The unique long-range disordered atomic arrangement inherent in amorphous materials endows them with a range of superior properties,rendering them highly promising for applications in catalysis,medicine,and battery te...The unique long-range disordered atomic arrangement inherent in amorphous materials endows them with a range of superior properties,rendering them highly promising for applications in catalysis,medicine,and battery technology,among other fields.Since not all materials can be synthesized into an amorphous structure,the composition design of amorphous materials holds significant importance.Machine learning offers a valuable alternative to traditional“trial-anderror”methods by predicting properties through experimental data,thus providing efficient guidance in material design.In this study,we develop a machine learning workflow to predict the critical casting diameter,glass transition temperature,and Young's modulus for 45 ternary reported amorphous alloy systems.The predicted results have been organized into a database,enabling direct retrieval of predicted values based on compositional information.Furthermore,the applications of high glass forming ability region screening for specified system,multi-property target system screening and high glass forming ability region search through iteration are also demonstrated.By utilizing machine learning predictions,researchers can effectively narrow the experimental scope and expedite the exploration of compositions.展开更多
High-precision and real-time diagnosis of sucker rod pumping system(SRPS)is important for quickly mastering oil well operations.Deep learning-based method for classifying the dynamometer card(DC)of oil wells is an eff...High-precision and real-time diagnosis of sucker rod pumping system(SRPS)is important for quickly mastering oil well operations.Deep learning-based method for classifying the dynamometer card(DC)of oil wells is an efficient diagnosis method.However,the input of the DC as a two-dimensional image into the deep learning framework suffers from low feature utilization and high computational effort.Additionally,different SRPSs in an oil field have various system parameters,and the same SRPS generates different DCs at different moments.Thus,there is heterogeneity in field data,which can dramatically impair the diagnostic accuracy.To solve the above problems,a working condition recognition method based on 4-segment time-frequency signature matrix(4S-TFSM)and deep learning is presented in this paper.First,the 4-segment time-frequency signature(4S-TFS)method that can reduce the computing power requirements is proposed for feature extraction of DC data.Subsequently,the 4S-TFSM is constructed by relative normalization and matrix calculation to synthesize the features of multiple data and solve the problem of data heterogeneity.Finally,a convolutional neural network(CNN),one of the deep learning frameworks,is used to determine the functioning conditions based on the 4S-TFSM.Experiments on field data verify that the proposed diagnostic method based on 4S-TFSM and CNN(4S-TFSM-CNN)can significantly improve the accuracy of working condition recognition with lower computational cost.To the best of our knowledge,this is the first work to discuss the effect of data heterogeneity on the working condition recognition performance of SRPS.展开更多
All-solid-state batteries(ASSBs)are a class of safer and higher-energy-density materials compared to conventional devices,from which solid-state electrolytes(SSEs)are their essential components.To date,investigations ...All-solid-state batteries(ASSBs)are a class of safer and higher-energy-density materials compared to conventional devices,from which solid-state electrolytes(SSEs)are their essential components.To date,investigations to search for high ion-conducting solid-state electrolytes have attracted broad concern.However,obtaining SSEs with high ionic conductivity is challenging due to the complex structural information and the less-explored structure-performance relationship.To provide a solution to these challenges,developing a database containing typical SSEs from available experimental reports would be a new avenue to understand the structureperformance relationships and find out new design guidelines for reasonable SSEs.Herein,a dynamic experimental database containing>600 materials was developed in a wide range of temperatures(132.40–1261.60 K),including mono-and divalent cations(e.g.,Li^(+),Na^(+),K^(+),Ag^(+),Ca^(2+),Mg^(2+),and Zn^(2+))and various types of anions(e.g.,halide,hydride,sulfide,and oxide).Data-mining was conducted to explore the relationships among different variates(e.g.,transport ion,composition,activation energy,and conductivity).Overall,we expect that this database can provide essential guidelines for the design and development of high-performance SSEs in ASSB applications.This database is dynamically updated,which can be accessed via our open-source online system.展开更多
In recent years,deep learning-based signal recognition technology has gained attention and emerged as an important approach for safeguarding the electromagnetic environment.However,training deep learning-based classif...In recent years,deep learning-based signal recognition technology has gained attention and emerged as an important approach for safeguarding the electromagnetic environment.However,training deep learning-based classifiers on large signal datasets with redundant samples requires significant memory and high costs.This paper proposes a support databased core-set selection method(SD)for signal recognition,aiming to screen a representative subset that approximates the large signal dataset.Specifically,this subset can be identified by employing the labeled information during the early stages of model training,as some training samples are labeled as supporting data frequently.This support data is crucial for model training and can be found using a border sample selector.Simulation results demonstrate that the SD method minimizes the impact on model recognition performance while reducing the dataset size,and outperforms five other state-of-the-art core-set selection methods when the fraction of training sample kept is less than or equal to 0.3 on the RML2016.04C dataset or 0.5 on the RML22 dataset.The SD method is particularly helpful for signal recognition tasks with limited memory and computing resources.展开更多
The performance of deep learning(DL)networks has been increased by elaborating the network structures. However, the DL netowrks have many parameters, which have a lot of influence on the performance of the network. We...The performance of deep learning(DL)networks has been increased by elaborating the network structures. However, the DL netowrks have many parameters, which have a lot of influence on the performance of the network. We propose a genetic algorithm(GA) based deep belief neural network(DBNN) method for robot object recognition and grasping purpose. This method optimizes the parameters of the DBNN method, such as the number of hidden units, the number of epochs, and the learning rates, which would reduce the error rate and the network training time of object recognition. After recognizing objects, the robot performs the pick-andplace operations. We build a database of six objects for experimental purpose. Experimental results demonstrate that our method outperforms on the optimized robot object recognition and grasping tasks.展开更多
