Search

Abstract To enhance the real-time performance and reduce CPU usage in feature-based visual SLAM, this paper introduces a lightweight tightly coupled stereo-inertial SLAM with fisheye cameras, incorporating several key innovations. First, the stereo-fisheye camera is treated as two independent monocular cameras, and the SE(3) transformation is computed between them to minimize the CPU burden during stereo feature matching and eliminate the need for camera rectification. Another important innovation is the application of maximum-a-posteriori (MAP) estimation for the inertial measurement unit (IMU), which effectively reduces inertial bias and noise in a short time frame. By optimizing the system’s parameters, the constant-velocity model is replaced from the beginning, resulting in improved tracking efficiency. Furthermore, the system incorporates the inertial data in the loop closure thread. The IMU data are employed to determine the translation direction relative to world coordinates and utilized as a necessary condition for loop detection. Experimental results demonstrate that the proposed system achieves superior real-time performance and lower CPU usage compared to the majority of other SLAM systems.

Recently, deep learning methods and multisensory fusion have been applied to address odometry challenges in unmanned ground vehicles (UGVs). In this paper, we propose an end-to-end visual-lidar-inertial odometry framework to enhance the accuracy of pose estimation. Grayscale images, 3D point clouds, and inertial data are used as inputs to overcome the limitations of a single sensor. Convolutional neural network (CNN) and recurrent neural network (RNN) are employed as encoders for different sensor modalities. In contrast to previous multisensory odometry methods, our framework introduces a novel attention-based fusion module that remaps feature vectors to adapt to various scenes. Evaluations on the Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago (KITTI) odometry benchmark demonstrate the effectiveness of our framework.

Increasing evidence shows that the early onset of puberty in female offspring may be caused by maternal prenatal exposure to bisphenol A (BPA) during pregnancy; however, the critical time window of maternal prenatal BPA exposure remains unknown. Here, we identify the critical time window of gestational BPA exposure that induces early onset of puberty in female offspring. Pregnant CD-1 mice were gavaged with BPA (8 mg/kg) daily during the early gestational stage (GD1–GD6), middle gestational stage (GD7–GD12) or late gestational stage (GD13–GD18). We show that maternal BPA exposure during the early and middle gestational stages could advance the vaginal opening time and increase the serum levels of kisspeptin-10 and GnRH in the female offspring at PND 34. Mechanistically, maternal BPA exposure during early and middle gestation could significantly increase CpG island methylation in the Eed gene promoters but reduce the mRNA expression of Eed in the hypothalamus tissues of the female offspring. In conclusion, the critical period of maternal BPA exposure-induced early onset of puberty in female offspring is early and middle gestation; this BPA-induced early onset of puberty might be partly attributed to epigenetic programming of the Eed gene in the hypothalamus. This study provides important insights regarding the relationship and the mechanisms between BPA and offspring pubertal development.

Unmanned aerial vehicles (UAVs) can experience significant performance issues during flight due to heavy CPU load, affecting their flight capabilities, communication, and endurance. To address this issue, this paper presents a lightweight stereo-inertial state estimator for addressing the heavy CPU load issue of ORB-SLAM. It utilizes nonlinear optimization and features to incorporate inertial information throughout the Simultaneous Localization and Mapping (SLAM) pipeline. The first key innovation is a coarse-to-fine optimization method that targets the enhancement of tracking speed by efficiently addressing bias and noise in the IMU parameters. A novel visual–inertial pose graph is proposed as an observer to assess error thresholds and guide the system towards visual-only or visual–inertial maximum a posteriori (MAP) estimation accordingly. Furthermore, this paper introduces the incorporation of inertial data in the loop closure thread. The IMU data provide displacement direction relative to world coordinates, which is serving as a necessary condition for loop detection. The experimental results demonstrate that our method maintains excellent localization accuracy compared to other state-of-the-art approaches on benchmark datasets, while also significantly reducing CPU load.

It is a challenge to detect pre-seismic anomalies by using only one dataset due to the complexity of earthquakes. Therefore, it is a promising direction to use multiparameteric data. The earthquake cross partial multi-view data fusion approach (EQ-CPM) is proposed in this paper. By using this method, electromagnetic data and seismicity indicators are fused. This approach tolerates the absence of data and complements the missing part in fusion. First, the effectiveness of seismicity indicators and electromagnetic data was validated through two earthquake case studies. Then, four machine learning algorithms were applied to detect pre-seismic anomalies by using the fused data and two original datasets. The results show that the fused data provided better performance than the single-modal data. In the Matthews correlation coefficient index, the results of our method showed an 8% improvement compared with the latest study.

