Single-atom catalysts(SACs)have garnered significant attention in lithium-sulfur(Li-S)batteries for their potential to mitigate the severe polysulfide shuttle effect and sluggish redox kinetics.However,the development...Single-atom catalysts(SACs)have garnered significant attention in lithium-sulfur(Li-S)batteries for their potential to mitigate the severe polysulfide shuttle effect and sluggish redox kinetics.However,the development of highly efficient SACs and a comprehensive understanding of their structure-activity relationships remain enormously challenging.Herein,a novel kind of Fe-based SAC featuring an asymmetric FeN_(5)-TeN_(4) coordination structure was precisely designed by introducing Te atom adjacent to the Fe active center to enhance the catalytic activity.Theoretical calculations reveal that the neighboring Te atom modulates the local coordination environment of the central Fe site,elevating the d-band center closer to the Fermi level and strengthening the d-p orbital hybridization between the catalyst and sulfur species,thereby immobilizing polysulfides and improving the bidirectional catalysis of Li-S redox.Consequently,the Fe-Te atom pair catalyst endows Li-S batteries with exceptional rate performance,achieving a high specific capacity of 735 mAh g^(−1) at 5 C,and remarkable cycling stability with a low decay rate of 0.038%per cycle over 1000 cycles at 1 C.This work provides fundamental insights into the electronic structure modulation of SACs and establishes a clear correlation between precisely engineered atomic configurations and their enhanced catalytic performance in Li-S electrochemistry.展开更多
Pipelines are extensively used in environments such as nuclear power plants,chemical factories,and medical devices to transport gases and liquids.These tubular environments often feature complex geometries,confined sp...Pipelines are extensively used in environments such as nuclear power plants,chemical factories,and medical devices to transport gases and liquids.These tubular environments often feature complex geometries,confined spaces,and millimeter-scale height restrictions,presenting significant challenges to conventional inspection methods.Here,we present an ultrasonic microrobot(weight,80 mg;dimensions,24 mm×7 mm;thickness,210μm)to realize agile and bidirectional navigation in narrow pipelines.The ultrathin structural design of the robot is achieved through a high-performance piezoelectric composite film microstructure based on MEMS technology.The robot exhibits various vibration modes when driven by ultrasonic frequency signals,its motion speed reaches81 cm s-1 at 54.8 k Hz,exceeding that of the fastest piezoelectric microrobots,and its forward and backward motion direction is controllable through frequency modulation,while the minimum driving voltage for initial movement can be as low as 3 VP-P.Additionally,the robot can effortlessly climb slopes up to 24.25°and carry loads more than 36 times its weight.The robot is capable of agile navigation through curved L-shaped pipes,pipes made of various materials(acrylic,stainless steel,and polyvinyl chloride),and even over water.To further demonstrate its inspection capabilities,a micro-endoscope camera is integrated into the robot,enabling real-time image capture inside glass pipes.展开更多
Lithium-sulfur (Li-S) batteries have gained great attention due to the high theoretical energy density and low cost,yet their further commercialization has been obstructed by the notorious shuttle effect and sluggish ...Lithium-sulfur (Li-S) batteries have gained great attention due to the high theoretical energy density and low cost,yet their further commercialization has been obstructed by the notorious shuttle effect and sluggish redox dynamics.Herein,we supply a strategy to optimize the electron structure of Ni_(2)P by concurrently introducing B-doped atoms and P vacancies in Ni_(2)P (Vp-B-Ni_(2)P),thereby enhancing the bidirectional sulfur conversion.The study indicates that the simultaneous introduction of B-doped atoms and P vacancies in Ni_(2)P causes the redistribution of electron around Ni atoms,bringing about the upward shift of d-band center of Ni atoms and effective d-p orbital hybridization between Ni atoms and sulfur species,thus strengthening the chemical anchoring for lithium polysulfides (LiPSs) as well as expediting the bidirectional conversion kinetics of sulfur species.Meanwhile,theoretical calculations reveal that the incorporation of B-doped atoms and P vacancies in Ni_(2)P selectively promotes Li2S dissolution and nucleation processes.Thus,the Li-S batteries with Vp-B-Ni_(2)P-separators present outstanding rate ability of 777 m A h g^(-1)at 5 C and high areal capacity of 8.03 mA h cm^(-2)under E/S of 5μL mg^(-1)and sulfur loading of 7.20 mg cm^(-2).This work elucidates that introducing heteroatom and vacancy in metal phosphide collaboratively regulates the electron structure to accelerate bidirectional sulfur conversion.展开更多