Expanding photovoltaic(PV)resources in rural-grid areas is an essential means to augment the share of solar energy in the energy landscape,aligning with the“carbon peaking and carbon neutrality”objectives.However,ru...Expanding photovoltaic(PV)resources in rural-grid areas is an essential means to augment the share of solar energy in the energy landscape,aligning with the“carbon peaking and carbon neutrality”objectives.However,rural power grids often lack digitalization;thus,the load distribution within these areas is not fully known.This hinders the calculation of the available PV capacity and deduction of node voltages.This study proposes a load-distribution modeling approach based on remote-sensing image recognition in pursuit of a scientific framework for developing distributed PV resources in rural grid areas.First,houses in remote-sensing images are accurately recognized using deep-learning techniques based on the YOLOv5 model.The distribution of the houses is then used to estimate the load distribution in the grid area.Next,equally spaced and clustered distribution models are used to adaptively determine the location of the nodes and load power in the distribution lines.Finally,by calculating the connectivity matrix of the nodes,a minimum spanning tree is extracted,the topology of the network is constructed,and the node parameters of the load-distribution model are calculated.The proposed scheme is implemented in a software package and its efficacy is demonstrated by analyzing typical remote-sensing images of rural grid areas.The results underscore the ability of the proposed approach to effectively discern the distribution-line structure and compute the node parameters,thereby offering vital support for determining PV access capability.展开更多
Due to the lack of large-scale emotion databases,it is hard to obtain comparable improvement in multimodal emotion recognition of the deep neural network by deep learning,which has made great progress in other areas.W...Due to the lack of large-scale emotion databases,it is hard to obtain comparable improvement in multimodal emotion recognition of the deep neural network by deep learning,which has made great progress in other areas.We use transfer learning to improve its performance with pretrained models on largescale data.Audio is encoded using deep speech recognition networks with 500 hours’speech and video is encoded using convolutional neural networks with over 110,000 images.The extracted audio and visual features are fed into Long Short-Term Memory to train models respectively.Logistic regression and ensemble method are performed in decision level fusion.The experiment results indicate that 1)audio features extracted from deep speech recognition networks achieve better performance than handcrafted audio features;2)the visual emotion recognition obtains better performance than audio emotion recognition;3)the ensemble method gets better performance than logistic regression and prior knowledge from micro-F1 value further improves the performance and robustness,achieving accuracy of 67.00%for“happy”,54.90%for“an?gry”,and 51.69%for“sad”.展开更多
In order to improve the recognition accuracy of similar weather scenarios(SWSs)in terminal area,a recognition model for SWS based on contrastive learning(SWS-CL)is proposed.Firstly,a data augmentation method is design...In order to improve the recognition accuracy of similar weather scenarios(SWSs)in terminal area,a recognition model for SWS based on contrastive learning(SWS-CL)is proposed.Firstly,a data augmentation method is designed to improve the number and quality of weather scenarios samples according to the characteristics of convective weather images.Secondly,in the pre-trained recognition model of SWS-CL,a loss function is formulated to minimize the distance between the anchor and positive samples,and maximize the distance between the anchor and the negative samples in the latent space.Finally,the pre-trained SWS-CL model is fine-tuned with labeled samples to improve the recognition accuracy of SWS.The comparative experiments on the weather images of Guangzhou terminal area show that the proposed data augmentation method can effectively improve the quality of weather image dataset,and the proposed SWS-CL model can achieve satisfactory recognition accuracy.It is also verified that the fine-tuned SWS-CL model has obvious advantages in datasets with sparse labels.展开更多
In speech recognition, acoustic modeling always requires tremendous transcribed samples, and the transcription becomes intensively time-consuming and costly. In order to aid this labor-intensive process, Active Learni...In speech recognition, acoustic modeling always requires tremendous transcribed samples, and the transcription becomes intensively time-consuming and costly. In order to aid this labor-intensive process, Active Learning （AL） is adopted for speech recognition, where only the most informative training samples are selected for manual annotation. In this paper, we propose a novel active learning method for Chinese acoustic modeling, the methods for initial training set selection based on Kullback-Leibler Divergence （KLD） and sample evaluation based on multi-level confusion networks are proposed and adopted in our active learning system, respectively. Our experiments show that our proposed method can achieve satisfying performances.展开更多
The accurate and intelligent identification of the working conditions of a sucker-rod pumping system is necessary. As onshore oil extraction gradually enters its mid-to late-stage, the cost required to train a deep le...The accurate and intelligent identification of the working conditions of a sucker-rod pumping system is necessary. As onshore oil extraction gradually enters its mid-to late-stage, the cost required to train a deep learning working condition recognition model for pumping wells by obtaining enough new working condition samples is expensive. For the few-shot problem and large calculation issues of new working conditions of oil wells, a working condition recognition method for pumping unit wells based on a 4-dimensional time-frequency signature (4D-TFS) and meta-learning convolutional shrinkage neural network (ML-CSNN) is proposed. First, the measured pumping unit well workup data are converted into 4D-TFS data, and the initial feature extraction task is performed while compressing the data. Subsequently, a convolutional shrinkage neural network (CSNN) with a specific structure that can ablate low-frequency features is designed to extract working conditions features. Finally, a meta-learning fine-tuning framework for learning the network parameters that are susceptible to task changes is merged into the CSNN to solve the few-shot issue. The results of the experiments demonstrate that the trained ML-CSNN has good recognition accuracy and generalization ability for few-shot working condition recognition. More specifically, in the case of lower computational complexity, only few-shot samples are needed to fine-tune the network parameters, and the model can be quickly adapted to new classes of well conditions.展开更多
