Low-Cost Federated Broad Learning for Privacy-Preserved Knowledge Sharing in the RIS-Aided Internet of Vehicles

High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency of local data learning models while preventing privacy leakage in a high mobility environment.In order to protect data privacy and improve data learning efficiency in knowledge sharing,we propose an asynchronous federated broad learning(FBL)framework that integrates broad learning(BL)into federated learning(FL).In FBL,we design a broad fully connected model(BFCM)as a local model for training client data.To enhance the wireless channel quality for knowledge sharing and reduce the communication and computation cost of participating clients,we construct a joint resource allocation and reconfigurable intelligent surface(RIS)configuration optimization framework for FBL.The problem is decoupled into two convex subproblems.Aiming to improve the resource scheduling efficiency in FBL,a double Davidon–Fletcher–Powell(DDFP)algorithm is presented to solve the time slot allocation and RIS configuration problem.Based on the results of resource scheduling,we design a reward-allocation algorithm based on federated incentive learning(FIL)in FBL to compensate clients for their costs.The simulation results show that the proposed FBL framework achieves better performance than the comparison models in terms of efficiency,accuracy,and cost for knowledge sharing in the IoV.

Spontaneous Paravesical and Broad Ligament Hematoma after Vaginal Delivery Had Uterine Artery Embolization after Evacuating the Hematoma

Broad ligament hematoma is typically seen during cesarean section due to rupture of branches of uterine and vaginal vessels and it’s rare to be seen post-normal vaginal delivery. Addressing puerperal hematomas postpartum presents considerable challenges for obstetric care providers. While hematomas such as those affecting the vulva, vulvovaginal region, or paravaginal area are frequently encountered, retroperitoneal hematomas are rare and notably pose a greater risk to the life of the patient. The medical literature contains scant case reports on retroperitoneal hematomas, with no consensus on a definitive treatment approach. Pelvic arterial embolization has emerged as both a sensible and increasingly preferred method for treating these hematomas recently, but its application is contingent upon the patient maintaining hemodynamic stability and the availability of a specialized interventional embolization unit. In our case, we are presenting a very rare case of a 31-year-old primigravida female with a history of in vitro fertilization pregnancy. She delivered a normal vaginal delivery at 31 weeks gestation. Unfortunately, she experienced multiple complications intrapartum, including preeclampsia and placental abruption. These complications increased her risk of developing a broad ligament hematoma.

High efficient broad-spectrum Bradyrhizobium elkanii Y63-1

Soybean(Glycine max),the primary source of high-quality plant protein,plays a crucial role as a grain and oil crop in China.Harnessing the full potential of symbiotic nitrogen fixation in soybean production holds immense significance for agriculture and ecology alike.Zhongdou 63,a newly developed early-maturing summer soybean cultivar in 2021,exhibits remarkable traits such as high yield,superior quality,multi-resistance,and wide adaptability.In this study,eight distinct rhizobia strains from diverse regions were meticulously screened to identify highly effective strains specifically suited for Zhongdou 63.The aboveground biomass,plant height,chlorophyll content,root length,nodule number,and nodule dry weight of Zhongdou 63 were measured and the data were subjected to statistical analysis.The results demonstrated that Y63-1 is a predominant strain of Zhongdou 63.Subsequently,we conducted further investigations on the broad-spectrum nodulation characteristics of Y63-1.Ten representative soybean cultivars were individually inoculated with Y63-1 and subsequently analyzed for nodule numbers and nodule dry weight in their symbiotic systems with rhizobia.The findings revealed that Y63-1 effectively formed nodules with all ten soybean varieties tested.In summary,our current study identified highly efficient broad-spectrum Bradyrhizobium elkanii strain Y63-1 as the predominant strain in Zhongdou 63 and provided a theoretical foundation for enhancing yield potential not only in Zhongdou 63 but also in other varieties through inoculation with highly efficient rhizobia in production.

