To enhance the accuracy of intuitionistic fuzzy time series forecasting model, this paper analyses the influence of universe of discourse partition and compares with relevant literature. Traditional models usually par...To enhance the accuracy of intuitionistic fuzzy time series forecasting model, this paper analyses the influence of universe of discourse partition and compares with relevant literature. Traditional models usually partition the global universe of discourse, which is not appropriate for all objectives. For example, the universe of the secular trend model is continuously variational. In addition, most forecasting methods rely on prior information, i.e., fuzzy relationship groups (FRG). Numerous relationship groups lead to the explosive growth of relationship library in a linear model and increase the computational complexity. To overcome problems above and ascertain an appropriate order, an intuitionistic fuzzy time series forecasting model based on order decision and adaptive partition algorithm is proposed. By forecasting the vector operator matrix, the proposed model can adjust partitions and intervals adaptively. The proposed model is tested on student enrollments of Alabama dataset, typical seasonal dataset Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) and a secular trend dataset of total retail sales for social consumer goods in China. Experimental results illustrate the validity and applicability of the proposed method for different patterns of dataset.展开更多
提出了一种模糊最优间隔分布矩阵分类器(Fuzzy Optimal-margin Distribution Matrix Classifier,FODMC)。该模型通过整合模糊隶属度理论与间隔分布优化机制,实现了矩阵结构信息的有效提取与异常值的鲁棒处理。具体而言,FODMC采用基于间...提出了一种模糊最优间隔分布矩阵分类器(Fuzzy Optimal-margin Distribution Matrix Classifier,FODMC)。该模型通过整合模糊隶属度理论与间隔分布优化机制,实现了矩阵结构信息的有效提取与异常值的鲁棒处理。具体而言,FODMC采用基于间隔分布的损失函数来优化分类边界,结合核范数正则化策略保持矩阵的低秩特性,并利用交替方向乘子法(Alternating Direction Method of Multipliers,ADMM)实现模型的高效训练。在多个基准数据集上的实验结果表明:与现有方法相比,FODMC在分类准确率、鲁棒性和泛化能力等方面均展现出显著优势,为矩阵数据分类问题提供了一种有效的解决方案。展开更多
To make the modulation classification system more suitable for signals in a wide range of signal to noise rate （SNR）, a feature extraction method based on signal wavelet packet transform modulus maxima matrix （WPT...To make the modulation classification system more suitable for signals in a wide range of signal to noise rate （SNR）, a feature extraction method based on signal wavelet packet transform modulus maxima matrix （WPTMMM） and a novel support vector machine fuzzy network （SVMFN） classifier is presented. The WPTMMM feature extraction method has less computational complexity, more stability, and has the preferable advantage of robust with the time parallel moving and white noise. Further, the SVMFN uses a new definition of fuzzy density that incorporates accuracy and uncertainty of the classifiers to improve recognition reliability to classify nine digital modulation types （i.e. 2ASK, 2FSK, 2PSK, 4ASK, 4FSK, 4PSK, 16QAM, MSK, and OQPSK）. Computer simulation shows that the proposed scheme has the advantages of high accuracy and reliability （success rates are over 98% when SNR is not lower than 0dB）, and it adapts to engineering applications.展开更多
基金supported by the National Natural Science Foundation of China(61309022)
文摘To enhance the accuracy of intuitionistic fuzzy time series forecasting model, this paper analyses the influence of universe of discourse partition and compares with relevant literature. Traditional models usually partition the global universe of discourse, which is not appropriate for all objectives. For example, the universe of the secular trend model is continuously variational. In addition, most forecasting methods rely on prior information, i.e., fuzzy relationship groups (FRG). Numerous relationship groups lead to the explosive growth of relationship library in a linear model and increase the computational complexity. To overcome problems above and ascertain an appropriate order, an intuitionistic fuzzy time series forecasting model based on order decision and adaptive partition algorithm is proposed. By forecasting the vector operator matrix, the proposed model can adjust partitions and intervals adaptively. The proposed model is tested on student enrollments of Alabama dataset, typical seasonal dataset Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) and a secular trend dataset of total retail sales for social consumer goods in China. Experimental results illustrate the validity and applicability of the proposed method for different patterns of dataset.
文摘提出了一种模糊最优间隔分布矩阵分类器(Fuzzy Optimal-margin Distribution Matrix Classifier,FODMC)。该模型通过整合模糊隶属度理论与间隔分布优化机制,实现了矩阵结构信息的有效提取与异常值的鲁棒处理。具体而言,FODMC采用基于间隔分布的损失函数来优化分类边界,结合核范数正则化策略保持矩阵的低秩特性,并利用交替方向乘子法(Alternating Direction Method of Multipliers,ADMM)实现模型的高效训练。在多个基准数据集上的实验结果表明:与现有方法相比,FODMC在分类准确率、鲁棒性和泛化能力等方面均展现出显著优势,为矩阵数据分类问题提供了一种有效的解决方案。
文摘To make the modulation classification system more suitable for signals in a wide range of signal to noise rate （SNR）, a feature extraction method based on signal wavelet packet transform modulus maxima matrix （WPTMMM） and a novel support vector machine fuzzy network （SVMFN） classifier is presented. The WPTMMM feature extraction method has less computational complexity, more stability, and has the preferable advantage of robust with the time parallel moving and white noise. Further, the SVMFN uses a new definition of fuzzy density that incorporates accuracy and uncertainty of the classifiers to improve recognition reliability to classify nine digital modulation types （i.e. 2ASK, 2FSK, 2PSK, 4ASK, 4FSK, 4PSK, 16QAM, MSK, and OQPSK）. Computer simulation shows that the proposed scheme has the advantages of high accuracy and reliability （success rates are over 98% when SNR is not lower than 0dB）, and it adapts to engineering applications.