BACKGROUND Propofol has been widely used in bidirectional gastrointestinal endoscopy sedation;however,it frequently leads to cardiovascular adverse events and respiratory depression.Propofol target-controlled infusion...BACKGROUND Propofol has been widely used in bidirectional gastrointestinal endoscopy sedation;however,it frequently leads to cardiovascular adverse events and respiratory depression.Propofol target-controlled infusion(TCI)can provide safe sedation but may require higher dosages of propofol.On the contrary,etomidate offers hemodynamic stability.AIM To evaluate the effect of different dose etomidate added to propofol TCI sedation during same-visit bidirectional endoscopy.METHODS A total of 330 patients from Fujian Provincial Hospital were randomly divided into three groups:P,0.1EP,and 0.15EP.Patients in the P group received propofol TCI only,with an initial effect-site concentration of the propofol TCI system of 3.0 mg/mL.Patients in the 0.1EP and 0.15EP groups received 0.1 and 0.15 mg/kg etomidate intravenous injection,respectively,followed by propofol TCI.RESULTS Patients in the 0.15EP group had higher mean blood pressure after induction than the other groups(P group:78 mmHg,0.1EP group:82 mmHg,0.15EP group:88 mmHg;P<0.05).Total doses of propofol consumption significantly decreased in the 0.15EP group compared with that in the other groups(P group:260.6 mg,0.1EP group:228.1 mg,0.15EP group:201.2 mg;P<0.05).The induction time was longer in the P group than in the other groups(P group:1.9±0.7 minutes,0.1EP group:1.2±0.4 minutes,0.15EP group:1.1±0.3 minutes;P<0.01).The recovery time was shorter in the 0.15EP group than in the other groups(P group:4.8±2.1 minutes,0.1EP group:4.5±1.6 minutes,0.15EP group:3.9±1.4 minutes;P<0.01).The incidence of hypotension(P group:36.4%,0.1EP group:29.1%,0.15EP group:11.8%;P<0.01)and injection pain was lower in the 0.15EP group than in the other groups(P<0.05).Furthermore,the incidence of respiratory depression was lower in the 0.15EP group than in the P group(P<0.05).Additionally,the satisfaction of the patient,endoscopist,and anesthesiologist was higher in the 0.15EP group than in the other groups(P<0.05).CONCLUSION Our findings suggest that 0.15 mg/kg etomidate plus propofol TCI can significantly reduce propofol consumption,which is followed by fewer cardiovascular adverse events and respiratory depression,along with higher patient,endoscopist,and anesthesiologist satisfaction.展开更多
Motivated by the early works on bidirectional interaction and the breakthrough to estimate seismic response to bidirectional shaking via unidirectional analysis,it is essential to answer the question:When is the inter...Motivated by the early works on bidirectional interaction and the breakthrough to estimate seismic response to bidirectional shaking via unidirectional analysis,it is essential to answer the question:When is the interaction effect significant?Early works concluded that the effect of interaction is pronounced for stiff systems;consequently,the straightforward method for estimating seismic response to bidirectional excitation by using unidirectional analyses is verified primarily for short period systems.Hence,it is essential to identify the domain of significance for bidirectional interaction before adopting this simple methodology in design.Several parametrically defined systems with elastoplastic and degrading hysteresis models are studied under near-fault motions,assuming strength-independent and strength-dependent stiffness.The force-based and displacement-based analyses,conducted in parallel,reveal that the interaction effect is considerable for stiff systems,especially with degrading characteristics in a relatively low inelasticity range.However,the bidirectional effect may be significant even for highly flexible systems,especially for residual deformation,which in earlier works was shrouded.The range of significance depends on the hysteresis model,system parameters,and response indices.Regression analysis is carried out with the results of the case studies,and the derived regression models may be used for a preliminary assessment of the impact of interaction in advance.展开更多
