In order to effectively conduct emotion recognition from spontaneous, non-prototypical and unsegmented speech so as to create a more natural human-machine interaction; a novel speech emotion recognition algorithm base...In order to effectively conduct emotion recognition from spontaneous, non-prototypical and unsegmented speech so as to create a more natural human-machine interaction; a novel speech emotion recognition algorithm based on the combination of the emotional data field （EDF） and the ant colony search （ACS） strategy, called the EDF-ACS algorithm, is proposed. More specifically, the inter- relationship among the turn-based acoustic feature vectors of different labels are established by using the potential function in the EDF. To perform the spontaneous speech emotion recognition, the artificial colony is used to mimic the turn- based acoustic feature vectors. Then, the canonical ACS strategy is used to investigate the movement direction of each artificial ant in the EDF, which is regarded as the emotional label of the corresponding turn-based acoustic feature vector. The proposed EDF-ACS algorithm is evaluated on the continueous audio）＇visual emotion challenge （AVEC） 2012 dataset, which contains the spontaneous, non-prototypical and unsegmented speech emotion data. The experimental results show that the proposed EDF-ACS algorithm outperforms the existing state-of-the-art algorithm in turn-based speech emotion recognition.展开更多
Target detection is always an important application in hyperspectral image processing field. In this paper, a spectral-spatial target detection algorithm for hyperspectral data is proposed.The spatial feature and spec...Target detection is always an important application in hyperspectral image processing field. In this paper, a spectral-spatial target detection algorithm for hyperspectral data is proposed.The spatial feature and spectral feature were unified based on the data filed theory and extracted by weighted manifold embedding. The novelties of the proposed method lie in two aspects. One is the way in which the spatial features and spectral features were fused as a new feature based on the data field theory, and the other is that local information was introduced to describe the decision boundary and explore the discriminative features for target detection. The extracted features based on data field modeling and manifold embedding techniques were considered for a target detection task.Three standard hyperspectral datasets were considered in the analysis. The effectiveness of the proposed target detection algorithm based on data field theory was proved by the higher detection rates with lower False Alarm Rates（FARs） with respect to those achieved by conventional hyperspectral target detectors.展开更多
The advanced data mining technologies and the large quantities of remotely sensed Imagery provide a data mining opportunity with high potential for useful results. Extracting interesting patterns and rules from data s...The advanced data mining technologies and the large quantities of remotely sensed Imagery provide a data mining opportunity with high potential for useful results. Extracting interesting patterns and rules from data sets composed of images and associated ground data can be of importance in object identification, community planning, resource discovery and other areas. In this paper, a data field is presented to express the observed spatial objects and conduct behavior mining on them. First, most of the important aspects are discussed on behavior mining and its implications for the future of data mining. Furthermore, an ideal framework of the behavior mining system is proposed in the network environment. Second, the model of behavior mining is given on the observed spatial objects, including the objects described by the first feature data field and the main feature data field by means of the potential function. Finally, a case study about object identification in public is given and analyzed. The experimental results show that the new model is feasible in behavior mining.展开更多
In order to realize visualization of three-dimensional data field （TDDF） in instrument, two methods of visualization of TDDF and the usual manner of quick graphic and image processing are analyzed. And how to use Op...In order to realize visualization of three-dimensional data field （TDDF） in instrument, two methods of visualization of TDDF and the usual manner of quick graphic and image processing are analyzed. And how to use OpenGL technique and the characteristic of analyzed data to construct a TDDF, the ways of reality processing and interactive processing are described. Then the medium geometric element and a related realistic model are constructed by means of the first algorithm. Models obtained for attaching the third dimension in three-dimensional data field are presented. An example for TDDF realization of machine measuring is provided. The analysis of resultant graphic indicates that the three-dimensional graphics built by the method developed is featured by good reality, fast processing and strong interaction展开更多
Big data is a highlighted challenge for many fields with the rapid expansion of large-volume, complex, and fast-growing sources of data. Mining from big data is required for exploring the essence of data and providing...Big data is a highlighted challenge for many fields with the rapid expansion of large-volume, complex, and fast-growing sources of data. Mining from big data is required for exploring the essence of data and providing meaningful information. To this end, we have previously introduced the theory of physical field to explore relations between objects in data space and proposed a framework of data field to discover the underlying distribution of big data. This paper concerns an overview of big data mining by the use of data field. It mainly discusses the theory of data field and different aspects of applications including feature selection for high-dimensional data, clustering, and the recognition of facial expression in human-computer interaction. In these applications, data field is employed to capture the intrinsic distribution of data objects for selecting meaningful features, fast clustering, and describing variation of facial expression. It is expected that our contributions would help overcome the problems in accordance with big data.展开更多
