A new approach to classification of MQAM/MPSK signals in multipath fading environments is presented. The proposed approach, in which the two-step equalization strategy and higher-order cumulants based classifier are adopted, can effectively classify the MPSK and high-order QAM signals. The performance of proposed approach is evaluated by the computer simulations, which shows it has better classification ability. I. INTRODUCTIONModulation Classification of a received signal plays an important role in a variety of military and commercial applications. The examples include spectrum monitoring and management, surveillance and control of broadcasting activities, adaptive transmission schemes, and electronic warfare. Although significant progress has been made in the areas of modulation classification in flat fading environments, less attention is paid to modulation classification in multipath fading environments. In multipath fading environments, the inter-symbol interference (ISI) causes the distortion of received signal, which deteriorates the performance of classification methods developed for the flat fading channels.Among the existing methods, Lay[1] employed persurvivor processing (PSP) to address modulation classification with an assumption of a known multipath channel impulse. Flusser[2] used so-called fading invariants to classify the signals, but the construction of the fading invariants requires the channel impulse response must be symmetrical, which is impractical in the applications. Paris[3] presented a classifier that incorporated blind channel identification into universal classifier, and discriminated only between 4QAM and 8QAM. Wang[4] presented an approach that also uses the blind equalization to mitigate effects of multipath fading, then clusters signal spatial distribution, and the resulting centres are extracted to match the standard constellation patterns. Theoretically, the method can classify MASK, MPSK and MQAM signals, but the actual ability to classify is restricted by the performance of the blind equalization. This method, generally speaking, can only classify the signal with modulation order no more than 32. Xi[5] utilized higher-order statistics (HOS) to identify the channel, then the estimated channel was used to modify the higher-order cumulants based classifier for the flat fading channel. It should be noted that the classifier itself don't distinguish the signals with high order modulation. On the other hand, if the error of channel estimation is considered, the method performs more poorly.

Osteoporosis is a significant global health concern that can be difficult to detect early due to a lack of symptoms. At present, the examination of osteoporosis depends mainly on methods containing dual-energy X-ray, quantitative CT, etc., which are high costs in terms of equipment and human time. Therefore, a more efficient and economical method is urgently needed for diagnosing osteoporosis. With the development of deep learning, automatic diagnosis models for various diseases have been proposed. However, the establishment of these models generally requires images with only lesion areas, and annotating the lesion areas is time-consuming. To address this challenge, we propose a joint learning framework for osteoporosis diagnosis that combines localization, segmentation, and classification to enhance diagnostic accuracy. Our method includes a boundary heat map regression branch for thinning segmentation and a gated convolution module for adjusting context features in the classification module. We also integrate segmentation and classification features and propose a feature fusion module to adjust the weight of different levels of vertebrae. We trained our model on a self-built dataset and achieved an overall accuracy rate of 93.3% for the three label categories (normal, osteopenia, and osteoporosis) in the testing datasets. The area under the curve for the normal category is 0.973; for the osteopenia category, it is 0.965; and for the osteoporosis category, it is 0.985. Our method provides a promising alternative for the diagnosis of osteoporosis at present.

Vascular images contain a lot of key information, such as length, diameter and distribution. Thus reconstruction of vessels such as the Superior Mesenteric Artery is critical for the diagnosis of some abdominal diseases. However automatic segmentation of abdominal vessels is extremely challenging due to the multi-scale nature of vessels, boundary-blurring, low contrast, artifact disturbance and vascular cracks in Maximum Intensity Projection images. In this work, we propose a dual attention guided method where an adaptive adjustment field is applied to deal with multi-scale vessel information, and a channel feature fusion module is used to refine the extraction of thin vessels, reducing the interference and background noise. In particular, we propose a novel structure that accepts multiple sequential images as input, and successfully introduces spatial-temporal features by contextual information. A further IterUnet step is introduced to connect tiny cracks caused using CT scans. Comparing our proposed model with other state-of-the-art models, our model yields better segmentation and achieves an average F1 metric of 0.812.

No abstract

No abstract