A panoptic driving perception system is an essential part of autonomous driving.A high-precision and real-time perception system can assist the vehicle in making reasonable decisions while driving.We present a panopti...A panoptic driving perception system is an essential part of autonomous driving.A high-precision and real-time perception system can assist the vehicle in making reasonable decisions while driving.We present a panoptic driving perception network(you only look once for panoptic(YOLOP))to perform traffic object detection,drivable area segmentation,and lane detection simultaneously.It is composed of one encoder for feature extraction and three decoders to handle the specific tasks.Our model performs extremely well on the challenging BDD100K dataset,achieving state-of-the-art on all three tasks in terms of accuracy and speed.Besides,we verify the effectiveness of our multi-task learning model for joint training via ablative studies.To our best knowledge,this is the first work that can process these three visual perception tasks simultaneously in real-time on an embedded device Jetson TX2(23 FPS),and maintain excellent accuracy.To facilitate further research,the source codes and pre-trained models are released at https://github.com/hustvl/YOLOP.展开更多
A novel robust fault tolerant controller is developed for the problem of attitude control of a quadrotor aircraft in the presence of actuator faults and wind gusts in this paper.Firstly, a dynamical system of the quad...A novel robust fault tolerant controller is developed for the problem of attitude control of a quadrotor aircraft in the presence of actuator faults and wind gusts in this paper.Firstly, a dynamical system of the quadrotor taking into account aerodynamical effects induced by lateral wind and actuator faults is considered using the Newton-Euler approach. Then,based on active disturbance rejection control(ADRC), the fault tolerant controller is proposed to recover faulty system and reject perturbations. The developed controller takes wind gusts,actuator faults and measurement noises as total perturbations which are estimated by improved extended state observer(ESO)and compensated by nonlinear feedback control law. So, the developed robust fault tolerant controller can successfully accomplish the tracking of the desired output values. Finally, some simulation studies are given to illustrate the effectiveness of fault recovery of the proposed scheme and also its ability to attenuate external disturbances that are introduced from environmental causes such as wind gusts and measurement noises.展开更多
The quantum dot spectrometer,fabricated by integrating different quantum dots with an image sensor to reconstruct the target spectrum from spectral-coupled measurements,is an emerging and promising hyperspectrometry t...The quantum dot spectrometer,fabricated by integrating different quantum dots with an image sensor to reconstruct the target spectrum from spectral-coupled measurements,is an emerging and promising hyperspectrometry technology with high resolution and a compact size.The spectral resolution and spectral range of quantum dot spectrometers have been limited by the spectral variety of the available quantum dots and the robustness of algorithmic reconstruction.Moreover,the spectrometer integration of quantum dots also suffers from inherent photoluminescence emission and poor batch-to-batch repeatability.In this work,we developed nonemissive in situ fabricated MA_(3)Bi_(2)X_(9) and Cs_(2)SnX_(6)(MA=CH_(3)NH_(3);X=Cl,Br,I)perovskite-quantum-dot-embedded films(PQDFs)with precisely tunable transmittance spectra for quantum dot spectrometer applications.The resulting PQDFs contain in situ fabricated perovskite nanocrystals with homogenous dispersion in a polymeric matrix,giving them advantageous features such as high transmittance efficiency and good batch-to-batch repeatability.By integrating a filter array of 361 kinds of PQDFs with a silicon-based photodetector array,we successfully demonstrated the construction of a perovskite quantum dot spectrometer combined with a compressive-sensing-based total-variation optimization algorithm.A spectral resolution of ~1.6 nm was achieved in the broadband of 250-1000 nm.The performance of the perovskite quantum dot spectrometer is well beyond that of human eyes in terms of both the spectral range and spectral resolution.This advancement will not only pave the way for using quantum dot spectrometers for practical applications but also significantly impact the development of artificial intelligence products,clinical treatment equipment,scientific instruments,etc.展开更多
Based on the stability and inequality of texture features between coal and rock,this study used the digital image analysis technique to propose a coal–rock interface detection method.By using gray level co-occurrence...Based on the stability and inequality of texture features between coal and rock,this study used the digital image analysis technique to propose a coal–rock interface detection method.By using gray level co-occurrence matrix,twenty-two texture features were extracted from the images of coal and rock.Data dimension of the feature space reduced to four by feature selection,which was according to a separability criterion based on inter-class mean difference and within-class scatter.The experimental results show that the optimized features were effective in improving the separability of the samples and reducing the time complexity of the algorithm.In the optimized low-dimensional feature space,the coal–rock classifer was set up using the fsher discriminant method.Using the 10-fold cross-validation technique,the performance of the classifer was evaluated,and an average recognition rate of 94.12%was obtained.The results of comparative experiments show that the identifcation performance of the proposed method was superior to the texture description method based on gray histogram and gradient histogram.展开更多
Motion planning is one of the most significant technologies for autonomous driving. To make motion planning models able to learn from the environment and to deal with emergency situations, a new motion planning framew...Motion planning is one of the most significant technologies for autonomous driving. To make motion planning models able to learn from the environment and to deal with emergency situations, a new motion planning framework called as"parallel planning" is proposed in this paper. In order to generate sufficient and various training samples, artificial traffic scenes are firstly constructed based on the knowledge from the reality.A deep planning model which combines a convolutional neural network(CNN) with the Long Short-Term Memory module(LSTM) is developed to make planning decisions in an end-toend mode. This model can learn from both real and artificial traffic scenes and imitate the driving style of human drivers.Moreover, a parallel deep reinforcement learning approach is also presented to improve the robustness of planning model and reduce the error rate. To handle emergency situations, a hybrid generative model including a variational auto-encoder(VAE) and a generative adversarial network(GAN) is utilized to learn from virtual emergencies generated in artificial traffic scenes. While an autonomous vehicle is moving, the hybrid generative model generates multiple video clips in parallel, which correspond to different potential emergency scenarios. Simultaneously, the deep planning model makes planning decisions for both virtual and current real scenes. The final planning decision is determined by analysis of real observations. Leveraging the parallel planning approach, the planner is able to make rational decisions without heavy calculation burden when an emergency occurs.展开更多