The density peak clustering algorithm can rapidly identify cluster centers by drawing decision graphs without any prior knowledge;however,when multiple density peaks are present in one cluster of the dataset,the clust...The density peak clustering algorithm can rapidly identify cluster centers by drawing decision graphs without any prior knowledge;however,when multiple density peaks are present in one cluster of the dataset,the cluster centers cannot be accurately obtained,leading to incorrect clustering.Moreover,the single-step allocation strategy is poorly fault-tolerant and can lead to successive allocation errors.To address these problems,this study proposes a density peak clustering method based on data field theory and grid similarity,which divides the original data into grid spaces to obtain subspace codes and grid data.Subsequently,the potential grid density is introduced to measure the density of each grid based on the data field,and the density peaks are identified to obtain the cluster centers from the high-density grids.Finally,self-organized clustering is realized based on neighborhood extension centers and grid similarity.It thus reduces the possibility of successive assignment errors and the negative impact of multiple density peaks on the clustering results.In addition,the algorithm automatically determines the cluster centers and can correctly assign the non-density-peak grid to the corresponding clusters.Experimental results with synthetic and real-world datasets demonstrate that the proposed algorithm outperforms similar algorithms in terms of accuracy and efficiency when dealing with complex datasets with large density differences and cross-tangling.展开更多
Accurate capacity estimation is of great importance for the reliable state monitoring,timely maintenance,and second-life utilization of lithium-ion batteries.Despite numerous works on battery capacity estimation using...Accurate capacity estimation is of great importance for the reliable state monitoring,timely maintenance,and second-life utilization of lithium-ion batteries.Despite numerous works on battery capacity estimation using laboratory datasets,most of them are applied to battery cells and lack satisfactory fidelity when extended to real-world electric vehicle(EV)battery packs.The challenges intensify for large-sized EV battery packs,where unpredictable operating profiles and low-quality data acquisition hinder precise capacity estimation.To fill the gap,this study introduces a novel data-driven battery pack capacity estimation method grounded in field data.The proposed approach begins by determining labeled capacity through an innovative combination of the inverse ampere-hour integral,open circuit voltage-based,and resistance-based correction methods.Then,multiple health features are extracted from incremental capacity curves,voltage curves,equivalent circuit model parameters,and operating temperature to thoroughly characterize battery aging behavior.A feature selection procedure is performed to determine the optimal feature set based on the Pearson correlation coefficient.Moreover,a convolutional neural network and bidirectional gated recurrent unit,enhanced by an attention mechanism,are employed to estimate the battery pack capacity in real-world EV applications.Finally,the proposed method is validated with a field dataset from two EVs,covering approximately 35,000 kilometers.The results demonstrate that the proposed method exhibits better estimation performance with an error of less than 1.1%compared to existing methods.This work shows great potential for accurate large-sized EV battery pack capacity estimation based on field data,which provides significant insights into reliable labeled capacity calculation,effective features extraction,and machine learning-enabled health diagnosis.展开更多
This study aims to improve knowledge of the structure of southwest Cameroon based on the analysis and interpretation of gravity data derived from the SGG-UGM-2 model. A residual anomaly map was first calculated from t...This study aims to improve knowledge of the structure of southwest Cameroon based on the analysis and interpretation of gravity data derived from the SGG-UGM-2 model. A residual anomaly map was first calculated from the Bouguer anomaly map, which is strongly affected by a regional gradient. The residual anomaly map generated provides information on the variation in subsurface density, but does not provide sufficient information, hence the interest in using filtering with the aim of highlighting the structures affecting the area of south-west Cameroon. Three interpretation methods were used: vertical gradient, horizontal gradient coupled with upward continuation and Euler deconvolution. The application of these treatments enabled us to map a large number of gravimetric lineaments materializing density discontinuities. These lineaments are organized along main preferential directions: NW-SE, NNE-SSW, ENE-WSW and secondary directions: NNW-SSE, NE-SW, NS and E-W. Euler solutions indicate depths of up to 7337 m. Thanks to the results of this research, significant information has been acquired, contributing to a deeper understanding of the structural composition of the study area. The resulting structural map vividly illustrates the major tectonic events that shaped the geological framework of the study area. It also serves as a guide for prospecting subsurface resources (water and hydrocarbons). .展开更多
In this paper the application of image enhancement techniques to potential field data is briefly described and two improved enhancement methods are introduced. One method is derived from the histogram equalization tec...In this paper the application of image enhancement techniques to potential field data is briefly described and two improved enhancement methods are introduced. One method is derived from the histogram equalization technique and automatically determines the color spectra of geophysical maps. Colors can be properly distributed and visual effects and resolution can be enhanced by the method. The other method is based on the modified Radon transform and gradient calculation and is used to detect and enhance linear features in gravity and magnetic images. The method facilites the detection of line segments in the transform domain. Tests with synthetic images and real data show the methods to be effective in feature enhancement.展开更多
