1D-CONVOLUTIONAL AUTOENCODER BASED HYPERSPECTRAL DATA COMPRESSION

Hyperspectral sensor technology has been advancing in recent years and become more practical to tackle a variety of applications. The arising issues of data transmission and storage can be addressed with the help of compression. To minimize the loss of important information, high spectral correlation between adjacent bands is exploited. In this paper, we introduce an approach to compress hyperspectral data based on a 1D-Convolutional Autoencoder. Compression is achieved through reducing correlation by transforming the spectral signature into a low-dimensional space, while simultaneously preserving the significant features. The focus lies on compression of the spectral dimension. The spatial dimension is not used in the compression in order not to falsify correlation between the spectral dimension and accuracy of the reconstruction. The proposed 1D-Convolutional Autoencoder efficiently finds and extracts features relevant for compression. Additionally, it can be exploited as a feature extractor or for dimensionality reduction. The hyperspectral data sets Greding Village and Pavia University were used for the training and the evaluation process. The reconstruction accuracy is evaluated using the Signal to Noise Ratio and the Spectral Angle. Additionally, a land cover classification using a multi-class Support Vector Machine is used as a target application. The classification performance of the original and reconstructed data are compared. The reconstruction accuracy of the 1D-Convolutional Autoencoder outperforms the Deep Autoencoder and Nonlinear Principal Component Analysis for the used metrics and for both data sets using a fixed compression ratio.

Adaptive multi-layer structure with spatial-spectrum combination for hyperspectral image anomaly detection

A new algorithm for hyperspectral image anomaly detection is proposed by designing an adaptive multi-layer structure with spatial-spectral combination information, which is different from the traditional anomaly detection algorithms only considering the spectral difference between the anomaly point and the background pixels, and ignoring the difference between the local spatial structure and spectrum. Firstly, the present algorithm not only calculates the spectral dimension difference between the pixels to be measured and the pixels in the background window, but also measures the spatial structure difference between the internal window and the background window. Mostly, an adaptive multi-layer structure for anomaly detection framework is carried out based on the idea of background suppression, and a multi-layered anomaly detector is constructed. The anomaly detection results of each layer of the detector are taken as the constraints, and the background information of the image input in the detector of the next layer is suppressed, adaptively suppressing the background noises. The experimental results show that the present algorithm makes better use of both the local spatial structure and the spectral dimension information than the traditional two-window models (global RX, local RX and KRX), adaptively suppresses background, reduces the false alarm rate, and improves the detection effect of the abnormal targets with fewer pixels.

Dimension-Selective Attention and Dimensional Salience Modulate Cortical Tracking of Acoustic Dimensions

Some theories of auditory categorization suggest that auditory dimensions that are strongly diagnostic for particular categories - for instance voice onset time or fundamental frequency in the case of some spoken consonants - attract attention. However, prior cognitive neuroscience research on auditory selective attention has largely focused on attention to simple auditory objects or streams, and so little is known about the neural mechanisms that underpin dimension-selective attention, or how the relative salience of variations along these dimensions might modulate neural signatures of attention. Here we investigate whether dimensional salience and dimension-selective attention modulate cortical tracking of acoustic dimensions. In two experiments, participants listened to tone sequences varying in pitch and spectral peak frequency; these two dimensions changed at systematically different rates. Inter-trial phase coherence (ITPC) and EEG signal amplitude at the rates of pitch and spectral change allowed us to measure cortical tracking of these dimensions. In Experiment 1, tone sequences varied in the size of the pitch intervals, while the size of spectral peak intervals remained constant. Neural entrainment to pitch changes was greater for sequences with larger compared to smaller pitch intervals, with no difference in entrainment to the spectral dimension. In Experiment 2, participants selectively attended to either the pitch or spectral dimension. Neural entrainment was stronger in response to the attended compared to unattended dimension for both pitch and spectral dimensions. These findings demonstrate that bottom-up and top-down attentional mechanisms enhance the cortical tracking of different acoustic dimensions within a single sound stream.

Coding in the automorphism group of a computably categorical structure

Using new techniques for controlling the categoricity spectrum of a structure, we construct a structure with degree of categoricity but infinite spectral dimension, answering a question of Bazhenov, Kalimullin and Yamaleev. Using the same techniques, we construct a computably categorical structure of non-computable Scott rank.