.53%to 6.12%.Moreover,the MSRI method reduced computation time by 98.62%compared to wrapper methods,without sacrificing accuracy.
基金supported by Natural Science Foundation of China(Nos.62303126,62362008,author Z.Z,https://www.nsfc.gov.cn/,accessed on 20 December 2024)Major Scientific and Technological Special Project of Guizhou Province([2024]014)+2 种基金Guizhou Provincial Science and Technology Projects(No.ZK[2022]General149) ,author Z.Z,https://kjt.guizhou.gov.cn/,accessed on 20 December 2024)The Open Project of the Key Laboratory of Computing Power Network and Information Security,Ministry of Education under Grant 2023ZD037,author Z.Z,https://www.gzu.edu.cn/,accessed on 20 December 2024)Open Research Project of the State Key Laboratory of Industrial Control Technology,Zhejiang University,China(No.ICT2024B25),author Z.Z,https://www.gzu.edu.cn/,accessed on 20 December 2024).
文摘Due to the development of cloud computing and machine learning,users can upload their data to the cloud for machine learning model training.However,dishonest clouds may infer user data,resulting in user data leakage.Previous schemes have achieved secure outsourced computing,but they suffer from low computational accuracy,difficult-to-handle heterogeneous distribution of data from multiple sources,and high computational cost,which result in extremely poor user experience and expensive cloud computing costs.To address the above problems,we propose amulti-precision,multi-sourced,andmulti-key outsourcing neural network training scheme.Firstly,we design a multi-precision functional encryption computation based on Euclidean division.Second,we design the outsourcing model training algorithm based on a multi-precision functional encryption with multi-sourced heterogeneity.Finally,we conduct experiments on three datasets.The results indicate that our framework achieves an accuracy improvement of 6%to 30%.Additionally,it offers a memory space optimization of 1.0×2^(24) times compared to the previous best approach.
基金supported by the National Natural Science Foundation of China(Nos.52279107 and 52379106)the Qingdao Guoxin Jiaozhou Bay Second Submarine Tunnel Co.,Ltd.,the Academician and Expert Workstation of Yunnan Province(No.202205AF150015)the Science and Technology Innovation Project of YCIC Group Co.,Ltd.(No.YCIC-YF-2022-15)。
文摘Rock mass quality serves as a vital index for predicting the stability and safety status of rock tunnel faces.In tunneling practice,the rock mass quality is often assessed via a combination of qualitative and quantitative parameters.However,due to the harsh on-site construction conditions,it is rather difficult to obtain some of the evaluation parameters which are essential for the rock mass quality prediction.In this study,a novel improved Swin Transformer is proposed to detect,segment,and quantify rock mass characteristic parameters such as water leakage,fractures,weak interlayers.The site experiment results demonstrate that the improved Swin Transformer achieves optimal segmentation results and achieving accuracies of 92%,81%,and 86%for water leakage,fractures,and weak interlayers,respectively.A multisource rock tunnel face characteristic(RTFC)dataset includes 11 parameters for predicting rock mass quality is established.Considering the limitations in predictive performance of incomplete evaluation parameters exist in this dataset,a novel tree-augmented naive Bayesian network(BN)is proposed to address the challenge of the incomplete dataset and achieved a prediction accuracy of 88%.In comparison with other commonly used Machine Learning models the proposed BN-based approach proved an improved performance on predicting the rock mass quality with the incomplete dataset.By utilizing the established BN,a further sensitivity analysis is conducted to quantitatively evaluate the importance of the various parameters,results indicate that the rock strength and fractures parameter exert the most significant influence on rock mass quality.
文摘When employing penetration ammunition to strike multi-story buildings,the detection methods using acceleration sensors suffer from signal aliasing,while magnetic detection methods are susceptible to interference from ferromagnetic materials,thereby posing challenges in accurately determining the number of layers.To address this issue,this research proposes a layer counting method for penetration fuze that incorporates multi-source information fusion,utilizing both the temporal convolutional network(TCN)and the long short-term memory(LSTM)recurrent network.By leveraging the strengths of these two network structures,the method extracts temporal and high-dimensional features from the multi-source physical field during the penetration process,establishing a relationship between the multi-source physical field and the distance between the fuze and the target plate.A simulation model is developed to simulate the overload and magnetic field of a projectile penetrating multiple layers of target plates,capturing the multi-source physical field signals and their patterns during the penetration process.The analysis reveals that the proposed multi-source fusion layer counting method reduces errors by 60% and 50% compared to single overload layer counting and single magnetic anomaly signal layer counting,respectively.The model's predictive performance is evaluated under various operating conditions,including different ratios of added noise to random sample positions,penetration speeds,and spacing between target plates.The maximum errors in fuze penetration time predicted by the three modes are 0.08 ms,0.12 ms,and 0.16 ms,respectively,confirming the robustness of the proposed model.Moreover,the model's predictions indicate that the fitting degree for large interlayer spacings is superior to that for small interlayer spacings due to the influence of stress waves.