Enterprise applications utilize relational databases and structured business processes, requiring slow and expensive conversion of inputs and outputs, from business documents such as invoices, purchase orders, and rec...Enterprise applications utilize relational databases and structured business processes, requiring slow and expensive conversion of inputs and outputs, from business documents such as invoices, purchase orders, and receipts, into known templates and schemas before processing. We propose a new LLM Agent-based intelligent data extraction, transformation, and load (IntelligentETL) pipeline that not only ingests PDFs and detects inputs within it but also addresses the extraction of structured and unstructured data by developing tools that most efficiently and securely deal with respective data types. We study the efficiency of our proposed pipeline and compare it with enterprise solutions that also utilize LLMs. We establish the supremacy in timely and accurate data extraction and transformation capabilities of our approach for analyzing the data from varied sources based on nested and/or interlinked input constraints.展开更多
Edge detection and enhancement techniques are commonly used in recognizing the edge of geologic bodies using potential field data. We present a new edge recognition technology based on the normalized vertical derivati...Edge detection and enhancement techniques are commonly used in recognizing the edge of geologic bodies using potential field data. We present a new edge recognition technology based on the normalized vertical derivative of the total horizontal derivative which has the functions of both edge detection and enhancement techniques. First, we calculate the total horizontal derivative （THDR） of the potential-field data and then compute the n-order vertical derivative （VDRn） of the THDR. For the n-order vertical derivative, the peak value of total horizontal derivative （PTHDR） is obtained using a threshold value greater than 0. This PTHDR can be used for edge detection. Second, the PTHDR value is divided by the total horizontal derivative and normalized by the maximum value. Finally, we used different kinds of numerical models to verify the effectiveness and reliability of the new edge recognition technology.展开更多
The present study aims to improve the efficiency of typical procedures used for post-processing flow field data by applying a neural-network technology.Assuming a problem of aircraft design as the workhorse,a regressi...The present study aims to improve the efficiency of typical procedures used for post-processing flow field data by applying a neural-network technology.Assuming a problem of aircraft design as the workhorse,a regression calculation model for processing the flow data of a FCN-VGG19 aircraft is elaborated based on VGGNet(Visual Geometry Group Net)and FCN(Fully Convolutional Network)techniques.As shown by the results,the model displays a strong fitting ability,and there is almost no over-fitting in training.Moreover,the model has good accuracy and convergence.For different input data and different grids,the model basically achieves convergence,showing good performances.It is shown that the proposed simulation regression model based on FCN has great potential in typical problems of computational fluid dynamics(CFD)and related data processing.展开更多
Predominantly the localization accuracy of the magnetic field-based localization approaches is severed by two limiting factors:Smartphone heterogeneity and smaller data lengths.The use of multifarioussmartphones cripp...Predominantly the localization accuracy of the magnetic field-based localization approaches is severed by two limiting factors:Smartphone heterogeneity and smaller data lengths.The use of multifarioussmartphones cripples the performance of such approaches owing to the variability of the magnetic field data.In the same vein,smaller lengths of magnetic field data decrease the localization accuracy substantially.The current study proposes the use of multiple neural networks like deep neural network(DNN),long short term memory network(LSTM),and gated recurrent unit network(GRN)to perform indoor localization based on the embedded magnetic sensor of the smartphone.A voting scheme is introduced that takes predictions from neural networks into consideration to estimate the current location of the user.Contrary to conventional magnetic field-based localization approaches that rely on the magnetic field data intensity,this study utilizes the normalized magnetic field data for this purpose.Training of neural networks is carried out using Galaxy S8 data while the testing is performed with three devices,i.e.,LG G7,Galaxy S8,and LG Q6.Experiments are performed during different times of the day to analyze the impact of time variability.Results indicate that the proposed approach minimizes the impact of smartphone variability and elevates the localization accuracy.Performance comparison with three approaches reveals that the proposed approach outperforms them in mean,50%,and 75%error even using a lesser amount of magnetic field data than those of other approaches.展开更多
The monopile is the most common foundation to support offshore wind turbines.In the marine environment,local scour due to combined currents and waves is a significant issue that must be considered in the design of win...The monopile is the most common foundation to support offshore wind turbines.In the marine environment,local scour due to combined currents and waves is a significant issue that must be considered in the design of wind turbine foundations.In this paper,a full-scale numerical model was developed and validated based on field data from Rudong,China.The scour development around monopiles was investigated,and the effects of waves and the Reynolds number Re were analyzed.Several formulas for predicting the scour depth in the literature have been evaluated.It is found that waves can accelerate scour development even if the KC number is small(0.78<KC<1.57).The formula obtained from small-scale model tests may be unsafe or wasteful when it is applied in practical design due to the scale effect.A new equation for predicting the scour depth based on the average pile Reynolds number(Rea)is proposed and validated with field data.The equilibrium scour depth predicted using the proposed equation is evaluated and compared with those from nine equations in the literature.It is demonstrated that the values predicted from the proposed equation and from the S/M(Sheppard/Melville)equation are closer to the field data.展开更多