In underwater optical wireless communication(UOWC),a channel is characterized by abundant scattering/absorption effects and optical turbulence.Most previous studies on UOWC have been limited to scattering/absorption e...In underwater optical wireless communication(UOWC),a channel is characterized by abundant scattering/absorption effects and optical turbulence.Most previous studies on UOWC have been limited to scattering/absorption effects.However,experiments in the literature indicate that underwater optical turbulence(UOT)can cause severe degradation of UOWC performance.In this paper,we characterize an UOWC channel with both scattering/absorption and UOT taken into consideration,and a spatial diversity receiver scheme,say a singleinput–multiple-output(SIMO) scheme,based on a light-emitting-diode(LED) source and multiple detectors is proposed to mitigate deep fading.The Monte Carlo based statistical simulation method is introduced to evaluate the bit-error-rate performance of the system.It is shown that spatial diversity can effectively reduce channel fading and remarkably extend communication range.展开更多
Threat assessment is one of the most important parts of the tactical decisions,and it has a very important influence on task allocation.An application of fuzzy cognitive map(FCM) for target threat assessment in the ai...Threat assessment is one of the most important parts of the tactical decisions,and it has a very important influence on task allocation.An application of fuzzy cognitive map(FCM) for target threat assessment in the air combat is introduced.Considering the fact that the aircrafts participated in the cooperation may not have the same threat assessment mechanism,two different FCM models are established.Using the method of combination,the model of cooperative threat assessment in air combat of multi-aircrafts is established.Simulation results show preliminarily that the method is reasonable and effective.Using FCM for threat assessment is feasible.展开更多
Hippocampal morphological change is one of the main hallmarks of Alzheimer’s disease(AD).However,whether hippocampal radiomic features are robust as predictors of progression from mild cognitive impairment(MCI)to AD ...Hippocampal morphological change is one of the main hallmarks of Alzheimer’s disease(AD).However,whether hippocampal radiomic features are robust as predictors of progression from mild cognitive impairment(MCI)to AD dementia and whether these features provide any neurobiological foundation remains unclear.The primary aim of this study was to verify whether hippocampal radiomic features can serve as robust magnetic resonance imaging(MRI)markers for AD.Multivariate classifier-based support vector machine(SVM)analysis provided individual-level predictions for distinguishing AD patients(n=261)from normal controls(NCs;n=231)with an accuracy of 88.21%and intersite crossvalidation.Further analyses of a large,independent the Alzheimer’s Disease Neuroimaging Initiative(ADNI)dataset(n=1228)reinforced these findings.In MCI groups,a systemic analysis demonstrated that the identified features were significantly associated with clinical features(e.g.,apolipoprotein E(APOE)genotype,polygenic risk scores,cerebrospinal fluid(CSF)Ab,CSF Tau),and longitudinal changes in cognition ability;more importantly,the radiomic features had a consistently altered pattern with changes in the MMSE scores over 5 years of follow-up.These comprehensive results suggest that hippocampal radiomic features can serve as robust biomarkers for clinical application in AD/MCI,and further provide evidence for predicting whether an MCI subject would convert to AD based on the radiomics of the hippocampus.The results of this study are expected to have a substantial impact on the early diagnosis of AD/MCI.展开更多
To overcome nonlinear and 6-DOF(degrees of freedom)under-actuated problems for the attitude and position of quadrotor UAVs,an adaptive backstepping sliding mode method for flight attitude of quadrotor UAVs is proposed...To overcome nonlinear and 6-DOF(degrees of freedom)under-actuated problems for the attitude and position of quadrotor UAVs,an adaptive backstepping sliding mode method for flight attitude of quadrotor UAVs is proposed,in which an adaptive law is designed to online estimate the parameter variations and the upper bound of external disturbances and the assessments is utilized to compensate the backstepping sliding mode control.In addition,the tracking error of the design method is shown to asymptotically converge to zero by using Lyapunov theory.Finally,based on the numerical simulation of quadrotor UAVs using the setting parameters,the results show that the proposed control approach can stabilize the attitude and has hover flight capabilities under the parameter perturbations and external disturbances.展开更多
Dempster-Shafer (DS) theory of evidence has been widely used in many data fusion ap- plication systems. However, how to determine basic probability assignment, which is the main and the first step in evidence theory, ...Dempster-Shafer (DS) theory of evidence has been widely used in many data fusion ap- plication systems. However, how to determine basic probability assignment, which is the main and the first step in evidence theory, is still an open issue. In this paper, a new method to obtain Basic Probability Assignment (BPA) is proposed based on the similarity measure between generalized fuzzy numbers. In the proposed method, species model can be constructed by determination of the min, average and max value to construct a fuzzy number. Then, a new Radius Of Gravity (ROG) method to determine the similarity measure between generalized fuzzy numbers is used to calculate the BPA functions of each instance. Finally, the efficiency of the proposed method is illustrated by the classi- fication of Iris data.展开更多
