Spondylis buprestoides adults in Pians masoniana forests in Xianju Dabei Dixi Forestry Center were continuously investigated during 2006 and 2011. According to the survey data, multiple spatial pattern indicators of a...Spondylis buprestoides adults in Pians masoniana forests in Xianju Dabei Dixi Forestry Center were continuously investigated during 2006 and 2011. According to the survey data, multiple spatial pattern indicators of adult population were calculated, and the relationship between various indicators and density was analyzed. The K values of negative binomial distribution less affected by density were selected to describe the spatial pattern and time series dynamics of S. buprestoides adults. The results indicated that S. buprestoides adults showed aggregated distribution in the forest, but the aggregation degree varied with the season. There were 2 obvious diffusion peaks during May and June as well as September and October each year. The aggregation trend within a generation was aggregation-diffusion-aggregation.展开更多
The existing pattern matching methods of multivariate time series can hardly measure the similarity of multivariate hydrological time series accurately and efficiently.Considering the characteristics of multivariate h...The existing pattern matching methods of multivariate time series can hardly measure the similarity of multivariate hydrological time series accurately and efficiently.Considering the characteristics of multivariate hydrological time series,the continuity and global features of variables,we proposed a pattern matching method,PP-DTW,which is based on dynamic time warping.In this method,the multivariate time series is firstly segmented,and the average of each segment is used as the feature.Then,PCA is operated on the feature sequence.Finally,the weighted DTW distance is used as the measure of similarity in sequences.Carrying out experiments on the hydrological data of Chu River,we conclude that the pattern matching method can effectively describe the overall characteristics of the multivariate time series,which has a good matching effect on the multivariate hydrological time series.展开更多
Pattern discovery from time series is of fundamental importance. Most of the algorithms of pattern discovery in time series capture the values of time series based on some kinds of similarity measures. Affected by the...Pattern discovery from time series is of fundamental importance. Most of the algorithms of pattern discovery in time series capture the values of time series based on some kinds of similarity measures. Affected by the scale and baseline, value-based methods bring about problem when the objective is to capture the shape. Thus, a similarity measure based on shape, Sh measure, is originally proposed, andthe properties of this similarity and corresponding proofs are given. Then a time series shape pattern discovery algorithm based on Sh measure is put forward. The proposed algorithm is terminated in finite iteration with given computational and storage complexity. Finally the experiments on synthetic datasets and sunspot datasets demonstrate that the time series shape pattern algorithm is valid.展开更多
Patterned-based time series segmentation (PTSS) is an important task for many time series data mining applications. In this paper, according to the characteristics of PTSS, a generalized model is proposed for PTSS. Fi...Patterned-based time series segmentation (PTSS) is an important task for many time series data mining applications. In this paper, according to the characteristics of PTSS, a generalized model is proposed for PTSS. First, a new inter-pretation for PTSS is given by comparing this problem with the prototype-based clustering (PC). Then, a novel model, called clustering-inverse model (CI-model), is presented. Finally, two algorithms are presented to implement this model. Our experimental results on artificial and real-world time series demonstrate that the proposed algorithms are quite effective.展开更多
It is of paramount importance to have sustainable agriculture since agriculture is the backbone of many nations’ economic development. Majority of agricultural professionals rarely capture the cropping patterns neces...It is of paramount importance to have sustainable agriculture since agriculture is the backbone of many nations’ economic development. Majority of agricultural professionals rarely capture the cropping patterns necessary to promote Good Agricultural Practises.Objective of this research is to explore the potential of mapping cropping patterns occurring on different field parcels on small-scale farmlands in Zimbabwe. The first study location under investigation are the International Maize and Wheat Improvement Center(CIMMYT) research station and a few neighboring fields, the second is Middle Sabi Estate. Fourier time series modeling was implemented to determine the trends befalling on the two study sites. Results reveal that Sentinel-1 synthetic aperture radar(SAR) time series allow detection of subtle changes that occur to the crops and fields respectively, hence can be utilized to detect cropping patterns on small-scale farmlands. Discrimination of the main crops(maize and soybean) grown at CIMMYT was possible, and crop rotation was synthesized where sowing starts in November. A single cropping of early and late crops was observed, there were no winter crops planted during the investigation period. At Middle Sabi Estate, single cropping on perennial sugarcane fields and triple cropping of fields growing leafy vegetables, tomatoes and onions were observed. Classification of stacked images was used to derive the crop rotation maps representing what is practised at the farming lands. Random forest classification of the multi-temporal image stacks achieved overall accuracies of 99% and 95% on the respective study sites. In conclusion, Sentinel-1 time series can be implemented effectively to map the cropping patterns and crop rotations occurring on small-scale farming land. We recommend the use of Sentinel-1 SAR multi-temporal data to spatially explicitly map cropping patterns of single-, double-and triple-cropping systems on both small-scale and large-scale farming areas to ensure food security.展开更多
