Search

Slow and deep breathing (SDB) is a relaxation technique that can increase vagal activity. Respiratory sinus arrhythmia (RSA) serves as an index of vagal function usually quantified by the high-frequency power of heart rate variability (HRV). However, the low breathing rate during SDB results in deviations when estimating RSA by HRV. Besides, the impact of the inspiration-expiration (I: E) ratio and guidelines ways (fixed breathing rate or intelligent guidance) on SDB is not yet clear. In our study, 30 healthy people (mean age = 26.5 years, 17 females) participated in three SDB modes, including 6 breaths per minute (bpm) with an I:E ratio of 1:1/ 1:2, and intelligent guidance mode (I:E ratio of 1:2 with guiding to gradually lower breathing rate to 6 bpm). Parameters derived from HRV, multimodal coupling analysis (MMCA), Poincaré plot, and detrended fluctuation analysis were introduced to examine the effects of SDB exercises. Besides, multiple machine learning methods were applied to classify breathing patterns (spontaneous breathing vs. SDB) after feature selection by max-relevance and min-redundancy. All vagal-activity markers, especially MMCA-derived RSA, statistically increased during SDB. Among all SDB modes, breathing at 6 bpm with a 1:1 I:E ratio activated the vagal function the most statistically, while the intelligent guidance mode had more indicators that still significantly increased after training, including SDRR and MMCA-derived RSA, etc. About the classification of breathing patterns, the Naive Bayes classifier has the highest accuracy (92.2%) with input features including LFn, CPercent, pNN50, $\alpha 2$ , SDRatio, $\alpha 1$ , and LF. Our study proposed a system that can be applied to medical devices for automatic SDB identification and real-time feedback on the training effect. We demonstrated that breathing at 6 bpm with an I:E ratio of 1:1 performed best during the training phase, while intelligent guidance mode had a more long-lasting effect.

This paper studies the elevation angle-based formation tracking control of multi-agent systems. Unlike bearing-based formation control, which uses bearing vectors, formation control using elevation angles eliminates the need for a global coordinate frame. This is beneficial because the coordinate frames of individual agents are often not aligned. Previous studies on elevation angle-based formation control have predominantly focused on leaderless formations. By incorporating a leader-follower structure, follower agents can effectively track and move with leaders, allowing the formation to move together and maneuver through obstacles. We consider three types of agents: single-integrator, double-integrator, and nonholonomic robots. For agents with a single integrator model, we first propose a control law for stationary leaders case and then modify the proposed control law to address moving leaders. Finite-time convergence to the desired formation is guaranteed. We then consider agents with double-integrator dynamics and nonholonomic robots, showing asymptotic convergence to the desired formation. Simulation results are provided to validate the proposed control laws.

Traditional low-light enhancement methods are often based on paired datasets for training. The training data is difficult to obtain and the resulting model has poor generalization. In unsupervised low-light enhancement networks, because paired data is not used for training, there is a lack of effective denoising methods, which often leads to noise problems. In this paper, we propose a low-light enhancement network based on Swin-Transformer and CNN, guided by brightness information. It is worth noting that it also has an unsupervised denoising module, which allows our network to achieve low-light restoration and noise removal goals with a single training session without any additional or fake samples. Our network is based on the idea of generative adversarial networks. We conducted extensive experiments on datasets such as LOL and VE-LOL-L, and compared our results with mainstream unsupervised learning, zero-shot learning, and even partially supervised learning low-light enhancement methods using a series of image indicators and visual effects such as PSNR, SSIM, NIQE, and LOE. The results show that our network is superior to mainstream unsupervised learning and partially supervised learning methods.

Over the past few decades, the ground-based global navigation satellite systems (GNSSs) tropospheric sounding technique has undergone rapid development and has proven to be highly effective in sensing atmospheric variables. Through the utilization of the maturing data assimilation technique, GNSS products, e.g., precipitable water vapor (PWV), can be effectively integrated into a numerical weather prediction (NWP) model, thereby significantly bolstering its performance. In this study, to further refine this practice, a comprehensive investigation of the optimal spatial resolutions for assimilating near real-time PWV into the Weather Research and Forecasting model to improve the accuracy of atmospheric humidity field was conducted under different weather conditions in the context of Victoria, Australia. Results revealed that the optimal spatial resolutions under the heavy rainfall and normal conditions were 46.40 and 55.10 km, respectively. Therefore, the overall optimal spatial resolution for assimilating PWV was ultimately determined as 46.40 km, which can capture the necessary details and improve the accuracy of humidity field across different weather scenarios. Specifically, by incorporating PWV into an NWP model using the optimal spatial resolution, the accuracy of atmospheric humidity fields under the heavy rainfall and normal conditions were significantly improved by 26.0% and 24.7%, respectively. Therefore, the findings have considerable implications for further advancing the assimilation technique and offer valuable insights for the construction and deployment of GNSS ground infrastructure in future scenarios.