To meet the multi-cooperation production demand of enterprises,the distributed permutation flow shop scheduling problem(DPFSP)has become the frontier research in the field of manufacturing systems.In this paper,we inv...To meet the multi-cooperation production demand of enterprises,the distributed permutation flow shop scheduling problem(DPFSP)has become the frontier research in the field of manufacturing systems.In this paper,we investigate the DPFSP by minimizing a makespan criterion under the constraint of sequence-dependent setup times.To solve DPFSPs,significant developments of some metaheuristic algorithms are necessary.In this context,a simple and effective improved iterated greedy(NIG)algorithm is proposed to minimize makespan in DPFSPs.According to the features of DPFSPs,a two-stage local search based on single job swapping and job block swapping within the key factory is designed in the proposed algorithm.We compare the proposed algorithm with state-of-the-art algorithms,including the iterative greedy algorithm(2019),iterative greedy proposed by Ruiz and Pan(2019),discrete differential evolution algorithm(2018),discrete artificial bee colony(2018),and artificial chemical reaction optimization(2017).Simulation results show that NIG outperforms the compared algorithms.展开更多
An adaptive state feedback predictive control （SFPC） scheme and an expert control scheme are presented and applied to the temperature control of a 1200 kt·a^-1 delayed coking furnace, which is the key equipment...An adaptive state feedback predictive control （SFPC） scheme and an expert control scheme are presented and applied to the temperature control of a 1200 kt·a^-1 delayed coking furnace, which is the key equipment for the delayed coking process. Adaptive SFPC is used to improve the performance of temperature control in normal operation. A simplified nonlinear model on the basis of first principles of the furnace is developed to obtain a state space model by linearization. Taking advantage of the nonlinear model, an online model adapting method is presented to accommodate the dynamic change of process characteristics because of tube coking and load changes. To compensate the large inverse response of outlet temperature resulting from the sudden increase of injected steam of a particular velocity to tubes, a monitoring method and an expert control scheme based on heat balance calculation are proposed. Industrial implementation shows the effectiveness and feasibility of the proposed control strategy.展开更多
Arabidopsis thaliana is an important and long-established model species for plant molecular biology,genetics,epigenetics,and genomics.However,the latest version of reference genome still contains a significant number ...Arabidopsis thaliana is an important and long-established model species for plant molecular biology,genetics,epigenetics,and genomics.However,the latest version of reference genome still contains a significant number of missing segments.Here,we reported a high-quality and almost complete Col-0 genome assembly with two gaps(named Col-XJTU)by combining the Oxford Nanopore Technologies ultra-long reads,Pacific Biosciences high-fidelity long reads,and Hi-C data.The total genome assembly size is 133,725,193 bp,introducing 14.6 Mb of novel sequences compared to the TAIR10.1 reference genome.All five chromosomes of the Col-XJTU assembly are highly accurate with consensus quality(QV)scores>60(ranging from 62 to 68),which are higher than those of the TAIR10.1 reference(ranging from 45 to 52).We completely resolved chromosome(Chr)3 and Chr5 in a telomere-to-telomere manner.Chr4 was completely resolved except the nucleolar organizing regions,which comprise long repetitive DNA fragments.The Chrl centromere(CEN1),reportedly around 9 Mb in length,is particularly challenging to assemble due to the presence of tens of thousands of CEN180 satellite repeats.Using the cutting-edge sequencing data and novel computational approaches,we assembled a 3.8-Mb-long CEN1 and a 3.5-Mb-long CEN2.We also investigated the structure and epigenetics of centromeres.Four clusters of CEN180 monomers were detected,and the centromere-specific histone H3-like protein(CENH3)exhibited a strong preference for CEN180 Cluster 3.Moreover,we observed hypomethylation patterns in CENH3-enriched regions.We believe that this high-quality genome assembly,Col-XJTU,would serve as a valuable reference to better understand the global pattern of centromeric polymorphisms,as well as the genetic and epigenetic features in plants.展开更多
Since the beginning of the 21 st century,the geoscience research has been entering a significant transitional period with the establishment of a new knowledge system as the core and with the drive of big data as the m...Since the beginning of the 21 st century,the geoscience research has been entering a significant transitional period with the establishment of a new knowledge system as the core and with the drive of big data as the means.It is a revolutionary leap in the research of geoscience knowledge discovery from the traditional encyclopedic discipline knowledge system to the computer-understandable and operable knowledge graph.Based on adopting the graph pattern of general knowledge representation,the geoscience knowledge graph expands the unique spatiotemporal features to the Geoscience knowledge,and integrates geoscience knowledge elements,such as map,text,and number,to establish an all-domain geoscience knowledge representation model.A federated,crowd intelligence-based collaborative method of constructing the geoscience knowledge graph is developed here,which realizes the construction of high-quality professional knowledge graph in collaboration with global geo-scientists.We also develop a method for constructing a dynamic knowledge graph of multi-modal geoscience data based on in-depth text analysis,which extracts geoscience knowledge from massive geoscience literature to construct the latest and most complete dynamic geoscience knowledge graph.A comprehensive and systematic geoscience knowledge graph can not only deepen the existing geoscience big data analysis,but also advance the construction of the high-precision geological time scale driven by big data,the compilation of intelligent maps driven by rules and data,and the geoscience knowledge evolution and reasoning analysis,among others.It will further expand the new directions of geoscience research driven by both data and knowledge,break new ground where geoscience,information science,and data science converge,realize the original innovation of the geoscience research and achieve major theoretical breakthroughs in the spatiotemporal big data research.展开更多