基金supported by the National Key Research and Development Program of China(grant number 2019YFE0123600)。
文摘The power Internet of Things(IoT)is a significant trend in technology and a requirement for national strategic development.With the deepening digital transformation of the power grid,China’s power system has initially built a power IoT architecture comprising a perception,network,and platform application layer.However,owing to the structural complexity of the power system,the construction of the power IoT continues to face problems such as complex access management of massive heterogeneous equipment,diverse IoT protocol access methods,high concurrency of network communications,and weak data security protection.To address these issues,this study optimizes the existing architecture of the power IoT and designs an integrated management framework for the access of multi-source heterogeneous data in the power IoT,comprising cloud,pipe,edge,and terminal parts.It further reviews and analyzes the key technologies involved in the power IoT,such as the unified management of the physical model,high concurrent access,multi-protocol access,multi-source heterogeneous data storage management,and data security control,to provide a more flexible,efficient,secure,and easy-to-use solution for multi-source heterogeneous data access in the power IoT.
基金supported by the National Natural Science Foundation of China(41977215)。
文摘Long runout landslides involve a massive amount of energy and can be extremely hazardous owing to their long movement distance,high mobility and strong destructive power.Numerical methods have been widely used to predict the landslide runout but a fundamental problem remained is how to determine the reliable numerical parameters.This study proposes a framework to predict the runout of potential landslides through multi-source data collaboration and numerical analysis of historical landslide events.Specifically,for the historical landslide cases,the landslide-induced seismic signal,geophysical surveys,and possible in-situ drone/phone videos(multi-source data collaboration)can validate the numerical results in terms of landslide dynamics and deposit features and help calibrate the numerical(rheological)parameters.Subsequently,the calibrated numerical parameters can be used to numerically predict the runout of potential landslides in the region with a similar geological setting to the recorded events.Application of the runout prediction approach to the 2020 Jiashanying landslide in Guizhou,China gives reasonable results in comparison to the field observations.The numerical parameters are determined from the multi-source data collaboration analysis of a historical case in the region(2019 Shuicheng landslide).The proposed framework for landslide runout prediction can be of great utility for landslide risk assessment and disaster reduction in mountainous regions worldwide.
基金National Key Research and Development Program of China(No.2023YFB3907103).
文摘Effectively managing extensive,multi-source,and multi-level real-scene 3D models for responsive retrieval scheduling and rapid visualization in the Web environment is a significant challenge in the current development of real-scene 3D applications in China.In this paper,we address this challenge by reorganizing spatial and temporal information into a 3D geospatial grid.It introduces the Global 3D Geocoding System(G_(3)DGS),leveraging neighborhood similarity and uniqueness for efficient storage,retrieval,updating,and scheduling of these models.A combination of G_(3)DGS and non-relational databases is implemented,enhancing data storage scalability and flexibility.Additionally,a model detail management scheduling strategy(TLOD)based on G_(3)DGS and an importance factor T is designed.Compared with mainstream commercial and open-source platforms,this method significantly enhances the loadable capacity of massive multi-source real-scene 3D models in the Web environment by 33%,improves browsing efficiency by 48%,and accelerates invocation speed by 40%.
基金supported by the National Natural Science Foundation of China(61903305,62073267)the Fundamental Research Funds for the Central Universities(HXGJXM202214).
文摘Dempster-Shafer evidence theory is broadly employed in the research of multi-source information fusion.Nevertheless,when fusing highly conflicting evidence it may pro-duce counterintuitive outcomes.To address this issue,a fusion approach based on a newly defined belief exponential diver-gence and Deng entropy is proposed.First,a belief exponential divergence is proposed as the conflict measurement between evidences.Then,the credibility of each evidence is calculated.Afterwards,the Deng entropy is used to calculate information volume to determine the uncertainty of evidence.Then,the weight of evidence is calculated by integrating the credibility and uncertainty of each evidence.Ultimately,initial evidences are amended and fused using Dempster’s rule of combination.The effectiveness of this approach in addressing the fusion of three typical conflict paradoxes is demonstrated by arithmetic exam-ples.Additionally,the proposed approach is applied to aerial tar-get recognition and iris dataset-based classification to validate its efficacy.Results indicate that the proposed approach can enhance the accuracy of target recognition and effectively address the issue of fusing conflicting evidences.
