Search

Radar beam blockage is an important error source that affects the quality of weather radar data. The S-band dual-polarization radar in Guangzhou has multi-azimuth occlusion at low elevation and is partially occluded at high elevation. Based on deep learning methods such as convolutional neural network, two echo filling networks, i.e., VEF(vertical echo-filling) and HEF(horizontal echo-filling) are constructed. Based on this architecture, echoes from the unblocked area are used to construct training datasets and fill the reflectivity ZH and differential reflectivity ZDR in the occlusion area. For the area with only 0.5° elevation occlusion, multi-modal modeling is carried out based on VEF architecture by using 3D data from multiple upper elevations, radial directions and gates. Considering that the radar beam broadens with distance and to avoid the influence of the melting layer, the radar beam is divided into four sections according to the oblique distance of 0.5° elevation, and the vertical echo-filling model is trained respectively. For the area with high occlusion elevation, multi-mode modeling is carried out based on HEF architecture using the data of multiple adjacent radial directions and gates with the same elevation. According to the number of occlusion radial, two types of horizontal echo-filling models, three radials echo-filling model and five radials echo-filling model are constructed respectively. Finally, the models are evaluated by three cases and three indicators:Explained variance, mean absolute error and correlation coefficient. The maximum explained variance of ZH vertical echo-filling model is 0.91, the minimum mean absolute error is 1.72 dB, and the maximum correlation coefficient is 0.96. The maximum explained variance of ZDR vertical echo-filling model is 0.87, the minimum mean absolute error is 0.12 dB, and the maximum correlation coefficient is 0.92. The maximum explained variance of ZH horizontal fill model is 0.92, the minimum mean absolute error is 1.69 dB, and the maximum correlation coefficient is 0.96. The maximum explained variance of ZDR horizontal echo-filling model is 0.92, the minimum mean absolute error is 0.12 dB, and the maximum correlation coefficient is 0.96. The deep learning echo-filling model can be used to correct the echoes of Guangzhou S-band dual-polarization radar occlusion area effectively, and the quality of weather radar data is improved.

A new method is proposed for identifying ground clutter in single-polarization radar data based on the gated recurrent unit (GRU) neural network. This method needs five independent input variables related to radar reflectivity structure, which are the reflectivity at current tilt, the reflectivity at the upper tilt, the reflectivity at 3.5 km, the echo top height, and the texture of reflectivity at current tilt, respectively. The performance of the new method is compared with that of the traditional method used in the Weather Surveillance Radar 1988-Doppler system in four cases with different scenarios. The results show that the GRU method is more effective than the traditional method in capturing ground clutter, particularly in situations where ground clutter exists at two adjacent elevation angles. Furthermore, in order to assess the new method more comprehensively, 709 radar scans from Nanchang radar in July 2019 and 708 scans from Jingdezhen radar in June 2019 were collected and processed by the two methods, and the frequency map of radar reflectivity exceeding 20 dBZ was analyzed. The results indicate that the GRU method has a stronger ability than the traditional method to identify and remove ground clutter. Meanwhile, the GRU method can also preserve meteorological echoes well. [ABSTRACT FROM AUTHOR]

Stationary or mobile microwave radiometers (MRs) can measure atmospheric temperature, relative humidity, and water vapor density profiles with high spatio-temporal resolution, but cannot obtain the vertical variations of wind field. Based on a dataset of brightness temperatures (TBs) measured with a mobile MR over the Three-River-Source Region of the Tibetan Plateau from 18 to 30 July 2021, we develop a direct retrieval method for the wind profile (WP) based on the Long Short-Term Memory (LSTM) network technique, and obtain the reliable dynamic variation characteristics of the WP in the region. Furthermore, the ground-based radiative transfer model for TOVS (RTTOV-gb) was employed to validate the reliability of the TB observation, and we analyzed the impact of weather conditions, altitude, observational mode, and TB diurnal variation on the accuracy of the TB measurement and the retrieval of the WP. Results show that the TB from the mobile observation (MOTB) on clear and cloudy days are close to those of the simulated TB with the RTTOV-gb model, while TB measurements on rainy days are far larger than the modeled TBs. When compared with radiosonde observations, the WPs retrieved with the LSTM algorithm are better than the ERA5 reanalysis data, especially below 350 hPa, where the root mean square errors for both wind speed and wind direction are smaller than those of ERA5. The major factors influencing WP retrieval include the weather conditions, altitude, observational mode, and TB diurnal variation. Under clear-sky and cloudy conditions, the LSTM retrieval method can reproduce the spatio-temporal evolution of wind field and vertical wind shear characteristics. The findings of this study help to improve our understanding of meso-scale atmospheric dynamic structures, characteristics of vertical wind shear, atmospheric boundary layer turbulence, and enhance the assessment and forecasting accuracy of wind energy resources. [ABSTRACT FROM AUTHOR]