In the process of encoding and decoding,erasure codes over binary fields,which just need AND operations and XOR operations and therefore have a high computational efficiency,are widely used in various fields of inform...In the process of encoding and decoding,erasure codes over binary fields,which just need AND operations and XOR operations and therefore have a high computational efficiency,are widely used in various fields of information technology.A matrix decoding method is proposed in this paper.The method is a universal data reconstruction scheme for erasure codes over binary fields.Besides a pre-judgment that whether errors can be recovered,the method can rebuild sectors of loss data on a fault-tolerant storage system constructed by erasure codes for disk errors.Data reconstruction process of the new method has simple and clear steps,so it is beneficial for implementation of computer codes.And more,it can be applied to other non-binary fields easily,so it is expected that the method has an extensive application in the future.展开更多
Regarding the rapid compensation of the influence of the Earth＇ s disturbing gravity field upon trajectory calculation,the key point lies in how to derive the analytical solutions to the partial derivatives of the st...Regarding the rapid compensation of the influence of the Earth＇ s disturbing gravity field upon trajectory calculation,the key point lies in how to derive the analytical solutions to the partial derivatives of the state of burnout point with respect to the launch data.In view of this,this paper mainly expounds on two issues：one is based on the approximate analytical solution to the motion equation for the vacuum flight section of a long-range rocket,deriving the analytical solutions to the partial derivatives of the state of burnout point with respect to the changing rate of the finalstage pitch program;the other is based on the initial positioning and orientation error propagation mechanism,proposing the analytical calculation formula for the partial derivatives of the state of burnout point with respect to the launch azimuth.The calculation results of correction data are simulated and verified under different circumstances.The simulation results are as follows：（1） the accuracy of approximation between the analytical solutions and the results attained via the difference method is higher than 90%,and the ratio of calculation time between them is lower than 0.2%,thus demonstrating the accuracy of calculation of data corrections and advantages in calculation speed;（2） after the analytical solutions are compensated,the longitudinal landing deviation of the rocket is less than 20 m and the lateral landing deviation of the rocket is less than 10 m,demonstrating that the corrected data can meet the requirements for the hit accuracy of a long-range rocket.展开更多
The genetic algorithm is useful for solving an inversion of complex nonlinear geophysical equations. The multi-point search of the genetic algorithm makes it easier to find a globally optimal solution and avoid fall...The genetic algorithm is useful for solving an inversion of complex nonlinear geophysical equations. The multi-point search of the genetic algorithm makes it easier to find a globally optimal solution and avoid falling into a local extremum. The search efficiency of the genetic algorithm is a key to producing successful solutions in a huge multi-parameter model space. The encoding mechanism of the genetic algorithm affects the searching processes in the evolution. Not all genetic operations perform perfectly in a search under either a binary or decimal encoding system. As such, a standard genetic algorithm (SGA) is sometimes unable to resolve an optimization problem such as a simple geophysical inversion. With the binary encoding system the operation of the crossover may produce more new individuals. The decimal encoding system, on the other hand, makes the mutation generate more new genes. This paper discusses approaches of exploiting the search potentials of genetic operations with different encoding systems and presents a hybrid-encoding mechanism for the genetic algorithm. This is referred to as the hybrid-encoding genetic algorithm (HEGA). The method is based on the routine in which the mutation operation is executed in decimal code and other operations in binary code. HEGA guarantees the birth of better genes by mutation processing with a high probability, so that it is beneficial for resolving the inversions of complicated problems. Synthetic and real-world examples demonstrate the advantages of using HEGA in the inversion of potential-field data.展开更多
There has long been discussion about the distinctions of library science,information science,and informatics,and how these areas differ and overlap with computer science.Today the term data science is emerging that ge...There has long been discussion about the distinctions of library science,information science,and informatics,and how these areas differ and overlap with computer science.Today the term data science is emerging that generates excitement and questions about how it relates to and differs from these other areas of study.展开更多
The anisotropic properties of subsurface media cause waveform distortions in seismic wave propagation,resulting in a negative infl uence on seismic imaging.In addition,wavefields simulated by the conventional coupled ...The anisotropic properties of subsurface media cause waveform distortions in seismic wave propagation,resulting in a negative infl uence on seismic imaging.In addition,wavefields simulated by the conventional coupled pseudo-acoustic equation are not only aff ected by SV-wave artifacts but are also limited by anisotropic parameters.We propose a least-squares reverse time migration(LSRTM)method based on the pure q P-wave equation in vertically transverse isotropic media.A fi nite diff erence and fast Fourier transform method,which can improve the effi ciency of the numerical simulation compared to a pseudo-spectral method,is used to solve the pure q P-wave equation.We derive the corresponding demigration operator,migration operator,and gradient updating formula to implement the LSRTM.Numerical tests on the Hess model and field data confirm that the proposed method has a good correction eff ect for the travel time deviation caused by underground anisotropic media.Further,it signifi cantly suppresses the migration noise,balances the imaging amplitude,and improves the imaging resolution.展开更多