基金supported by National Natural Science Foundation of China(62072416)Key Research and Development Special Project of Henan Province(221111210500)Key TechnologiesR&DProgram of Henan rovince(232102211053,242102211071).
文摘The rapid development of short video platforms poses new challenges for traditional recommendation systems.Recommender systems typically depend on two types of user behavior feedback to construct user interest profiles:explicit feedback(interactive behavior),which significantly influences users’short-term interests,and implicit feedback(viewing time),which substantially affects their long-term interests.However,the previous model fails to distinguish between these two feedback methods,leading it to predict only the overall preferences of users based on extensive historical behavior sequences.Consequently,it cannot differentiate between users’long-term and shortterm interests,resulting in low accuracy in describing users’interest states and predicting the evolution of their interests.This paper introduces a video recommendationmodel calledCAT-MFRec(CrossAttention Transformer-Mixed Feedback Recommendation)designed to differentiate between explicit and implicit user feedback within the DIEN(Deep Interest Evolution Network)framework.This study emphasizes the separate learning of the two types of behavioral feedback,effectively integrating them through the cross-attention mechanism.Additionally,it leverages the long sequence dependence capabilities of Transformer technology to accurately construct user interest profiles and predict the evolution of user interests.Experimental results indicate that CAT-MF Rec significantly outperforms existing recommendation methods across various performance indicators.This advancement offers new theoretical and practical insights for the development of video recommendations,particularly in addressing complex and dynamic user behavior patterns.
基金supported by National Key R&D Program(2022YFB3903802)National Natural Science Foundation(62303310,62273228)
文摘The good estimation consistency of Invariant Extended Kalman Filter(InEKF)is mainly attributed to its excellent trajectory-independent property.However,when the InEKF is applied to multi-source inertial-based navigation that coexists left-invariant and right-invariant observations,the observation matrix would be unavoidably trajectory-dependent and might lead to the degradation of estimation performance.This paper for the first time performs theoretical analyses on the covariance switch between the left error and the right error in multi-source inertial-based navigation.Furthermore,detailed realizations of the covariance switch-based InEKF are formulated in this work,which are lacked in previous works.Numerical simulations and experiments demonstrate that the covariance switch significantly reduces the attitude errors during the transient phase in contrast with the original method using the incompatible error definition.
基金supported by the National Key Research and Devel-opment Program of China (Grant No.2022YFC3005503)the National Natural Science Foundation of China (Grant Nos.52322907,52179141,U23B20149,U2340232)+1 种基金the Fundamental Research Funds for the Central Universities (Grant Nos.2042024kf1031,2042024kf0031)the Key Program of Science and Technology of Yunnan Province (Grant Nos.202202AF080004,202203AA080009).
文摘Accurately and efficiently predicting the permeability of porous media is essential for addressing a wide range of hydrogeological issues.However,the complexity of porous media often limits the effectiveness of individual prediction methods.This study introduces a novel Particle Swarm Optimization-based Permeability Integrated Prediction model(PSO-PIP),which incorporates a particle swarm optimization algorithm enhanced with dy-namic clustering and adaptive parameter tuning(KGPSO).The model integrates multi-source data from the Lattice Boltzmann Method(LBM),Pore Network Modeling(PNM),and Finite Difference Method(FDM).By assigning optimal weight coefficients to the outputs of these methods,the model minimizes deviations from actual values and enhances permeability prediction performance.Initially,the computational performances of the LBM,PNM,and FDM are comparatively analyzed on datasets consisting of sphere packings and real rock samples.It is observed that these methods exhibit computational biases in certain permeability ranges.The PSOPIP model is proposed to combine the strengths of each computational approach and mitigate their limitations.The PSO-PIP model consistently produces predictions that are highly congruent with actual permeability values across all prediction intervals,significantly enhancing prediction accuracy.The outcomes of this study provide a new tool and perspective for the comprehensive,rapid,and accurate prediction of permeability in porous media.
文摘Airway management plays a crucial role in providing adequate oxygenation and ventilation to patients during various medical procedures and emergencies.When patients have a limited mouth opening due to factors such as trauma,inflammation,or anatomical abnormalities airway management becomes challenging.A commonly utilized method to overcome this challenge is the use of video laryngoscopy(VL),which employs a specialized device equipped with a camera and a light source to allow a clear view of the larynx and vocal cords.VL overcomes the limitations of direct laryngoscopy in patients with limited mouth opening,enabling better visualization and successful intubation.Various types of VL blades are available.We devised a novel flangeless video laryngoscope for use in patients with a limited mouth opening and then tested it on a manikin.