Tactile perception plays a vital role for the human body and is also highly desired for smart prosthesis and advanced robots.Compared to active sensing devices,passive piezoelectric and triboelectric tactile sensors c...Tactile perception plays a vital role for the human body and is also highly desired for smart prosthesis and advanced robots.Compared to active sensing devices,passive piezoelectric and triboelectric tactile sensors consume less power,but lack the capability to resolve static stimuli.Here,we address this issue by utilizing the unique polarization chemistry of conjugated polymers for the first time and propose a new type of bioinspired,passive,and bio-friendly tactile sensors for resolving both static and dynamic stimuli.Specifically,to emulate the polarization process of natural sensory cells,conjugated polymers(including poly(3,4-ethylenedioxythiophen e):poly(styrenesulfonate),polyaniline,or polypyrrole)are controllably polarized into two opposite states to create artificial potential differences.The controllable and reversible polarization process of the conjugated polymers is fully in situ characterized.Then,a micro-structured ionic electrolyte is employed to imitate the natural ion channels and to encode external touch stimulations into the variation in potential difference outputs.Compared with the currently existing tactile sensing devices,the developed tactile sensors feature distinct characteristics including fully organic composition,high sensitivity(up to 773 mV N^(−1)),ultralow power consumption(nW),as well as superior bio-friendliness.As demonstrations,both single point tactile perception(surface texture perception and material property perception)and two-dimensional tactile recognitions(shape or profile perception)with high accuracy are successfully realized using self-defined machine learning algorithms.This tactile sensing concept innovation based on the polarization chemistry of conjugated polymers opens up a new path to create robotic tactile sensors and prosthetic electronic skins.展开更多
A group activity recognition algorithm is proposed to improve the recognition accuracy in video surveillance by using complex wavelet domain based Cayley-Klein metric learning.Non-sampled dual-tree complex wavelet pac...A group activity recognition algorithm is proposed to improve the recognition accuracy in video surveillance by using complex wavelet domain based Cayley-Klein metric learning.Non-sampled dual-tree complex wavelet packet transform(NS-DTCWPT)is used to decompose the human images in videos into multi-scale and multi-resolution.An improved local binary pattern(ILBP)and an inner-distance shape context(IDSC)combined with bag-of-words model is adopted to extract the decomposed high and low frequency coefficient features.The extracted coefficient features of the training samples are used to optimize Cayley-Klein metric matrix by solving a nonlinear optimization problem.The group activities in videos are recognized by using the method of feature extraction and Cayley-Klein metric learning.Experimental results on behave video set,group activity video set,and self-built video set show that the proposed algorithm has higher recognition accuracy than the existing algorithms.展开更多
Top-view fisheye cameras are widely used in personnel surveillance for their broad field of view,but their unique imaging characteristics pose challenges like distortion,complex scenes,scale variations,and small objec...Top-view fisheye cameras are widely used in personnel surveillance for their broad field of view,but their unique imaging characteristics pose challenges like distortion,complex scenes,scale variations,and small objects near image edges.To tackle these,we proposed peripheral focus you only look once(PF-YOLO),an enhanced YOLOv8n-based method.Firstly,we introduced a cutting-patch data augmentation strategy to mitigate the problem of insufficient small-object samples in various scenes.Secondly,to enhance the model's focus on small objects near the edges,we designed the peripheral focus loss,which uses dynamic focus coefficients to provide greater gradient gains for these objects,improving their regression accuracy.Finally,we designed the three dimensional(3D)spatial-channel coordinate attention C2f module,enhancing spatial and channel perception,suppressing noise,and improving personnel detection.Experimental results demonstrate that PF-YOLO achieves strong performance on the challenging events for person detection from overhead fisheye images(CEPDTOF)and in-the-wild events for people detection and tracking from overhead fisheye cameras(WEPDTOF)datasets.Compared to the original YOLOv8n model,PFYOLO achieves improvements on CEPDTOF with increases of 2.1%,1.7%and 2.9%in mean average precision 50(mAP 50),mAP 50-95,and tively.On WEPDTOF,PF-YOLO achieves substantial improvements with increases of 31.4%,14.9%,61.1%and 21.0%in 91.2%and 57.2%,respectively.展开更多
A learner's stages of L2 development are connected by his or her L1 and culture. It is, accordingly, of paramount impor-tance to understand the second language learners' culture and learning process and better...A learner's stages of L2 development are connected by his or her L1 and culture. It is, accordingly, of paramount impor-tance to understand the second language learners' culture and learning process and better assist them through this process in theway of teaching them English writing.This essay has demonstrated several elements which affect learners' English writing throughmy own experiences, such as different cultures, reading and correct recognition of writing, and the writing process.展开更多
Modulation recognition has been long investigated in the literature,however,the performance could be severely degraded in multipath fading channels especially for high-order Quadrature Amplitude Modulation(QAM)signals...Modulation recognition has been long investigated in the literature,however,the performance could be severely degraded in multipath fading channels especially for high-order Quadrature Amplitude Modulation(QAM)signals.This could be a critical problem in the broadband maritime wireless communications,where various propagation paths with large differences in the time of arrival are very likely to exist.Specifically,multiple paths may stem from the direct path,the reflection paths from the rough sea surface,and the refraction paths from the atmospheric duct,respectively.To address this issue,we propose a novel blind equalization-aided deep learning(DL)approach to recognize QAM signals in the presence of multipath propagation.The proposed approach consists of two modules:A blind equalization module and a subsequent DL network which employs the structure of ResNet.With predefined searching step-sizes for the blind equalization algorithm,which are designed according to the set of modulation formats of interest,the DL network is trained and tested over various multipath channel parameter settings.It is shown that as compared to the conventional DL approaches without equalization,the proposed method can achieve an improvement in the recognition accuracy up to 30%in severe multipath scenarios,especially in the high SNR regime.Moreover,it efficiently reduces the number of training data that is required.展开更多
