高光谱遥感图像中不仅存在空间域噪声而且存在光谱域噪声.传统的图像滤波仅对图像空间域噪声进行处理,而不能去除光谱域噪声,为改进这种状况,提出了DSGF(Derivative based Savitzky-Golay F ilter)方法.首先,基于反射率光谱的二阶导数...高光谱遥感图像中不仅存在空间域噪声而且存在光谱域噪声.传统的图像滤波仅对图像空间域噪声进行处理,而不能去除光谱域噪声,为改进这种状况,提出了DSGF(Derivative based Savitzky-Golay F ilter)方法.首先,基于反射率光谱的二阶导数对反射率光谱各波段噪声大小进行判定,然后用不同大小平滑窗的Savitzky-Golay滤波器对反射率光谱作两步滤波.对高光谱图像进行的逐像元DSGF滤波,在去除光谱域中噪声的同时,保留了图像反射率光谱的大部分细微特征.展开更多
Human speech indirectly represents the mental state or emotion of others.The use of Artificial Intelligence(AI)-based techniques may bring revolution in this modern era by recognizing emotion from speech.In this study...Human speech indirectly represents the mental state or emotion of others.The use of Artificial Intelligence(AI)-based techniques may bring revolution in this modern era by recognizing emotion from speech.In this study,we introduced a robust method for emotion recognition from human speech using a well-performed preprocessing technique together with the deep learning-based mixed model consisting of Long Short-Term Memory(LSTM)and Convolutional Neural Network(CNN).About 2800 audio files were extracted from the Toronto emotional speech set(TESS)database for this study.A high pass and Savitzky Golay Filter have been used to obtain noise-free as well as smooth audio data.A total of seven types of emotions;Angry,Disgust,Fear,Happy,Neutral,Pleasant-surprise,and Sad were used in this study.Energy,Fundamental frequency,and Mel Frequency Cepstral Coefficient(MFCC)have been used to extract the emotion features,and these features resulted in 97.5%accuracy in the mixed LSTM+CNN model.This mixed model is found to be performed better than the usual state-of-the-art models in emotion recognition from speech.It also indicates that this mixed model could be effectively utilized in advanced research dealing with sound processing.展开更多
Rice yellow mottle is considered the most destructive disease threatening rice production in Africa. Early detection of this infection in rice is essential to limit its expansion and proliferation. However, there is n...Rice yellow mottle is considered the most destructive disease threatening rice production in Africa. Early detection of this infection in rice is essential to limit its expansion and proliferation. However, there is no research devoted to the spectral detection of rice yellow mottle virus (RYMV) infection, especially in the asymptomatic or early stages. This work proposes the use of hyperspectral fluorescence and reflectance data at leaf level for the detection of this disease in asymptomatic stages. A greenhouse experiment was therefore conducted to collect hyperspectral fluorescence and reflectance data at different stages of infection. These data allowed to calculate nine vegetation indices: one from fluorescence spectra and eight from reflectance spectra. A t-test made it possible to identify, from the second day after infection, four relevant reflectance vegetation indices to discriminate healthy leaves from those infected: these are Photochemical Reflectance Index (PRI), Transformed Chlorophyll Absorption in Reflectance Index (TCARI), Structure Intensive Pigment Index (SIPI) and Simple Ratio Pigment Index (SRPI). The fluorescence index was less sensitive in detecting infection. The four significant vegetation indices for the detection of RYMV were then used to build and evaluate models for discriminating plants according to their health status by the supervised classification of support vector machine (SVM) at different stages of infection. The maximum overall accuracy is 92.5% six days after inoculation (6 DAI). The sixth day after inoculation would be the adequate day to detect RYMV. This plants discrimination was validated by the mean reflectance spectra and by the histograms showing the differences between the average reflectance vegetation indices values of the two types of plants. Our results demonstrate the feasibility of differentiating RYMV-infected samples. They suggest that support vector machine learning models could be developed to diagnose RYMV-infected plants based on vegetation indices derived from spectral profiles at early stages of disease development.展开更多
文摘高光谱遥感图像中不仅存在空间域噪声而且存在光谱域噪声.传统的图像滤波仅对图像空间域噪声进行处理,而不能去除光谱域噪声,为改进这种状况,提出了DSGF(Derivative based Savitzky-Golay F ilter)方法.首先,基于反射率光谱的二阶导数对反射率光谱各波段噪声大小进行判定,然后用不同大小平滑窗的Savitzky-Golay滤波器对反射率光谱作两步滤波.对高光谱图像进行的逐像元DSGF滤波,在去除光谱域中噪声的同时,保留了图像反射率光谱的大部分细微特征.
文摘Human speech indirectly represents the mental state or emotion of others.The use of Artificial Intelligence(AI)-based techniques may bring revolution in this modern era by recognizing emotion from speech.In this study,we introduced a robust method for emotion recognition from human speech using a well-performed preprocessing technique together with the deep learning-based mixed model consisting of Long Short-Term Memory(LSTM)and Convolutional Neural Network(CNN).About 2800 audio files were extracted from the Toronto emotional speech set(TESS)database for this study.A high pass and Savitzky Golay Filter have been used to obtain noise-free as well as smooth audio data.A total of seven types of emotions;Angry,Disgust,Fear,Happy,Neutral,Pleasant-surprise,and Sad were used in this study.Energy,Fundamental frequency,and Mel Frequency Cepstral Coefficient(MFCC)have been used to extract the emotion features,and these features resulted in 97.5%accuracy in the mixed LSTM+CNN model.This mixed model is found to be performed better than the usual state-of-the-art models in emotion recognition from speech.It also indicates that this mixed model could be effectively utilized in advanced research dealing with sound processing.
文摘Rice yellow mottle is considered the most destructive disease threatening rice production in Africa. Early detection of this infection in rice is essential to limit its expansion and proliferation. However, there is no research devoted to the spectral detection of rice yellow mottle virus (RYMV) infection, especially in the asymptomatic or early stages. This work proposes the use of hyperspectral fluorescence and reflectance data at leaf level for the detection of this disease in asymptomatic stages. A greenhouse experiment was therefore conducted to collect hyperspectral fluorescence and reflectance data at different stages of infection. These data allowed to calculate nine vegetation indices: one from fluorescence spectra and eight from reflectance spectra. A t-test made it possible to identify, from the second day after infection, four relevant reflectance vegetation indices to discriminate healthy leaves from those infected: these are Photochemical Reflectance Index (PRI), Transformed Chlorophyll Absorption in Reflectance Index (TCARI), Structure Intensive Pigment Index (SIPI) and Simple Ratio Pigment Index (SRPI). The fluorescence index was less sensitive in detecting infection. The four significant vegetation indices for the detection of RYMV were then used to build and evaluate models for discriminating plants according to their health status by the supervised classification of support vector machine (SVM) at different stages of infection. The maximum overall accuracy is 92.5% six days after inoculation (6 DAI). The sixth day after inoculation would be the adequate day to detect RYMV. This plants discrimination was validated by the mean reflectance spectra and by the histograms showing the differences between the average reflectance vegetation indices values of the two types of plants. Our results demonstrate the feasibility of differentiating RYMV-infected samples. They suggest that support vector machine learning models could be developed to diagnose RYMV-infected plants based on vegetation indices derived from spectral profiles at early stages of disease development.