We generate a directed weighted complex network by a method based on Markov transition probability to represent an experimental two-phase flow. We first systematically carry out gas-liquid two-phase flow experiments f...We generate a directed weighted complex network by a method based on Markov transition probability to represent an experimental two-phase flow. We first systematically carry out gas-liquid two-phase flow experiments for measuring the time series of flow signals. Then we construct directed weighted complex networks from various time series in terms of a network generation method based on Markov transition probability. We find that the generated network inherits the main features of the time series in the network structure. In particular, the networks from time series with different dynamics exhibit distinct topological properties. Finally, we construct two-phase flow directed weighted networks from experimental signals and associate the dynamic behavior of gas-liquid two-phase flow with the topological statistics of the generated networks. The results suggest that the topological statistics of two-phase flow networks allow quantitative characterization of the dynamic flow behavior in the transitions among different gas-liquid flow patterns.展开更多
There are many techniques using sensors and wearable devices for detecting and monitoring patients with Parkinson’s disease(PD).A recent development is the utilization of human interaction with computer keyboards for...There are many techniques using sensors and wearable devices for detecting and monitoring patients with Parkinson’s disease(PD).A recent development is the utilization of human interaction with computer keyboards for analyzing and identifying motor signs in the early stages of the disease.Current designs for classification of time series of computer-key hold durations recorded from healthy control and PD subjects require the time series of length to be considerably long.With an attempt to avoid discomfort to participants in performing long physical tasks for data recording,this paper introduces the use of fuzzy recurrence plots of very short time series as input data for the machine training and classification with long short-term memory(LSTM)neural networks.Being an original approach that is able to both significantly increase the feature dimensions and provides the property of deterministic dynamical systems of very short time series for information processing carried out by an LSTM layer architecture,fuzzy recurrence plots provide promising results and outperform the direct input of the time series for the classification of healthy control and early PD subjects.展开更多
In this article we shall examine several different types of figurative numbers which have been studied extensively over the period of 2500 years, and currently scattered on hundreds of websites. We shall discuss their...In this article we shall examine several different types of figurative numbers which have been studied extensively over the period of 2500 years, and currently scattered on hundreds of websites. We shall discuss their computation through simple recurrence relations, patterns and properties, and mutual relationships which have led to curious results in the field of elementary number theory. Further, for each type of figurative numbers we shall show that the addition of first finite numbers and infinite addition of their inverses often require new/strange techniques. We sincerely hope that besides experts, students and teachers of mathematics will also be benefited with this article.展开更多
This study used time-series of global inventory modeling and mapping studies (GIMMS) normalized difference vegetation index (NDVI) datasets at a spatial resolution of 8 km and 15-d interval to investigate the spat...This study used time-series of global inventory modeling and mapping studies (GIMMS) normalized difference vegetation index (NDVI) datasets at a spatial resolution of 8 km and 15-d interval to investigate the spatial patterns of cropland phenology in China. A smoothing algorithm based on an asymmetric Gaussian function was first performed on NDVI dataset to minimize the effects of anomalous values caused by atmospheric haze and cloud contamination. Subsequent processing for identifying cropping systems and extracting phenological parameters, the starting date of growing season (SGS) and the ending date of growing season (EGS) was based on the smoothed NVDI time-series data. The results showed that the cropping systems in China became complex as moving from north to south of China. Under these cropping systems, the SGS and EGS for the first growing season varied largely over space, and those regions with multiple cropping systems generally presented a significant advanced SGS and EGS than the regions with single cropping patterns. On the contrary, the phenological events of the second growing season including both the SGS and EGS showed little difference between regions. The spatial patterns of cropping systems and phenology in Chinese cropland were highly related to the geophysical environmental factors. Several anthropogenic factors, such as crop variety, cultivation levels, irrigation, and fertilizers, could profoundly influence crop phenological status. How to discriminate the impacts of biophysical forces and anthropogenic drivers on phenological events of cultivation remains a great challenge for further studies.展开更多
