In the remote sensing image processing field, the synthetic aperture radar (SAR) target-detection methods based on convolutional neural networks (CNNs) have gained remarkable performance relying on ...large-scale labeled data. However, it is hard to obtain many labeled SAR images. Semi-supervised learning is an effective way to address the issue of limited labels on SAR images because it uses unlabeled data. In this paper, we propose an improved faster regions with CNN features (R-CNN) method, with a decoding module and a domain-adaptation module called FDDA, for semi-supervised SAR target detection. In FDDA, the decoding module is adopted to reconstruct all the labeled and unlabeled samples. In this way, a large number of unlabeled SAR images can be utilized to help structure the latent space and learn the representative features of the SAR images, devoting attention to performance promotion. Moreover, the domain-adaptation module is further introduced to utilize the unlabeled SAR images to promote the discriminability of features with the assistance of the abundantly labeled optical remote sensing (ORS) images. Specifically, the transferable features between the ORS images and SAR images are learned to reduce the domain discrepancy via the mean embedding matching, and the knowledge of ORS images is transferred to the SAR images for target detection. Ultimately, the joint optimization of the detection loss, reconstruction, and domain adaptation constraints leads to the promising performance of the FDDA. The experimental results on the measured SAR image datasets and the ORS images dataset indicate that our method achieves superior SAR target detection performance with limited labeled SAR images.
Statistical modeling for radar high-resolution range profile (HRRP) is a challenging task in radar HRRP statistical recognition. Theoretical analysis and experimental results show that elements in an ...HRRP sample are statistically correlated and non-Gaussian distributed. First, this paper introduces three joint-Gaussian models, i.e., subspace approximation model, probability principal components analysis (PPCA) model and factor analysis (FA) model, into radar HRRP statistical recognition. Due to the experimental results, we can have the conclusion that the jointly non-Gaussian distributed HRRP samples approximately follow the joint-Gaussian distribution described by FA model. Therefore, we can apply FA model to radar HRRP statistical recognition rather than a joint-Gaussian mixture model, e.g., PPCA mixture model or FA mixture model, which is a more accurate choice for modeling non-Gaussian distributed correlations in multidimensional data but with high learning complexity and large computation burden, and the difficulty in the statistical modeling for HRRP samples is largely reduced. Second, this paper concerns model selection of FA model in radar HRRP statistical recognition, in which there are two issues, i.e., the partition of target-aspect frames and the determination of the number of factors in each frame. Based on the Akaike information criterion (AIC) and the Bayes' information criterion (BIC), an iterated algorithm for model selection is proposed in this paper, which can automatically give the optimal aspect-frame boundaries and determine the optimal number of factors in each aspect-frame. The recognition experiments based on measured data show that the proposed adaptive partition approach can further improve the recognition performance with higher recognition efficiency.
The single shot multibox detector (SSD), a proposal-free method based on convolutional neural network (CNN), has recently been proposed for target detection and has found applications in synthetic ...aperture radar (SAR) images. Moreover, the saliency information reflected in the saliency map can highlight the target of interest while suppressing clutter, which is beneficial for better scene understanding. Therefore, in this article, we propose a saliency-guided SSD (S-SSD) for target detection in SAR images, in which we effectively integrate the saliency into the SSD network not only to suggest where to focus on but also to improve the representation capability in complex scenes. The proposed S-SSD contains two separated convolutional backbone subnetwork architectures, one with the original SAR image as input to extract features, and the other with the corresponding saliency map obtained from the modified Itti's method as input to acquire refined saliency information under supervision. In addition, the dense connection structure, instead of the plain structure used in original SSD, is applied in the two convolutional backbone architectures to utilize multiscale information with fewer parameters. Then, for integrating saliency information to guide the network to emphasize informative regions, multilevel fusion modules are utilized to merge the two streams into a unified framework, thereby making the whole network end-to-end jointly trained. Finally, the convolutional predictors are used to predict targets. The experimental results on the miniSAR real data demonstrate that the proposed S-SSD can achieve better detection performance than state-of-the-art methods.