Gust fronts (GFs) belong to the boundary layer convergence system. A strong GF can cause serious wind disasters, so its automatic monitoring and identification are very helpful but difficult in daily meteorological operations. By collecting convective weather processes in Hubei, Jiangsu, and other regions of China, 1422 GFs from 106 S-band new-generation weather radar (CINRAD/SA) volume scan data are labeled as positive samples by means of human–computer interaction, and the same number of negative samples are randomly tagged from no GF radar data. A deep learning dataset including 2844 labels with a positive and negative sample ratio of 1:1 is constructed, and 80%, 10%, and 10% of the dataset are separated as training, validation, and test sets, respectively. Then, the training dataset is expanded to 273,120 samples by data augmentation technology. Since the height of a GF is generally less than 1.5 km, three deep-learning-based models are trained for GF automatic recognition according to the distance from the radars. Three models (M1, M2, M3) are trained with the data at a 0.5° elevation angle from 65 to 180 km away from the radars, at 0.5° and 1.5° angles from 40 to 65 km, and at 0.5°, 1.5°, and 2.4° angles within 40 km, respectively. The precision, confusion matrix, and its derived indicators including receiver operating characteristic curve (ROC) and the area under ROC (AUC) are used to evaluate the three models by the test set. The results show that the identification precisions of the models are 97.66% (M1), 90% (M2), and 90.43% (M3), respectively. All the hit rates are over 89%, the false positive rates are less than 11%, and the critical success indexes (CSIs) surpass 82%. In addition, all the optimal critical points on the ROC curves are close to (0, 1), and the AUC values are above 0.93. These results suggest that the three models can effectively achieve the automatic discrimination of GFs. Finally, the models are demonstrated by three GF events detected with Qingpu, Nantong, and Cangzhou radars. [ABSTRACT FROM AUTHOR]

Highlights: A deep learning dataset of squall lines with over 49,920 samples was constructed based on RADAR-base data by means of manual classification and data augment. Three squall lines automatic recognition modes are trained according to the distance of label data away from RADARs. The models have good generalization ability which can effectively capture the characteristics of squall lines from RADAR-base data to realize its automatic recognition well. Squall line (SL) is a convective weather process that often causes disasters. The automatic recognition and early warning of SL are important objectives in the field of meteorology. By collecting the new-generation weather RADARs (CINRAD/SA and CINRAD/SAD) base data during 12 SL weather events occurred in Jiangsu, Shanghai, Shandong, Hebei, and other regions of China from 2019 to 2021, the dataset has a total of 49,920 samples with a window size of 40 km. The 40 km area was labeled by employing manual classification and data augmentation to construct the deep learning dataset with a positive and negative sample ratio of 1:1, of which 80% and 20% are separated as the training and test set, respectively. Based on the echo height of each elevation beam at different distances, three deep learning-based models are trained for SL automatic recognition, which include a near-distance model (M1) trained by the data in nine RADAR elevation angles within 45 km from RADARs, a mid-distance model (M2) by the data in six elevations from 45 to 135 km, and a far-distance model (M3) by the data in three elevations from 135 to 230 km. A confusion matrix and its derived metrics including receiver operating characteristic (ROC) curves and the area under the ROC curve (AUC) are introduced as the indicators to evaluate the models by the test dataset. The results indicate that the accuracy of models are over 86% with the hit rates over 87%, the false alarm rates less than 21%, and the critical success indexes (CSI) surpass 78%. All the optimal critical points on the ROC curves are close to (0, 1), and the AUC values are above 0.95, so the three models have high hit rates and low false alarm rates for ensuring SL discrimination. Finally, the effectiveness of the models is further demonstrated through two SL events detected with Nanjing, Yancheng and Qingpu RADARs. [ABSTRACT FROM AUTHOR]