The chaotic characteristics of time series of five partial discharge (PD) patterns in oil-paper insulation are studied. The results verify obvious chaotic characteristic of the time series of discharge signals and t...The chaotic characteristics of time series of five partial discharge (PD) patterns in oil-paper insulation are studied. The results verify obvious chaotic characteristic of the time series of discharge signals and the fact that PD is a chaotic process. These time series have distinctive features, and the chaotic attractors obtained from time series differed greatly from each other by shapes in the phase space, so they could be used to qualitatively identify the PD patterns. The phase space parameters are selected, then the chaotic characteristic quantities can be extracted. These quantities could quantificationally characterize the PD patterns. The effects on pattern recognition of PRPD and CAPD are compared by using the neural network of radial basis function. The results show that both of the two recognition methods work well and have their respective advantages. Then, both the statistical operators under PRPD mode and the chaotic characteristic quantities under CAPD mode are selected comprehensively as the input vectors of neural network, and the PD pattern recognition accuracy is thereby greatly improved.展开更多
Various pattern evolutions are presented in one- and two-dimensional spatially coupled phase-conjugate systems (SCPCSs). As the system parameters change, different patterns are obtained from the period-doubling of k...Various pattern evolutions are presented in one- and two-dimensional spatially coupled phase-conjugate systems (SCPCSs). As the system parameters change, different patterns are obtained from the period-doubling of kink-antikinks in space to the spatiotemporal chaos in a one-dimensional SCPCS. The homogeneous symmetric states induce symmetry breaking from the four corners and the boundaries, finally leading to spatiotemporal chaos with the increase of the iteration time in a two-dimensional SCPCS. Numerical simulations are very helpful for understanding the complex optical phenomena.展开更多
With the continuous development of machine learning and the increasing complexity of financial data analysis,it is more popular to use models in the field of machine learning to solve the hot and difficult problems in...With the continuous development of machine learning and the increasing complexity of financial data analysis,it is more popular to use models in the field of machine learning to solve the hot and difficult problems in the financial industry.To improve the effectiveness of stock trend prediction and solve the problems in time series data processing,this paper combines the fuzzy affiliation function with stock-related technical indicators to obtain nominal data that can widely reflect the constituent stocks in the case of time series changes by analysing the S&P 500 index.Meanwhile,in order to optimise the current machine learning algorithm in which the setting and adjustment of hyperparameters rely too much on empirical knowledge,this paper combines the deep forest model to train the stock data separately.The experimental results show that(1)the accuracy of the extreme random forest and the accuracy of the multi-grain cascade forest are both higher than that of the gated recurrent unit(GRU)model when the un-fuzzy index-adjusted dataset is used as features for input,(2)the accuracy of the extreme random forest and the accuracy of the multigranular cascade forest are improved by using the fuzzy index-adjusted dataset as features for input,(3)the accuracy of the fuzzy index-adjusted dataset as features for inputting the extreme random forest is improved by 18.89% compared to that of the un-fuzzy index-adjusted dataset as features for inputting the extreme random forest and(4)the average accuracy of the fuzzy index-adjusted dataset as features for inputting multi-grain cascade forest increased by 5.67%.展开更多
The motivation for this article is to propose new damage classifiers based on a supervised learning problem for locating and quantifying damage.A new feature extraction approach using time series analysis is introduce...The motivation for this article is to propose new damage classifiers based on a supervised learning problem for locating and quantifying damage.A new feature extraction approach using time series analysis is introduced to extract damage-sensitive features from auto-regressive models.This approach sets out to improve current feature extraction techniques in the context of time series modeling.The coefficients and residuals of the AR model obtained from the proposed approach are selected as the main features and are applied to the proposed supervised learning classifiers that are categorized as coefficient-based and residual-based classifiers.These classifiers compute the relative errors in the extracted features between the undamaged and damaged states.Eventually,the abilities of the proposed methods to localize and quantify single and multiple damage scenarios are verified by applying experimental data for a laboratory frame and a four-story steel structure.Comparative analyses are performed to validate the superiority of the proposed methods over some existing techniques.Results show that the proposed classifiers,with the aid of extracted features from the proposed feature extraction approach,are able to locate and quantify damage;however,the residual-based classifiers yield better results than the coefficient-based classifiers.Moreover,these methods are superior to some classical techniques.展开更多