Mulching broad ridges with a woven polypropylene fabric increases the growth and yield of young pear trees ‘Yuluxiang' in the North China Plain

Unlike traditional ridging, mulching broad ridges with a woven polypropylene fabric (WPF) can reduce soil evaporation during the drought season and avoid long saturation time in the root zone of pear trees during the rainy season. In this study, field experiments were conducted from 2017 to 2020 in a pear orchard in the North China Plain to investigate the effects of mulching broad ridges (0.3 m in height and 2 m in width) with WPF on soil temperature and moisture, nitrogen leaching, vegetative and reproductive growth of young pear trees(Pyrus bretschneideri Rehd.‘Yuluxiang’). The experiments involved two treatments, namely, control (traditional no-ridge planting without mulching) and mulching broad ridges with WPF (RM treatment). The results showed that the RM treatment increased soil moisture and temperature and decreased nitrogen leaching, resulting in vigorous growth of the young pear trees. Moreover, the RM treatment increased the tree trunk cross-sectional area and height of the young pear trees by 37%and 8%in 2020, respectively. The nitrate nitrogen content at the soil layer depth of 0-30 cm was significantly higher in the RM than that in control. Furthermore, the RM treatment significantly increased the fruit yield due to larger tree size. In addition, compared with control, significantly higher fruit soluble solid content of RM treatment was detected in 2020. High precipitation (423 mm) occurred during fruit enlargement stage in 2020, RM treatment decreased the rainfall infiltration in the ridge and the soil moisture in root region, resulting in the improvement of fruit quality, compared with control.Therefore, mulching broad ridges with WPF can be implemented to increase soil moisture during drought season, soil temperature, and nitrate nitrogen content, thereby improving the growth and fruit yield of young pear trees. Additionally, it can reduce soil moisture in the root zone during the rainy season and improve the fruit quality of the trees. Finally, it can reduce nitrate nitrogen leaching, thereby reducing environmental pollution.

Flexible broadband WS_(2)/Si optical position-sensitive detector with high sensitivity and fast speed

Si-based optical position-sensitive detectors(PSDs)have stimulated the interest of researchers due to their wide range of practical applications.However,due to the rigidity and fragility of Si crystals,the applications of flexible PSDs have been limited.Therefore,we presented a flexible broadband PSD based on a WS_(2)/Si heterostructure for the first time.A scalable sputtering method was used to deposit WS_(2)thin films onto the etched ultrathin crystalline Si surface.The fabricated flexible PSD device has a broad spectral response in the wavelength range of 450-1350 nm,with a high position sensitivity of~539.8 mV·mm^(−1)and a fast response of 2.3μs,thanks to the strong light absorption,the built-in electrical field at the WS_(2)/Si interface,and facilitated transport.Furthermore,mechanical-bending tests revealed that after 200 mechanical-bending cycles,the WS_(2)/Si PSDs have excellent mechanical flexibility,stability,and durability,demonstrating the great potential in wearable PSDs with competitive performance.

A broad learning-based comprehensive defence against SSDP reflection attacks in IoTs

The proliferation of Internet of Things(IoT)rapidly increases the possiblities of Simple Service Discovery Protocol(SSDP)reflection attacks.Most DDoS attack defence strategies deploy only to a certain type of devices in the attack chain,and need to detect attacks in advance,and the detection of DDoS attacks often uses heavy algorithms consuming lots of computing resources.This paper proposes a comprehensive DDoS attack defence approach which combines broad learning and a set of defence strategies against SSDP attacks,called Broad Learning based Comprehensive Defence(BLCD).The defence strategies work along the attack chain,starting from attack sources to victims.It defends against attacks without detecting attacks or identifying the roles of IoT devices in SSDP reflection attacks.BLCD also detects suspicious traffic at bots,service providers and victims by using broad learning,and the detection results are used as the basis for automatically deploying defence strategies which can significantly reduce DDoS packets.For evaluations,we thoroughly analyze attack traffic when deploying BLCD to different defence locations.Experiments show that BLCD can reduce the number of packets received at the victim to 39 without affecting the standard SSDP service,and detect malicious packets with an accuracy of 99.99%.