Speed and enhancement are the two most important metrics for anti-scattering light focusing by wavefront shaping(WS),which requires a spatial light modulator with a large number of modulation modes and a fast speed of...Speed and enhancement are the two most important metrics for anti-scattering light focusing by wavefront shaping(WS),which requires a spatial light modulator with a large number of modulation modes and a fast speed of response.Among the commercial modulators,the digital-micromirror device(DMD)is the sole solution providing millions of modulation modes and a pattern rate higher than 20 kHz.Thus,it has the potential to accelerate the process of anti-scattering light focusing with a high enhancement.Nevertheless,modulating light in a binary mode by the DMD restricts both the speed and enhancement seriously.Here,we propose a multi-pixel encoded DMD-based WS method by combining multiple micromirrors into a single modulation unit to overcome the drawbacks of binary modulation.In addition,to efficiently optimize the wavefront,we adopted separable natural evolution strategies(SNES),which could carry out a global search against a noisy environment.Compared with the state-of-the-art DMD-based WS method,the proposed method increased the speed of optimization and enhancement of focus by a factor of 179 and 16,respectively.In our demonstration,we achieved 10 foci with homogeneous brightness at a high speed and formed W-and S-shape patterns against the scattering medium.The experimental results suggest that the proposed method will pave a new avenue for WS in the applications of biomedical imaging,photon therapy,optogenetics,dynamic holographic display,etc.展开更多
Spinal cord stimulation （SCS） is a promising technique for treating disorders of consciousness （DOCs）. However, differences in the spatio-temporal responsiveness of the brain under varied SCS parameters remain unc...Spinal cord stimulation （SCS） is a promising technique for treating disorders of consciousness （DOCs）. However, differences in the spatio-temporal responsiveness of the brain under varied SCS parameters remain unclear. In this pilot study, functional near-infrared spectroscopy was used to measure the hemodynamic responses of 10 DOC patients to different SCS frequencies （5 Hz, 10 Hz, 50 Hz, 70 Hz, and 100 Hz）. In the prefrontal cortex, a key area in consciousness circuits, we found significantly increased hemodynamic responses at 70 Hz and 100 Hz, and significantly different hemodynamic responses between 50 Hz and 70 Hz/100 Hz. In addition, the functional connectivity between prefrontal and occipital areas was significantly improved with SCS at 70 Hz. These results demonstrated that SCS modulates the hemodynamic responses and long-range connectivity in a frequency-specific manner （with 70 Hz apparently better）, perhaps by improving the cerebral blood volume and information transmission through the reticular formation-thalamus-cortex pathway.展开更多
Despite rapid developments in visual image-based road detection, robustly identifying road areas in visual images remains challenging due to issues like illumination changes and blurry images. To this end, LiDAR senso...Despite rapid developments in visual image-based road detection, robustly identifying road areas in visual images remains challenging due to issues like illumination changes and blurry images. To this end, LiDAR sensor data can be incorporated to improve the visual image-based road detection,because LiDAR data is less susceptible to visual noises. However,the main difficulty in introducing LiDAR information into visual image-based road detection is that LiDAR data and its extracted features do not share the same space with the visual data and visual features. Such gaps in spaces may limit the benefits of LiDAR information for road detection. To overcome this issue, we introduce a novel Progressive LiDAR adaptation-aided road detection(PLARD) approach to adapt LiDAR information into visual image-based road detection and improve detection performance. In PLARD, progressive LiDAR adaptation consists of two subsequent modules: 1) data space adaptation, which transforms the LiDAR data to the visual data space to align with the perspective view by applying altitude difference-based transformation; and 2) feature space adaptation, which adapts LiDAR features to visual features through a cascaded fusion structure. Comprehensive empirical studies on the well-known KITTI road detection benchmark demonstrate that PLARD takes advantage of both the visual and LiDAR information, achieving much more robust road detection even in challenging urban scenes. In particular, PLARD outperforms other state-of-theart road detection models and is currently top of the publicly accessible benchmark leader-board.展开更多
One of the most important open issues is that the classical conflict coefficient in D-S evidence theory （DST） cannot correctly determine the conflict degree between two pieces of evidence. This drawback greatly limi...One of the most important open issues is that the classical conflict coefficient in D-S evidence theory （DST） cannot correctly determine the conflict degree between two pieces of evidence. This drawback greatly limits the use of DST in real application systems. Early researches mainly focused on the improvement of Dempster’s rule of combination （DRC）. However, the current research shows it is very important to define new conflict coefficients to determine the conflict degree between two or more pieces of evidence. The evidential sources of information are considered in this work and the definition of a conflict measure function （CMF） is proposed for selecting some useful CMFs in the next fusion work when sources are available at each instant. Firstly, the definition and theorems of CMF are put forward. Secondly, some typical CMFs are extended and then new CMFs are put forward. Finally, experiments illustrate that the CMF based on Jousselme and its similar ones are the best suited ones.展开更多
基金supported by National Natural Science Foundation of China(Nos.61876212 and 1733007)Zhejiang Laboratory,China(No.2019NB0AB02)Hubei Province College Students Innovation and Entrepreneurship Training Program,China(No.S202010487058).
文摘A panoptic driving perception system is an essential part of autonomous driving.A high-precision and real-time perception system can assist the vehicle in making reasonable decisions while driving.We present a panoptic driving perception network(you only look once for panoptic(YOLOP))to perform traffic object detection,drivable area segmentation,and lane detection simultaneously.It is composed of one encoder for feature extraction and three decoders to handle the specific tasks.Our model performs extremely well on the challenging BDD100K dataset,achieving state-of-the-art on all three tasks in terms of accuracy and speed.Besides,we verify the effectiveness of our multi-task learning model for joint training via ablative studies.To our best knowledge,this is the first work that can process these three visual perception tasks simultaneously in real-time on an embedded device Jetson TX2(23 FPS),and maintain excellent accuracy.To facilitate further research,the source codes and pre-trained models are released at https://github.com/hustvl/YOLOP.
