Network intrusion detection system (NIDS) is a commonly used tool to detect attacks and protect networks, while one of its general limitations is the false positive issue. On the basis of our comparative experiments and analysis for the characteristics of the particle swarm optimization (PSO) and Xgboost, this paper proposes the PSO-Xgboost model given its overall higher classification accuracy than other alternative models such like Xgboost, Random Forest, Bagging and Adaboost. Firstly, a classification model based on Xgboost is constructed, and then PSO is used to adaptively search for the optimal structure of Xgboost. The benchmark NSL-KDD dataset is used to evaluate the proposed model. Our experimental results demonstrate that PSO-Xgboost model outperforms other comparative models in precision, recall, macro-average (macro) and mean average precision (mAP), especially when identifying minority groups of attacks like U2R and R2L. This work also provides experimental arguments for the application of swarm intelligence in NIDS.

Depth image-based rendering (DIBR) techniques play an important role in free viewpoint videos (FVVs), which have a wide range of applications including immersive entertainment, remote monitoring, education, etc. FVVs are usually synthesized by DIBR techniques in a “blind” environment (without a reference video). Thus, an effective reference-free synthesized video quality assessment (VQA) metric is vital. At present, many image quality assessment (IQA) algorithms for DIBR-synthesized images have been proposed, but limited researches have been concerned about the quality assessment of DIBR-synthesized videos. To this end, this paper proposes a novel reference-free VQA method for synthesized videos, which operates in Spatial and Temporal Domains, dubbed as STD. The design fundamental of the proposed STD metric considers the effects of two major distortions introduced by DIBR techniques on the visual quality of synthesized videos. First, considering the geometric distortion introduced by DIBR technologies can increase high-frequency contents of the synthesized frame, the influence of the geometric distortion on the visual quality of a synthesized video can be effectively evaluated by estimating high-frequency energies of each synthesized frame in spatial domain. Second, temporal inconsistency caused by DIBR techniques brings the temporal flicker distortion, which is one of the most annoying artifacts in DIBR-synthesized videos. In temporal domain, we quantify temporal inconsistency by measuring motion differences between consecutive frames. Specifically, optical flow method is first used to estimate the motion field between adjacent frames. Then, we calculate the structural similarity of adjacent optical flow fields and further adopt the structural similarity value to weight the pixel differences of adjacent optical flow fields. Experiments show that the above two features are able to well perceive the visual quality of DIBR-synthesized videos. Furthermore, since the two features are extracted from spatial and temporal domains, respectively, we integrate them using a linear weighting strategy to obtain our STD metric, which proves advantageous over two components and the competing state-of-the-art I/VQA methods. The source code is available at https://github.com/wgc-vsfm/DIBR-video-quality-assessment .

Gait recognition refers to video-based biometric techniques for recognizing subjects by walking patterns under a long-distance situation. Despite the progress of existing gait recognition methods, the recognition ability of subjects in carrying situations is still limited (e.g., carrying bags or wearing coats or jackets). To address this issue, this paper proposes to extract human gait information from different ranges of receptive fields, providing richer internal features of the deep network. Moreover, we propose two attention mechanisms, Local Pyramid Attention and Global Attention Fusion Learning, to focus on the key features in human gait from different perspectives. Depending on the different attention mechanisms employed in the network, three network variants are derived, where the Gait Pyramid Attention Network (GPAN) contains two attention mechanisms, while GPAN-P and GPAN-L contain a single attention mechanism. We evaluated our method on two large datasets, CASIA-B and OUMVLP. Experiments show that the proposed network gives an average rank-1 accuracy of 97.8% on CASIA-B under normal walking conditions. We also achieve 94.2% and 81.8% accuracy on CASIA-B dataset under the complex bag-walking and coat-walking scenarios, which are dramatically superior to the state-of-the-art methods.

Loop-closure detection is an indispensable module in the visual simultaneous localization and mapping (vSLAM) system. It typically consists of three main steps: image representation, loop-closure candidate selection, and loop-closure event verification. This article proposes a novel approach for loop-closure detection. In particular, we first introduce a lightweight convolutional auto-encoder network trained by the deep perceptual similarity loss for image representation. We then propose an image-to-sequence selection approach based on place sequence division and distance-weighted voting for loop-closure candidate selection. Furthermore, we propose a motion vector consensus constraint to improve locality preserving matching, which can be used for efficient loop-closure event verification that is robust for various complex environments. Extensive experiments have been conducted on four publicly available datasets. The results demonstrate that our method is able to achieve better recall performance than the state-of-the-art and meet the real-time requirement of vSLAM systems.

With the popularity of location-based services and applications, a large amount of mobility data has been generated. Identification through mobile trajectory information, especially asynchronous trajectory data has raised great concerns in social security prevention and control. This paper advocates an identification resolution method based on the most frequently distributed TOP-N (the most frequently distributed N regions regarding user trajectories) regions regarding user trajectories. This method first finds TOP-N regions whose trajectory points are most frequently distributed to reduce the computational complexity. Based on this, we discuss three methods of trajectory similarity metrics for matching tracks belonging to the same user in two datasets. We conducted extensive experiments on two real GPS trajectory datasets GeoLife and Cabspotting and comprehensively discussed the experimental results. Experimentally, our method is substantially effective and efficiency for user identification.

Prenatal ethanol exposure (PEE) is an established risk factor for intrauterine growth retardation. The present study was designed to determine whether PEE can increase the susceptibility of high-fat diet (HFD)-induced metabolic syndrome (MS) in adult offspring in a sex-specific manner, based on a generalized linear model analysis. Pregnant Wistar rats were administered ethanol (4 g/kg.d) from gestational day 11 until term delivery. All offspring were fed either a normal diet or a HFD after weaning and were sacrificed at postnatal week 20 and blood samples were collected. Results showed that PEE reduced serum adrenocorticotropic hormone (ACTH) and corticosterone levels but enhanced serum glucose, insulin, insulin resistant index (IRI), triglyceride and total cholesterol (TC) concentrations. Moreover, the analysis showed interactions among PEE, HFD and sex. In the PEE offspring, HFD aggravated the decrease in ACTH and corticosterone levels and further increased serum glucose, insulin, triglyceride and TC levels. The changes of serum ACTH, glucose and IRI levels in the female HFD rats were greater than those in the male HFD rats. Our findings suggest that PEE enhances the susceptibility to MS induced by HFD in a sex-specific manner, which might be primarily associated with the neuroendocrine metabolic programming by PEE.