Closed loop ileus caused by a defect in the broad ligament:A case report

BACKGROUND Closed loop ileus caused by entrapment of bowel in a defect of the broad ligament is a rarity.Only a few cases have been reported in the literature.CASE SUMMARY We present the case of a 44-year-old,healthy patient with no prior history of abdominal surgery who developed a closed loop ileus due to an internal hernia secondary to a defect in the right broad ligament.She first presented to the emergency department with diarrhea and vomiting.As she had had no previous abdominal surgery,she was diagnosed with probable gastroenteritis and discharged.The patient subsequently returned to the emergency department due to a lack of improvement in her symptoms.Blood tests showed an elevated white blood cell count and a closed loop ileus was diagnosed on an abdominal computer tomography scan.Diagnostic laparoscopy revealed an internal hernia entrapped in a 2 cm large defect in the right broad ligament.The hernia was reduced and the ligament defect was closed using a running,barbed suture.CONCLUSION Bowel incarceration through an internal hernia may present with misleading symptoms and laparoscopy may reveal unexpected findings.

Broadband and continuous wave pumped second-harmonic generation from microfiber coated with layered GaSe crystal

The conversion-efficiency for second-harmonic(SH)in optical fibers is significantly limited by extremely weak second-order nonlinearity of fused silica,and pulse pump lasers with high peak power are widely employed.Here,we propose a simple strategy to efficiently realize the broadband and continuous wave(CW)pumped SH,by transferring a crystalline GaSe coating onto a microfiber with phase-matching diameter.In the experiment,high efficiency up to 0.08%W-1mm-1 is reached for a C-band pump laser.The high enough efficiency not only guarantees SH at a single frequency pumped by a CW laser,but also multi-frequencies mixing supported by three CW light sources.Moreover,broadband SH spectrum is also achieved under the pump of a superluminescent light-emitting diode source with a 79.3 nm bandwidth.The proposed scheme provides a beneficial method to the enhancement of various nonlinear parameter processes,development of quasi-monochromatic or broadband CW light sources at new wavelength regions.

Target tracking method of Siamese networks based on the broad learning system

Target tracking has a wide range of applications in intelligent transportation,real‐time monitoring,human‐computer interaction and other aspects.However,in the tracking process,the target is prone to deformation,occlusion,loss,scale variation,background clutter,illumination variation,etc.,which bring great challenges to realize accurate and real‐time tracking.Tracking based on Siamese networks promotes the application of deep learning in the field of target tracking,ensuring both accuracy and real‐time performance.However,due to its offline training,it is difficult to deal with the fast motion,serious occlusion,loss and deformation of the target during tracking.Therefore,it is very helpful to improve the performance of the Siamese networks by learning new features of the target quickly and updating the target position in time online.The broad learning system(BLS)has a simple network structure,high learning efficiency,and strong feature learning ability.Aiming at the problems of Siamese networks and the characteristics of BLS,a target tracking method based on BLS is proposed.The method combines offline training with fast online learning of new features,which not only adopts the powerful feature representation ability of deep learning,but also skillfully uses the BLS for re‐learning and re‐detection.The broad re‐learning information is used for re‐detection when the target tracking appears serious occlusion and so on,so as to change the selection of the Siamese networks search area,solve the problem that the search range cannot meet the fast motion of the target,and improve the adaptability.Experimental results show that the proposed method achieves good results on three challenging datasets and improves the performance of the basic algorithm in difficult scenarios.

Music Emotion Recognition Based on Feature Fusion Broad Learning Method

With the rapid development in the field of artificial intelligence and natural language processing(NLP),research on music retrieval has gained importance.Music messages express emotional signals.The emotional classification of music can help in conveniently organizing and retrieving music.It is also the premise of using music for psychological intervention and physiological adjustment.A new chord-to-vector method was proposed,which converted the chord information of music into a chord vector of music and combined the weight of the Mel-frequency cepstral coefficient(MFCC) and residual phase(RP) with the feature fusion of a cochleogram.The music emotion recognition and classification training was carried out using the fusion of a convolution neural network and bidirectional long short-term memory(BiLSTM).In addition,based on the self-collected dataset,a comparison of the proposed model with other model structures was performed.The results show that the proposed method achieved a higher recognition accuracy compared with other models.