Noise is an unneglectable problem in emotion recognition if we want to put it into practice. First, aiming at the problem of noise in speech, we design a new acoustic feature, Long time frame Analysis Weighted Wavelet Packet Cepstral Coefficient (LW-WPCC), for better robustness. To extract LW-WPCC feature, first the best wavelet packet basis is constructed. On the basis of this, a robust wavelet packet Cepstral Coefficient is extracted by combining short time frame analysis with long time frame analysis. After that, we introduce a sub-band spectral center-of-mass parameter with good robustness to additive noise and propose an extraction algorithm of LW-WPCC. Through experiments on speech emotion recognition of different SNR levels, it is shown that our proposed method shows better noise robustness and performance on speech emotion recognition. What's more, as facial expressions will not be affected by noise, we do bio-modal emotion recognition based on audio-visual data to improve robustness by making a decision-level fusion. Experiments based on audio-visual data are conducted to evaluate efficiency of our method. Results show that bio-modal emotion recognition based on audio-visual data can improve robustness and achieve better performance by benefiting from different kinds of emotion data.

Recently, many firms in various industries implement corporate social responsibility (CSR) in different ways. Based on considering a CSR-concerned retailer and an altruistic fairness concern manufacturer, this paper investigates pricing decisions as well as carbon emission policies in a socially responsible supply chain. In this paper, two different modes (the centralized model and decentralized model) are, respectively, conducted and investigated for equilibria. Analytical results reveal that socially responsible retailer (manufacturer) cares more about CSR (altruistic fairness) concern and will increase his counterpart’s pure profit as well as the pure channel profit, ending up with decreasing his own pure profit. The cooperative agents in decentralized scenario can coordinate the channel and achieve the maximum pure channel profit as much as that in a pure profit-maximizing centralized model. Moreover, this paper proposes a novel two-stage carbon cap-and-trade policy for the government and examines how it is affected by the CSR concern level and the altruistic fairness in such a socially responsible supply chain.

Swimming training is a kind of aquatic exercise that has been shown to be beneficial to physical fitness at any age. This study aimed to determine how mental and physical aspects of swimming affect aerobic and anaerobic capacity describes the physiological and psychological effects of swimming training at different ages. This study examines how swimming impacts youthful and elderly cardio-respiratory fitness, muscular strength, flexibility, and body composition. A correlation and stepwise regression analysis was performed on the information gathered from a RESTQ-76 sport questionnaire, a Heart Rate Variability (HRV) test, and the efforts of swimmers to improve their aerobic and anaerobic swimming performance. We also investigate the benefits that swimming has on lowering stress, boosting self-esteem, and improving mental health for people of varying ages. We use SPSS version 17.0 was used for the statistical analysis. An examination of the relevant research reveals that swimmers of all ages enjoy significant advantages as a result of their training, including enhancements to their physical and mental health. In that case, they can be able to tailor swimming programs to match the changing physiological and psychological needs of their swimmers. Findings from this study add to a growing body of evidence that open-water swimming is perceived to have positive effects on participants' mental and physical health regardless of age and can be used to inform co-created policy formation to advance outdoor recreation possibilities that are safer, healthier, and more sustainable about this expanding outside activity. [ABSTRACT FROM AUTHOR]

Purpose: To investigate the efficacy of Sijunzi decoction (SJZD) against ulcerative colitis (UC) in vitro, and to unravel the probable mechanism of action. Methods: SEC-6 cells were exposed to lipopolysaccharide (LPS) in order to establish an ulcerative colitis model, and then treated with SJZD. CCK-8 assay was employed to evaluate cell viability, while cell apoptosis was determined by flow cytometry. Enzyme-linked immunosorbent assay (ELISA) and quantitative real-time polymerase chain reaction (qRT-PCR) were used to assess inflammation factors, viz, TNF-a, IL-1ß and IL-6, whereas the expression levels of Bax, Bcl-2 and peroxisome proliferatoractivated receptors (PPARs) were evaluated by Western blot. Results: SJZD doses of 80 and 160 mg/L increased cell viability in LPS-induced SEC-6 cells, while Bcl2 and Bax expressions were regulated, and apoptosis inhibited at these doses (p < 0.05), indicating that SJZD attenuated cell apoptosis. Inflammation was also repressed by SJZD, based on the reduced expressions of TNF-a, IL-1ß and IL-6 (p < 0.05). Furthermore, SJZD significantly increased PPARa level, thus enhancing cell viability, inhibiting apoptosis as well as inhibiting inflammation (p < 0.05). Conclusion: SJZD lowers cell damage, and inhibits cell apoptosis and inflammation through the activation of PPARa pathway, thus suggesting that SJZD is a potential therapeutic candidate for the treatment of ulcerative colitis. [ABSTRACT FROM AUTHOR]