Recently, use of mobile communicational devices in field data collection is increasing such as smart phones and cellular phones due to emergence of embedded Global Position System GPS and Wi-Fi Internet access. Accura...Recently, use of mobile communicational devices in field data collection is increasing such as smart phones and cellular phones due to emergence of embedded Global Position System GPS and Wi-Fi Internet access. Accurate timely and handy field data collection is required for disaster management and emergency quick responses. In this article, we introduce web-based GIS system to collect the field data by personal mobile phone through Post Office Protocol POP3 mail server. The main objective of this work is to demonstrate real-time field data collection method to the students using their mobile phone to collect field data by timely and handy manners, either individual or group survey in local or global scale research.展开更多
基金The National Natural Science Foundation of China(No.61231002,61273266,61571106)the Foundation of the Department of Science and Technology of Guizhou Province(No.[2015]7637)
文摘In order to effectively conduct emotion recognition from spontaneous, non-prototypical and unsegmented speech so as to create a more natural human-machine interaction; a novel speech emotion recognition algorithm based on the combination of the emotional data field （EDF） and the ant colony search （ACS） strategy, called the EDF-ACS algorithm, is proposed. More specifically, the inter- relationship among the turn-based acoustic feature vectors of different labels are established by using the potential function in the EDF. To perform the spontaneous speech emotion recognition, the artificial colony is used to mimic the turn- based acoustic feature vectors. Then, the canonical ACS strategy is used to investigate the movement direction of each artificial ant in the EDF, which is regarded as the emotional label of the corresponding turn-based acoustic feature vector. The proposed EDF-ACS algorithm is evaluated on the continueous audio）＇visual emotion challenge （AVEC） 2012 dataset, which contains the spontaneous, non-prototypical and unsegmented speech emotion data. The experimental results show that the proposed EDF-ACS algorithm outperforms the existing state-of-the-art algorithm in turn-based speech emotion recognition.
文摘Target detection is always an important application in hyperspectral image processing field. In this paper, a spectral-spatial target detection algorithm for hyperspectral data is proposed.The spatial feature and spectral feature were unified based on the data filed theory and extracted by weighted manifold embedding. The novelties of the proposed method lie in two aspects. One is the way in which the spatial features and spectral features were fused as a new feature based on the data field theory, and the other is that local information was introduced to describe the decision boundary and explore the discriminative features for target detection. The extracted features based on data field modeling and manifold embedding techniques were considered for a target detection task.Three standard hyperspectral datasets were considered in the analysis. The effectiveness of the proposed target detection algorithm based on data field theory was proved by the higher detection rates with lower False Alarm Rates（FARs） with respect to those achieved by conventional hyperspectral target detectors.
基金Supported by the National 973 Program of China(No.2006CB701305,No.2007CB310804)the National Natural Science Fundation of China(No.60743001)+1 种基金the Best National Thesis Fundation (No.2005047)the National New Century Excellent Talent Fundation (No.NCET-06-0618)
文摘The advanced data mining technologies and the large quantities of remotely sensed Imagery provide a data mining opportunity with high potential for useful results. Extracting interesting patterns and rules from data sets composed of images and associated ground data can be of importance in object identification, community planning, resource discovery and other areas. In this paper, a data field is presented to express the observed spatial objects and conduct behavior mining on them. First, most of the important aspects are discussed on behavior mining and its implications for the future of data mining. Furthermore, an ideal framework of the behavior mining system is proposed in the network environment. Second, the model of behavior mining is given on the observed spatial objects, including the objects described by the first feature data field and the main feature data field by means of the potential function. Finally, a case study about object identification in public is given and analyzed. The experimental results show that the new model is feasible in behavior mining.
基金This project is supported by National Natural Science Foundation of China (No.50405009)
文摘In order to realize visualization of three-dimensional data field （TDDF） in instrument, two methods of visualization of TDDF and the usual manner of quick graphic and image processing are analyzed. And how to use OpenGL technique and the characteristic of analyzed data to construct a TDDF, the ways of reality processing and interactive processing are described. Then the medium geometric element and a related realistic model are constructed by means of the first algorithm. Models obtained for attaching the third dimension in three-dimensional data field are presented. An example for TDDF realization of machine measuring is provided. The analysis of resultant graphic indicates that the three-dimensional graphics built by the method developed is featured by good reality, fast processing and strong interaction
文摘Big data is a highlighted challenge for many fields with the rapid expansion of large-volume, complex, and fast-growing sources of data. Mining from big data is required for exploring the essence of data and providing meaningful information. To this end, we have previously introduced the theory of physical field to explore relations between objects in data space and proposed a framework of data field to discover the underlying distribution of big data. This paper concerns an overview of big data mining by the use of data field. It mainly discusses the theory of data field and different aspects of applications including feature selection for high-dimensional data, clustering, and the recognition of facial expression in human-computer interaction. In these applications, data field is employed to capture the intrinsic distribution of data objects for selecting meaningful features, fast clustering, and describing variation of facial expression. It is expected that our contributions would help overcome the problems in accordance with big data.