In addition to its recognized role in providing structural support, bone plays a crucial role in maintaining the functionality and balance of various organs by secreting specific cytokines(also known as osteokines). T...In addition to its recognized role in providing structural support, bone plays a crucial role in maintaining the functionality and balance of various organs by secreting specific cytokines(also known as osteokines). This reciprocal influence extends to these organs modulating bone homeostasis and development, although this aspect has yet to be systematically reviewed. This review aims to elucidate this bidirectional crosstalk, with a particular focus on the role of osteokines. Additionally, it presents a unique compilation of evidence highlighting the critical function of extracellular vesicles(EVs) within bone-organ axes for the first time. Moreover, it explores the implications of this crosstalk for designing and implementing bone-on-chips and assembloids, underscoring the importance of comprehending these interactions for advancing physiologically relevant in vitro models. Consequently, this review establishes a robust theoretical foundation for preventing, diagnosing, and treating diseases related to the bone-organ axis from the perspective of cytokines, EVs, hormones, and metabolites.展开更多
Over the past few years,Malware attacks have become more and more widespread,posing threats to digital assets throughout the world.Although numerous methods have been developed to detect malicious attacks,these malwar...Over the past few years,Malware attacks have become more and more widespread,posing threats to digital assets throughout the world.Although numerous methods have been developed to detect malicious attacks,these malware detection techniques need to be more efficient in detecting new and progressively sophisticated variants of malware.Therefore,the development of more advanced and accurate techniques is necessary for malware detection.This paper introduces a comprehensive Dual-Channel Attention Deep Bidirectional Long Short-Term Memory(DCADBiLSTM)model for malware detection and riskmitigation.The Dual Channel Attention(DCA)mechanism improves themodel’s capability to concentrate on the features that aremost appropriate in the input data,which reduces the false favourable rates.The Bidirectional Long,Short-Term Memory framework helps capture crucial interdependence from past and future circumstances,which is essential for enhancing the model’s understanding of malware behaviour.As soon as malware is detected,the risk mitigation phase is implemented,which evaluates the severity of each threat and helps mitigate threats earlier.The outcomes of the method demonstrate better accuracy of 98.96%,which outperforms traditional models.It indicates the method detects and mitigates several kinds of malware threats,thereby providing a proactive defence mechanism against the emerging challenges in cybersecurity.展开更多
Intent detection and slot filling are two important components of natural language understanding.Because their relevance,joint training is often performed to improve performance.Existing studies mostly use a joint mod...Intent detection and slot filling are two important components of natural language understanding.Because their relevance,joint training is often performed to improve performance.Existing studies mostly use a joint model of multi-intent detection and slot-filling with unidirectional interaction,which improves the overall performance of the model by fusing the intent information in the slot-filling part.On this basis,in order to further improve the overall performance of the model by exploiting the correlation between the two,this paper proposes a joint multi-intent detection and slot-filling model based on a bidirectional interaction structure,which fuses the intent encoding information in the encoding part of slot filling and fuses the slot decoding information in the decoding part of intent detection.Experimental results on two public multi-intent joint training datasets,MixATIS and MixSNIPS,show that the bidirectional interaction structure proposed in this paper can effectively improve the performance of the joint model.In addition,in order to verify the generalization of the bidirectional interaction structure between intent and slot,a joint model for single-intent scenarios is proposed on the basis of the model in this paper.This model also achieves excellent performance on two public single-intent joint training datasets,CAIS and SNIPS.展开更多
Gastric cancer(GC)is a highly prevalent and life-threatening malignant tumor worldwide,posing a serious threat to human health.Depression is also highly prevalent among patients with GC.A complex bidirectional relatio...Gastric cancer(GC)is a highly prevalent and life-threatening malignant tumor worldwide,posing a serious threat to human health.Depression is also highly prevalent among patients with GC.A complex bidirectional relationship exists between the two.A total of 52 articles were included in this study to synthesize the evidence on the association between depression and the risk of GC as well as the prognosis of affected patients.The findings indicated that depression can activate the sympathetic nervous system and the hypothalamic-pituitary-adrenal axis,promote the release of catecholamine neurotransmitters,and influence the proliferation,invasion,and metastasis of GC through signaling pathways such as theβ2-adrenergic receptor.Furthermore,the severity of depression is positively correlated with indicators of GC progression.At the same time,GC can induce or aggravate depression through psychological and cognitive factors,social environment interactions,and diverse pathophysiological mechanisms,including tumor biological characteristics,treatment-related damage,and metabolic disorders.These interactions form a vicious cycle.This minireview summarizes the existing evidence and provides a theoretical basis for clinical interventions aimed at improving treatment outcomes and quality of life in patients with GC.展开更多