The insulation aging of cross-linked polyethylene(XLPE)cables is the main reason for the reduction in cable life.There is currently a lack of rapid and effective methods for detecting cable insulation defects in power...The insulation aging of cross-linked polyethylene(XLPE)cables is the main reason for the reduction in cable life.There is currently a lack of rapid and effective methods for detecting cable insulation defects in power-related sectors.To this end,this paper presents a method for identifying insulation defects in XLPE cables based on deep learning algorithms.First,the principle of the harmonic method for detecting cable insulation defects is introduced.Second,the ANSYS software is used to simulate the cable insulation layer containing bubbles,protrusions,and water tree defects,and the effects of each type of defect on the magnetic field strength and eddy loss current of the cable insulation layer are analyzed.Then,a total of 10 characteristic quantities of the total harmonic content and 2nd to 10th harmonic currents are constructed to establish a database of cable insulation defects.Finally,the deep learning algorithm,long short-term memory(LSTM),is used to accurately identify the types of insulation defects in cables.The results indicate that the LSTM algorithm can effectively diagnose and identify insulation defects in cables with an accuracy of 95.83%.展开更多
The history and current status of materials data activities from handbook to database are reviewed, with introduction to some important products. Through an example of prediction of interfacial thermal resistance base...The history and current status of materials data activities from handbook to database are reviewed, with introduction to some important products. Through an example of prediction of interfacial thermal resistance based on data and data science methods, we show the advantages and potential of material informatics to study material issues which are too complicated or time consuming for conventional theoretical and experimental methods. Materials big data is the fundamental of material informatics. The challenges and strategy to construct materials big data are discussed, and some solutions are proposed as the results of our experiences to construct National Institute for Materials Science（NIMS） materials databases.展开更多
Offline Urdu Nastaleeq text recognition has long been a serious problem due to its very cursive nature. In order to get rid of the character segmentation problems, many researchers are shifting focus towards segmentat...Offline Urdu Nastaleeq text recognition has long been a serious problem due to its very cursive nature. In order to get rid of the character segmentation problems, many researchers are shifting focus towards segmentation free ligature based recognition approaches. Majority of the prevalent ligature based recognition systems heavily rely on hand-engineered feature extraction techniques. However, such techniques are more error prone and may often lead to a loss of useful information that might hardly be captured later by any manual features. Most of the prevalent Urdu Nastaleeq test recognition was trained and tested on small sets. This paper proposes the use of stacked denoising autoencoder for automatic feature extraction directly from raw pixel values of ligature images. Such deep learning networks have not been applied for the recognition of Urdu text thus far. Different stacked denoising autoencoders have been trained on 178573 ligatures with 3732 classes from un-degraded(noise free) UPTI(Urdu Printed Text Image) data set. Subsequently, trained networks are validated and tested on degraded versions of UPTI data set. The experimental results demonstrate accuracies in range of 93% to 96% which are better than the existing Urdu OCR systems for such large dataset of ligatures.展开更多
We present a ghost handwritten digit recognition method for the unknown handwritten digits based on ghost imaging(GI)with deep neural network,where a few detection signals from the bucket detector,generated by the cos...We present a ghost handwritten digit recognition method for the unknown handwritten digits based on ghost imaging(GI)with deep neural network,where a few detection signals from the bucket detector,generated by the cosine transform speckle,are used as the characteristic information and the input of the designed deep neural network(DNN),and the output of the DNN is the classification.The results show that the proposed scheme has a higher recognition accuracy(as high as 98%for the simulations,and 91%for the experiments)with a smaller sampling ratio(say 12.76%).With the increase of the sampling ratio,the recognition accuracy is enhanced.Compared with the traditional recognition scheme using the same DNN structure,the proposed scheme has slightly better performance with a lower complexity and non-locality property.The proposed scheme provides a promising way for remote sensing.展开更多
A large database is desired for machine learning(ML) technology to make accurate predictions of materials physicochemical properties based on their molecular structure.When a large database is not available,the develo...A large database is desired for machine learning(ML) technology to make accurate predictions of materials physicochemical properties based on their molecular structure.When a large database is not available,the development of proper featurization method based on physicochemical nature of target proprieties can improve the predictive power of ML models with a smaller database.In this work,we show that two new featurization methods,volume occupation spatial matrix and heat contribution spatial matrix,can improve the accuracy in predicting energetic materials' crystal density(ρ_(crystal)) and solid phase enthalpy of formation(H_(f,solid)) using a database containing 451 energetic molecules.Their mean absolute errors are reduced from 0.048 g/cm~3 and 24.67 kcal/mol to 0.035 g/cm~3 and 9.66 kcal/mol,respectively.By leave-one-out-cross-validation,the newly developed ML models can be used to determine the performance of most kinds of energetic materials except cubanes.Our ML models are applied to predict ρ_(crystal) and H_(f,solid) of CHON-based molecules of the 150 million sized PubChem database,and screened out 56 candidates with competitive detonation performance and reasonable chemical structures.With further improvement in future,spatial matrices have the potential of becoming multifunctional ML simulation tools that could provide even better predictions in wider fields of materials science.展开更多
基金Project supported by funding from the National Natural Science Foundation of China(Grant Nos.52172258,52473227 and 52171150)the Strategic Priority Research Program of Chinese Academy of Sciences(Grant No.XDB0500200)。
文摘The unique long-range disordered atomic arrangement inherent in amorphous materials endows them with a range of superior properties,rendering them highly promising for applications in catalysis,medicine,and battery technology,among other fields.Since not all materials can be synthesized into an amorphous structure,the composition design of amorphous materials holds significant importance.Machine learning offers a valuable alternative to traditional“trial-anderror”methods by predicting properties through experimental data,thus providing efficient guidance in material design.In this study,we develop a machine learning workflow to predict the critical casting diameter,glass transition temperature,and Young's modulus for 45 ternary reported amorphous alloy systems.The predicted results have been organized into a database,enabling direct retrieval of predicted values based on compositional information.Furthermore,the applications of high glass forming ability region screening for specified system,multi-property target system screening and high glass forming ability region search through iteration are also demonstrated.By utilizing machine learning predictions,researchers can effectively narrow the experimental scope and expedite the exploration of compositions.