长期生态学研究中的经典实验途径——Lawcs和Gilbrt的Broad balk实验

没有长期实验领域的资料而去讨论长期实验是困难的,最早的实验在Rothamsted进行,在那里,测定了植物的氮素来源和化肥及农家肥对小麦产量的影响,该实验始于1843年,与类似的芜％Barnfild实验一样,随后变得更复杂而最终终止了。Barnfield实验以其简单的形式,仍然存在着而基本上没有改变,就象那时能够想象一样,该实验对“长期实验”做出了贡献,简单的设计可能是其成功的关键。当随后R.A.Fi sher试图分析时,这导致他设计新的野外实验统计和随机因子设计(Fisher 1925,1935),并变成了后来田间分析的基础;因为Broadbalk没有反复的实验,现在也不能重复;已经产生了如此多的不同且可改变的变化,就象后来土壤分析所示的,这是在做到最初目的之后继续取样的。存在(Survival)已是实验最显著的成就之一,一起进行的有费歇尔(Fi的叮i＊)的田间统计和对土壤、植物营养、/h麦产量、病害、昆虫、线虫、微生物和杂草的研究(例子见Bawden)。

A Federated Bidirectional Connection Broad Learning Scheme for Secure Data Sharing in Internet of Vehicles

Data sharing in Internet of Vehicles(IoV)makes it possible to provide personalized services for users by service providers in Intelligent Transportation Systems(ITS).As IoV is a multi-user mobile scenario,the reliability and efficiency of data sharing need to be further enhanced.Federated learning allows the server to exchange parameters without obtaining private data from clients so that the privacy is protected.Broad learning system is a novel artificial intelligence technology that can improve training efficiency of data set.Thus,we propose a federated bidirectional connection broad learning scheme(FeBBLS)to solve the data sharing issues.Firstly,we adopt the bidirectional connection broad learning system(BiBLS)model to train data set in vehicular nodes.The server aggregates the collected parameters of BiBLS from vehicular nodes through the federated broad learning system(FedBLS)algorithm.Moreover,we propose a clustering FedBLS algorithm to offload the data sharing into clusters for improving the aggregation capability of the model.Some simulation results show our scheme can improve the efficiency and prediction accuracy of data sharing and protect the privacy of data sharing.

Combined community ecology and floristics,a synthetic study on the upper montane evergreen broad-leaved forests in Yunnan,southwestern China

The upper montane evergreen broad-leaved forest in Yunnan occurs mainly in the zone of persistent cloud and has a discontinuous,island-like,distribution.It is diverse,rich in endemic species,and likely to be sensitive to climate change.Six 1-ha sampling plots were established across the main distribution area of the upper montane evergreen broad-leaved forest in Yunnan.All trees with d.b.h.>1 cm in each plot were identified.Patterns of seed plant distributions were quantified at the specific,generic and family levels.The forests are dominated by the families Fagaceae,Lauraceae,Theaceae and Magnoliaceae,but are very diverse with only a few species shared between sites.Floristic similarities at the family and generic level were high,but they were low at the specific level,with species complementarity between plots.Diversity varied greatly among sites,with greater species richness and more rare species in western Yunnan than central Yunnan.The flora is dominated by tropical biogeographical elements,mainly the pantropic and the tropical Asian distributions at the family and genus levels.In contrast,at the species level,the flora is dominated by the southwest or the southeast China distributions,including Yunnan endemics.This suggests that the flora of the upper montane forest in Yunnan could have a tropical floristic origin,and has adapted to cooler temperatures with the uplift of the Himalayas.Due to great sensitivity to climate,high endemism and species complementarity,as well as the discontinuous,island-like,distribution patterns of the upper montane forest in Yunnan,the regional conservation of the forest is especially needed.