This study examines the bidirectional shaping mechanism between short-video algorithms and film narratives within the attention economy.It investigates how algorithmic logic influences cinematic storytelling and how f...This study examines the bidirectional shaping mechanism between short-video algorithms and film narratives within the attention economy.It investigates how algorithmic logic influences cinematic storytelling and how films,in turn,contribute to the aesthetic enhancement of short-video content.Drawing on Communication Accommodation Theory and Berry’s Acculturation Theory,along with case analyses and industry data,this research demonstrates that algorithms push films toward high-stimulus,fast-paced narrative patterns—characterized by increased shot density and structural fragmentation—to capture and retain viewer attention.Conversely,films counter this influence by supplying narratively deep and artistically refined content that elevates short-video aesthetics and encourages critical audience engagement.This dynamic reflects a process of mutual adaptation rather than one-sided dominance.The study concludes that such interaction signifies a broader restructuring of cultural production logic,facilitating cross-media convergence while simultaneously posing risks to cultural diversity due to the prioritization of high-traffic content.Balancing this relationship will require policy support,algorithmic transparency,and strengthened industry self-regulation to preserve artistic integrity and cultural ecosystem diversity.展开更多
This paper introduces an Improved Bidirectional Jump Point Search(I-BJPS)algorithm to address the challenges of the traditional Jump Point Search(JPS)in mobile robot path planning.These challenges include excessive no...This paper introduces an Improved Bidirectional Jump Point Search(I-BJPS)algorithm to address the challenges of the traditional Jump Point Search(JPS)in mobile robot path planning.These challenges include excessive node expansions,frequent path inflexion points,slower search times,and a high number of jump points in complex environments with large areas and dense obstacles.Firstly,we improve the heuristic functions in both forward and reverse directions to minimize expansion nodes and search time.We also introduce a node optimization strategy to reduce non-essential nodes so that the path length is optimized.Secondly,we employ a second-order Bezier Curve to smooth turning points,making generated paths more suitable for mobile robot motion requirements.Then,we integrate the Dynamic Window Approach(DWA)to improve path planning safety.Finally,the simulation results demonstrate that the I-BJPS algorithm significantly outperforms both the original unidirectional JPS algorithm and the bidirectional JPS algorithm in terms of search time,the number of path inflexion points,and overall path length,the advantages of the I-BJPS algorithm are particularly pronounced in complex environments.Experimental results from real-world scenarios indicate that the proposed algorithm can efficiently and rapidly generate an optimal path that is safe,collision-free,and well-suited to the robot’s locomotion requirements.展开更多
Efficient energy management is a cornerstone of advancing cognitive cities,where AI,IoT,and cloud computing seamlessly integrate to meet escalating global energy demands.Within this context,the ability to forecast ele...Efficient energy management is a cornerstone of advancing cognitive cities,where AI,IoT,and cloud computing seamlessly integrate to meet escalating global energy demands.Within this context,the ability to forecast electricity consumption with precision is vital,particularly in residential settings where usage patterns are highly variable and complex.This study presents an innovative approach to energy consumption forecasting using a bidirectional Long Short-Term Memory(LSTM)network.Leveraging a dataset containing over twomillionmultivariate,time-series observations collected froma single household over nearly four years,ourmodel addresses the limitations of traditional time-series forecasting methods,which