基金supported by the National Natural Science Foundation of China(61573282)the Foundation of the Education Department of Sichuan Province(16ZA0132)the Foundation of Robot Technology Used for Special Environment,Key Laboratory of Sichuan Province(13zxtk06)
文摘A novel robust fault tolerant controller is developed for the problem of attitude control of a quadrotor aircraft in the presence of actuator faults and wind gusts in this paper.Firstly, a dynamical system of the quadrotor taking into account aerodynamical effects induced by lateral wind and actuator faults is considered using the Newton-Euler approach. Then,based on active disturbance rejection control(ADRC), the fault tolerant controller is proposed to recover faulty system and reject perturbations. The developed controller takes wind gusts,actuator faults and measurement noises as total perturbations which are estimated by improved extended state observer(ESO)and compensated by nonlinear feedback control law. So, the developed robust fault tolerant controller can successfully accomplish the tracking of the desired output values. Finally, some simulation studies are given to illustrate the effectiveness of fault recovery of the proposed scheme and also its ability to attenuate external disturbances that are introduced from environmental causes such as wind gusts and measurement noises.
基金supported by the National Key R&D Program(No.2017YFB0404600)National Natural Science Foundation of China(61722502,61971045,61827901)Fundamental Research Funds for the Central Universities(3052019024).
文摘The quantum dot spectrometer,fabricated by integrating different quantum dots with an image sensor to reconstruct the target spectrum from spectral-coupled measurements,is an emerging and promising hyperspectrometry technology with high resolution and a compact size.The spectral resolution and spectral range of quantum dot spectrometers have been limited by the spectral variety of the available quantum dots and the robustness of algorithmic reconstruction.Moreover,the spectrometer integration of quantum dots also suffers from inherent photoluminescence emission and poor batch-to-batch repeatability.In this work,we developed nonemissive in situ fabricated MA_(3)Bi_(2)X_(9) and Cs_(2)SnX_(6)(MA=CH_(3)NH_(3);X=Cl,Br,I)perovskite-quantum-dot-embedded films(PQDFs)with precisely tunable transmittance spectra for quantum dot spectrometer applications.The resulting PQDFs contain in situ fabricated perovskite nanocrystals with homogenous dispersion in a polymeric matrix,giving them advantageous features such as high transmittance efficiency and good batch-to-batch repeatability.By integrating a filter array of 361 kinds of PQDFs with a silicon-based photodetector array,we successfully demonstrated the construction of a perovskite quantum dot spectrometer combined with a compressive-sensing-based total-variation optimization algorithm.A spectral resolution of ~1.6 nm was achieved in the broadband of 250-1000 nm.The performance of the perovskite quantum dot spectrometer is well beyond that of human eyes in terms of both the spectral range and spectral resolution.This advancement will not only pave the way for using quantum dot spectrometers for practical applications but also significantly impact the development of artificial intelligence products,clinical treatment equipment,scientific instruments,etc.
基金Supported by National Natural science Foundation-of P.R.Chlna （60474038, 60774022）, Specialized Research Fund for the Doctoral Program of Higher Educatlon（20060004002）
基金the National Natural Science Foundation of China(No.51134024/E0422)for the financial support
文摘Based on the stability and inequality of texture features between coal and rock,this study used the digital image analysis technique to propose a coal–rock interface detection method.By using gray level co-occurrence matrix,twenty-two texture features were extracted from the images of coal and rock.Data dimension of the feature space reduced to four by feature selection,which was according to a separability criterion based on inter-class mean difference and within-class scatter.The experimental results show that the optimized features were effective in improving the separability of the samples and reducing the time complexity of the algorithm.In the optimized low-dimensional feature space,the coal–rock classifer was set up using the fsher discriminant method.Using the 10-fold cross-validation technique,the performance of the classifer was evaluated,and an average recognition rate of 94.12%was obtained.The results of comparative experiments show that the identifcation performance of the proposed method was superior to the texture description method based on gray histogram and gradient histogram.
基金supported in part by the National Natural Science Foundation of China (61773414,61806076)Hubei Provincial Natural Science Foundation of China (2018CFB158)
文摘Motion planning is one of the most significant technologies for autonomous driving. To make motion planning models able to learn from the environment and to deal with emergency situations, a new motion planning framework called as"parallel planning" is proposed in this paper. In order to generate sufficient and various training samples, artificial traffic scenes are firstly constructed based on the knowledge from the reality.A deep planning model which combines a convolutional neural network(CNN) with the Long Short-Term Memory module(LSTM) is developed to make planning decisions in an end-toend mode. This model can learn from both real and artificial traffic scenes and imitate the driving style of human drivers.Moreover, a parallel deep reinforcement learning approach is also presented to improve the robustness of planning model and reduce the error rate. To handle emergency situations, a hybrid generative model including a variational auto-encoder(VAE) and a generative adversarial network(GAN) is utilized to learn from virtual emergencies generated in artificial traffic scenes. While an autonomous vehicle is moving, the hybrid generative model generates multiple video clips in parallel, which correspond to different potential emergency scenarios. Simultaneously, the deep planning model makes planning decisions for both virtual and current real scenes. The final planning decision is determined by analysis of real observations. Leveraging the parallel planning approach, the planner is able to make rational decisions without heavy calculation burden when an emergency occurs.
基金supported by the National Key Basic Research Program of China (Grant No.2013CB329201)the National Natural Science Foundation of China (Grant Nos.61171066 and 61471332)the State Key Laboratory of Robotics
文摘In underwater optical wireless communication(UOWC),a channel is characterized by abundant scattering/absorption effects and optical turbulence.Most previous studies on UOWC have been limited to scattering/absorption effects.However,experiments in the literature indicate that underwater optical turbulence(UOT)can cause severe degradation of UOWC performance.In this paper,we characterize an UOWC channel with both scattering/absorption and UOT taken into consideration,and a spatial diversity receiver scheme,say a singleinput–multiple-output(SIMO) scheme,based on a light-emitting-diode(LED) source and multiple detectors is proposed to mitigate deep fading.The Monte Carlo based statistical simulation method is introduced to evaluate the bit-error-rate performance of the system.It is shown that spatial diversity can effectively reduce channel fading and remarkably extend communication range.
