Structure of porous media and fluid distribution in rocks can significantly affect the transport characteristics during the process of microscale tracer flow.To clarify the effect of micro heterogeneity on aqueous tra...Structure of porous media and fluid distribution in rocks can significantly affect the transport characteristics during the process of microscale tracer flow.To clarify the effect of micro heterogeneity on aqueous tracer transport,this paper demonstrates microscopic experiments at pore level and proposes an improved mathematical model for tracer transport.The visualization results show a faster tracer movement into movable water than it into bound water,and quicker occupancy in flowing pores than in storage pores caused by the difference of tracer velocity.Moreover,the proposed mathematical model includes the effects of bound water and flowing porosity by applying interstitial flow velocity expression.The new model also distinguishes flowing and storage pores,accounting for different tracer transport mechanisms(dispersion,diffusion and adsorption)in different types of pores.The resulting analytical solution better matches with tracer production data than the standard model.The residual sum of squares(RSS)from the new model is 0.0005,which is 100 times smaller than the RSS from the standard model.The sensitivity analysis indicates that the dispersion coefficient and flowing porosity shows a negative correlation with the tracer breakthrough time and the increasing slope,whereas the superficial velocity and bound water saturation show a positive correlation.展开更多
This article elucidates the concept of large model technology,summarizes the research status of large model technology both domestically and internationally,provides an overview of the application status of large mode...This article elucidates the concept of large model technology,summarizes the research status of large model technology both domestically and internationally,provides an overview of the application status of large models in vertical industries,outlines the challenges and issues confronted in applying large models in the oil and gas sector,and offers prospects for the application of large models in the oil and gas industry.The existing large models can be briefly divided into three categories:large language models,visual large models,and multimodal large models.The application of large models in the oil and gas industry is still in its infancy.Based on open-source large language models,some oil and gas enterprises have released large language model products using methods like fine-tuning and retrieval augmented generation.Scholars have attempted to develop scenario-specific models for oil and gas operations by using visual/multimodal foundation models.A few researchers have constructed pre-trained foundation models for seismic data processing and interpretation,as well as core analysis.The application of large models in the oil and gas industry faces challenges such as current data quantity and quality being difficult to support the training of large models,high research and development costs,and poor algorithm autonomy and control.The application of large models should be guided by the needs of oil and gas business,taking the application of large models as an opportunity to improve data lifecycle management,enhance data governance capabilities,promote the construction of computing power,strengthen the construction of“artificial intelligence+energy”composite teams,and boost the autonomy and control of large model technology.展开更多
The 3D visualization model of slop with structural plane can displayed the characters of structural plane in slop directly, and illustrated the spatial combination. It is a modem and critical question in the field of ...The 3D visualization model of slop with structural plane can displayed the characters of structural plane in slop directly, and illustrated the spatial combination. It is a modem and critical question in the field of geotechnical engineering. Based on the peculiarity of the reconnaissance and the research of the visualization by formers, systemized the method fit for building 3D visualization model of slop with structural plane. Write the special program with Visual C^-＋ computer language and illustrated it by OpenGL, the program can displayed and captured the random section plane. The program has a satisfied result by proving with the real projects.展开更多
Brood parasitism and egg mimicry of Himalayan Cuckoo（Cuculus saturatus） on its host Blyth＇s Leaf Warbler（Phylloscopus reguloides） were studied in south-western China from April to July 2009.The cuckoo laid a whit...Brood parasitism and egg mimicry of Himalayan Cuckoo（Cuculus saturatus） on its host Blyth＇s Leaf Warbler（Phylloscopus reguloides） were studied in south-western China from April to July 2009.The cuckoo laid a white egg with fine brown markings on the blunt end.The eggs were conspicuously bigger than the host＇s own,with 2.06 g in mass and 1.91 cm3 in volume.Visual modeling showed that the cuckoo eggs,which from the human eye appeared to mimic the host eggs to a great extent,were completely different from the host eggs in both hue and chroma.The characters of the Himalayan Cuckoo nestling,reported for the first time,included two triangular and black patches on its gape,which appeared from four days old and became darker with age and growth.While this character also exists in nestlings of Oriental Cuckoo（C.optatus）,it has not been found for other Cuculus species.Our results reveal cryptic aspects in the cuckoo-host egg color matching,which are not visible to the naked human eye,and indicate that high mimetic cuckoo eggs rejected by hosts,as determined by human observers in previous studies,might not be mimetic as birds see them.展开更多
This article proposes an innovative adversarial attack method,AMA(Adaptive Multimodal Attack),which introduces an adaptive feedback mechanism by dynamically adjusting the perturbation strength.Specifically,AMA adjusts...This article proposes an innovative adversarial attack method,AMA(Adaptive Multimodal Attack),which introduces an adaptive feedback mechanism by dynamically adjusting the perturbation strength.Specifically,AMA adjusts perturbation amplitude based on task complexity and optimizes the perturbation direction based on the gradient direction in real time to enhance attack efficiency.Experimental results demonstrate that AMA elevates attack success rates from approximately 78.95%to 89.56%on visual question answering and from78.82%to 84.96%on visual reasoning tasks across representative vision-language benchmarks.These findings demonstrate AMA’s superior attack efficiency and reveal the vulnerability of current visual language models to carefully crafted adversarial examples,underscoring the need to enhance their robustness.展开更多