Multi‐agent reinforcement learning has played an increasingly important role in intelligent traffic signal control due to its self‐learning ability. However, existing algorithms only focus on signal timing mechanism design while ignoring the exponential growth of the joint action dimension as the number of intersections increases, which will ultimately face the learning difficulty. In this paper, traditional traffic methods are introduced into MARL to flexibly determine the phase and duration of each intersection. The proposed MARL algorithm based on mean field theory has the ability to convert a large number of agents to approximately binary interaction, which can effectively reduce the dimension of joint action space in multi‐agent environment and learn in a robust process. Besides, to improve the performance of traditional traffic methods, the recurrent neural network (RNN) and an improved Webster's formula with revised parameters are combined to dynamically determine the phase duration according to the historical volume of traffic flow. The simulation results indicate that the proposed algorithm shows superior scalability compared to baseline methods and has great potential to be applied in the large scale road‐networks scenario. [ABSTRACT FROM AUTHOR]

The unmanned aerial vehicles (UAVs) network is vulnerable due to the high mobility and energy-constrained characteristics of UAVs. Nonetheless, as a UAV-based communication network, a stable network topology is crucial for efficient communication. To this end, in this paper, we propose a dynamic weighted clustering algorithm with dual cluster heads (DWCA-DCH) in this paper to deploy the UAV network. To trade off communication efficiency and lifetime, the selection of prime and backup cluster heads is designed by synthetically considering communication quality and remaining energy of the UAV. Furthermore, a survivability analysis method based on Markov process (SAM-MP) is constructed to analyze the survivability performance of the proposed UAV network based on DWCA-DCH when the UAV node suffers from energy exhausting or accidents. The simulation results show that the survivability and stability of the UAV cluster ad hoc network based on DWCA-DCH proposed in this paper is improved by about 35% compared with the single cluster head network. [ABSTRACT FROM AUTHOR]

The observation of and research on raindrop size distribution (DSD) is important for mastering and understanding the mutual restriction relationship between cloud dynamics and cloud microphysics in a process of precipitation; it also plays an irreplaceable role in many fields, such as radar meteorology, weather modification, boundary layer land surface processes, aerosols, etc. Using more than 1.7 million minutes of raindrop data observed with 17 laser disdrometers at 17 stations in Anhui Province, China, from 7 August 2009 to 30 April 2020, a DSD training dataset was constructed. Furthermore, the data are fitted to a normalized Gamma function and used to obtain its three parameters, i.e., the normalized intercept Nw, the mass weighted average diameter Dm, and the shape factor μ. Based on the long short-term memory network (LSTM), a DSD Gamma distribution prediction network (DSDnet) was designed. In the process of modeling based on DSDnet, a self-defined loss function (SLF) was proposed in order to improve the DSD prediction by increasing the weight values in the poor fitting regions according to the common mean square error loss function (MLF). By means of the training dataset, a DSDnet-based model was trained to realize the prediction of Nw, Dm, and μ minute-to-minute over the course of 30 min, and then was evaluated by the test dataset according to three indicators, namely, mean relative error (MRE), mean absolute error (MAE), and correlation coefficient (CC). The CC of lgNw, Dm, and μ can reach 0.93403, 0.90934, and 0.89741 for 12-min predictions, and 0.87559, 0.85261, and 0.84564 for 30-min predictions, respectively, which means that the DSD prediction accuracy within 30 min can basically reach the application level. Furthermore, the 12- and 30-min predictions of 3 precipitation processes were taken as examples to fully demonstrate the application effect of model. The prediction effects of Nw and Dm are better than that of μ, and the stratiform precipitation is better than the convective and convective-stratiform mixed cloud precipitation. [ABSTRACT FROM AUTHOR]

Sample imbalance prevents the Bayesian model from making effective potential forecasts of gale. An approach is thus proposed to modify the Bayesian model to deal with sample imbalance and verified using years (2015–2019) of reanalysis and radar data. The approach reduces sample imbalance by the resampling based on the value ranges of environmental parameters and the application of multi‐layer conditional probabilities. The samples that are insensitive to gale forecasts are excluded according to the value ranges of environmental parameters for gale occurrence. This resampling greatly improves gale occurrence hits of and suppresses its false alarms, leading to significant improvement in gale forecasting skill. On the basis of the resampling, the application of the multi‐layer conditional probabilities that forecast gale occurrence balances the samples to an equivalent magnitude. Consequently, the false alarms are further suppressed although some hits are reduced, resulting in a higher forecasting skill of gale. Plain Language Summary: Due to large sample imbalance, the Bayesian model with the basic probability is difficult to use effectively in the potential forecasts of gale. This study proposes an approach to modify the Bayesian model to handle sample imbalance, and verify the application of the modified Bayesian model in the potential forecasts of gale using years (2015–2019) of reanalysis and radar data. The approach deals with the sample imbalance problem through the resampling based on environmental parameters and the application of multiple layers of conditional probabilities. Excluding the samples that are insensitive to gale forecasts based on the value ranges of environmental parameters for gale occurrence significantly reduces sample imbalance. The resampling in this way significantly improves gale occurrence hits and suppresses its false alarms, leading to a great improvement in gale forecasting skill. On this basis, applying multiple layers of conditional probabilities that forecast gale occurrence further balances the samples to an equivalent magnitude. As a result, although the hits of gale occurrence are somewhat lowered, its false alarms are further reduced, leading to a higher forecasting skill of gale. Key Points: The Bayesian model with the basic probability tends to forecast gale non‐occurrence, resulting in few hits of gale occurrenceBased on the Bayesian model with no basic probability, resampling greatly promotes gale occurrence hits while suppressing its false alarmsAdditional application of multi‐layer conditional probabilities further suppresses gale occurrence false alarms while promoting its hits [ABSTRACT FROM AUTHOR]