Chronic myeloid leukemia(CML) is characterized by the accumulation of active BCR-ABL protein. Imatinib is the first-line treatment of CML; however, many patients are resistant to this drug. In this study, we aimed t...Chronic myeloid leukemia(CML) is characterized by the accumulation of active BCR-ABL protein. Imatinib is the first-line treatment of CML; however, many patients are resistant to this drug. In this study, we aimed to compare the differences in expression patterns and functions of time-series genes in imatinib-resistant CML cells under different drug treatments. GSE24946 was downloaded from the GEO database, which included 17 samples of K562-r cells with(n=12) or without drug administration(n=5). Three drug treatment groups were considered for this study: arsenic trioxide(ATO), AMN107, and ATO+AMN107. Each group had one sample at each time point(3, 12, 24, and 48 h). Time-series genes with a ratio of standard deviation/average(coefficient of variation) 〉0.15 were screened, and their expression patterns were revealed based on Short Time-series Expression Miner(STEM). Then, the functional enrichment analysis of time-series genes in each group was performed using DAVID, and the genes enriched in the top ten functional categories were extracted to detect their expression patterns. Different time-series genes were identified in the three groups, and most of them were enriched in the ribosome and oxidative phosphorylation pathways. Time-series genes in the three treatment groups had different expression patterns and functions. Time-series genes in the ATO group(e.g. CCNA2 and DAB2) were significantly associated with cell adhesion, those in the AMN107 group were related to cellular carbohydrate metabolic process, while those in the ATO+AMN107 group(e.g. AP2M1) were significantly related to cell proliferation and antigen processing. In imatinib-resistant CML cells, ATO could influence genes related to cell adhesion, AMN107 might affect genes involved in cellular carbohydrate metabolism, and the combination therapy might regulate genes involved in cell proliferation.展开更多
Since the candlestick patterns were mined,there is a contentious dispute on whether the candlestick patterns have predictive power in academia.To help resolve the debate,this paper uses the data mining methods of patt...Since the candlestick patterns were mined,there is a contentious dispute on whether the candlestick patterns have predictive power in academia.To help resolve the debate,this paper uses the data mining methods of pattern recognition,pattern clustering and pattern knowledge mining to research the predictive power of candlestick patterns.In addition,we propose the similarity match model and nearest neighbor-clustering algorithm to solve the problem of similarity match and clustering of candlestick series,respectively.The experiment includes testing the predictive power of the Morning Star pattern and Evening Star pattern with the testing dataset of the candlestick series data of Shanghai 180 index component stocks over the latest 10 years.Experimental results show that(1)There have some spurious patterns in the existing candlestick patterns.However,after further classification of a spurious pattern based on its shape feature,those patterns with special shapes still have predictive power.(2)Some patterns do have the predictive power.(3)As there is no precise mathematical definition to describe the existing patterns’predictive power,it is essential to give the mathematical formula for improving the candlestick patterns’prediction performance.展开更多
文摘Spondylis buprestoides adults in Pians masoniana forests in Xianju Dabei Dixi Forestry Center were continuously investigated during 2006 and 2011. According to the survey data, multiple spatial pattern indicators of adult population were calculated, and the relationship between various indicators and density was analyzed. The K values of negative binomial distribution less affected by density were selected to describe the spatial pattern and time series dynamics of S. buprestoides adults. The results indicated that S. buprestoides adults showed aggregated distribution in the forest, but the aggregation degree varied with the season. There were 2 obvious diffusion peaks during May and June as well as September and October each year. The aggregation trend within a generation was aggregation-diffusion-aggregation.
文摘The existing pattern matching methods of multivariate time series can hardly measure the similarity of multivariate hydrological time series accurately and efficiently.Considering the characteristics of multivariate hydrological time series,the continuity and global features of variables,we proposed a pattern matching method,PP-DTW,which is based on dynamic time warping.In this method,the multivariate time series is firstly segmented,and the average of each segment is used as the feature.Then,PCA is operated on the feature sequence.Finally,the weighted DTW distance is used as the measure of similarity in sequences.Carrying out experiments on the hydrological data of Chu River,we conclude that the pattern matching method can effectively describe the overall characteristics of the multivariate time series,which has a good matching effect on the multivariate hydrological time series.