Medical image classification is crucial in disease diagnosis,treatment planning,and clinical decisionmaking.We introduced a novel medical image classification approach that integrates Bayesian Random Semantic Data Aug...Medical image classification is crucial in disease diagnosis,treatment planning,and clinical decisionmaking.We introduced a novel medical image classification approach that integrates Bayesian Random Semantic Data Augmentation(BSDA)with a Vision Mamba-based model for medical image classification(MedMamba),enhanced by residual connection blocks,we named the model BSDA-Mamba.BSDA augments medical image data semantically,enhancing the model’s generalization ability and classification performance.MedMamba,a deep learning-based state space model,excels in capturing long-range dependencies in medical images.By incorporating residual connections,BSDA-Mamba further improves feature extraction capabilities.Through comprehensive experiments on eight medical image datasets,we demonstrate that BSDA-Mamba outperforms existing models in accuracy,area under the curve,and F1-score.Our results highlight BSDA-Mamba’s potential as a reliable tool for medical image analysis,particularly in handling diverse imaging modalities from X-rays to MRI.The open-sourcing of our model’s code and datasets,will facilitate the reproduction and extension of our work.展开更多
Background:Familiarity with a simulation platform can seduce modellers into accepting untested assumptions for convenience of implementation.These assumptions may have consequences greater than commonly suspected,and ...Background:Familiarity with a simulation platform can seduce modellers into accepting untested assumptions for convenience of implementation.These assumptions may have consequences greater than commonly suspected,and it is important that modellers remain mindful of assumptions and remain diligent with sensitivity testing.Methods:Familiarity with a technique can lead to complacency,and alternative approaches and software can reveal untested assumptions.Visual modelling environments based on system dynamics may help to make critical assumptions more evident by offering an accessible visual overview and empowering a focus on representational rather than computational efficiency.This capacity is illustrated using a cohort-based forest growth model developed for mixed species forest.Results:The alternative model implementation revealed that untested assumptions in the original model could have substantial influence on simulated outcomes.Conclusions:An important implication is that modellers should remain conscious of all assumptions,consider alternative implementations that reveal assumptions more clearly,and conduct sensitivity tests to inform decisions.展开更多
A Robust Adaptive Video Encoder (RAVE) based on human visual model is proposed. The encoder combines the best features of Fine Granularity Scalable (FGS) coding, framedropping coding, video redundancy coding, and huma...A Robust Adaptive Video Encoder (RAVE) based on human visual model is proposed. The encoder combines the best features of Fine Granularity Scalable (FGS) coding, framedropping coding, video redundancy coding, and human visual model. According to packet loss and available bandwidth of the network, the encoder adjust the output bit rate by jointly adapting quantization step-size instructed by human visual model, rate shaping, and periodically inserting key frame. The proposed encoder is implemented based on MPEG-4 encoder and is compared with the case of a conventional FGS algorithm. It is shown that RAVE is a very efficient robust video encoder that provides improved visual quality for the receiver and consumes equal or less network resource. Results are confirmed by subjective tests and simulation tests.展开更多
Traditional vehicle detection algorithms use traverse search based vehicle candidate generation and hand crafted based classifier training for vehicle candidate verification.These types of methods generally have high ...Traditional vehicle detection algorithms use traverse search based vehicle candidate generation and hand crafted based classifier training for vehicle candidate verification.These types of methods generally have high processing times and low vehicle detection performance.To address this issue,a visual saliency and deep sparse convolution hierarchical model based vehicle detection algorithm is proposed.A visual saliency calculation is firstly used to generate a small vehicle candidate area.The vehicle candidate sub images are then loaded into a sparse deep convolution hierarchical model with an SVM-based classifier to perform the final detection.The experimental results demonstrate that the proposed method is with 94.81% correct rate and 0.78% false detection rate on the existing datasets and the real road pictures captured by our group,which outperforms the existing state-of-the-art algorithms.More importantly,high discriminative multi-scale features are generated by deep sparse convolution network which has broad application prospects in target recognition in the field of intelligent vehicle.展开更多
The dynamic multichannel binocular visual image modeling is studied based on Internet of Things (IoT) Perception Layer, using mobile robot self-organizing network. By employing multigroup mobile robots with binocular ...The dynamic multichannel binocular visual image modeling is studied based on Internet of Things (IoT) Perception Layer, using mobile robot self-organizing network. By employing multigroup mobile robots with binocular visual system, the real visual images of the object will be obtained. Then through the mobile self-organizing network, a three-dimensional model is rebuilt by synthesizing the returned images. On this basis, we formalize a novel algorithm for multichannel binocular visual three-dimensional images based on fast three-dimensional modeling. Compared with the method based on single binocular visual system, the new algorithm can improve the Integrity and accuracy of the dynamic three-dimensional object modeling. The simulation results show that the new method can effectively accelerate the modeling speed, improve the similarity and not increase the data size.展开更多
Vehicle recognition system (VRS) plays a very important role in the field of intelligent transportation systems.A novel and intuitive method is proposed for vehicle location.The method we provide for vehicle location ...Vehicle recognition system (VRS) plays a very important role in the field of intelligent transportation systems.A novel and intuitive method is proposed for vehicle location.The method we provide for vehicle location is based on human visual perception model technique. The perception color space HSI in this algorithm is adopted.Three color components of a color image and more potential edge patterns are integrated for solving the feature extraction problem.A fast and automatic threshold technique based on human visual perception model is also developed.The vertical edge projection and horizontal edge projection are adopted for locating left-right boundary of vehicle and top-bottom boundary of vehicle, respectively. Very promising experimental results are obtained using real-time vehicle image sequences, which have confirmed that this proposed location vehicle method is efficient and reliable, and its calculation speed meets the needs of the VRS.展开更多