often struggle with temporal dependencies and non-linear relationships.The bidirectional LSTM architecture processes data in both forward and backward directions,capturing past and future contexts at each time step,whereas existing unidirectional LSTMs consider only a single temporal direction.This design,combined with dropout regularization,leads to a 20.6%reduction in RMSE and an 18.8%improvement in MAE over conventional unidirectional LSTMs,demonstrating a substantial enhancement in prediction accuracy and robustness.Compared to existing models—including SVM,Random Forest,MLP,ANN,and CNN—the proposed model achieves the lowest MAE of 0.0831 and RMSE of 0.2213 during testing,significantly outperforming these benchmarks.These results highlight the model’s superior ability to navigate the complexities of energy usage patterns,reinforcing its potential application in AI-driven IoT and cloud-enabled energy management systems for cognitive cities.By integrating advanced machine learning techniqueswith IoT and cloud infrastructure,this research contributes to the development of intelligent,sustainable urban environments.展开更多
The initiation and progression of colorectal cancer(CRC)are profoundly influenced by the complex interplay between the gut microbiota and the immune system,underscoring the clinical importance of exploring the bidirec...The initiation and progression of colorectal cancer(CRC)are profoundly influenced by the complex interplay between the gut microbiota and the immune system,underscoring the clinical importance of exploring the bidirectional regulatory mechanisms of the microbiota-immune axis within the CRC immune microenvironment.Emerging evidence indicates that the composition and functional capacity of the gut microbiota play a vital role in modulating the host’s immune responses,while the immune system,in turn,can reciprocally regulate the structure and function of the microbiota.Despite significant insights into the role of the microbiota-immune axis in CRC progression,several critical questions remain unanswered-including how microbial heterogeneity affects therapeutic outcomes and the specific consequences of dysregulated regulatory mechanisms on the immune microenvironment.This review aims to provide a comprehensive analysis of the compositional features of the CRC immune microenvironment,examine the bidirectional molecular mechanisms underpinning the microbiotaimmune axis,and evaluate the potential of targeted therapeutic strategies,thereby offering novel research perspectives and clinical applications for CRC treatment.展开更多
To address the limitations of conventional energy systems and optimize the energy conversion pathways and efficiency,a type of“five-in-one”multifunctional phase-change composite with magnetothermal,electrothermal,so...To address the limitations of conventional energy systems and optimize the energy conversion pathways and efficiency,a type of“five-in-one”multifunctional phase-change composite with magnetothermal,electrothermal,solar-thermal,and thermoelectric energy conversion and electromagnetic shielding functions is developed for multipurpose applications.Such a novel phase-change composite is fabricated by an innovative combination of paraffin wax(PW)as a phase-change material and a carbonized polyimide/Kevlar/graphene oxide@ZIF-67 complex aerogel as a supporting material.The carbonized complex aerogel exhibits a unique bidirectional porous structure with high porosity and robust skeleton to support the loading of PW.The reduced graphene oxide and Co NC resulting from high-temperature carbonization are anchored on the aerogel skeleton to generate high thermal conduction and magnetic effect,enhancing the phonon and electron transfer of the aerogel and improving its energy conversion efficiency.The phase-change composite not only exhibits excellent solar-thermal,thermoelectric,electrothermal,and magnetothermal energy conversion performance,but also achieves high electromagnetic interference shielding effectiveness of 66.2 d B in the X-band.The introduction of PW significantly improves the thermal energy-storage capacity during multi-energy conversion.The developed composite exhibits great application potential for efficient solar energy utilization,sustainable power generation,outdoor deicing,human thermal therapy,and electronic device protection.展开更多