文摘Pattern discovery from time series is of fundamental importance. Most of the algorithms of pattern discovery in time series capture the values of time series based on some kinds of similarity measures. Affected by the scale and baseline, value-based methods bring about problem when the objective is to capture the shape. Thus, a similarity measure based on shape, Sh measure, is originally proposed, andthe properties of this similarity and corresponding proofs are given. Then a time series shape pattern discovery algorithm based on Sh measure is put forward. The proposed algorithm is terminated in finite iteration with given computational and storage complexity. Finally the experiments on synthetic datasets and sunspot datasets demonstrate that the time series shape pattern algorithm is valid.
文摘Patterned-based time series segmentation (PTSS) is an important task for many time series data mining applications. In this paper, according to the characteristics of PTSS, a generalized model is proposed for PTSS. First, a new inter-pretation for PTSS is given by comparing this problem with the prototype-based clustering (PC). Then, a novel model, called clustering-inverse model (CI-model), is presented. Finally, two algorithms are presented to implement this model. Our experimental results on artificial and real-world time series demonstrate that the proposed algorithms are quite effective.
基金Under the auspices of Fundamental Research Funds for the Central Universities,China(No.2017TD-26)the Plan for Changbai Mountain Scholars of Jilin Province,China(No.JJLZ[2015]54)
文摘It is of paramount importance to have sustainable agriculture since agriculture is the backbone of many nations’ economic development. Majority of agricultural professionals rarely capture the cropping patterns necessary to promote Good Agricultural Practises.Objective of this research is to explore the potential of mapping cropping patterns occurring on different field parcels on small-scale farmlands in Zimbabwe. The first study location under investigation are the International Maize and Wheat Improvement Center(CIMMYT) research station and a few neighboring fields, the second is Middle Sabi Estate. Fourier time series modeling was implemented to determine the trends befalling on the two study sites. Results reveal that Sentinel-1 synthetic aperture radar(SAR) time series allow detection of subtle changes that occur to the crops and fields respectively, hence can be utilized to detect cropping patterns on small-scale farmlands. Discrimination of the main crops(maize and soybean) grown at CIMMYT was possible, and crop rotation was synthesized where sowing starts in November. A single cropping of early and late crops was observed, there were no winter crops planted during the investigation period. At Middle Sabi Estate, single cropping on perennial sugarcane fields and triple cropping of fields growing leafy vegetables, tomatoes and onions were observed. Classification of stacked images was used to derive the crop rotation maps representing what is practised at the farming lands. Random forest classification of the multi-temporal image stacks achieved overall accuracies of 99% and 95% on the respective study sites. In conclusion, Sentinel-1 time series can be implemented effectively to map the cropping patterns and crop rotations occurring on small-scale farming land. We recommend the use of Sentinel-1 SAR multi-temporal data to spatially explicitly map cropping patterns of single-, double-and triple-cropping systems on both small-scale and large-scale farming areas to ensure food security.
基金Project supported by the National Natural Science Foundation of China ( Grant Nos. 61104148, 41174109, and 50974095)the National Science and Technology Major Project of the Ministry of Science and Technology of China (Grant No. 2011ZX05020-006)the Specialized Research Fund for the Doctoral Program of Higher Education of China (Grant No. 20110032120088)
文摘We generate a directed weighted complex network by a method based on Markov transition probability to represent an experimental two-phase flow. We first systematically carry out gas-liquid two-phase flow experiments for measuring the time series of flow signals. Then we construct directed weighted complex networks from various time series in terms of a network generation method based on Markov transition probability. We find that the generated network inherits the main features of the time series in the network structure. In particular, the networks from time series with different dynamics exhibit distinct topological properties. Finally, we construct two-phase flow directed weighted networks from experimental signals and associate the dynamic behavior of gas-liquid two-phase flow with the topological statistics of the generated networks. The results suggest that the topological statistics of two-phase flow networks allow quantitative characterization of the dynamic flow behavior in the transitions among different gas-liquid flow patterns.
文摘There are many techniques using sensors and wearable devices for detecting and monitoring patients with Parkinson’s disease(PD).A recent development is the utilization of human interaction with computer keyboards for analyzing and identifying motor signs in the early stages of the disease.Current designs for classification of time series of computer-key hold durations recorded from healthy control and PD subjects require the time series of length to be considerably long.With an attempt to avoid discomfort to participants in performing long physical tasks for data recording,this paper introduces the use of fuzzy recurrence plots of very short time series as input data for the machine training and classification with long short-term memory(LSTM)neural networks.Being an original approach that is able to both significantly increase the feature dimensions and provides the property of deterministic dynamical systems of very short time series for information processing carried out by an LSTM layer architecture,fuzzy recurrence plots provide promising results and outperform the direct input of the time series for the classification of healthy control and early PD subjects.