As a major food production crop in China,the growth and development of rice is an extremely complex systemic process,and the root system is the main organ for rice to obtain nutrients.Therefore,3D modeling and visuali...As a major food production crop in China,the growth and development of rice is an extremely complex systemic process,and the root system is the main organ for rice to obtain nutrients.Therefore,3D modeling and visualization of the rice root system can help to further understand its morphology,structure and function,and provide an aid for scientific cultivation of rice and improving rice yield for decision making.In this paper,a mathematical model of the rice root system is established based on the B spline curve combined with the L-system approach,using mathematical knowledge based on the 3D morphological characteristics of the real rice root system.The B-Spline Curve is chosen to simulate this,and the recursive definition of B-Spline Curve and its formula are used to realize the modeling of the rice root system curve.Based on the mathematical method of rice root system integration,the bending effect of rice root system at different periods and different growth positions is realized.Finally,the L-system combined with B-Spline Curve is used to construct a rice root system model and realize the rice root system visualization simulation.The simulated image is closer to the real rice root system image in terms of morphological structure and has a strong sense of realism.展开更多
Knowledge of migration and retention mechanisms of elastic gel particles(EGPs)in pore-throats is essential for the effective application of EGPs as a smart sweep improvement and profile control agent for enhanced oil ...Knowledge of migration and retention mechanisms of elastic gel particles(EGPs)in pore-throats is essential for the effective application of EGPs as a smart sweep improvement and profile control agent for enhanced oil recovery(EOR).The matching coefficient(defined as the ratio of particle size to pore-throat size)is used to investigate its influence on migration,retention and profile control performance of EGPs.A 1-D continuous pore-throat visualization model(PTVM),a 2-D heterogeneous PTVM and a 3-D heterogeneous core model were constructed and used to investigate pore-scale migration,retention and controlling mechanism of migration and retention characteristics on EGPs profile control.The results of the 1-D continuous PTVM indicated that while the matching coefficient was in the optimal range(i.e.,0.20-0.32),the EGPs could not only smoothly migrate to the deeper pore-throats,but also form stable retention in the pores to resist the erosion of injected water,which was conducive to the effective indepth profile control.The results of the 2-D heterogeneous PTVM verified that the sweep efficiency in low-permeability regions could be significantly improved by in-depth migration and stable retention of EGPs in the pore-throats with an optimal matching coefficient(0.29),which was much better than that in cases with a smaller matching coefficient(0.17)or an excessive matching coefficient(0.39).Moreover,the NMR displacement experiments of 3-D heterogeneous cores were carried out to simulate the EGPs profile control in actual reservoir porous media.Saturation images and T2 spectrum curves of crude oil showed that EOR in the low-permeability layer was highest(56.1%)using EGPs profile control with an optimal matching coefficient,attributing to the in-depth migration and stable retention of EGPs.展开更多
A method to detect traffic dangers based on visual attention model of sparse sampling was proposed. The hemispherical sparse sampling model was used to decrease the amount of calculation which increases the detection ...A method to detect traffic dangers based on visual attention model of sparse sampling was proposed. The hemispherical sparse sampling model was used to decrease the amount of calculation which increases the detection speed. Bayesian probability model and Gaussian kernel function were applied to calculate the saliency of traffic videos. The method of multiscale saliency was used and the final saliency was the average of all scales, which increased the detection rates extraordinarily. The detection results of several typical traffic dangers show that the proposed method has higher detection rates and speed, which meets the requirement of real-time detection of traffic dangers.展开更多
To solve the unbalanced data problems of learning models for semantic concepts, an optimized modeling method based on the posterior probability support vector machine （PPSVM） is presented. A neighborbased posterior ...To solve the unbalanced data problems of learning models for semantic concepts, an optimized modeling method based on the posterior probability support vector machine （PPSVM） is presented. A neighborbased posterior probability estimator for visual concepts is provided. The proposed method has been applied in a high-level visual semantic concept classification system and the experiment results show that it results in enhanced performance over the baseline SVM models, as well as in improved robustness with respect to high-level visual semantic concept classification.展开更多
How do individual neurons develop and how are they in- tegrated into neuronal circuitry？ To answer this question is essential to understand how the nervous system develops and how it is maintained during the adult li...How do individual neurons develop and how are they in- tegrated into neuronal circuitry？ To answer this question is essential to understand how the nervous system develops and how it is maintained during the adult life. A neural stem cell must go through several stages of maturation, including proliferation, migration, differentiation, and integration, to become fully embedded to an existing neuronal circuit. The knowledge on this topic so far has come mainly from cell culture studies. Studying the development of individual neurons within intact neuronal networks in vivo is inherently difficult. Most neurons are generated form neural stem cells during embryonic and early postnatal development.展开更多