In traditional CSMA/CA-based MAC designs supporting successive interference cancellation (SIC), channel utilization is inefficient, because the inherited CSMA/CA-style contention approach often forces the whole channel to remain idle and the early released channel is not utilized. In this paper, we propose Multi-CQ, which is the first software-defined networking (SDN)-based MAC design for wireless LANs that supports SIC and significantly improves the channel utilization. Multi-CQ, adopting SDN’s functional separation idea and OFDMA, makes contention and data transmission be executed over two subchannels independently and concurrently, where the superposition coding are used for decoding combined signals, and multiple CQs (contention queues) are introduced to coordinate the concurrency. This concurrent execution greatly reduces the waste in channel contention. Next, adopting SDN’s central control idea, Multi-CQ controller selects nodes who can finish their frame transmissions in almost equal time, thereby improving the channel utilization. Finally, we develop a theoretical model to optimize bandwidth allocation for channel contention and data transmission. Extensive simulations verify the effectiveness of our design and the accuracy of our theoretical model. This study is also helpful to better design wireless MAC protocols supporting other advanced functionalities such as MU-MIMO.

The low resolution and less feature information of small targets make it difficult to recognize and locate, which greatly hinders the improvement of object detection accuracy. In this paper, an object detection model (TDFP) based on CNN and transformer was established, which combines local and global context to establish the connection between features. In the proposed transformed dynamic feature pyramid network, a transformer module was designed to dynamically transform and fuse the multi-scale features generated by the backbone to generate a transformed feature pyramid with richer multi-scale features and context information. In this transformation process, gate block is used to dynamically select single-scale transformation or cross-scale transformation to achieve an optimal style of transformation and fusion of multi-scale features. The experimental results show that the model improves the small targets detection accuracy based on CNN and transformer. Based on the backbone ResNeXt-101, TDFP achieves 46.2% AP and 26.3% APS on MS COCO, and takes the amount of computation as a loss constraint to achieve a better balance between detection accuracy and computational complexity.

Class-incremental learning is a model learning technique that can help classification models incrementally learn about new target classes and realize knowledge accumulation. It has become one of the major concerns of the machine learning and classification community. To overcome the catastrophic forgetting that occurs when the network is trained sequentially on a multi-class data stream, a double consolidation class-incremental learning (DCCIL) method is proposed. In the incremental learning process, the network parameters are adjusted by combining knowledge distillation and elastic weight consolidation, so that the network can better maintain the recognition ability of the old classes while learning the new ones. The incremental learning experiment is designed, and the proposed method is compared with the popular incremental learning methods such as EWC, LwF, and iCaRL. Experimental results show that the proposed DCCIL method can achieve better incremental accuracy than that of the current popular incremental learning algorithms, which can effectively improve the expansibility and intelligence of the classification model.

The smart meters and meter collectors in Advanced Metering Infrastructure (AMI), which are installed in every home, rely on wireless Virtual Private Network (VPN) for communicating with Head End System (HES). Therefore, they are prone to suffer from malicious cyber-attack. Usually, based on General Packet Radio Service (GPRS) communicated method is the most popular for meter collectors and consequently they are vulnerable to rogue Base Stations (BS) and get compromised by malicious adversaries further. Thus a Density-based spatial clustering of applications with noise (DBSCAN) method is employed to filter rogue BSs out and prevent meter collectors from attaching to them, because there is a notable difference between Signal Strength (SS) profile of legitimate BSs and rogue BSs, Numerical simulation indicates that the proposed approach is capable of detecting both stationary and moving rogue BSs online within fixed time window effectively. Moreover, the method can be implemented in existing meter collectors with limited computation resource. In conclusion, the proposed approach can enhance the level of cyber security of meter collectors.

Underwater automatic target recognition (ATR) is a challenging task for marine robots due to the complex environment. The existing recognition methods basically use hand-crafted features and classifiers to recognize targets, which are difficult to achieve ideal recognition accuracy. In this paper, we proposed a novel method to realize accurate multiclass underwater ATR by using forward-looking sonar-Echoscope and deep convolutional neural networks (DCNNs). A complete recognition process from data preprocessing to network training and image recognition was realized. Firstly, we established a real, measured Echoscope sonar image dataset. Inspired by the human visual attention mechanism, the suspected target region was extracted via the graph-based manifold ranking method in image preprocessing. Secondly, an end-to-end DCNNs model, named EchoNet, was designed for Echoscope sonar image feature extraction and recognition. Finally, a network training method based on transfer learning was developed to solve the problem of insufficient training data, and mini-batch gradient descent was used for network optimization. Experimental results demonstrated that our method can implement efficiently, and the recognition accuracy on a nine-class underwater ATR task reached 97.3%, outperforming traditional feature-based methods. The proposed method is expected to be a potential novel technology for the intelligent perception of autonomous underwater vehicles.