The recent article by Jiang et al published in World Journal of Gastroenterology reports substantial bidirectional associations between gallstone disease(GSD),non-alcoholic fatty liver disease(NAFLD),and kidney stone ...The recent article by Jiang et al published in World Journal of Gastroenterology reports substantial bidirectional associations between gallstone disease(GSD),non-alcoholic fatty liver disease(NAFLD),and kidney stone disease(KSD),based on multicenter cross-sectional studies and a systematic review with meta-analysis.While the findings have the potential to significantly impact clinical and pre-ventive strategies,several methodological issues merit closer examination.This letter critiques key aspects of the study,including sample population hetero-geneity,potential confounding variables,and the reliance on cross-sectional data that may limit causal inferences.We also discuss the generalizability of these results to broader populations given the study's focus on the Chinese demogra-phic.By addressing these concerns,we suggest a more nuanced interpretation of the associations between GSD,NAFLD,and KSD,advocating for longitudinal studies to validate these findings and enhance their applicability in global health contexts.展开更多
Background Although studies in recent years have explored the impact of gut microbiota on various sleep characteristics,the interaction between gut microbiota and insomnia remains unclear.Aims We aimed to evaluate the...Background Although studies in recent years have explored the impact of gut microbiota on various sleep characteristics,the interaction between gut microbiota and insomnia remains unclear.Aims We aimed to evaluate the mutual influences between gut microbiota and insomnia.Methods We conducted Mendelian randomisation(MR)analysis using genome-wide association studies datasets on insomnia(N=386533),gut microbiota data from the MiBioGen alliance(N=18340)and the Dutch Microbiome Project(N=8208).The inverse variance weighted(IVW)technique was selected as the primary approach.Then,Cochrane’s Q,Mendelian randomization-Egger(MR-Egger)and MR Pleiotropy RESidual Sum and Outlier test(MRPRESSO)tests were used to detect heterogeneity and pleiotropy.The leave-one-out method was used to test the stability of the MR results.In addition,we performed the Steiger test to thoroughly verify the causation.Results According to IVW,our results showed that 14 gut bacterial taxa may contribute to the risks of insomnia(odds ratio(OR):1.01 to 1.04),while 8 gut bacterial taxa displayed a protective effect on this condition(OR:0.97 to 0.99).Conversely,reverse MR analysis showed that insomnia may causally decrease the abundance of 7 taxa(OR:0.21 to 0.57)and increase the abundance of 12 taxa(OR:1.65 to 4.43).Notably,the genus Odoribacter showed a significant positive causal relationship after conducting the Steiger test.Cochrane’s Q test indicated no significant heterogeneity between most singlenucleotide polymorphisms.In addition,no significant level of pleiotropy was found according to MR-Egger and MRPRESSO.Conclusions Our study highlighted the reciprocal relationships between gut microbiota and insomnia,which may provide new insights into the treatment and prevention of insomnia.展开更多
To address the vibration issues of wind turbine towers,this paper proposes a bidirectional tuned bellow liquid column damper(BTBLCD).The configuration of the proposed BTBLCD is first described in detail,and its energy...To address the vibration issues of wind turbine towers,this paper proposes a bidirectional tuned bellow liquid column damper(BTBLCD).The configuration of the proposed BTBLCD is first described in detail,and its energy dissipation mechanism is derived through theoretical analysis.A refined dynamic model of the wind turbine tower equipped with the BTBLCD is then developed.The vibration energy dissipation performance of the BTBLCD in multiple directions is evaluated through two-way fluid-structure coupling numerical simulations.Finally,a 1/10 scaled model of the wind turbine tower is constructed,and the energy dissipation performance of the BTBLCD is validated using a shaking table test.The results show that the vibration energy dissipation performance of the BTBLCD outperforms that of the bidirectional tuned liquid column damper(BTLCD)in multiple directions.The shaking table test and dynamic response analysis demonstrate a maximum reduction of 61.0%in acceleration and 47.9%in displacement response.Furthermore,the vibration control and energy dissipation performance of the BTBLCD are influenced by the direction and amplitude of vibrations.This study contributes to the development of more effective and versatile vibration mitigation strategies for wind turbine tower structures in various engineering scenarios.展开更多