基金supported by the National Natural Science Foundation of China under Grant Nos.62272006 and 61972439the Natural Science Foundation of Anhui Province of China under Grant No.2208085MF164the University Natural Science Research Program of Anhui Province of China under Grant No.KJ2021A0125.
文摘The density peak clustering algorithm can rapidly identify cluster centers by drawing decision graphs without any prior knowledge;however,when multiple density peaks are present in one cluster of the dataset,the cluster centers cannot be accurately obtained,leading to incorrect clustering.Moreover,the single-step allocation strategy is poorly fault-tolerant and can lead to successive allocation errors.To address these problems,this study proposes a density peak clustering method based on data field theory and grid similarity,which divides the original data into grid spaces to obtain subspace codes and grid data.Subsequently,the potential grid density is introduced to measure the density of each grid based on the data field,and the density peaks are identified to obtain the cluster centers from the high-density grids.Finally,self-organized clustering is realized based on neighborhood extension centers and grid similarity.It thus reduces the possibility of successive assignment errors and the negative impact of multiple density peaks on the clustering results.In addition,the algorithm automatically determines the cluster centers and can correctly assign the non-density-peak grid to the corresponding clusters.Experimental results with synthetic and real-world datasets demonstrate that the proposed algorithm outperforms similar algorithms in terms of accuracy and efficiency when dealing with complex datasets with large density differences and cross-tangling.
基金supported in part by the National Key Research and Development Program of China(No.2022YFB3305403)Project of basic research funds for central universities(2022CDJDX006)+1 种基金Talent Plan Project of Chongqing(No.cstc2021ycjhbgzxm0295)National Natural Science Foundation of China(No.52111530194)。
文摘Accurate capacity estimation is of great importance for the reliable state monitoring,timely maintenance,and second-life utilization of lithium-ion batteries.Despite numerous works on battery capacity estimation using laboratory datasets,most of them are applied to battery cells and lack satisfactory fidelity when extended to real-world electric vehicle(EV)battery packs.The challenges intensify for large-sized EV battery packs,where unpredictable operating profiles and low-quality data acquisition hinder precise capacity estimation.To fill the gap,this study introduces a novel data-driven battery pack capacity estimation method grounded in field data.The proposed approach begins by determining labeled capacity through an innovative combination of the inverse ampere-hour integral,open circuit voltage-based,and resistance-based correction methods.Then,multiple health features are extracted from incremental capacity curves,voltage curves,equivalent circuit model parameters,and operating temperature to thoroughly characterize battery aging behavior.A feature selection procedure is performed to determine the optimal feature set based on the Pearson correlation coefficient.Moreover,a convolutional neural network and bidirectional gated recurrent unit,enhanced by an attention mechanism,are employed to estimate the battery pack capacity in real-world EV applications.Finally,the proposed method is validated with a field dataset from two EVs,covering approximately 35,000 kilometers.The results demonstrate that the proposed method exhibits better estimation performance with an error of less than 1.1%compared to existing methods.This work shows great potential for accurate large-sized EV battery pack capacity estimation based on field data,which provides significant insights into reliable labeled capacity calculation,effective features extraction,and machine learning-enabled health diagnosis.
文摘This study aims to improve knowledge of the structure of southwest Cameroon based on the analysis and interpretation of gravity data derived from the SGG-UGM-2 model. A residual anomaly map was first calculated from the Bouguer anomaly map, which is strongly affected by a regional gradient. The residual anomaly map generated provides information on the variation in subsurface density, but does not provide sufficient information, hence the interest in using filtering with the aim of highlighting the structures affecting the area of south-west Cameroon. Three interpretation methods were used: vertical gradient, horizontal gradient coupled with upward continuation and Euler deconvolution. The application of these treatments enabled us to map a large number of gravimetric lineaments materializing density discontinuities. These lineaments are organized along main preferential directions: NW-SE, NNE-SSW, ENE-WSW and secondary directions: NNW-SSE, NE-SW, NS and E-W. Euler solutions indicate depths of up to 7337 m. Thanks to the results of this research, significant information has been acquired, contributing to a deeper understanding of the structural composition of the study area. The resulting structural map vividly illustrates the major tectonic events that shaped the geological framework of the study area. It also serves as a guide for prospecting subsurface resources (water and hydrocarbons). .
基金This work is supported by the research project (grant No. G20000467) of the Institute of Geology and Geophysics, CAS and bythe China Postdoctoral Science Foundation (No. 2004036083).
文摘In this paper the application of image enhancement techniques to potential field data is briefly described and two improved enhancement methods are introduced. One method is derived from the histogram equalization technique and automatically determines the color spectra of geophysical maps. Colors can be properly distributed and visual effects and resolution can be enhanced by the method. The other method is based on the modified Radon transform and gradient calculation and is used to detect and enhance linear features in gravity and magnetic images. The method facilites the detection of line segments in the transform domain. Tests with synthetic images and real data show the methods to be effective in feature enhancement.