F-RAN is regarded as a promising paradigm for mobile networks to alleviate the unprecedented traffic pressures and meet quality of service requirements of various 5G services with great flexibility. To make F-RAN work in a reliable, efficient, and smart way, AI-enabled F-RAN could be innovative in a number of directions: computing task offloading, resource management, dynamic beam selection, cross-layer design, energy saving and harvesting, mobility enhancement, and so on. In this article, an AI-enabled F-RAN testbed has been designed and implemented in a portable way based on OpenAirInterface, where an AI module is integrated into the F-RAN architecture. The AI module encapsulates the underlying operators of various machine learning frameworks to help a network make policies for different applications. Based on the proposed testbed, the F-RAN research community can easily analyze and evaluate their novel methods and quickly develop intelligent algorithms in a lab environment. [ABSTRACT FROM AUTHOR]

Using melting layer (ML) and non-melting layer (NML) data observed with the X-band dual linear polarization Doppler weather radar (X-POL) in Shunyi, Beijing, the reflectivity (ZH), differential reflectivity (ZDR), and correlation coefficient (CC) in the ML and NML are obtained in several stable precipitation processes. The prior probability density distributions (PDDs) of the ZH, ZDR and CC are calculated first, and then the probabilities of ZH, ZDR and CC at each radar gate are determined (PBB in the ML and PNB in the NML) by the Bayesian method. When PBB > PNB the gate belongs to the ML, and when PBB < PNB the gate belongs to the NML. The ML identification results with the Bayesian method are contrasted under the conditions of the independent PDDs and joint PDDs of the ZH, ZDR and CC. The results suggest that MLs can be identified effectively, although there are slight differences between the two methods. Because the values of the polarization parameters are similar in light rain and dry snow, it is difficult for the polarization radar to distinguish them. After using the Bayesian method to identify the ML, light rain and dry snow can be effectively separated with the X-POL observed data. [ABSTRACT FROM AUTHOR]

Faced with explosive growth of data traffic and shortage of licensed spectrum, licensed-assisted access (LAA) to unlicensed spectrum has been proposed to boost system capacity. To ensure fair coexistence with WiFi systems, listen-before-talk mechanism has been standardized under LAA framework. However, in densely deployed urban networks, the system performance could severely deteriorate due to high collision probability. In this paper, we propose cooperative LAA (CLAA), where multiple LAA small base stations form a cluster and construct a virtual multiuser multiple-input single-output (MISO)/multiple-input and multiple-output (MIMO) system to transmit data cooperatively. CLAA can effectively reduce the number of contending nodes, thereby alleviating transmission collisions. A closed-form expression for the upper bound sum rate of the cluster is derived. Markov analysis is employed to derive the system collision probability and throughput for WiFi and LTE. Our analytical results point to an adequate cluster sizes, where the highest system throughput can be achieved. Extensive simulations confirm the validity of the proposed approach, and demonstrate that CLAA can increase by up to $\text{27}\%$ the overall system throughput, and improve by $\text{30}\%$ in fairness. [ABSTRACT FROM AUTHOR]

Rate adaptation (RA) is an essential mechanism in 802.11 WLAN. In the latest 802.11ac protocol, there are two emerging problems that need to be addressed for the RA. First, 802.11ac supporting more rate selections requires more efforts to find the optimal rate. Finally, 802.11ac supports higher rate. The difference between optimal rate and non-optimal rate can be so great that non-optimal rate would severely deteriorate the throughput of the WLAN. In order to tackle these problems, we develop a novel RA algorithm termed rate adaptation with Thompson sampling (RATS) for stationary and non-stationary channel environments. In this algorithm, we first consider compacting the search space by removing some rates to accelerate the convergence of the algorithm. Moreover, inspired by multi-armed bandit problem, we design RA algorithm based on Thompson sampling. Simulation results demonstrate that the performance of the proposed RATS outperforms the existing method. [ABSTRACT FROM AUTHOR]