Objectives＂ To deepen our understanding of the status quo and to identify the hot topics and develop- mental trends of research on nursing models in countries other than China in the most recent decade. Methods： The...Objectives＂ To deepen our understanding of the status quo and to identify the hot topics and develop- mental trends of research on nursing models in countries other than China in the most recent decade. Methods： The study subjects were the publications retrieved from the PubMed database using the MeSH terms of ＂Models, Nursing＂. Bibliographic item co-occurrence mining system （BICOMS） software was used for conventional bibliometric analysis of publications during two time periods, 2005-2009 and 2010-2014. The number of published journal articles, journal distribution, authors of publications, country of origin of journals, and language of publications were analyzed to establish a high-frequency keyword profile and co-occurrence matrix. Graphical clustering toolkit （gCLUTO） software was applied for two-way clustering analysis and visualized analysis. Results： A total of 1472 journal articles with a key theme of nursing models were retrieved for final analysis, including 771 published during 2005-2009 and 701 during 2010-2014. The bibliometric analysis revealed that publications other than China concerning nursing models were mostly concentrated in the United States and the United Kingdom and that the number of relevant publications has been continuously decreasing. The two-way clustering analysis showed that there were mainly four types of research themes in the relevant publications in countries other than China during 2005-2009, i.e., nursing education and theoretical research, clinical nursing and psychological care, nursing administration, and models of nursing education, whereas there were five types during 2010-2014, i.e., nursing theories and clinical nursing practice, nursing administration models and assessments of nurses＇ knowledge and skills, community nursing administration models, nursing human resource management, and nursing education models and approaches. Conclusions： Research on nursing models in countries other than China is relatively mature and stable with a broader view, but it has shown a declining trend in recent years. It emphasizes both theory and practice, with research content tending to be structured into four modules, i.e., nursing education, administration, clinical practice, and theoretical research. Community nursing models may become a key research direction in the international research on nursing models in the future.展开更多
The National University Corporation Tsukuba University of Technology（NTUT） is the only institute of higher education for the hearing and the visually impaired in Japan. In our university, hearing or visually impaire...The National University Corporation Tsukuba University of Technology（NTUT） is the only institute of higher education for the hearing and the visually impaired in Japan. In our university, hearing or visually impaired students are studying to be technicians after they graduate, toward social independence. From previous experience of higher education for students with disabilities, effects are increased when modeling is used by the teachers involved in professional education. In the Mechanical Engineering Course, we are using modeling, to match the drawing and shape for beginning students. It includes support for enhancing one＇s view, and how to draw out the ability of mechanical engineering students for the basics. For students to study Mechanical Design and Drawing, Modeling of Gear Pump, Jack and Globe Valve are easily shown through drawings and the operation of each mechanism through sample drawings in the textbook. It is possible to make an opportunity to think about the machine mechanism. It will be shown by students＇ works. The assembling of the model triggers the need for form accuracy by making a function, and improves the quality of learning. It is possible that a three-dimensional molding machine can be produced through experiential learning by the model, and modeling with the dimension numerical data. Moreover, it is also embodied in a three-dimensional modeling which results in the image processing programming created. Confirming the improvement of the program through the shape with the quality. In the Department of Synthetic Design, students have chances to realize and self-evaluate from the design of the lamp shade with a complicated shape. In the Faculty of Health Science from Department of Health, high quality teaching of visually-impaired students through the use of bone model teaching materials has become possible in the medical-related courses.展开更多
Recent studies have indicated that foundation models, such as BERT and GPT, excel atadapting to various downstream tasks. This adaptability has made them a dominant force in buildingartificial intelligence (AI) system...Recent studies have indicated that foundation models, such as BERT and GPT, excel atadapting to various downstream tasks. This adaptability has made them a dominant force in buildingartificial intelligence (AI) systems. Moreover, a newresearch paradigm has emerged as visualizationtechniques are incorporated into these models. Thisstudy divides these intersections into two researchareas: visualization for foundation model (VIS4FM)and foundation model for visualization (FM4VIS).In terms of VIS4FM, we explore the primary roleof visualizations in understanding, refining, and evaluating these intricate foundation models. VIS4FMaddresses the pressing need for transparency, explainability, fairness, and robustness. Conversely, in termsof FM4VIS, we highlight how foundation models canbe used to advance the visualization field itself. Theintersection of foundation models with visualizations ispromising but also introduces a set of challenges. Byhighlighting these challenges and promising opportunities, this study aims to provide a starting point forthe continued exploration of this research avenue.展开更多
Driver behavior is a critical factor in road safety,highlighting the need for advanced methods in Distracted riving lassification(DDC).In this study,we introduce DDC-Chat,a novel classification method based on a isual...Driver behavior is a critical factor in road safety,highlighting the need for advanced methods in Distracted riving lassification(DDC).In this study,we introduce DDC-Chat,a novel classification method based on a isual large anguageodel(VLM).DDC-Chat is an interactive multimodal system built upon LLAVA-Plus,fine-tuned specifically for addressing distracted driving detection.It utilizes logical reasoning chains to activate visual skills,including segmentation and pose detection,through end-to-end training.Furthermore,instruction tuning allows DDC-Chat to continuously incorporate new visual skills,enhancing its ability to classify distracted driving behavior.Our extensive experiments demonstrate that DDC-Chat achieves state-of-the-art performance on public DDC datasets,surpassing previous benchmarks.In evaluations on the 100-Driver dataset,the model exhibits superior results in both zero-shot and few-shot learning contexts,establishing it as a valuable tool for improving driving safety by accurately identifying driver distraction.Due to the computational intensity of inference,DDC-Chat is optimized for deployment on remote servers,with data streamed from in-vehicle monitoring systems for real-time analysis.展开更多
基金funded by National Science and Technology Major Projects(2017ZX05009004,2016ZX05058003)Beijing Natural Science Foundation(2173061)and State Energy Center for Shale Oil Research and Development(G5800-16-ZS-KFNY005).