文摘In this article we shall examine several different types of figurative numbers which have been studied extensively over the period of 2500 years, and currently scattered on hundreds of websites. We shall discuss their computation through simple recurrence relations, patterns and properties, and mutual relationships which have led to curious results in the field of elementary number theory. Further, for each type of figurative numbers we shall show that the addition of first finite numbers and infinite addition of their inverses often require new/strange techniques. We sincerely hope that besides experts, students and teachers of mathematics will also be benefited with this article.
基金supported by the National Natural Science Foundation of China (40930101,40971218)the 948 Program,Ministry of Agriculture of China (2009-Z31)the Foundation for National Non-Profit Scientific Institution,Ministry of Finance of China (IARRP-2010-2)
文摘This study used time-series of global inventory modeling and mapping studies (GIMMS) normalized difference vegetation index (NDVI) datasets at a spatial resolution of 8 km and 15-d interval to investigate the spatial patterns of cropland phenology in China. A smoothing algorithm based on an asymmetric Gaussian function was first performed on NDVI dataset to minimize the effects of anomalous values caused by atmospheric haze and cloud contamination. Subsequent processing for identifying cropping systems and extracting phenological parameters, the starting date of growing season (SGS) and the ending date of growing season (EGS) was based on the smoothed NVDI time-series data. The results showed that the cropping systems in China became complex as moving from north to south of China. Under these cropping systems, the SGS and EGS for the first growing season varied largely over space, and those regions with multiple cropping systems generally presented a significant advanced SGS and EGS than the regions with single cropping patterns. On the contrary, the phenological events of the second growing season including both the SGS and EGS showed little difference between regions. The spatial patterns of cropping systems and phenology in Chinese cropland were highly related to the geophysical environmental factors. Several anthropogenic factors, such as crop variety, cultivation levels, irrigation, and fertilizers, could profoundly influence crop phenological status. How to discriminate the impacts of biophysical forces and anthropogenic drivers on phenological events of cultivation remains a great challenge for further studies.
基金supported by National Natural Science Foundation of China(No.50877064)
文摘The chaotic characteristics of time series of five partial discharge (PD) patterns in oil-paper insulation are studied. The results verify obvious chaotic characteristic of the time series of discharge signals and the fact that PD is a chaotic process. These time series have distinctive features, and the chaotic attractors obtained from time series differed greatly from each other by shapes in the phase space, so they could be used to qualitatively identify the PD patterns. The phase space parameters are selected, then the chaotic characteristic quantities can be extracted. These quantities could quantificationally characterize the PD patterns. The effects on pattern recognition of PRPD and CAPD are compared by using the neural network of radial basis function. The results show that both of the two recognition methods work well and have their respective advantages. Then, both the statistical operators under PRPD mode and the chaotic characteristic quantities under CAPD mode are selected comprehensively as the input vectors of neural network, and the PD pattern recognition accuracy is thereby greatly improved.
基金Project supported by the National Natural Science Foundation of China (Grant No. 10847110)
文摘Various pattern evolutions are presented in one- and two-dimensional spatially coupled phase-conjugate systems (SCPCSs). As the system parameters change, different patterns are obtained from the period-doubling of kink-antikinks in space to the spatiotemporal chaos in a one-dimensional SCPCS. The homogeneous symmetric states induce symmetry breaking from the four corners and the boundaries, finally leading to spatiotemporal chaos with the increase of the iteration time in a two-dimensional SCPCS. Numerical simulations are very helpful for understanding the complex optical phenomena.