文摘Enterprise applications utilize relational databases and structured business processes, requiring slow and expensive conversion of inputs and outputs, from business documents such as invoices, purchase orders, and receipts, into known templates and schemas before processing. We propose a new LLM Agent-based intelligent data extraction, transformation, and load (IntelligentETL) pipeline that not only ingests PDFs and detects inputs within it but also addresses the extraction of structured and unstructured data by developing tools that most efficiently and securely deal with respective data types. We study the efficiency of our proposed pipeline and compare it with enterprise solutions that also utilize LLMs. We establish the supremacy in timely and accurate data extraction and transformation capabilities of our approach for analyzing the data from varied sources based on nested and/or interlinked input constraints.
基金supported by the National Science and Technology Major Projects (2008ZX05025)the Project of National Oil and Gas Resources Strategic Constituency Survey and Evaluation of the Ministry of Land and Resources,China (XQ-2007-05)
文摘Edge detection and enhancement techniques are commonly used in recognizing the edge of geologic bodies using potential field data. We present a new edge recognition technology based on the normalized vertical derivative of the total horizontal derivative which has the functions of both edge detection and enhancement techniques. First, we calculate the total horizontal derivative （THDR） of the potential-field data and then compute the n-order vertical derivative （VDRn） of the THDR. For the n-order vertical derivative, the peak value of total horizontal derivative （PTHDR） is obtained using a threshold value greater than 0. This PTHDR can be used for edge detection. Second, the PTHDR value is divided by the total horizontal derivative and normalized by the maximum value. Finally, we used different kinds of numerical models to verify the effectiveness and reliability of the new edge recognition technology.
文摘The present study aims to improve the efficiency of typical procedures used for post-processing flow field data by applying a neural-network technology.Assuming a problem of aircraft design as the workhorse,a regression calculation model for processing the flow data of a FCN-VGG19 aircraft is elaborated based on VGGNet(Visual Geometry Group Net)and FCN(Fully Convolutional Network)techniques.As shown by the results,the model displays a strong fitting ability,and there is almost no over-fitting in training.Moreover,the model has good accuracy and convergence.For different input data and different grids,the model basically achieves convergence,showing good performances.It is shown that the proposed simulation regression model based on FCN has great potential in typical problems of computational fluid dynamics(CFD)and related data processing.
基金supported by the MSIT(Ministry of Science and ICT),Korea,under the ITRC(Information Technology Research Center)support program(IITP-2019-2016-0-00313)supervised by the IITP(Institute for Information&communication Technology Promotion)+1 种基金supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Science,ICT and Future Planning(2017R1E1A1A01074345).
文摘Predominantly the localization accuracy of the magnetic field-based localization approaches is severed by two limiting factors:Smartphone heterogeneity and smaller data lengths.The use of multifarioussmartphones cripples the performance of such approaches owing to the variability of the magnetic field data.In the same vein,smaller lengths of magnetic field data decrease the localization accuracy substantially.The current study proposes the use of multiple neural networks like deep neural network(DNN),long short term memory network(LSTM),and gated recurrent unit network(GRN)to perform indoor localization based on the embedded magnetic sensor of the smartphone.A voting scheme is introduced that takes predictions from neural networks into consideration to estimate the current location of the user.Contrary to conventional magnetic field-based localization approaches that rely on the magnetic field data intensity,this study utilizes the normalized magnetic field data for this purpose.Training of neural networks is carried out using Galaxy S8 data while the testing is performed with three devices,i.e.,LG G7,Galaxy S8,and LG Q6.Experiments are performed during different times of the day to analyze the impact of time variability.Results indicate that the proposed approach minimizes the impact of smartphone variability and elevates the localization accuracy.Performance comparison with three approaches reveals that the proposed approach outperforms them in mean,50%,and 75%error even using a lesser amount of magnetic field data than those of other approaches.
基金financially supported by the National Natural Science Foundation of China (Grant No.52378329)。
文摘The monopile is the most common foundation to support offshore wind turbines.In the marine environment,local scour due to combined currents and waves is a significant issue that must be considered in the design of wind turbine foundations.In this paper,a full-scale numerical model was developed and validated based on field data from Rudong,China.The scour development around monopiles was investigated,and the effects of waves and the Reynolds number Re were analyzed.Several formulas for predicting the scour depth in the literature have been evaluated.It is found that waves can accelerate scour development even if the KC number is small(0.78<KC<1.57).The formula obtained from small-scale model tests may be unsafe or wasteful when it is applied in practical design due to the scale effect.A new equation for predicting the scour depth based on the average pile Reynolds number(Rea)is proposed and validated with field data.The equilibrium scour depth predicted using the proposed equation is evaluated and compared with those from nine equations in the literature.It is demonstrated that the values predicted from the proposed equation and from the S/M(Sheppard/Melville)equation are closer to the field data.