文摘Structure of porous media and fluid distribution in rocks can significantly affect the transport characteristics during the process of microscale tracer flow.To clarify the effect of micro heterogeneity on aqueous tracer transport,this paper demonstrates microscopic experiments at pore level and proposes an improved mathematical model for tracer transport.The visualization results show a faster tracer movement into movable water than it into bound water,and quicker occupancy in flowing pores than in storage pores caused by the difference of tracer velocity.Moreover,the proposed mathematical model includes the effects of bound water and flowing porosity by applying interstitial flow velocity expression.The new model also distinguishes flowing and storage pores,accounting for different tracer transport mechanisms(dispersion,diffusion and adsorption)in different types of pores.The resulting analytical solution better matches with tracer production data than the standard model.The residual sum of squares(RSS)from the new model is 0.0005,which is 100 times smaller than the RSS from the standard model.The sensitivity analysis indicates that the dispersion coefficient and flowing porosity shows a negative correlation with the tracer breakthrough time and the increasing slope,whereas the superficial velocity and bound water saturation show a positive correlation.
基金Supported by the National Natural Science Foundation of China(72088101,42372175)PetroChina Science and Technology Innovation Fund Program(2021DQ02-0904)。
文摘This article elucidates the concept of large model technology,summarizes the research status of large model technology both domestically and internationally,provides an overview of the application status of large models in vertical industries,outlines the challenges and issues confronted in applying large models in the oil and gas sector,and offers prospects for the application of large models in the oil and gas industry.The existing large models can be briefly divided into three categories:large language models,visual large models,and multimodal large models.The application of large models in the oil and gas industry is still in its infancy.Based on open-source large language models,some oil and gas enterprises have released large language model products using methods like fine-tuning and retrieval augmented generation.Scholars have attempted to develop scenario-specific models for oil and gas operations by using visual/multimodal foundation models.A few researchers have constructed pre-trained foundation models for seismic data processing and interpretation,as well as core analysis.The application of large models in the oil and gas industry faces challenges such as current data quantity and quality being difficult to support the training of large models,high research and development costs,and poor algorithm autonomy and control.The application of large models should be guided by the needs of oil and gas business,taking the application of large models as an opportunity to improve data lifecycle management,enhance data governance capabilities,promote the construction of computing power,strengthen the construction of“artificial intelligence+energy”composite teams,and boost the autonomy and control of large model technology.
文摘The 3D visualization model of slop with structural plane can displayed the characters of structural plane in slop directly, and illustrated the spatial combination. It is a modem and critical question in the field of geotechnical engineering. Based on the peculiarity of the reconnaissance and the research of the visualization by formers, systemized the method fit for building 3D visualization model of slop with structural plane. Write the special program with Visual C^-＋ computer language and illustrated it by OpenGL, the program can displayed and captured the random section plane. The program has a satisfied result by proving with the real projects.
基金supported by National Natural Science Foundation of China(3086004431071938)+1 种基金Program for New Century Excellent Talents in University(NCET-10-0111)China Postdoctoral Science Foundation(20110490967)funded project
文摘Brood parasitism and egg mimicry of Himalayan Cuckoo（Cuculus saturatus） on its host Blyth＇s Leaf Warbler（Phylloscopus reguloides） were studied in south-western China from April to July 2009.The cuckoo laid a white egg with fine brown markings on the blunt end.The eggs were conspicuously bigger than the host＇s own,with 2.06 g in mass and 1.91 cm3 in volume.Visual modeling showed that the cuckoo eggs,which from the human eye appeared to mimic the host eggs to a great extent,were completely different from the host eggs in both hue and chroma.The characters of the Himalayan Cuckoo nestling,reported for the first time,included two triangular and black patches on its gape,which appeared from four days old and became darker with age and growth.While this character also exists in nestlings of Oriental Cuckoo（C.optatus）,it has not been found for other Cuculus species.Our results reveal cryptic aspects in the cuckoo-host egg color matching,which are not visible to the naked human eye,and indicate that high mimetic cuckoo eggs rejected by hosts,as determined by human observers in previous studies,might not be mimetic as birds see them.
基金funded by the Natural Science Foundation of Jiangsu Province(Program BK20240699)National Natural Science Foundation of China(Program 62402228).
文摘This article proposes an innovative adversarial attack method,AMA(Adaptive Multimodal Attack),which introduces an adaptive feedback mechanism by dynamically adjusting the perturbation strength.Specifically,AMA adjusts perturbation amplitude based on task complexity and optimizes the perturbation direction based on the gradient direction in real time to enhance attack efficiency.Experimental results demonstrate that AMA elevates attack success rates from approximately 78.95%to 89.56%on visual question answering and from78.82%to 84.96%on visual reasoning tasks across representative vision-language benchmarks.These findings demonstrate AMA’s superior attack efficiency and reveal the vulnerability of current visual language models to carefully crafted adversarial examples,underscoring the need to enhance their robustness.