基金the Northwest Polytechnical University (NWPU) Foundation for Fundamental Research(No.JC201117)the "E-Starts" Youth Foundation of School of Electronics and Information of Northwest Polytechnical University
文摘Threat assessment is one of the most important parts of the tactical decisions,and it has a very important influence on task allocation.An application of fuzzy cognitive map(FCM) for target threat assessment in the air combat is introduced.Considering the fact that the aircrafts participated in the cooperation may not have the same threat assessment mechanism,two different FCM models are established.Using the method of combination,the model of cooperative threat assessment in air combat of multi-aircrafts is established.Simulation results show preliminarily that the method is reasonable and effective.Using FCM for threat assessment is feasible.
基金partially supported by the National Key Research and Development Program of China (2016YFC1305904)the National Natural Science Foundation of China (81871438, 81901101, 61633018, 81571062, 81400890, 81871398)+10 种基金the Strategic Priority Research Program (B) of the Chinese Academy of Sciences (XDB32020200)the Beijing Municipal Science & Technology Commission (Z171100000117001, Z171100000117002)the Primary Research & Development Plan of Shandong Province (2017GGX10112)the Open Project Program of the National Laboratory of Pattern Recognition (NLPR) (201900021)Data collection and sharing for this project was funded by the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904)DOD ADNI (Department of Defense award number W81XWH-12-2-0012)funded by the National Institute on Agingthe National Institute of Biomedical Imaging and Bioengineeringgenerous contributions from Abb Vie, Alzheimer’s AssociationAlzheimer’s Drug Discovery FoundationThe Canadian Institutes of Health Research provide funds to support ADNI clinical sites in Canada。
文摘Hippocampal morphological change is one of the main hallmarks of Alzheimer’s disease(AD).However,whether hippocampal radiomic features are robust as predictors of progression from mild cognitive impairment(MCI)to AD dementia and whether these features provide any neurobiological foundation remains unclear.The primary aim of this study was to verify whether hippocampal radiomic features can serve as robust magnetic resonance imaging(MRI)markers for AD.Multivariate classifier-based support vector machine(SVM)analysis provided individual-level predictions for distinguishing AD patients(n=261)from normal controls(NCs;n=231)with an accuracy of 88.21%and intersite crossvalidation.Further analyses of a large,independent the Alzheimer’s Disease Neuroimaging Initiative(ADNI)dataset(n=1228)reinforced these findings.In MCI groups,a systemic analysis demonstrated that the identified features were significantly associated with clinical features(e.g.,apolipoprotein E(APOE)genotype,polygenic risk scores,cerebrospinal fluid(CSF)Ab,CSF Tau),and longitudinal changes in cognition ability;more importantly,the radiomic features had a consistently altered pattern with changes in the MMSE scores over 5 years of follow-up.These comprehensive results suggest that hippocampal radiomic features can serve as robust biomarkers for clinical application in AD/MCI,and further provide evidence for predicting whether an MCI subject would convert to AD based on the radiomics of the hippocampus.The results of this study are expected to have a substantial impact on the early diagnosis of AD/MCI.
基金Project(61203021)supported by the National Natural Science Foundation of ChinaProject(2011216011)supported by the Scientific and Technological Project of Liaoning Province,China+1 种基金Project(2013020024)supported by the Natural Science Foundation of Liaoning Province,ChinaProjects(LJQ2015061,LR2015034)supported by the Program for Liaoning Excellent Talents in University,China
文摘To overcome nonlinear and 6-DOF(degrees of freedom)under-actuated problems for the attitude and position of quadrotor UAVs,an adaptive backstepping sliding mode method for flight attitude of quadrotor UAVs is proposed,in which an adaptive law is designed to online estimate the parameter variations and the upper bound of external disturbances and the assessments is utilized to compensate the backstepping sliding mode control.In addition,the tracking error of the design method is shown to asymptotically converge to zero by using Lyapunov theory.Finally,based on the numerical simulation of quadrotor UAVs using the setting parameters,the results show that the proposed control approach can stabilize the attitude and has hover flight capabilities under the parameter perturbations and external disturbances.
基金Supported by National High Technology Project (863)(No. 2006AA02Z320)the National Natural Science Founda-tion of China (No.30700154, No.60874105)+1 种基金Zhejiang Natural Science Foundation (No.Y107458, RY1080422)the School Youth Found of Shanghai Jiaotong University
文摘Dempster-Shafer (DS) theory of evidence has been widely used in many data fusion ap- plication systems. However, how to determine basic probability assignment, which is the main and the first step in evidence theory, is still an open issue. In this paper, a new method to obtain Basic Probability Assignment (BPA) is proposed based on the similarity measure between generalized fuzzy numbers. In the proposed method, species model can be constructed by determination of the min, average and max value to construct a fuzzy number. Then, a new Radius Of Gravity (ROG) method to determine the similarity measure between generalized fuzzy numbers is used to calculate the BPA functions of each instance. Finally, the efficiency of the proposed method is illustrated by the classi- fication of Iris data.
基金This work was jointly supported by the National Natural Science Foundation of China(Nos.61803192,61973203,61966012,61773192,61603169,61773246,and 71533001)Thanks for the support of Shandong province colleges and universities youth innovation talent introduction and education program.