基金We would like to thank the associate editor and the reviewers for their constructive comments.This work was supported in part by the National Natural Science Foundation of China under Grant 62203234in part by the State Key Laboratory of Robotics of China under Grant 2023-Z03+1 种基金in part by the Natural Science Foundation of Liaoning Province under Grant 2023-BS-025in part by the Research Program of Liaoning Liaohe Laboratory under Grant LLL23ZZ-02-02.
文摘High-precision and real-time diagnosis of sucker rod pumping system(SRPS)is important for quickly mastering oil well operations.Deep learning-based method for classifying the dynamometer card(DC)of oil wells is an efficient diagnosis method.However,the input of the DC as a two-dimensional image into the deep learning framework suffers from low feature utilization and high computational effort.Additionally,different SRPSs in an oil field have various system parameters,and the same SRPS generates different DCs at different moments.Thus,there is heterogeneity in field data,which can dramatically impair the diagnostic accuracy.To solve the above problems,a working condition recognition method based on 4-segment time-frequency signature matrix(4S-TFSM)and deep learning is presented in this paper.First,the 4-segment time-frequency signature(4S-TFS)method that can reduce the computing power requirements is proposed for feature extraction of DC data.Subsequently,the 4S-TFSM is constructed by relative normalization and matrix calculation to synthesize the features of multiple data and solve the problem of data heterogeneity.Finally,a convolutional neural network(CNN),one of the deep learning frameworks,is used to determine the functioning conditions based on the 4S-TFSM.Experiments on field data verify that the proposed diagnostic method based on 4S-TFSM and CNN(4S-TFSM-CNN)can significantly improve the accuracy of working condition recognition with lower computational cost.To the best of our knowledge,this is the first work to discuss the effect of data heterogeneity on the working condition recognition performance of SRPS.
基金supported by the Ensemble Grant for Early Career Researchers 2022 and the 2023 Ensemble Continuation Grant of Tohoku University,the Hirose Foundation,the Iwatani Naoji Foundation,and the AIMR Fusion Research Grantsupported by JSPS KAKENHI Nos.JP23K13599,JP23K13703,JP22H01803,and JP18H05513+2 种基金the Center for Computational Materials Science,Institute for Materials Research,Tohoku University for the use of MASAMUNEIMR(Nos.202212-SCKXX0204 and 202208-SCKXX-0212)the Institute for Solid State Physics(ISSP)at the University of Tokyo for the use of their supercomputersthe China Scholarship Council(CSC)fund to pursue studies in Japan.
文摘All-solid-state batteries(ASSBs)are a class of safer and higher-energy-density materials compared to conventional devices,from which solid-state electrolytes(SSEs)are their essential components.To date,investigations to search for high ion-conducting solid-state electrolytes have attracted broad concern.However,obtaining SSEs with high ionic conductivity is challenging due to the complex structural information and the less-explored structure-performance relationship.To provide a solution to these challenges,developing a database containing typical SSEs from available experimental reports would be a new avenue to understand the structureperformance relationships and find out new design guidelines for reasonable SSEs.Herein,a dynamic experimental database containing>600 materials was developed in a wide range of temperatures(132.40–1261.60 K),including mono-and divalent cations(e.g.,Li^(+),Na^(+),K^(+),Ag^(+),Ca^(2+),Mg^(2+),and Zn^(2+))and various types of anions(e.g.,halide,hydride,sulfide,and oxide).Data-mining was conducted to explore the relationships among different variates(e.g.,transport ion,composition,activation energy,and conductivity).Overall,we expect that this database can provide essential guidelines for the design and development of high-performance SSEs in ASSB applications.This database is dynamically updated,which can be accessed via our open-source online system.
基金supported by National Natural Science Foundation of China(62371098)Natural Science Foundation of Sichuan Province(2023NSFSC1422)+1 种基金National Key Research and Development Program of China(2021YFB2900404)Central Universities of South west Minzu University(ZYN2022032).
文摘In recent years,deep learning-based signal recognition technology has gained attention and emerged as an important approach for safeguarding the electromagnetic environment.However,training deep learning-based classifiers on large signal datasets with redundant samples requires significant memory and high costs.This paper proposes a support databased core-set selection method(SD)for signal recognition,aiming to screen a representative subset that approximates the large signal dataset.Specifically,this subset can be identified by employing the labeled information during the early stages of model training,as some training samples are labeled as supporting data frequently.This support data is crucial for model training and can be found using a border sample selector.Simulation results demonstrate that the SD method minimizes the impact on model recognition performance while reducing the dataset size,and outperforms five other state-of-the-art core-set selection methods when the fraction of training sample kept is less than or equal to 0.3 on the RML2016.04C dataset or 0.5 on the RML22 dataset.The SD method is particularly helpful for signal recognition tasks with limited memory and computing resources.