文摘Medical image classification is crucial in disease diagnosis,treatment planning,and clinical decisionmaking.We introduced a novel medical image classification approach that integrates Bayesian Random Semantic Data Augmentation(BSDA)with a Vision Mamba-based model for medical image classification(MedMamba),enhanced by residual connection blocks,we named the model BSDA-Mamba.BSDA augments medical image data semantically,enhancing the model’s generalization ability and classification performance.MedMamba,a deep learning-based state space model,excels in capturing long-range dependencies in medical images.By incorporating residual connections,BSDA-Mamba further improves feature extraction capabilities.Through comprehensive experiments on eight medical image datasets,we demonstrate that BSDA-Mamba outperforms existing models in accuracy,area under the curve,and F1-score.Our results highlight BSDA-Mamba’s potential as a reliable tool for medical image analysis,particularly in handling diverse imaging modalities from X-rays to MRI.The open-sourcing of our model’s code and datasets,will facilitate the reproduction and extension of our work.
文摘Background:Familiarity with a simulation platform can seduce modellers into accepting untested assumptions for convenience of implementation.These assumptions may have consequences greater than commonly suspected,and it is important that modellers remain mindful of assumptions and remain diligent with sensitivity testing.Methods:Familiarity with a technique can lead to complacency,and alternative approaches and software can reveal untested assumptions.Visual modelling environments based on system dynamics may help to make critical assumptions more evident by offering an accessible visual overview and empowering a focus on representational rather than computational efficiency.This capacity is illustrated using a cohort-based forest growth model developed for mixed species forest.Results:The alternative model implementation revealed that untested assumptions in the original model could have substantial influence on simulated outcomes.Conclusions:An important implication is that modellers should remain conscious of all assumptions,consider alternative implementations that reveal assumptions more clearly,and conduct sensitivity tests to inform decisions.
基金Supported by Innovation Fund of China(00C26224210641)
文摘A Robust Adaptive Video Encoder (RAVE) based on human visual model is proposed. The encoder combines the best features of Fine Granularity Scalable (FGS) coding, framedropping coding, video redundancy coding, and human visual model. According to packet loss and available bandwidth of the network, the encoder adjust the output bit rate by jointly adapting quantization step-size instructed by human visual model, rate shaping, and periodically inserting key frame. The proposed encoder is implemented based on MPEG-4 encoder and is compared with the case of a conventional FGS algorithm. It is shown that RAVE is a very efficient robust video encoder that provides improved visual quality for the receiver and consumes equal or less network resource. Results are confirmed by subjective tests and simulation tests.
基金Supported by National Natural Science Foundation of China(Grant Nos.U1564201,61573171,61403172,51305167)China Postdoctoral Science Foundation(Grant Nos.2015T80511,2014M561592)+3 种基金Jiangsu Provincial Natural Science Foundation of China(Grant No.BK20140555)Six Talent Peaks Project of Jiangsu Province,China(Grant Nos.2015-JXQC-012,2014-DZXX-040)Jiangsu Postdoctoral Science Foundation,China(Grant No.1402097C)Jiangsu University Scientific Research Foundation for Senior Professionals,China(Grant No.14JDG028)
文摘Traditional vehicle detection algorithms use traverse search based vehicle candidate generation and hand crafted based classifier training for vehicle candidate verification.These types of methods generally have high processing times and low vehicle detection performance.To address this issue,a visual saliency and deep sparse convolution hierarchical model based vehicle detection algorithm is proposed.A visual saliency calculation is firstly used to generate a small vehicle candidate area.The vehicle candidate sub images are then loaded into a sparse deep convolution hierarchical model with an SVM-based classifier to perform the final detection.The experimental results demonstrate that the proposed method is with 94.81% correct rate and 0.78% false detection rate on the existing datasets and the real road pictures captured by our group,which outperforms the existing state-of-the-art algorithms.More importantly,high discriminative multi-scale features are generated by deep sparse convolution network which has broad application prospects in target recognition in the field of intelligent vehicle.
基金supported by HiTech Researchand Development Program of China under Grant No.2007AA10Z235
文摘The dynamic multichannel binocular visual image modeling is studied based on Internet of Things (IoT) Perception Layer, using mobile robot self-organizing network. By employing multigroup mobile robots with binocular visual system, the real visual images of the object will be obtained. Then through the mobile self-organizing network, a three-dimensional model is rebuilt by synthesizing the returned images. On this basis, we formalize a novel algorithm for multichannel binocular visual three-dimensional images based on fast three-dimensional modeling. Compared with the method based on single binocular visual system, the new algorithm can improve the Integrity and accuracy of the dynamic three-dimensional object modeling. The simulation results show that the new method can effectively accelerate the modeling speed, improve the similarity and not increase the data size.
文摘Vehicle recognition system (VRS) plays a very important role in the field of intelligent transportation systems.A novel and intuitive method is proposed for vehicle location.The method we provide for vehicle location is based on human visual perception model technique. The perception color space HSI in this algorithm is adopted.Three color components of a color image and more potential edge patterns are integrated for solving the feature extraction problem.A fast and automatic threshold technique based on human visual perception model is also developed.The vertical edge projection and horizontal edge projection are adopted for locating left-right boundary of vehicle and top-bottom boundary of vehicle, respectively. Very promising experimental results are obtained using real-time vehicle image sequences, which have confirmed that this proposed location vehicle method is efficient and reliable, and its calculation speed meets the needs of the VRS.