Thermostable Broad Band Polarizing PVA-Film: Theoretical and Experimental Investigations

In the present work, for the first time on the basis ofpoly （vinyl alcohol） （PVA）, 2- （4-dimethylaminostyryl）-l-ethylquinolinium iodide （quinaldine red （QR）） and trisodium （4E）-5-oxo- 1-（4-sulfonatophenyl）-4-[（4-sulfonatophenyl）hydrazono]-3 pyrazolecarboxylate （tartrazine （T））, thermostable polarizing film in a wide range of spectra （λmax=394-511 nm） with polarization efficiency （PE） = 98% in absorption maximum and stretching degree （Rs） = 3.5 was developed. The basic spectral-polarization parameters （polarization efficiency and transmittance） of oriented colored PVA-films were measured and discussed. During the work it was found that oriented PVA-films are the phenomenon of anisotropy of thermal conductivity （λ｜/λ⊥）. It is a very important parameter for the development of thermostable PVA-polarizing films. For the first time quantum-chemical calculations using density functional theory （DFT） approach for structural analysis and electronic spectrum of the QR were carried out via the B3LYP/dgdzvp and TDB3LYP/dgdzvp methods. Interpretation of absorption strips in visible region of spectrum was also reported. The excitation energies, electronic transitions and oscillator strengths for the studied structures have also been calculated （B3LYP/dgdzvp）. The NBO analysis and Mulliken atomic charges of the QR were carried out.

A Broad Learning-Driven Network Traffic Analysis System Based on Fog Computing Paradigm

The development of communication technologies which support traffic-intensive applications presents new challenges in designing a real-time traffic analysis architecture and an accurate method that suitable for a wide variety of traffic types.Current traffic analysis methods are executed on the cloud,which needs to upload the traffic data.Fog computing is a more promising way to save bandwidth resources by offloading these tasks to the fog nodes.However,traffic analysis models based on traditional machine learning need to retrain all traffic data when updating the trained model,which are not suitable for fog computing due to the poor computing power.In this study,we design a novel fog computing based traffic analysis system using broad learning.For one thing,fog computing can provide a distributed architecture for saving the bandwidth resources.For another,we use the broad learning to incrementally train the traffic data,which is more suitable for fog computing because it can support incremental updates of models without retraining all data.We implement our system on the Raspberry Pi,and experimental results show that we have a 98%probability to accurately identify these traffic data.Moreover,our method has a faster training speed compared with Convolutional Neural Network(CNN).

Higher degree moment tensor inversion of Mani earthquake using far-field broadband recording

Breakthrough point source model, extended earthquake source model is used to calculate more seismic source parameters in this paper. We express seismic source using higher degree moment tensors, to reduce a Iarge number terms originally presenting in higher degree moment tensor representation, Haskell rupture model is used. We in verted the source parameters of Mani earthquake in Tibet using broad-band body wave of 32 stations of Global Seismograph Network (GSN), the results show that it is a strike-slip fault, rupture direction is 75°, rupture duration is 19 s, the fault plan is φ=77°， δ5=88°, A=0°, the auxiliare plane is φ=347°, δ=90°, k=178°, and the fault dimension is 47 km×28 km. These results will give new quantitative data for earth dynamics and have practical meaning for seismic source tomography research.

Factors controlling N_2O and CH_4 fluxes in mixed broad-leaved/Korean pine forest of Changbai Mountain, China

Using the closed chamber technique, the in situ measurements of N2O and CH4 fluxes was conducted in a broad-leaved Korean pine mixed forest ecosystem in Changbai Mountain, China. from June 1994 to october 1995. The relationships between fluxes (N2O and CH4) and some major environmental factors (temperature, soil water content and soil availabIe nitrogen) were studied. A significant positive correlation between Nzo emission and air/soil temperature was observed, but no significant correIation was found between N2O emission and soil water content (SWC). This result showed that temperature was an important controlling factor of N2O flux. There was a significant correlation between CH4 uptake and SWC, but no significant correlation was found between CH4 uptake and temperature. This suggested SWC was an important factor controlling CH4 uptake. The very significant negative correlation between logarithmic N2O flux and soil nitrate concentration, significant negative correlation between CH4 flux and soil ammonium content were also found.