基金Fundamental Research Foundation for Universities of Heilongjiang Province,Grant/Award Number:LGYC2018JQ003。
文摘With the continuous development of machine learning and the increasing complexity of financial data analysis,it is more popular to use models in the field of machine learning to solve the hot and difficult problems in the financial industry.To improve the effectiveness of stock trend prediction and solve the problems in time series data processing,this paper combines the fuzzy affiliation function with stock-related technical indicators to obtain nominal data that can widely reflect the constituent stocks in the case of time series changes by analysing the S&P 500 index.Meanwhile,in order to optimise the current machine learning algorithm in which the setting and adjustment of hyperparameters rely too much on empirical knowledge,this paper combines the deep forest model to train the stock data separately.The experimental results show that(1)the accuracy of the extreme random forest and the accuracy of the multi-grain cascade forest are both higher than that of the gated recurrent unit(GRU)model when the un-fuzzy index-adjusted dataset is used as features for input,(2)the accuracy of the extreme random forest and the accuracy of the multigranular cascade forest are improved by using the fuzzy index-adjusted dataset as features for input,(3)the accuracy of the fuzzy index-adjusted dataset as features for inputting the extreme random forest is improved by 18.89% compared to that of the un-fuzzy index-adjusted dataset as features for inputting the extreme random forest and(4)the average accuracy of the fuzzy index-adjusted dataset as features for inputting multi-grain cascade forest increased by 5.67%.
文摘The motivation for this article is to propose new damage classifiers based on a supervised learning problem for locating and quantifying damage.A new feature extraction approach using time series analysis is introduced to extract damage-sensitive features from auto-regressive models.This approach sets out to improve current feature extraction techniques in the context of time series modeling.The coefficients and residuals of the AR model obtained from the proposed approach are selected as the main features and are applied to the proposed supervised learning classifiers that are categorized as coefficient-based and residual-based classifiers.These classifiers compute the relative errors in the extracted features between the undamaged and damaged states.Eventually,the abilities of the proposed methods to localize and quantify single and multiple damage scenarios are verified by applying experimental data for a laboratory frame and a four-story steel structure.Comparative analyses are performed to validate the superiority of the proposed methods over some existing techniques.Results show that the proposed classifiers,with the aid of extracted features from the proposed feature extraction approach,are able to locate and quantify damage;however,the residual-based classifiers yield better results than the coefficient-based classifiers.Moreover,these methods are superior to some classical techniques.
基金supported by Natural Science Foundation of Heilongjiang Province of China(No.D201252)
文摘Chronic myeloid leukemia(CML) is characterized by the accumulation of active BCR-ABL protein. Imatinib is the first-line treatment of CML; however, many patients are resistant to this drug. In this study, we aimed to compare the differences in expression patterns and functions of time-series genes in imatinib-resistant CML cells under different drug treatments. GSE24946 was downloaded from the GEO database, which included 17 samples of K562-r cells with(n=12) or without drug administration(n=5). Three drug treatment groups were considered for this study: arsenic trioxide(ATO), AMN107, and ATO+AMN107. Each group had one sample at each time point(3, 12, 24, and 48 h). Time-series genes with a ratio of standard deviation/average(coefficient of variation) 〉0.15 were screened, and their expression patterns were revealed based on Short Time-series Expression Miner(STEM). Then, the functional enrichment analysis of time-series genes in each group was performed using DAVID, and the genes enriched in the top ten functional categories were extracted to detect their expression patterns. Different time-series genes were identified in the three groups, and most of them were enriched in the ribosome and oxidative phosphorylation pathways. Time-series genes in the three treatment groups had different expression patterns and functions. Time-series genes in the ATO group(e.g. CCNA2 and DAB2) were significantly associated with cell adhesion, those in the AMN107 group were related to cellular carbohydrate metabolic process, while those in the ATO+AMN107 group(e.g. AP2M1) were significantly related to cell proliferation and antigen processing. In imatinib-resistant CML cells, ATO could influence genes related to cell adhesion, AMN107 might affect genes involved in cellular carbohydrate metabolism, and the combination therapy might regulate genes involved in cell proliferation.
文摘Since the candlestick patterns were mined,there is a contentious dispute on whether the candlestick patterns have predictive power in academia.To help resolve the debate,this paper uses the data mining methods of pattern recognition,pattern clustering and pattern knowledge mining to research the predictive power of candlestick patterns.In addition,we propose the similarity match model and nearest neighbor-clustering algorithm to solve the problem of similarity match and clustering of candlestick series,respectively.The experiment includes testing the predictive power of the Morning Star pattern and Evening Star pattern with the testing dataset of the candlestick series data of Shanghai 180 index component stocks over the latest 10 years.Experimental results show that(1)There have some spurious patterns in the existing candlestick patterns.However,after further classification of a spurious pattern based on its shape feature,those patterns with special shapes still have predictive power.(2)Some patterns do have the predictive power.(3)As there is no precise mathematical definition to describe the existing patterns’predictive power,it is essential to give the mathematical formula for improving the candlestick patterns’prediction performance.