To solve the policy optimizing problem in many scenarios of smart wireless network management using a single universal algorithm, this letter proposes a universal learning framework, which is called AI framework based on deep reinforcement learning (DRL). This framework can also solve the problem that the state is painful to design in traditional RL. This AI framework adopts convolutional neural network and recurrent neural network to model the potential spatial features (i.e., location information) and sequential features from the raw wireless signal automatically. These features can be taken as the state definition of DRL. Meanwhile, this framework is suitable for many scenarios, such as resource management and access control due to DRL. The mean value of throughput, the standard deviation of throughput, and handover counts are used to evaluate its performance on the mobility management problem in the wireless local area network on a practical testbed. The results show that the framework gets significant improvements and learns intuitive features automatically. [ABSTRACT FROM PUBLISHER]

As part of the third Tibetan Plateau Atmospheric Scientific Experiment field campaign, raindrop size distribution (DSD) measurements were taken with a laser optical disdrometer in Naqu, China, at 4,508 m above sea level (asl) during the summer months of 2013, 2014, and 2015. The characteristics of DSDs for five different rain rates, for two rain types (convective and stratiform), and for daytime and nighttime rains were studied. The shapes of the averaged DSDs were similar for different rain rates, and the width increased with rainfall intensity. Little difference was found in stratiform DSDs between day and night, whereas convective DSDs exhibited a significant day-night difference. Daytime convective DSDs had larger mass-weighted mean diameters ( Dm) and smaller generalized intercepts ( NW) than the nighttime DSDs. The constrained relations between the intercept N0 and shape μ, slope Λ and μ, and NW and Dm of gamma DSDs were derived. We also derived empirical relations between Dm and the radar reflectivity factor in the Ku and Ka bands. [ABSTRACT FROM AUTHOR]

Recently the possibility of forming unmanned aerial vehicle base station (UAV-BS) network systems with energy harvesting capabilities to support persistent wireless access services for pedestrian users has been validated. Due to the need of sustaining wireless access services of the UAV-BSs, we investigate an optimal policy to maximize the overall energy utilization efficiency (renewable energy) of the UAV-BSs during their active in-flight network access operations. Since the natural sources of renewable energy (e.g., solar energy or wind energy harvesting) have stochastic properties with respect to the arrival rate of the dynamics of the unknown environment, we exploit an actor–critic reinforcement learning framework, which considers the continuous-valued states and action space for learning the best policy during interaction with the environment. To enhance and expedite the learning process, a transfer asynchronous advantage actor–critic (TA3C) algorithm is proposed, which enables UAV-BSs to transfer (i.e., share) knowledge gained in historical periods, during parallel task asynchronous executions on multiple instances of the environment. Numerical results reveal that the proposed TA3C algorithm surpasses the classic A3C and A2C algorithms in terms of throughput and optimal energy utilization efficiency. [ABSTRACT FROM AUTHOR]

Wireless multimedia services are increasingly becoming popular, which boosts the need for better quality-of-experience (QoE). However, there are many aspects leading to the degradation of real-time video QoE, especially, a large number of always-on-line (AOL) applications existing in future wireless networks transmit heartbeat message periodically to keep always-on, and hence induce heavy signaling costs and overload wireless networks. In this paper, we propose QoE-based pseudo heartbeat message compression mechanism to reduce the number of signaling loads in the radio access network by intercepting the heartbeat message at a certain frequency in the proxy client. To maintain the protocol feature of the AOL applications, the heartbeat messages are reconstructed by the proxy server and sent to the application server. Furthermore, to analyze the influence of this mechanism on the video user, a new QoE perception model is proposed. Finally, combined the QoE perception model for video services with AOL services, the utility function for joint optimization multi-services is developed to determine the optimum compression frequency. The simulation results show that the proposed mechanism greatly alleviates the signaling load and leads to a significant performance improvement on the QoE of video users, while a slight decrease in the QoE of AOL users. Copyright © 2016 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Wireless local area network (WLAN) is becoming increasingly important due to the explosive growth of mobile data traffic. The user in some hot spot areas is usually covered with multiple access points (APs). However, the subsequent challenge is the users' devices need to handover between these APs as the user moves, and it introduces large latency during the handoff process. For multimedia application, quality of experience (QoE) is an essential measurement for network evaluation. But the large handover latency which gives rise to an interruption will greatly degrade the users' QoE to an intolerable extent. Therefore a neighbor list based proactive handoff scheme which has sufficient low handover latency will reduce service disruptions. The proposed scheme exploits the active scan based on information of neighboring APs, received signal strength indicator (RSSI), and variable bitrate video coding (VBR) to reduce handover delay and service interruption. Based on the analysis and simulation, it can be seen that the proposed scheme can decrease the handover time efficiently and increase QoE. [ABSTRACT FROM PUBLISHER]

