Background: At present there are no objective, biological markers that can be used to reliably identify individuals with post-traumatic stress disorder (PTSD). This study assessed the diagnostic potential of structural magnetic resonance imaging (sMRI) for identifying trauma-exposed individuals with and without PTSD.Method: sMRI scans were acquired from 50 survivors of the Sichuan earthquake of 2008 who had developed PTSD, 50 survivors who had not developed PTSD and 40 healthy controls who had not been exposed to the earthquake. Support vector machine (SVM), a multivariate pattern recognition technique, was used to develop an algorithm that distinguished between the three groups at an individual level. The accuracy of the algorithm and its statistical significance were estimated using leave-one-out cross-validation and permutation testing.Results: When survivors with PTSD were compared against healthy controls, both grey and white matter allowed discrimination with an accuracy of 91% (p < 0.001). When survivors without PTSD were compared against healthy controls, the two groups could be discriminated with accuracies of 76% (p < 0.001) and 85% (p < 0.001) based on grey and white matter, respectively. Finally, when survivors with and without PTSD were compared directly, grey matter allowed discrimination with an accuracy of 67% (p < 0.001); in contrast the two groups could not be distinguished based on white matter.Conclusions: These results reveal patterns of neuroanatomical alterations that could be used to inform the identification of trauma survivors with and without PTSD at the individual level, and provide preliminary support to the development of SVM as a clinically useful diagnostic aid.

The technology of vital signs detection has been proven of great use, whereas it is still limited by several challenges. One of the major challenges is the random body movements (RBMs), which significantly degrade the accuracy of the measurement. In this paper, a multi-channel 77GHz linear frequency modulated continuous-wave (LFMCW) radar system is investigated to perform vital signs monitoring on multiple targets with the mitigation of RBMs and a novel vital signs detection scheme is provided for the accurate estimates of the respiration rate (RR) and heart rate (HR). In the proposed scheme, a multi-channel Kalman smoother is firstly proposed to address the outliers in the extracted phase histories from the echoes in the multiple receivers, so that enhanced outlier-robust phase histories are acquired for the subsequent estimates of the RR and HR. Furthermore, a novel regional hidden Markov model is then proposed to carry out accurate estimates of RR and HR by exploiting the underlying slowly-varying characteristics of these vital signs for further mitigation of the effects of RBMs. Experimental results demonstrate that the estimated errors in the proposed scheme are less than 2 beats per minute (bpm) for both RR and HR under normal scenarios with young men in the RBMs environment.

Compressive sensing (CS) applied to through-the-wall radar imaging (TWRI) exploits the group sparsity of a target scene in the presence of wall clutter and multipath from enclosed structures towards achieving high-resolution imaging with limited measurements. In this paper, we extend the CS-based TWRI to include the clustering structure property of the target within a hierarchical Bayesian framework. An extended structured spike-and-slab prior is imposed to statistically encourage spatially extended cluster structures of a target scene and model the signal group sparsity due to multipath propagation. The expectation propagation scheme is used for the approximate posterior inference. The proposed nonparametric Bayesian algorithm can achieve substantial improvements in terms of preserving a target cluster structure and suppressing isolated spurious false alarms compared to other state-of-the-art algorithms. Furthermore, it does not require prior information about the targets themselves, such as size, shape or number.

Human–vehicle classification is an essential component to avoiding accidents in autonomous driving. The classification technique based on the automotive radar sensor has been paid more attention by related researchers, owing to its robustness to low-light conditions and severe weather. In the paper, we propose a hybrid support vector machine–convolutional neural network (SVM-CNN) approach to address the class-imbalance classification of vehicles and pedestrians with limited experimental radar data available. A two-stage scheme with the combination of feature-based SVM technique and deep learning-based CNN is employed. In the first stage, the modified SVM technique based on these distinct physical features is firstly used to recognize vehicles to effectively alleviate the imbalance ratio of vehicles to pedestrians in the data level. Then, the residual unclassified images will be used as inputs to the deep network for the subsequent classification, and we introduce a weighted false error function into deep network architectures to enhance the class-imbalance classification performance at the algorithm level. The proposed SVM-CNN approach takes full advantage of both the locations of underlying class in the entire Range-Doppler image and automatical local feature learning in the CNN with sliding filter bank to improve the classification performance. Experimental results demonstrate the superior performances of the proposed method with the $F_1$ score of $0.90$ and area under the curve (AUC) of the receiver operating characteristic (ROC) of $0.99$ over several state-of-the-art methods with limited experimental radar data available in a 77 GHz automotive radar.

Sparse arrays have obvious superiority in array element layout and the number of degrees of freedom (DOF) for resolving more sources than the number of physical sensors with high estimation accuracy. Nevertheless, any of the existing array configurations with fixed number of sensors corresponds to a certain array element arrangement, the virtual coarray and the uniform DOF may be affected significantly when the positions of one or several sensors changed. In this paper, a generalized nested array (GNA) configuration family is proposed by incorporating the concept of family into array design. The arrays in GNA family generally consist of three subarrays, and the inherent geometric characteristic is analyzed from the perspective of two-dimensional (2D) representation. For the array configurations of GNA family, one can be transformed into another by setting order factor, thus they can provide more flexible element arrangements as compared to a specific array configuration. Moreover, each array of the GNA family has hole-free difference coarray. Based on the GNA family, compressive sensing (CS) approach is employed for direction-of-arrival (DOA) estimation by solving an l ₁ norm minimization problem. The theoretical propositions are proved and numerical simulations are performed to demonstrate the superior performance of the proposed GNA family and the DOA estimation.