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.
文摘Objective: The purpose of this study was to evaluate health education using videos and leaflets for preconception care (PCC) awareness among adolescent females up to six months after the health education. Methods: The subjects were female university students living in the Kinki area. A longitudinal survey was conducted on 67 members in the intervention group, who received the health education, and 52 members in the control group, who did not receive the health education. The primary outcome measures were knowledge of PCC and the subscales of the Health Promotion Lifestyle Profile. Surveys were conducted before, after, and six months after the intervention in the intervention group, and an initial survey and survey six months later were conducted in the control group. Cochran’s Q test, Bonferroni’s multiple comparison test, and McNemar’s test were used to analyze the knowledge of PCC data. The Health Awareness, Nutrition, and Stress Management subscales of the Health Promotion Lifestyle Profile were analyzed by paired t-test, and comparisons between the intervention and control groups were performed using the two-way repeated measures analysis of variance. Results: In the intervention group of 67 people, the number of subjects who answered “correct” for five of the nine items concerning knowledge of PCC increased immediately after the health education (P = 0.006) but decreased for five items from immediately after the health education to six months later (P = 0.043). In addition, the number of respondents who answered “correct” for “low birth weight infants and future lifestyle-related diseases” (P = 0.016) increased after six months compared with before the health education. For the 52 subjects in the control group, there was no change in the number of subjects who answered “correct” for eight out of the nine items after six months. There was also no increase in scores for the Health Promotion Lifestyle Profile after six months for either the intervention or control group. Conclusion: Providing health education about PCC using videos and leaflets to adolescent females was shown to enhance the knowledge of PCC immediately after the education.
基金supported by the International Joint Research Project of Huiyan International College,Faculty of Education,Beijing Normal University(Grant Number:ICER202102).
文摘Objectives:Short video addiction has emerged as a significant public health issue in recent years,with a growing trend toward severity.However,research on the causes and impacts of short video addiction remains limited,and understanding of the variable“TikTok brain”is still in its infancy.Therefore,based on the Stimulus-Organism-Behavior-Consequence(SOBC)framework,we proposed six research hypotheses and constructed a model to explore the relationships between short video usage intensity,TikTok brain,short video addiction,and decreased attention control.Methods:Given that students are considered a high-risk group for excessive short video use,we collected 1086 valid participants from Chinese student users,including 609 males(56.1%)and 477 females(43.9%),with an average participant age of 19.84 years,to test the hypotheses.Results:(1)Short video usage intensity was positively related to short video addiction,TikTok brain,and decreased attention control;(2)TikTok brain was positively related to short video addiction and decreased attention control;and(3)Short video addiction was positively related to decreased attention control.Conclusions:These findings suggest that although excessive use of short video applications brings negative consequences,users still spend significant amounts of time on these platforms,indicating a need for strict self-regulation of usage time.
基金Fundamental Research Funds for the Central Universities,China(No.2232021A-10)National Natural Science Foundation of China(No.61903078)+1 种基金Shanghai Sailing Program,China(No.22YF1401300)Natural Science Foundation of Shanghai,China(No.20ZR1400400)。
文摘Video classification is an important task in video understanding and plays a pivotal role in intelligent monitoring of information content.Most existing methods do not consider the multimodal nature of the video,and the modality fusion approach tends to be too simple,often neglecting modality alignment before fusion.This research introduces a novel dual stream multimodal alignment and fusion network named DMAFNet for classifying short videos.The network uses two unimodal encoder modules to extract features within modalities and exploits a multimodal encoder module to learn interaction between modalities.To solve the modality alignment problem,contrastive learning is introduced between two unimodal encoder modules.Additionally,masked language modeling(MLM)and video text matching(VTM)auxiliary tasks are introduced to improve the interaction between video frames and text modalities through backpropagation of loss functions.Diverse experiments prove the efficiency of DMAFNet in multimodal video classification tasks.Compared with other two mainstream baselines,DMAFNet achieves the best results on the 2022 WeChat Big Data Challenge dataset.