基金supported by the National Natural Science Foundation of China under Grant No.61501064Sichuan Provincial Science and Technology Project under Grant No.2016GZ0122
文摘In the process of encoding and decoding,erasure codes over binary fields,which just need AND operations and XOR operations and therefore have a high computational efficiency,are widely used in various fields of information technology.A matrix decoding method is proposed in this paper.The method is a universal data reconstruction scheme for erasure codes over binary fields.Besides a pre-judgment that whether errors can be recovered,the method can rebuild sectors of loss data on a fault-tolerant storage system constructed by erasure codes for disk errors.Data reconstruction process of the new method has simple and clear steps,so it is beneficial for implementation of computer codes.And more,it can be applied to other non-binary fields easily,so it is expected that the method has an extensive application in the future.
文摘Regarding the rapid compensation of the influence of the Earth＇ s disturbing gravity field upon trajectory calculation,the key point lies in how to derive the analytical solutions to the partial derivatives of the state of burnout point with respect to the launch data.In view of this,this paper mainly expounds on two issues：one is based on the approximate analytical solution to the motion equation for the vacuum flight section of a long-range rocket,deriving the analytical solutions to the partial derivatives of the state of burnout point with respect to the changing rate of the finalstage pitch program;the other is based on the initial positioning and orientation error propagation mechanism,proposing the analytical calculation formula for the partial derivatives of the state of burnout point with respect to the launch azimuth.The calculation results of correction data are simulated and verified under different circumstances.The simulation results are as follows：（1） the accuracy of approximation between the analytical solutions and the results attained via the difference method is higher than 90%,and the ratio of calculation time between them is lower than 0.2%,thus demonstrating the accuracy of calculation of data corrections and advantages in calculation speed;（2） after the analytical solutions are compensated,the longitudinal landing deviation of the rocket is less than 20 m and the lateral landing deviation of the rocket is less than 10 m,demonstrating that the corrected data can meet the requirements for the hit accuracy of a long-range rocket.
文摘The genetic algorithm is useful for solving an inversion of complex nonlinear geophysical equations. The multi-point search of the genetic algorithm makes it easier to find a globally optimal solution and avoid falling into a local extremum. The search efficiency of the genetic algorithm is a key to producing successful solutions in a huge multi-parameter model space. The encoding mechanism of the genetic algorithm affects the searching processes in the evolution. Not all genetic operations perform perfectly in a search under either a binary or decimal encoding system. As such, a standard genetic algorithm (SGA) is sometimes unable to resolve an optimization problem such as a simple geophysical inversion. With the binary encoding system the operation of the crossover may produce more new individuals. The decimal encoding system, on the other hand, makes the mutation generate more new genes. This paper discusses approaches of exploiting the search potentials of genetic operations with different encoding systems and presents a hybrid-encoding mechanism for the genetic algorithm. This is referred to as the hybrid-encoding genetic algorithm (HEGA). The method is based on the routine in which the mutation operation is executed in decimal code and other operations in binary code. HEGA guarantees the birth of better genes by mutation processing with a high probability, so that it is beneficial for resolving the inversions of complicated problems. Synthetic and real-world examples demonstrate the advantages of using HEGA in the inversion of potential-field data.
文摘There has long been discussion about the distinctions of library science,information science,and informatics,and how these areas differ and overlap with computer science.Today the term data science is emerging that generates excitement and questions about how it relates to and differs from these other areas of study.
基金financially supported by the National Key R&D Program of China (No. 2019YFC0605503)the Major Scientific and Technological Projects of CNPC (No. ZD2019-183-003)the National Natural Science Foundation of China (No. 41922028,41874149)。
文摘The anisotropic properties of subsurface media cause waveform distortions in seismic wave propagation,resulting in a negative infl uence on seismic imaging.In addition,wavefields simulated by the conventional coupled pseudo-acoustic equation are not only aff ected by SV-wave artifacts but are also limited by anisotropic parameters.We propose a least-squares reverse time migration(LSRTM)method based on the pure q P-wave equation in vertically transverse isotropic media.A fi nite diff erence and fast Fourier transform method,which can improve the effi ciency of the numerical simulation compared to a pseudo-spectral method,is used to solve the pure q P-wave equation.We derive the corresponding demigration operator,migration operator,and gradient updating formula to implement the LSRTM.Numerical tests on the Hess model and field data confirm that the proposed method has a good correction eff ect for the travel time deviation caused by underground anisotropic media.Further,it signifi cantly suppresses the migration noise,balances the imaging amplitude,and improves the imaging resolution.
文摘Recently, use of mobile communicational devices in field data collection is increasing such as smart phones and cellular phones due to emergence of embedded Global Position System GPS and Wi-Fi Internet access. Accurate timely and handy field data collection is required for disaster management and emergency quick responses. In this article, we introduce web-based GIS system to collect the field data by personal mobile phone through Post Office Protocol POP3 mail server. The main objective of this work is to demonstrate real-time field data collection method to the students using their mobile phone to collect field data by timely and handy manners, either individual or group survey in local or global scale research.