Neuroligins (NLs) are critical for synapse formation and function. NL3 R451C is an autism-associated mutation. NL3 R451C knockin (KI) mice exhibit autistic behavioral abnormalities, including social ...novelty deficits. However, neither the brain regions involved in social novelty nor the underlying mechanisms are clearly understood. Here, we found decreased excitability of fast-spiking interneurons and dysfunction of gamma oscillation in the medial prefrontal cortex (mPFC), which contributed to the social novelty deficit in the KI mice. Neuronal firing rates and phase-coding abnormalities were also detected in the KI mice during social interactions. Interestingly, optogenetic stimulation of parvalbumin interneurons in the mPFC at 40 Hz nested at 8 Hz positively modulated the social behaviors of mice and rescued the social novelty deficit in the KI mice. Our findings suggest that gamma oscillation dysfunction in the mPFC leads to social deficits in autism, and manipulating mPFC PV interneurons may reverse the deficits in adulthood.
•Gamma and theta oscillation synchrony in mPFC is crucial for social behavior•Principal neuron encoding dysfunction in mPFC is associated with social deficits•Decreased FS IN excitability in mPFC is a causative factor in NL3-R451C KI mice•Patterned optogenetic stimulation of mPFC PV INs rescues social deficit in KI mice
Cao et al. demonstrated FS interneuron deficits and gamma oscillation dysfunction in the mPFC of NL3-R451C KI mice, and the social novelty defect in the KI mice rescued by optogenetic stimulation of the PV interneurons in a theta-gamma nested pattern.
Target detection for synthetic aperture radar (SAR) images has great influence on the successive discrimination based on the target regions. However, as a pixel-based method, the traditional constant ...false alarm rate (CFAR) detection could not work well for the ship target detection problem of multiple ship targets with different sizes in a SAR image, which is referred to as the multiscale situation. Moreover, it needs to use the clustering method on the pixel-level detection results to obtain the accurate target regions, which may merge two or more different targets into a target region. In this letter, a modified CFAR based on object proposals is proposed. We use the object proposal generator to generate a small set of object proposals with different sizes, and then use the proposal-based CFAR detector, where the extracted object proposals are regarded as the guard windows instead of setting fixed guard window, to detect the true positive object proposals. By introducing the object proposals as the variable guard windows in the CFAR detector, the proposed algorithm could gain good detection performance in the multiscale situation, since the missed detection resulting from the big differences between the sizes of the fixed guard window and ship targets can be avoided. Meanwhile, the proposed method can directly obtain the accurate target regions. The effectiveness of the proposed algorithm is verified using the measured SAR data.
•We comprehensively evaluate both sleep disorders and non-sleep circadian disorders are as predictors of the onset of depression.•Subjective sleep disorders predict future depression, while objective ...short sleep duration is contradictory to that of subjective short sleep duration.•Non-sleep circadian disorders are as a predictor of depression, although there are not enough studies to include in a meta-analysis.
Patients with depression often suffer from sleep disorders and non-sleep circadian disorders. However, whether they precede and predict subsequent depression is unclear. We conducted a meta-analysis of studies on sleep disorders and non-sleep circadian disorders. We found insomnia, hypersomnia, short and long sleep duration, obstructive sleep apnea, restless legs syndrome and eveningness orientation at baseline all led to subsequent depression. Those with propensity to late meal patterns, heightened levels of cortisol in awakening response and low robustness of rest-activity rhythm at baseline had higher risks for later depression. Among insomnia subtypes, difficulty initiating sleep and difficulty maintaining sleep predicted future depression. Notably, persistent insomnia at baseline contributed to more than two-fold risk of incident depression compared to insomnia. Moreover, insomnia symptom numbers showed dose-dependent relationship with the incident depression. In conclusion, different types of sleep disorders and non-sleep circadian disorders were proven to be risk factors of subsequent depression, and mechanisms underlying the relationship between sleep disorders, non-sleep circadian disorders and subsequent depression should be further elucidated in the future.