IEEE 802.11ac standard, adopting a downlink multi-user multiple-input and multiple-output (DL-MU-MIMO) scheme, can significantly improve the performance of wireless local area networks (WLANs). To support the DL-MU-MIMO technology, a transmission opportunity (TXOP) sharing mechanism has been proposed to allow an access point (AP) to communicate with multiple users simultaneously. In this letter, we present an analytical model based on Markov chains for a non-saturated IEEE 802.11ac enhanced distributed channel access (EDCA) network, which supports the TXOP sharing mechanism. The analytical model computes the 802.11ac EDCA throughput, in the assumption of ideal channel conditions. Extensive simulation and analysis results show that the analytical model can accurately predict the throughput of the 802.11ac networks under non-saturated operation. [ABSTRACT FROM PUBLISHER]

The radio resource allocation problem is studied, aiming to jointly optimize the energy efficiency (EE) and spectral efficiency (SE) of downlink OFDMA multi-cell networks. Different from existing works on either EE or SE optimization, a novel EE-SE tradeoff (EST) metric, which can capture both the EST relation and the individual cells' preferences for EE or SE performance, is introduced as the utility function for each base station (BS). Then the joint EE-SE optimization problem is formulated, and an iterative subchannel allocation and power allocation algorithm is proposed. Numerical results show that the proposed algorithm can exploit the EST relation flexibly and optimize the EE and SE simultaneously to meet diverse EE and SE preferences of individual cells. [ABSTRACT FROM PUBLISHER]

The emerging connected and automated vehicle (CAV) has the potential to improve traffic efficiency and safety. With the cooperation between vehicles and intersection, CAVs can adjust speed and form platoons to pass the intersection faster. However, perceptual errors may occur due to external conditions of vehicle sensors. Meanwhile, CAVs and conventional vehicles will coexist in the near future and imprecise perception needs to be tolerated in exchange for mobility. In this paper, we present a simulation model to capture the effect of vehicle perceptual error and time headway to the traffic performance at cooperative intersection, where the intelligent driver model (IDM) is extended by the Ornstein–Uhlenbeck process to describe the perceptual error dynamically. Then, we introduce the longitudinal control model to determine vehicle dynamics and role switching to form platoons and reduce frequent deceleration. Furthermore, to realize accurate perception and improve safety, we propose a data fusion scheme in which the Differential Global Positioning system (DGPS) data interpolates sensor data by the Kalman filter. Finally, a comprehensive study is presented on how the perceptual error and time headway affect crash, energy consumption as well as congestion at cooperative intersections in partially connected and automated traffic. The simulation results show the trade-off between the traffic efficiency and safety for which the number of accidents is reduced with larger vehicle intervals, but excessive time headway may result in low traffic efficiency and energy conversion. In addition, compared with an on-board sensor independently perception scheme, our proposed data fusion scheme improves the overall traffic flow, congestion time, and passenger comfort as well as energy efficiency under various CAV penetration rates. [ABSTRACT FROM AUTHOR]

Radar beam blockage is an important error source that affects the quality of weather radar data. An echo-filling network (EFnet) is proposed based on a deep learning algorithm to correct the echo intensity under the occlusion area in the Nanjing S-band new-generation weather radar (CINRAD/SA). The training dataset is constructed by the labels, which are the echo intensity at the 0.5° elevation in the unblocked area, and by the input features, which are the intensity in the cube including multiple elevations and gates corresponding to the location of bottom labels. Two loss functions are applied to compile the network: one is the common mean square error (MSE), and the other is a self-defined loss function that increases the weight of strong echoes. Considering that the radar beam broadens with distance and height, the 0.5° elevation scan is divided into six range bands every 25 km to train different models. The models are evaluated by three indicators: explained variance (EVar), mean absolute error (MAE), and correlation coefficient (CC). Two cases are demonstrated to compare the effect of the echo-filling model by different loss functions. The results suggest that EFnet can effectively correct the echo reflectivity and improve the data quality in the occlusion area, and there are better results for strong echoes when the self-defined loss function is used. [ABSTRACT FROM AUTHOR]