基金Supported by the National Natural Science Foundation of China(61862032)the Project of Natural Science Foundation of Jiangxi Province(20202BABL202034)the Special Foundation of Graduate Student Innovation of Jiangxi Province(YC2021-S347)
文摘As a major food production crop in China,the growth and development of rice is an extremely complex systemic process,and the root system is the main organ for rice to obtain nutrients.Therefore,3D modeling and visualization of the rice root system can help to further understand its morphology,structure and function,and provide an aid for scientific cultivation of rice and improving rice yield for decision making.In this paper,a mathematical model of the rice root system is established based on the B spline curve combined with the L-system approach,using mathematical knowledge based on the 3D morphological characteristics of the real rice root system.The B-Spline Curve is chosen to simulate this,and the recursive definition of B-Spline Curve and its formula are used to realize the modeling of the rice root system curve.Based on the mathematical method of rice root system integration,the bending effect of rice root system at different periods and different growth positions is realized.Finally,the L-system combined with B-Spline Curve is used to construct a rice root system model and realize the rice root system visualization simulation.The simulated image is closer to the real rice root system image in terms of morphological structure and has a strong sense of realism.
基金supported by the National Key Research and Development Project(2019YFA0708700)the National Natural Science Foundation of China(52104061)+2 种基金the project funded by China Postdoctoral Science Foundation(2020M682264)the Shandong Provincial Natural Science Foundation(ZR2021QE075)the Fundamental Research Funds for the Central Universities(20CX06090A)。
文摘Knowledge of migration and retention mechanisms of elastic gel particles(EGPs)in pore-throats is essential for the effective application of EGPs as a smart sweep improvement and profile control agent for enhanced oil recovery(EOR).The matching coefficient(defined as the ratio of particle size to pore-throat size)is used to investigate its influence on migration,retention and profile control performance of EGPs.A 1-D continuous pore-throat visualization model(PTVM),a 2-D heterogeneous PTVM and a 3-D heterogeneous core model were constructed and used to investigate pore-scale migration,retention and controlling mechanism of migration and retention characteristics on EGPs profile control.The results of the 1-D continuous PTVM indicated that while the matching coefficient was in the optimal range(i.e.,0.20-0.32),the EGPs could not only smoothly migrate to the deeper pore-throats,but also form stable retention in the pores to resist the erosion of injected water,which was conducive to the effective indepth profile control.The results of the 2-D heterogeneous PTVM verified that the sweep efficiency in low-permeability regions could be significantly improved by in-depth migration and stable retention of EGPs in the pore-throats with an optimal matching coefficient(0.29),which was much better than that in cases with a smaller matching coefficient(0.17)or an excessive matching coefficient(0.39).Moreover,the NMR displacement experiments of 3-D heterogeneous cores were carried out to simulate the EGPs profile control in actual reservoir porous media.Saturation images and T2 spectrum curves of crude oil showed that EOR in the low-permeability layer was highest(56.1%)using EGPs profile control with an optimal matching coefficient,attributing to the in-depth migration and stable retention of EGPs.
基金Project(50808025)supported by the National Natural Science Foundation of ChinaProject(20090162110057)supported by the Doctoral Fund of Ministry of Education of China
文摘A method to detect traffic dangers based on visual attention model of sparse sampling was proposed. The hemispherical sparse sampling model was used to decrease the amount of calculation which increases the detection speed. Bayesian probability model and Gaussian kernel function were applied to calculate the saliency of traffic videos. The method of multiscale saliency was used and the final saliency was the average of all scales, which increased the detection rates extraordinarily. The detection results of several typical traffic dangers show that the proposed method has higher detection rates and speed, which meets the requirement of real-time detection of traffic dangers.
基金Sponsored by the Beijing Municipal Natural Science Foundation(4082027)
文摘To solve the unbalanced data problems of learning models for semantic concepts, an optimized modeling method based on the posterior probability support vector machine （PPSVM） is presented. A neighborbased posterior probability estimator for visual concepts is provided. The proposed method has been applied in a high-level visual semantic concept classification system and the experiment results show that it results in enhanced performance over the baseline SVM models, as well as in improved robustness with respect to high-level visual semantic concept classification.
基金supported by DFG Schwerpunkt program 1392(project MA 4113/2-2)cluster of Excellence and DFG Research Center Nanoscale Microscopy and Molecular Physiology of the Brain(project B1-9)+1 种基金the German Ministry of Research and Education(BMBFproject 1364480)
文摘How do individual neurons develop and how are they in- tegrated into neuronal circuitry？ To answer this question is essential to understand how the nervous system develops and how it is maintained during the adult life. A neural stem cell must go through several stages of maturation, including proliferation, migration, differentiation, and integration, to become fully embedded to an existing neuronal circuit. The knowledge on this topic so far has come mainly from cell culture studies. Studying the development of individual neurons within intact neuronal networks in vivo is inherently difficult. Most neurons are generated form neural stem cells during embryonic and early postnatal development.