文摘The performance of deep learning(DL)networks has been increased by elaborating the network structures. However, the DL netowrks have many parameters, which have a lot of influence on the performance of the network. We propose a genetic algorithm(GA) based deep belief neural network(DBNN) method for robot object recognition and grasping purpose. This method optimizes the parameters of the DBNN method, such as the number of hidden units, the number of epochs, and the learning rates, which would reduce the error rate and the network training time of object recognition. After recognizing objects, the robot performs the pick-andplace operations. We build a database of six objects for experimental purpose. Experimental results demonstrate that our method outperforms on the optimized robot object recognition and grasping tasks.
基金supported by the State Grid Science&Technology Project of China(5400-202224153A-1-1-ZN).
文摘Expanding photovoltaic(PV)resources in rural-grid areas is an essential means to augment the share of solar energy in the energy landscape,aligning with the“carbon peaking and carbon neutrality”objectives.However,rural power grids often lack digitalization;thus,the load distribution within these areas is not fully known.This hinders the calculation of the available PV capacity and deduction of node voltages.This study proposes a load-distribution modeling approach based on remote-sensing image recognition in pursuit of a scientific framework for developing distributed PV resources in rural grid areas.First,houses in remote-sensing images are accurately recognized using deep-learning techniques based on the YOLOv5 model.The distribution of the houses is then used to estimate the load distribution in the grid area.Next,equally spaced and clustered distribution models are used to adaptively determine the location of the nodes and load power in the distribution lines.Finally,by calculating the connectivity matrix of the nodes,a minimum spanning tree is extracted,the topology of the network is constructed,and the node parameters of the load-distribution model are calculated.The proposed scheme is implemented in a software package and its efficacy is demonstrated by analyzing typical remote-sensing images of rural grid areas.The results underscore the ability of the proposed approach to effectively discern the distribution-line structure and compute the node parameters,thereby offering vital support for determining PV access capability.
文摘Due to the lack of large-scale emotion databases,it is hard to obtain comparable improvement in multimodal emotion recognition of the deep neural network by deep learning,which has made great progress in other areas.We use transfer learning to improve its performance with pretrained models on largescale data.Audio is encoded using deep speech recognition networks with 500 hours’speech and video is encoded using convolutional neural networks with over 110,000 images.The extracted audio and visual features are fed into Long Short-Term Memory to train models respectively.Logistic regression and ensemble method are performed in decision level fusion.The experiment results indicate that 1)audio features extracted from deep speech recognition networks achieve better performance than handcrafted audio features;2)the visual emotion recognition obtains better performance than audio emotion recognition;3)the ensemble method gets better performance than logistic regression and prior knowledge from micro-F1 value further improves the performance and robustness,achieving accuracy of 67.00%for“happy”,54.90%for“an?gry”,and 51.69%for“sad”.
基金supported by the Fundamental Research Funds for the Central Universities(NOS.NS2019054,NS2020045)。
文摘In order to improve the recognition accuracy of similar weather scenarios(SWSs)in terminal area,a recognition model for SWS based on contrastive learning(SWS-CL)is proposed.Firstly,a data augmentation method is designed to improve the number and quality of weather scenarios samples according to the characteristics of convective weather images.Secondly,in the pre-trained recognition model of SWS-CL,a loss function is formulated to minimize the distance between the anchor and positive samples,and maximize the distance between the anchor and the negative samples in the latent space.Finally,the pre-trained SWS-CL model is fine-tuned with labeled samples to improve the recognition accuracy of SWS.The comparative experiments on the weather images of Guangzhou terminal area show that the proposed data augmentation method can effectively improve the quality of weather image dataset,and the proposed SWS-CL model can achieve satisfactory recognition accuracy.It is also verified that the fine-tuned SWS-CL model has obvious advantages in datasets with sparse labels.
基金Acknowledgements This study is supported by the National Natural Science Foundation of China （60705019）, the National High-Tech Research and Development Plan of China （ 2006AA010102 and 2007AA01Z417）, the NOKIA project, and the 111 Project of China under Grant No. 1308004.
文摘In speech recognition, acoustic modeling always requires tremendous transcribed samples, and the transcription becomes intensively time-consuming and costly. In order to aid this labor-intensive process, Active Learning （AL） is adopted for speech recognition, where only the most informative training samples are selected for manual annotation. In this paper, we propose a novel active learning method for Chinese acoustic modeling, the methods for initial training set selection based on Kullback-Leibler Divergence （KLD） and sample evaluation based on multi-level confusion networks are proposed and adopted in our active learning system, respectively. Our experiments show that our proposed method can achieve satisfying performances.
基金supported in part by the National Natural Science Foundation of China under Grant U1908212,62203432 and 92067205in part by the State Key Laboratory of Robotics of China under Grant 2023-Z03 and 2023-Z15in part by the Natural Science Foundation of Liaoning Province under Grant 2020-KF-11-02.
文摘The accurate and intelligent identification of the working conditions of a sucker-rod pumping system is necessary. As onshore oil extraction gradually enters its mid-to late-stage, the cost required to train a deep learning working condition recognition model for pumping wells by obtaining enough new working condition samples is expensive. For the few-shot problem and large calculation issues of new working conditions of oil wells, a working condition recognition method for pumping unit wells based on a 4-dimensional time-frequency signature (4D-TFS) and meta-learning convolutional shrinkage neural network (ML-CSNN) is proposed. First, the measured pumping unit well workup data are converted into 4D-TFS data, and the initial feature extraction task is performed while compressing the data. Subsequently, a convolutional shrinkage neural network (CSNN) with a specific structure that can ablate low-frequency features is designed to extract working conditions features. Finally, a meta-learning fine-tuning framework for learning the network parameters that are susceptible to task changes is merged into the CSNN to solve the few-shot issue. The results of the experiments demonstrate that the trained ML-CSNN has good recognition accuracy and generalization ability for few-shot working condition recognition. More specifically, in the case of lower computational complexity, only few-shot samples are needed to fine-tune the network parameters, and the model can be quickly adapted to new classes of well conditions.