基金National Social Science Fund of the Chongqing,China(Grant No.2023PY86)。
文摘Dance video is an innovative form that integrates dance art with imaging technology,enriching the expression of dance through techniques such as photography,videography,and special effects.This paper explores the definition,current development,artistic expression,social impact,and future trends of dance video.Through narrative construction,visual impact,emotional resonance,technological innovation,and cultural expression,dance video enhances the narrative and visual appeal of dance.In the future,dance video will focus more on the integration of virtual reality(VR)and augmented reality(AR)technologies.However,it also faces challenges such as rapid technological updates,maintaining artistic originality,and balancing commercial interests.
基金supported by the National Natural Science Foundation of China(61931012,62171258,62088102,and 62271414)the Zhejiang Provincial Outstanding Youth Science Foundation(LR23F010001)the Key Project of Westlake Institute for Optoelectronics(2023GD007).
文摘It has been over a decade since the first coded aperture video compressive sensing(CS)system was reported.The underlying principle of this technology is to employ a high-frequency modulator in the optical path to modulate a recorded high-speed scene within one integration time.The superimposed image captured in this manner is modulated and compressed,since multiple modulation patterns are imposed.Following this,reconstruction algorithms are utilized to recover the desired high-speed scene.One leading advantage of video CS is that a single captured measurement can be used to reconstruct a multi-frame video,thereby enabling a low-speed camera to capture high-speed scenes.Inspired by this,a number of variants of video CS systems have been built,mainly using different modulation devices.Meanwhile,in order to obtain high-quality reconstruction videos,many algorithms have been developed,from optimization-based iterative algorithms to deep-learning-based ones.Recently,emerging deep learning methods have been dominant due to their high-speed inference and high-quality reconstruction,highlighting the possibility of deploying video CS in practical applications.Toward this end,this paper reviews the progress that has been achieved in video CS during the past decade.We further analyze the efforts that need to be made—in terms of both hardware and algorithms—to enable real applications.Research gaps are put forward and future directions are summarized to help researchers and engineers working on this topic.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(Nos.2019R1A2C1002221 and RS-2023-00252186)Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(Nos.2021-0-00590,RS-2021-II210590Decentralized High Performance Consensus for Large-Scale Blockchains).
文摘Personal video recorders (PVRs) have altered the way users consume television (TV) content by allowing users to record programs and watch them at their convenience, overcoming the constraints of live broadcasting. However, standalone PVRs are limited by their individual storage capacities, restricting the number of programs they can store. While online catch-up TV services such as Hulu and Netflix mitigate this limitation by offering on-demand access to broadcast programs shortly after their initial broadcast, they require substantial storage and network resources, leading to significant infrastructural costs for service providers. To address these challenges, we propose a collaborative TV content recording system that leverages distributed PVRs, combining their storage into a virtual shared pool without additional costs. Our system aims to support all concurrent playback requests without service interruption while ensuring program availability comparable to that of local devices. The main contributions of our proposed system are fourfold. First, by sharing storage and upload bandwidth among PVRs, our system significantly expands the overall recording capacity and enables simultaneous recording of multiple programs without the physical constraints of standalone devices. Second, by utilizing erasure coding efficiently, our system reduces the storage space required for each program, allowing more programs to be recorded compared to traditional replication. Third, we propose an adaptive redundancy scheme to control the degree of redundancy of each program based on its evolving playback demand, ensuring high-quality playback by providing sufficient bandwidth for popular programs. Finally, we introduce a contribution-based incentive policy that encourages PVRs to actively participate by contributing resources, while discouraging excessive consumption of the combined storage pool. Through extensive experiments, we demonstrate the effectiveness of our proposed collaborative TV program recording system in terms of storage efficiency and performance.
文摘Video camouflaged object detection(VCOD)has become a fundamental task in computer vision that has attracted significant attention in recent years.Unlike image camouflaged object detection(ICOD),VCOD not only requires spatial cues but also needs motion cues.Thus,effectively utilizing spatiotemporal information is crucial for generating accurate segmentation results.Current VCOD methods,which typically focus on exploring motion representation,often ineffectively integrate spatial and motion features,leading to poor performance in diverse scenarios.To address these issues,we design a novel spatiotemporal network with an encoder-decoder structure.During the encoding stage,an adjacent space-time memory module(ASTM)is employed to extract high-level temporal features(i.e.,motion cues)from the current frame and its adjacent frames.In the decoding stage,a selective space-time aggregation module is introduced to efficiently integrate spatial and temporal features.Additionally,a multi-feature fusion module is developed to progressively refine the rough prediction by utilizing the information provided by multiple types of features.Furthermore,we incorporate multi-task learning into the proposed network to obtain more accurate predictions.Experimental results show that the proposed method outperforms existing cutting-edge baselines on VCOD benchmarks.