基金supported by Shanxi Provincial Health Department(No.201201031)
文摘Objectives＂ To deepen our understanding of the status quo and to identify the hot topics and develop- mental trends of research on nursing models in countries other than China in the most recent decade. Methods： The study subjects were the publications retrieved from the PubMed database using the MeSH terms of ＂Models, Nursing＂. Bibliographic item co-occurrence mining system （BICOMS） software was used for conventional bibliometric analysis of publications during two time periods, 2005-2009 and 2010-2014. The number of published journal articles, journal distribution, authors of publications, country of origin of journals, and language of publications were analyzed to establish a high-frequency keyword profile and co-occurrence matrix. Graphical clustering toolkit （gCLUTO） software was applied for two-way clustering analysis and visualized analysis. Results： A total of 1472 journal articles with a key theme of nursing models were retrieved for final analysis, including 771 published during 2005-2009 and 701 during 2010-2014. The bibliometric analysis revealed that publications other than China concerning nursing models were mostly concentrated in the United States and the United Kingdom and that the number of relevant publications has been continuously decreasing. The two-way clustering analysis showed that there were mainly four types of research themes in the relevant publications in countries other than China during 2005-2009, i.e., nursing education and theoretical research, clinical nursing and psychological care, nursing administration, and models of nursing education, whereas there were five types during 2010-2014, i.e., nursing theories and clinical nursing practice, nursing administration models and assessments of nurses＇ knowledge and skills, community nursing administration models, nursing human resource management, and nursing education models and approaches. Conclusions： Research on nursing models in countries other than China is relatively mature and stable with a broader view, but it has shown a declining trend in recent years. It emphasizes both theory and practice, with research content tending to be structured into four modules, i.e., nursing education, administration, clinical practice, and theoretical research. Community nursing models may become a key research direction in the international research on nursing models in the future.
文摘The National University Corporation Tsukuba University of Technology（NTUT） is the only institute of higher education for the hearing and the visually impaired in Japan. In our university, hearing or visually impaired students are studying to be technicians after they graduate, toward social independence. From previous experience of higher education for students with disabilities, effects are increased when modeling is used by the teachers involved in professional education. In the Mechanical Engineering Course, we are using modeling, to match the drawing and shape for beginning students. It includes support for enhancing one＇s view, and how to draw out the ability of mechanical engineering students for the basics. For students to study Mechanical Design and Drawing, Modeling of Gear Pump, Jack and Globe Valve are easily shown through drawings and the operation of each mechanism through sample drawings in the textbook. It is possible to make an opportunity to think about the machine mechanism. It will be shown by students＇ works. The assembling of the model triggers the need for form accuracy by making a function, and improves the quality of learning. It is possible that a three-dimensional molding machine can be produced through experiential learning by the model, and modeling with the dimension numerical data. Moreover, it is also embodied in a three-dimensional modeling which results in the image processing programming created. Confirming the improvement of the program through the shape with the quality. In the Department of Synthetic Design, students have chances to realize and self-evaluate from the design of the lamp shade with a complicated shape. In the Faculty of Health Science from Department of Health, high quality teaching of visually-impaired students through the use of bone model teaching materials has become possible in the medical-related courses.
基金supported by the National Natural Science Foundation of China(Grant Nos.U21A20469 and 61936002)the National Key R&D Program of China(Grant No.2020YFB2104100)grants from the Institute Guo Qiang,THUIBCS,and BLBCI.
文摘Recent studies have indicated that foundation models, such as BERT and GPT, excel atadapting to various downstream tasks. This adaptability has made them a dominant force in buildingartificial intelligence (AI) systems. Moreover, a newresearch paradigm has emerged as visualizationtechniques are incorporated into these models. Thisstudy divides these intersections into two researchareas: visualization for foundation model (VIS4FM)and foundation model for visualization (FM4VIS).In terms of VIS4FM, we explore the primary roleof visualizations in understanding, refining, and evaluating these intricate foundation models. VIS4FMaddresses the pressing need for transparency, explainability, fairness, and robustness. Conversely, in termsof FM4VIS, we highlight how foundation models canbe used to advance the visualization field itself. Theintersection of foundation models with visualizations ispromising but also introduces a set of challenges. Byhighlighting these challenges and promising opportunities, this study aims to provide a starting point forthe continued exploration of this research avenue.
基金supported by the National Natural Science Foundation of China(62173253,52272374)the Research and Practice Project of New Engineering in Ordinary Undergraduate Universities in Guangxi Zhuang Autonomous Region(XGK202310)+1 种基金educational reform projects(JGT202302,JGKQ202309)the 2024 Guangxi Collegiate Innovation and Entrepreneurship Training Project"Eye-Smart Driving-Fatigue Driving Monitoring and Warning System Based on Computer Vision"(Project No.S202410595158).
文摘Driver behavior is a critical factor in road safety,highlighting the need for advanced methods in Distracted riving lassification(DDC).In this study,we introduce DDC-Chat,a novel classification method based on a isual large anguageodel(VLM).DDC-Chat is an interactive multimodal system built upon LLAVA-Plus,fine-tuned specifically for addressing distracted driving detection.It utilizes logical reasoning chains to activate visual skills,including segmentation and pose detection,through end-to-end training.Furthermore,instruction tuning allows DDC-Chat to continuously incorporate new visual skills,enhancing its ability to classify distracted driving behavior.Our extensive experiments demonstrate that DDC-Chat achieves state-of-the-art performance on public DDC datasets,surpassing previous benchmarks.In evaluations on the 100-Driver dataset,the model exhibits superior results in both zero-shot and few-shot learning contexts,establishing it as a valuable tool for improving driving safety by accurately identifying driver distraction.Due to the computational intensity of inference,DDC-Chat is optimized for deployment on remote servers,with data streamed from in-vehicle monitoring systems for real-time analysis.