文摘To meet the multi-cooperation production demand of enterprises,the distributed permutation flow shop scheduling problem(DPFSP)has become the frontier research in the field of manufacturing systems.In this paper,we investigate the DPFSP by minimizing a makespan criterion under the constraint of sequence-dependent setup times.To solve DPFSPs,significant developments of some metaheuristic algorithms are necessary.In this context,a simple and effective improved iterated greedy(NIG)algorithm is proposed to minimize makespan in DPFSPs.According to the features of DPFSPs,a two-stage local search based on single job swapping and job block swapping within the key factory is designed in the proposed algorithm.We compare the proposed algorithm with state-of-the-art algorithms,including the iterative greedy algorithm(2019),iterative greedy proposed by Ruiz and Pan(2019),discrete differential evolution algorithm(2018),discrete artificial bee colony(2018),and artificial chemical reaction optimization(2017).Simulation results show that NIG outperforms the compared algorithms.
基金the State Key Development Program for Basic Research of China(2002CB312200)the National High Technology Research and Development Program of China(2007AA04Z193)
文摘An adaptive state feedback predictive control （SFPC） scheme and an expert control scheme are presented and applied to the temperature control of a 1200 kt·a^-1 delayed coking furnace, which is the key equipment for the delayed coking process. Adaptive SFPC is used to improve the performance of temperature control in normal operation. A simplified nonlinear model on the basis of first principles of the furnace is developed to obtain a state space model by linearization. Taking advantage of the nonlinear model, an online model adapting method is presented to accommodate the dynamic change of process characteristics because of tube coking and load changes. To compensate the large inverse response of outlet temperature resulting from the sudden increase of injected steam of a particular velocity to tubes, a monitoring method and an expert control scheme based on heat balance calculation are proposed. Industrial implementation shows the effectiveness and feasibility of the proposed control strategy.
基金supported by the National Natural Science Foundation of China(Grant Nos.62172325 and 32070663)the China Postdoctoral Science Foundation(Grant No.2020M673420)+2 种基金the Fundamental Research Funds for the Central Universities,Chinathe World-Class Universities(Disciplines)the Characteristic Development Guidance Funds for the Central Universities,China。
文摘Arabidopsis thaliana is an important and long-established model species for plant molecular biology,genetics,epigenetics,and genomics.However,the latest version of reference genome still contains a significant number of missing segments.Here,we reported a high-quality and almost complete Col-0 genome assembly with two gaps(named Col-XJTU)by combining the Oxford Nanopore Technologies ultra-long reads,Pacific Biosciences high-fidelity long reads,and Hi-C data.The total genome assembly size is 133,725,193 bp,introducing 14.6 Mb of novel sequences compared to the TAIR10.1 reference genome.All five chromosomes of the Col-XJTU assembly are highly accurate with consensus quality(QV)scores>60(ranging from 62 to 68),which are higher than those of the TAIR10.1 reference(ranging from 45 to 52).We completely resolved chromosome(Chr)3 and Chr5 in a telomere-to-telomere manner.Chr4 was completely resolved except the nucleolar organizing regions,which comprise long repetitive DNA fragments.The Chrl centromere(CEN1),reportedly around 9 Mb in length,is particularly challenging to assemble due to the presence of tens of thousands of CEN180 satellite repeats.Using the cutting-edge sequencing data and novel computational approaches,we assembled a 3.8-Mb-long CEN1 and a 3.5-Mb-long CEN2.We also investigated the structure and epigenetics of centromeres.Four clusters of CEN180 monomers were detected,and the centromere-specific histone H3-like protein(CENH3)exhibited a strong preference for CEN180 Cluster 3.Moreover,we observed hypomethylation patterns in CENH3-enriched regions.We believe that this high-quality genome assembly,Col-XJTU,would serve as a valuable reference to better understand the global pattern of centromeric polymorphisms,as well as the genetic and epigenetic features in plants.
基金supported by the National Natural Science Foundation of China(Grant Nos.41421001,42050101,and 42050105)。
文摘Since the beginning of the 21 st century,the geoscience research has been entering a significant transitional period with the establishment of a new knowledge system as the core and with the drive of big data as the means.It is a revolutionary leap in the research of geoscience knowledge discovery from the traditional encyclopedic discipline knowledge system to the computer-understandable and operable knowledge graph.Based on adopting the graph pattern of general knowledge representation,the geoscience knowledge graph expands the unique spatiotemporal features to the Geoscience knowledge,and integrates geoscience knowledge elements,such as map,text,and number,to establish an all-domain geoscience knowledge representation model.A federated,crowd intelligence-based collaborative method of constructing the geoscience knowledge graph is developed here,which realizes the construction of high-quality professional knowledge graph in collaboration with global geo-scientists.We also develop a method for constructing a dynamic knowledge graph of multi-modal geoscience data based on in-depth text analysis,which extracts geoscience knowledge from massive geoscience literature to construct the latest and most complete dynamic geoscience knowledge graph.A comprehensive and systematic geoscience knowledge graph can not only deepen the existing geoscience big data analysis,but also advance the construction of the high-precision geological time scale driven by big data,the compilation of intelligent maps driven by rules and data,and the geoscience knowledge evolution and reasoning analysis,among others.It will further expand the new directions of geoscience research driven by both data and knowledge,break new ground where geoscience,information science,and data science converge,realize the original innovation of the geoscience research and achieve major theoretical breakthroughs in the spatiotemporal big data research.
基金Shanghai Municipal of Science and Technology Project(No.20JC1419500)Foundation of National Facility for Translational Medicine(Shanghai)(No.TMSK-2020-129)+2 种基金Shanghai Pujiang Program(NO.20PJ 1408700)National Natural Science Foundation of China(No.62005007)the Fundamental Research Funds for the Central Universities(Beihang University).