基金financially supported by the Sichuan Science and Technology Program(2022YFS0025 and 2024YFFK0133)supported by the“Fundamental Research Funds for the Central Universities of China.”。
文摘Tactile perception plays a vital role for the human body and is also highly desired for smart prosthesis and advanced robots.Compared to active sensing devices,passive piezoelectric and triboelectric tactile sensors consume less power,but lack the capability to resolve static stimuli.Here,we address this issue by utilizing the unique polarization chemistry of conjugated polymers for the first time and propose a new type of bioinspired,passive,and bio-friendly tactile sensors for resolving both static and dynamic stimuli.Specifically,to emulate the polarization process of natural sensory cells,conjugated polymers(including poly(3,4-ethylenedioxythiophen e):poly(styrenesulfonate),polyaniline,or polypyrrole)are controllably polarized into two opposite states to create artificial potential differences.The controllable and reversible polarization process of the conjugated polymers is fully in situ characterized.Then,a micro-structured ionic electrolyte is employed to imitate the natural ion channels and to encode external touch stimulations into the variation in potential difference outputs.Compared with the currently existing tactile sensing devices,the developed tactile sensors feature distinct characteristics including fully organic composition,high sensitivity(up to 773 mV N^(−1)),ultralow power consumption(nW),as well as superior bio-friendliness.As demonstrations,both single point tactile perception(surface texture perception and material property perception)and two-dimensional tactile recognitions(shape or profile perception)with high accuracy are successfully realized using self-defined machine learning algorithms.This tactile sensing concept innovation based on the polarization chemistry of conjugated polymers opens up a new path to create robotic tactile sensors and prosthetic electronic skins.
基金Supported by the National Natural Science Foundation of China(61672032,61401001)the Natural Science Foundation of Anhui Province(1408085MF121)the Opening Foundation of Anhui Key Laboratory of Polarization Imaging Detection Technology(2016-KFKT-003)
文摘A group activity recognition algorithm is proposed to improve the recognition accuracy in video surveillance by using complex wavelet domain based Cayley-Klein metric learning.Non-sampled dual-tree complex wavelet packet transform(NS-DTCWPT)is used to decompose the human images in videos into multi-scale and multi-resolution.An improved local binary pattern(ILBP)and an inner-distance shape context(IDSC)combined with bag-of-words model is adopted to extract the decomposed high and low frequency coefficient features.The extracted coefficient features of the training samples are used to optimize Cayley-Klein metric matrix by solving a nonlinear optimization problem.The group activities in videos are recognized by using the method of feature extraction and Cayley-Klein metric learning.Experimental results on behave video set,group activity video set,and self-built video set show that the proposed algorithm has higher recognition accuracy than the existing algorithms.
基金supported by National Natural Science Foundation of China(Nos.62171042,62102033,U24A20331)the R&D Program of Beijing Municipal Education Commission(No.KZ202211417048)+2 种基金the Project of Construction and Support for High-Level Innovative Teams of Beijing Municipal Institutions(No.BPHR20220121)Beijing Natural Science Foundation(Nos.4232026,4242020)the Academic Research Projects of Beijing Union University(Nos.ZKZD202302,ZK20202403)。
文摘Top-view fisheye cameras are widely used in personnel surveillance for their broad field of view,but their unique imaging characteristics pose challenges like distortion,complex scenes,scale variations,and small objects near image edges.To tackle these,we proposed peripheral focus you only look once(PF-YOLO),an enhanced YOLOv8n-based method.Firstly,we introduced a cutting-patch data augmentation strategy to mitigate the problem of insufficient small-object samples in various scenes.Secondly,to enhance the model's focus on small objects near the edges,we designed the peripheral focus loss,which uses dynamic focus coefficients to provide greater gradient gains for these objects,improving their regression accuracy.Finally,we designed the three dimensional(3D)spatial-channel coordinate attention C2f module,enhancing spatial and channel perception,suppressing noise,and improving personnel detection.Experimental results demonstrate that PF-YOLO achieves strong performance on the challenging events for person detection from overhead fisheye images(CEPDTOF)and in-the-wild events for people detection and tracking from overhead fisheye cameras(WEPDTOF)datasets.Compared to the original YOLOv8n model,PFYOLO achieves improvements on CEPDTOF with increases of 2.1%,1.7%and 2.9%in mean average precision 50(mAP 50),mAP 50-95,and tively.On WEPDTOF,PF-YOLO achieves substantial improvements with increases of 31.4%,14.9%,61.1%and 21.0%in 91.2%and 57.2%,respectively.
文摘A learner's stages of L2 development are connected by his or her L1 and culture. It is, accordingly, of paramount impor-tance to understand the second language learners' culture and learning process and better assist them through this process in theway of teaching them English writing.This essay has demonstrated several elements which affect learners' English writing throughmy own experiences, such as different cultures, reading and correct recognition of writing, and the writing process.
基金the National Natural Science Foundation of China under Grant 61771264,61801114,61501264,61771286the Nantong University-Nantong Joint Research Center for Intelligent Information Technology under Grant No.KFKT2017B01,KFKT2017A04the Natural Science Foundation of Jiangsu Province under Grant BK20170688.