Linear Piezoelectric Stepping Motor with Broad Operating Frequency

The existing resonant linear piezoelectric motors must operate with high working voltage in resonant condition,resulting in their narrow operating frequency range and poor running stability.Here,with the large displacement output characteristics of piezoelectric stacks,the trajectory at the drive foot of stator is firstly produced with two space quadrature piezoelectric actuators excited by sawtooth wave and square wave.Secondly,the friction drive principle of motor is used to analyze the working mechanisms of the continuous stepping motion.Finally,the motor prototype is designed and experiments are carried out.The experimental result shows that the motor can stably operate within the scope of 350 Hz to 750 Hz.When the excitation voltage is 30 Vand pre-load is 3Nor10 N,the lateral amplitude of the drive foot is approximately 4μm and the stable average interval ranges from3.1μm to 3.2μm with the error rate of 5%—7.5%.

Photoluminescence and Ce^(3+)→Tb^(3+)→Eu^(3+) Energy Transfer Processes of the Ce^(3+)/Tb^(3+)/Eu^(3+)-doped β-NaYF_(4) Phosphors with Broadened Excitation Spectrum

Ce^(3+)/Tb^(3+) co-doped and Ce^(3+)/Tb^(3+)/Eu^(3+) tri-doped β-NaYF_(4) photoluminescent microcrystals using oleic acid as surfactant were synthesized using the solvothermal method.Their microstructural characteristics and photoluminescence properties were investigated in detail.They have the shape of hexagonal prism bipyramids with uniform particle size,which decreases with the concentrations of Tb^(3+) and Eu^(3+).The energy transfer processes of both the Ce^(3+)→Tb^(3+) and the Ce^(3+)→Tb^(3+)→Eu^(3+) were systematically studied.Compared with Eu^(3+) or Tb^(3+) single-doped β-NaYF_(4) microcrystals,the sensitization by Ce^(3+) for the photoluminescence of Tb^(3+) and Eu^(3+) leads to a broad excitation spectral bandwidth in the ultraviolet (UV) range.Meanwhile,the corresponding optical absorption efficiency is greatly enhanced.High energy transfer efficiencies have been observed from Ce^(3+) to Tb^(3+) and from Tb^(3+) to Eu^(3+).

Study on guided-mode resonance characteristic of multilayer dielectric grating with broadband and wide using-angle

Guided-mode resonance in a diffraction band of multilayer dielectric gratings may lead to a catastrophic result in laser system, especially in the ultrashort pulse laser system, so the inhibition of guided-mode resonance is very important. In this paper the characteristics of guided-mode resonance in multilayer dielectric grating are studied with the aim of better understanding the physical process of guided-mode resonance and designing a broadband multilayer dielectric grating with no guided-mode resonance. By employing waveguide theory, all guided-wave modes appearing in multilayer dielectric grating are found, and the incident conditions, separately, corresponding to each guided-wave mode are also obtained. The electric field enhancement in multilayer dielectric grating is shown obviously. Furthermore, from the detailed analyses on the guided-mode resonance conditions, it is found that the reduction of the grating period would effectively avoid the appearing of guided-mode resonance. And the expressions for calculating maximum periods, which ensure that no guided-mode resonance occurs in the requiring broad angle or wavelength range, are first reported. The above results calculated by waveguide theory and Fourier mode method are compared with each other, and they are coincident completely. Moreover, the method that relies on waveguide theory is more helpful for understanding the guided-mode resonance excited process and analyzing how each parameter affects the characteristic of guided-mode resonance. Therefore, the effects of multilayer dielectric grating parameters, such as period, fill factor, thickness of grating layer, et al., on the guided-mode resonance characteristic are discussed in detail based on waveguide theory, and some meaningful results are obtained.