In order to meet the ever-increasing traffic demand of Wireless Local Area Networks (WLANs), channel bonding is introduced in IEEE 802.11 standards. Although channel bonding effectively increases the transmission rate, the wider channel reduces the number of non-overlapping channels and is more susceptible to interference. Meanwhile, the traffic load differs from one access point (AP) to another and changes significantly depending on the time of day. Therefore, the primary channel and channel bonding bandwidth should be carefully selected to meet traffic demand and guarantee the performance gain. In this paper, we proposed an On-Demand Channel Bonding (O-DCB) algorithm based on Deep Reinforcement Learning (DRL) for heterogeneous WLANs to reduce transmission delay, where the APs have different channel bonding capabilities. In this problem, the state space is continuous and the action space is discrete. However, the size of action space increases exponentially with the number of APs by using single-agent DRL, which severely affects the learning rate. To accelerate learning, Multi-Agent Deep Deterministic Policy Gradient (MADDPG) is used to train O-DCB. Real traffic traces collected from a campus WLAN are used to train and test O-DCB. Simulation results reveal that the proposed algorithm has good convergence and lower delay than other algorithms. [ABSTRACT FROM AUTHOR]

The unmanned aerial vehicle (UAV) enabled mobile edge computing (MEC) system is attracting a lot of attentions for the potential of low latency and low transmission energy consumption, due to the advantages of high mobility and easy deployment. It has been widely applied to provide communication and computing services, especially in Internet of Things (IoT). However, there are still some challenges in the UAV-enabled MEC system. Firstly, the endurance of the UAV is limited and further impacts the performance of the system. Secondly, mobile devices are battery-powered and the batteries of some devices are hard to change. Therefore, in this paper, a UAV-enabled MEC system in which the UAV is empowered to have computing capability and provides tasks offloading service is studied. The total energy consumption of the UAV-enabled system, which includes the energy consumption of the UAV and the energy consumption of the ground users, is minimized under the constraints of the UAV's energy budget, the number of each task's bits, the causality of the data and the velocity of the UAV. The bits allocation of uploading data, computing data, downloading data and the trajectory of the UAV are jointly optimized with the goal of minimizing the total energy consumption. Moreover, a two-stage alternating algorithm is proposed to solve the non-convex formulated problem. Finally, the simulation results show the superiority of the proposed scheme compared with other benchmark schemes. Finally, the performance of the proposed scheme is demonstrated under different settings. [ABSTRACT FROM AUTHOR]

Litchi (Litchi chinensis), a prominent fruit tree in the Sapindaceae, initiates flowering in response to low autumn and winter temperatures. This study investigates the epigenetic regulation of this process, focusing on the marks histone H3 lysine 27 trimethylation (H3K27me3) and its deposition genes during the chilling-induced floral induction (FId) and initiation stages. Our genomic analysis delineated the H3K27me3 deposition landscape across the prefloral induction (PFId), FId, and floral initiation (FIn) stages. We identified 5,635 differentially H3K27me3-modified genes (DHGs) in buds and 4,801 DHGs in leaves. Integration of the RNA-seq and ChIP-seq datasets identified 1,001 differentially regulated genes (DRGs) in buds and 675 DRGs in leaves, offering insights into the genes potentially targeted by H3K27me3. To probe the functional role of H3K27me3, we employed GSK343, a histone H3 lysine methyltransferase inhibitor. Treatment with GSK343 during the chilling-induced flowering process led to reduced H3K27me3 deposition at the TREHALOSE-6-PHOSPHATE SYNTHASE 1 (LcTPS1) and FRIGIDA (LcFRI) loci, resulting in increased gene expression. This manipulation delayed flowering and reduced flowering rates, confirming the pivotal role of H3K27me3 in chilling-induced flowering in litchi. Gene coexpression network analysis identified SHORT VEGETATIVE PHASE 10 (LcSVP10) as a crucial regulator in litchi flowering. Overexpression of LcSVP10 in Arabidopsis thaliana delayed flowering, indicating a conserved function in flowering time control. Our results elucidate the molecular and epigenetic mechanisms that govern FId in litchi and highlight the potential of epigenetic modifications to regulate flowering time in horticultural plants., Competing Interests: Conflict of interest statement. None declared., (© The Author(s) 2024. Published by Oxford University Press on behalf of American Society of Plant Biologists. All rights reserved. For commercial re-use, please contact reprints@oup.com for reprints and translation rights for reprints. All other permissions can be obtained through our RightsLink service via the Permissions link on the article page on our site—for further information please contact journals.permissions@oup.com.)