文摘Modulation recognition has been long investigated in the literature,however,the performance could be severely degraded in multipath fading channels especially for high-order Quadrature Amplitude Modulation(QAM)signals.This could be a critical problem in the broadband maritime wireless communications,where various propagation paths with large differences in the time of arrival are very likely to exist.Specifically,multiple paths may stem from the direct path,the reflection paths from the rough sea surface,and the refraction paths from the atmospheric duct,respectively.To address this issue,we propose a novel blind equalization-aided deep learning(DL)approach to recognize QAM signals in the presence of multipath propagation.The proposed approach consists of two modules:A blind equalization module and a subsequent DL network which employs the structure of ResNet.With predefined searching step-sizes for the blind equalization algorithm,which are designed according to the set of modulation formats of interest,the DL network is trained and tested over various multipath channel parameter settings.It is shown that as compared to the conventional DL approaches without equalization,the proposed method can achieve an improvement in the recognition accuracy up to 30%in severe multipath scenarios,especially in the high SNR regime.Moreover,it efficiently reduces the number of training data that is required.
基金supported by the technology project of the State Grid Shanxi Electric Power Company.The name of the project is“Research and Application of Cable electrification diagnosis Technology based on Harmonic method”(5205C02000GL).
文摘The insulation aging of cross-linked polyethylene(XLPE)cables is the main reason for the reduction in cable life.There is currently a lack of rapid and effective methods for detecting cable insulation defects in power-related sectors.To this end,this paper presents a method for identifying insulation defects in XLPE cables based on deep learning algorithms.First,the principle of the harmonic method for detecting cable insulation defects is introduced.Second,the ANSYS software is used to simulate the cable insulation layer containing bubbles,protrusions,and water tree defects,and the effects of each type of defect on the magnetic field strength and eddy loss current of the cable insulation layer are analyzed.Then,a total of 10 characteristic quantities of the total harmonic content and 2nd to 10th harmonic currents are constructed to establish a database of cable insulation defects.Finally,the deep learning algorithm,long short-term memory(LSTM),is used to accurately identify the types of insulation defects in cables.The results indicate that the LSTM algorithm can effectively diagnose and identify insulation defects in cables with an accuracy of 95.83%.
基金Project supported by “Materials Research by Information Integration” Initiative(MI2I) project of the Support Program for Starting Up Innovation Hub from Japan Science and Technology Agency(JST)
文摘The history and current status of materials data activities from handbook to database are reviewed, with introduction to some important products. Through an example of prediction of interfacial thermal resistance based on data and data science methods, we show the advantages and potential of material informatics to study material issues which are too complicated or time consuming for conventional theoretical and experimental methods. Materials big data is the fundamental of material informatics. The challenges and strategy to construct materials big data are discussed, and some solutions are proposed as the results of our experiences to construct National Institute for Materials Science（NIMS） materials databases.
基金National Natural Science Foundation of China (Project No. 61273365)111 Project (No. B08004) are gratefully acknowledged
文摘Offline Urdu Nastaleeq text recognition has long been a serious problem due to its very cursive nature. In order to get rid of the character segmentation problems, many researchers are shifting focus towards segmentation free ligature based recognition approaches. Majority of the prevalent ligature based recognition systems heavily rely on hand-engineered feature extraction techniques. However, such techniques are more error prone and may often lead to a loss of useful information that might hardly be captured later by any manual features. Most of the prevalent Urdu Nastaleeq test recognition was trained and tested on small sets. This paper proposes the use of stacked denoising autoencoder for automatic feature extraction directly from raw pixel values of ligature images. Such deep learning networks have not been applied for the recognition of Urdu text thus far. Different stacked denoising autoencoders have been trained on 178573 ligatures with 3732 classes from un-degraded(noise free) UPTI(Urdu Printed Text Image) data set. Subsequently, trained networks are validated and tested on degraded versions of UPTI data set. The experimental results demonstrate accuracies in range of 93% to 96% which are better than the existing Urdu OCR systems for such large dataset of ligatures.
基金the National Natural Science Foundation of China(Grant Nos.61871234 and 11847062).
文摘We present a ghost handwritten digit recognition method for the unknown handwritten digits based on ghost imaging(GI)with deep neural network,where a few detection signals from the bucket detector,generated by the cosine transform speckle,are used as the characteristic information and the input of the designed deep neural network(DNN),and the output of the DNN is the classification.The results show that the proposed scheme has a higher recognition accuracy(as high as 98%for the simulations,and 91%for the experiments)with a smaller sampling ratio(say 12.76%).With the increase of the sampling ratio,the recognition accuracy is enhanced.Compared with the traditional recognition scheme using the same DNN structure,the proposed scheme has slightly better performance with a lower complexity and non-locality property.The proposed scheme provides a promising way for remote sensing.
基金support from the Ministry of Education(MOE) Singapore Tier 1 (RG8/20)。
文摘A large database is desired for machine learning(ML) technology to make accurate predictions of materials physicochemical properties based on their molecular structure.When a large database is not available,the development of proper featurization method based on physicochemical nature of target proprieties can improve the predictive power of ML models with a smaller database.In this work,we show that two new featurization methods,volume occupation spatial matrix and heat contribution spatial matrix,can improve the accuracy in predicting energetic materials' crystal density(ρ_(crystal)) and solid phase enthalpy of formation(H_(f,solid)) using a database containing 451 energetic molecules.Their mean absolute errors are reduced from 0.048 g/cm~3 and 24.67 kcal/mol to 0.035 g/cm~3 and 9.66 kcal/mol,respectively.By leave-one-out-cross-validation,the newly developed ML models can be used to determine the performance of most kinds of energetic materials except cubanes.Our ML models are applied to predict ρ_(crystal) and H_(f,solid) of CHON-based molecules of the 150 million sized PubChem database,and screened out 56 candidates with competitive detonation performance and reasonable chemical structures.With further improvement in future,spatial matrices have the potential of becoming multifunctional ML simulation tools that could provide even better predictions in wider fields of materials science.