文摘Speed and enhancement are the two most important metrics for anti-scattering light focusing by wavefront shaping(WS),which requires a spatial light modulator with a large number of modulation modes and a fast speed of response.Among the commercial modulators,the digital-micromirror device(DMD)is the sole solution providing millions of modulation modes and a pattern rate higher than 20 kHz.Thus,it has the potential to accelerate the process of anti-scattering light focusing with a high enhancement.Nevertheless,modulating light in a binary mode by the DMD restricts both the speed and enhancement seriously.Here,we propose a multi-pixel encoded DMD-based WS method by combining multiple micromirrors into a single modulation unit to overcome the drawbacks of binary modulation.In addition,to efficiently optimize the wavefront,we adopted separable natural evolution strategies(SNES),which could carry out a global search against a noisy environment.Compared with the state-of-the-art DMD-based WS method,the proposed method increased the speed of optimization and enhancement of focus by a factor of 179 and 16,respectively.In our demonstration,we achieved 10 foci with homogeneous brightness at a high speed and formed W-and S-shape patterns against the scattering medium.The experimental results suggest that the proposed method will pave a new avenue for WS in the applications of biomedical imaging,photon therapy,optogenetics,dynamic holographic display,etc.
基金supported by the National Key Research and Development Program of China (2017YFB1002502)the National Natural Science Foundation of China (81501550, 81600919, and 31771076)+5 种基金the Cross Training (Shipei) Project of High-Caliber Talents in Beijing Municipal Institutions (2017–2018)the Supplementary and Supportive Project for Teachers at Beijing Information Science and Technology University (2018–2020, 5029011103)the School Scientific Research Project at Beijing Information Science and Technology University (1825010) the Beijing Municipal Science and Technology Commission (Z161100000516165) the Shenzhen Peacock Plan (KQTD2015033016104926)the Guangdong Pearl River Talents Plan Innovative and Entrepreneurial Team grant (2016ZT06S220)
文摘Spinal cord stimulation （SCS） is a promising technique for treating disorders of consciousness （DOCs）. However, differences in the spatio-temporal responsiveness of the brain under varied SCS parameters remain unclear. In this pilot study, functional near-infrared spectroscopy was used to measure the hemodynamic responses of 10 DOC patients to different SCS frequencies （5 Hz, 10 Hz, 50 Hz, 70 Hz, and 100 Hz）. In the prefrontal cortex, a key area in consciousness circuits, we found significantly increased hemodynamic responses at 70 Hz and 100 Hz, and significantly different hemodynamic responses between 50 Hz and 70 Hz/100 Hz. In addition, the functional connectivity between prefrontal and occipital areas was significantly improved with SCS at 70 Hz. These results demonstrated that SCS modulates the hemodynamic responses and long-range connectivity in a frequency-specific manner （with 70 Hz apparently better）, perhaps by improving the cerebral blood volume and information transmission through the reticular formation-thalamus-cortex pathway.
基金supported by Australian Research Council Projects(FL-170100117,DP-180103424,IH-180100002)National Natural Science Foundation of China(NSFC)(61806062)
文摘Despite rapid developments in visual image-based road detection, robustly identifying road areas in visual images remains challenging due to issues like illumination changes and blurry images. To this end, LiDAR sensor data can be incorporated to improve the visual image-based road detection,because LiDAR data is less susceptible to visual noises. However,the main difficulty in introducing LiDAR information into visual image-based road detection is that LiDAR data and its extracted features do not share the same space with the visual data and visual features. Such gaps in spaces may limit the benefits of LiDAR information for road detection. To overcome this issue, we introduce a novel Progressive LiDAR adaptation-aided road detection(PLARD) approach to adapt LiDAR information into visual image-based road detection and improve detection performance. In PLARD, progressive LiDAR adaptation consists of two subsequent modules: 1) data space adaptation, which transforms the LiDAR data to the visual data space to align with the perspective view by applying altitude difference-based transformation; and 2) feature space adaptation, which adapts LiDAR features to visual features through a cascaded fusion structure. Comprehensive empirical studies on the well-known KITTI road detection benchmark demonstrate that PLARD takes advantage of both the visual and LiDAR information, achieving much more robust road detection even in challenging urban scenes. In particular, PLARD outperforms other state-of-theart road detection models and is currently top of the publicly accessible benchmark leader-board.
基金State Key Development Program for Basic Research of China (2007CB311006)Major Program of National Natural Science Foundation of China (6103200)+8 种基金National Natural Science Foundation of China (60572161, 60874105, 60904099)Excellent Ph.D. Paper Author Foundation of China (200443)Postdoctoral Science Foundation of China (20070421094)Program for New Century Excellent Talents in University (NCET-08-0345)Shanghai Rising-Star Program (09QA-1402900)Aeronautical Science Foundation of China (20090557004)"Chenxing" Scholarship Youth Found of Shanghai Jiaotong University (T241460612)Ministry of Education Key Laboratory of Intelligent Computing & Signal Processing (2009ICIP03)Research Fund of Shaanxi Key Laboratory of Electronic Information System Integration (200910A)
文摘One of the most important open issues is that the classical conflict coefficient in D-S evidence theory （DST） cannot correctly determine the conflict degree between two pieces of evidence. This drawback greatly limits the use of DST in real application systems. Early researches mainly focused on the improvement of Dempster’s rule of combination （DRC）. However, the current research shows it is very important to define new conflict coefficients to determine the conflict degree between two or more pieces of evidence. The evidential sources of information are considered in this work and the definition of a conflict measure function （CMF） is proposed for selecting some useful CMFs in the next fusion work when sources are available at each instant. Firstly, the definition and theorems of CMF are put forward. Secondly, some typical CMFs are extended and then new CMFs are put forward. Finally, experiments illustrate that the CMF based on Jousselme and its similar ones are the best suited ones.