Target discrimination plays an important role in the typical synthetic aperture radar (SAR) automatic target recognition (ATR) system. The conventional discrimination features roughly describing the ...difference between the target and the clutter are useful to discriminate the target from natural clutter, but these features may not well discriminate the target from the artificial clutter. To solve the above problem, a new algorithm for target discrimination is proposed based on the scattering center feature and the K-center one-class classification in this paper. The amplitudes and locations of the scattering centers have not been used as discrimination feature to our best knowledge, even though the distributions of the scattering centers associated with the targets are different from those of the natural clutter and artificial clutter. Then, since the scattering center feature is a typical kind of point set feature, we improve the K-center one-class classification based on Hausdorff distance (HD), where HD is a distance measure for the point set feature. Experimental results based on the measured MiniSAR dataset show that the discrimination performance of the scattering center feature is better than that of the conventional discrimination features, especially for the artificial clutter.
In the statistical target recognition based on radar high-resolution range profile (HRRP), two challenging tasks are how to deal with the target-aspect, time-shift, and amplitude-scale sensitivity of ...HRRP and how to accurately describe HRRPs statistical characteristics. In this paper, based on the scattering center model, range cells are classified, in accordance with the number of predominant scatterers in each cell, into three statistical types. After resolving the three sensitivity problems, this paper develops a statistical model comprising two distribution forms, i.e., Gamma distribution and Gaussian mixture distribution, to model echoes of different types of range cells as the corresponding distribution forms. Determination of the type of a range cell is achieved by using the rival penalized competitive learning (RPCL) algorithm, while estimation for the parameters of Gamma distribution and Gaussian mixture distribution by the maximum likelihood (ML) method and the expectation-maximization (EM) algorithm, respectively. Experimental results for measured data show that the proposed statistical model not only has better recognition performance but also is more robust to noises than the two existing statistical models, i.e., Gaussian model and Gamma model.
Two-dimensional materials with intrinsic magnetism are considered as ideal candidate for spintronic application. Herein, we investigated the effect of vacancy and strain on the electronic and ...magnetic properties of two-dimensional CrX2 (X=S, Se, Te). Perfect CrX2 was predicted to be nonmagnetic semiconductor. After considering the Cr vacancy, CrS2 and CrSe2 behave as ferromagnetic metal and semiconductor, and CrTe2 is antiferromagnetic metal. CrX2 with Cr vacancy and biaxial strain exhibits a rich phase diagram. Finally, we discuss the mechanism of vacancy induced magnetism and strain induced phase transition. Our research may offer some valuable hints for the application of CrX2 in spintronic devices.
•Two-dimensional monolayer CrX2 (X=S, Se, Te) are predicted to be non-magnetic semiconductors.•The introduced Cr vacancy induce the intrinsic magnetism of CrX2.•The biaxial strain leads to a rich phase diagram of CrX2 with Cr vacancy.•The mechanisms of vacancy and phase transition are discussed.
As an efficient way to interpret the measurements of high-frequency synthetic aperture radar (SAR), an attributed scattering center (ASC) model provides concise and physically relevant features of ...complex targets. However, accurate extractions of ASCs have been heavily penalized by high memory requirements and computational complexity. We propose to convert SAR measurements to sparse representations in the image domain where the ASC model parameters can be estimated by using an orthogonal matching pursuit (OMP) algorithm or its Newtonlized variation. Two important new properties of the ASC model are unveiled in the image domain, namely, "translatability" and "additivity." The properties can help save the dictionary of OMP from sampling the position and length parameters. The atoms of the dictionary become localized, thereby reducing the dictionary size and accelerating ASC extractions. Extensive experiments are conducted based on open-source XPATCH Backhoe data, measured MSTAR data, and synthetic backscatter data. The results show that the proposed approach is able to outperform existing image-domain algorithms in terms of accuracy and noise resistance, and outperform existing frequency-domain algorithms in terms of memory requirement and runtime.
PDF