DEAD box proteins perform diverse cellular functions in bacteria. Our group previously reported that the transposon Tn4531 insertion in Riean&#95;0395 (designated dhR1 ), which encodes a putative DEAD box helicase, attenuated the virulence of R. anatipestifer strain YZb1. Here, we show that, compared to the wild-type (WT) R. anatipestifer strain Yb2, the growth or survival of the ΔdhR1 mutant in tryptic soy broth (TSB) was significantly decreased in response to cold, pH, osmotic stress, ethanol, Triton X-100, and oxidative stress, and the dhR1 deletion significantly reduced biofilm formation and the adhesion capacity to Vero cells, whereas the growth of ΔdhR1 was less impaired in iron-limited TSB. Moreover, the virulence of ΔdhR1 in ducklings was attenuated by about 80-fold, compared to the WT. In addition, a transcriptome analysis showed that the dhR1 deletion in the strain Yb2 affected the expression of 58 upregulated genes and 98 downregulated genes that are responsible for various functions. Overall, our work reveals that the deletion of DhR1 results in a broad effect on the bacterial fitness, biofilm formation, iron utilization, and virulence of R. anatipestifer, which makes it a global regulator. IMPORTANCE R. anatipestifer infection has been a continued and serious problem in many duck farms, but little is known about the mechanism underlying the pathogenesis of R. anatipestifer and how R. anatipestifer adapts to the external environment and thereby persists in duck farms. The results of this study demonstrate that the DEAD box protein DhR1 is required for the tolerance of R. anatipestifer to cold, pH, and other stresses, and it is also necessary for biofilm formation, iron utilization, and virulence in ducklings, demonstrating multiple functions of DhR1.

Riemerella anatipestifer mainly infects domestic ducks, geese, turkeys, and other birds, and causes considerable economic losses to the global duck industry. Previous studies have shown that concentrated cell-free culture filtrates of R. anatipestifer induce highly significant protection against homologous challenge. In this study, 12 immunogenic proteins were identified in the culture supernatant of R. anatipestifer strain Yb2 with immunoproteomic analysis. Of these, three immunogenic proteins, AS87&#95;RS06600 (designated "PaR1" in this study), AS87&#95;RS09020, and AS87&#95;RS09965, which appeared in more than three spots on the western-blotted membrane, were expressed in Escherichia coli and purified. Animal experiments showed that the recombinant PaR1 (rPaR1) protein protected 41.67% of immunized ducklings against challenge with virulent Yb2, whereas rAS87&#95;RS09020 or rAS87&#95;RS09965 did not, and that ducklings immunized once with rPaR1 were 20, 40, and 0% protected from challenge with R. anatipestifer strains WJ4 (serotype 1), Yb2 (serotype 2), and HXb2 (serotype 10), respectively. In addition, rPaR1 immunized rabbit serum showed bactericidal activity against strain Yb2 at a titer of 1:8. These results indicate that rPaR1 of strain Yb2 protects against homologous challenge. Amino acid homology analysis show that PaR1 is a non-serotype-specific protein among different R. anatipestifer serotypes. Furthermore, PaR1 is mainly secreted outside the cell through the T9SS. Overall, our results demonstrate that R. anatipestifer PaR1 is a non-serotype-specific protective protein secreted by the T9SS., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Wang, Chen, He, Du, Gao, Shan, Hu and Hu.)

The continuous development of intelligent traffic control systems has a profound influence on urban traffic planning and traffic management. Indeed, as big data and artificial intelligence continue to evolve, the traffic control strategy based on deep reinforcement learning (RL) has been proven to be a promising method to improve the efficiency of intersections and save people's travel time. However, the existing algorithms ignore the temporal and spatial characteristics of intersections. In this article, we propose a multiagent RL based on the deep spatiotemporal attentive neural network (MARL-DSTAN) to determine the traffic signal timing in a large-scale road network. In this model, the state information captures the spatial dependency of the entire road network by leveraging the graph convolutional network (GCN) and integrates the information based on the importance of intersections via the attention mechanism. Meanwhile, to accumulate more valuable samples and enhance the learning efficiency, the recurrent neural network (RNN) is introduced in the exploration stage to constrain the action search space instead of fully random exploration. MARL-DSTAN decomposes the large-scale area into multiple base environments, and the agents in each base environment use the idea of "centralized training and decentralized execution" to learn to accelerate the algorithm convergence. The simulation results show that our algorithm significantly outperforms the fixed timing scheme and several other state-of-the-art baseline RL algorithms.