The remaining useful life prediction of rolling bearing is vital in safety and reliability guarantee.In engineering scenarios,only a small amount of bearing performance degradation data can be obtained through acceler...The remaining useful life prediction of rolling bearing is vital in safety and reliability guarantee.In engineering scenarios,only a small amount of bearing performance degradation data can be obtained through accelerated life testing.In the absence of lifetime data,the hidden long-term correlation between performance degradation data is challenging to mine effectively,which is the main factor that restricts the prediction precision and engineering application of the residual life prediction method.To address this problem,a novel method based on the multi-layer perception neural network and bidirectional long short-term memory network is proposed.Firstly,a nonlinear health indicator(HI)calculation method based on kernel principal component analysis(KPCA)and exponential weighted moving average(EWMA)is designed.Then,using the raw vibration data and HI,a multi-layer perceptron(MLP)neural network is trained to further calculate the HI of the online bearing in real time.Furthermore,The bidirectional long short-term memory model(BiLSTM)optimized by particle swarm optimization(PSO)is used to mine the time series features of HI and predict the remaining service life.Performance verification experiments and comparative experiments are carried out on the XJTU-SY bearing open dataset.The research results indicate that this method has an excellent ability to predict future HI and remaining life.展开更多
Pedestrian trajectory prediction is pivotal and challenging in applications such as autonomous driving,social robotics,and intelligent surveillance systems.Pedestrian trajectory is governed not only by individual inte...Pedestrian trajectory prediction is pivotal and challenging in applications such as autonomous driving,social robotics,and intelligent surveillance systems.Pedestrian trajectory is governed not only by individual intent but also by interactions with surrounding agents.These interactions are critical to trajectory prediction accuracy.While prior studies have employed Convolutional Neural Networks(CNNs)and Graph Convolutional Networks(GCNs)to model such interactions,these methods fail to distinguish varying influence levels among neighboring pedestrians.To address this,we propose a novel model based on a bidirectional graph attention network and spatio-temporal graphs to capture dynamic interactions.Specifically,we construct temporal and spatial graphs encoding the sequential evolution and spatial proximity among pedestrians.These features are then fused and processed by the Bidirectional Graph Attention Network(Bi-GAT),which models the bidirectional interactions between the target pedestrian and its neighbors.The model computes node attention weights(i.e.,similarity scores)to differentially aggregate neighbor information,enabling fine-grained interaction representations.Extensive experiments conducted on two widely used pedestrian trajectory prediction benchmark datasets demonstrate that our approach outperforms existing state-of-theartmethods regarding Average Displacement Error(ADE)and Final Displacement Error(FDE),highlighting its strong prediction accuracy and generalization capability.展开更多
This article provides a method by which the scour depth and scour width below pipelines,and the scour depth around single vertical piles as well as the time scales of scour for both structures due to bichromatic and b...This article provides a method by which the scour depth and scour width below pipelines,and the scour depth around single vertical piles as well as the time scales of scour for both structures due to bichromatic and bidirectional waves are calculated.The scour and time scale formulae summarized by Sumer and Fredsøe(2002)as well as the bottom shear stress formulae under bichromatic and bidirectional waves by Myrhaug et al.(2023)are used.Results for unidirectional bichromatic waves and symmetrically bidirectional monochromatic waves are provided,showing qualitative agreement with what is expected physically.Qualitative comparisons are made with the data from Schendel et al.’s(2020)small scale laboratory tests on scour around a monopile induced by directionally spread waves.Applications to related cases for pipelines are also suggested.In order to conclude regarding the validity of the method for pipelines and vertical piles,it is required to compare with data in its validity range.展开更多
基金supported by the National Natural Science Foundation(52302284,22002086,22204096)Shanghai Sailing Program(23YF1412200)the Fundamental Research Funds for the Central Universities(22120240314).
文摘Single-atom catalysts(SACs)have garnered significant attention in lithium-sulfur(Li-S)batteries for their potential to mitigate the severe polysulfide shuttle effect and sluggish redox kinetics.However,the development of highly efficient SACs and a comprehensive understanding of their structure-activity relationships remain enormously challenging.Herein,a novel kind of Fe-based SAC featuring an asymmetric FeN_(5)-TeN_(4) coordination structure was precisely designed by introducing Te atom adjacent to the Fe active center to enhance the catalytic activity.Theoretical calculations reveal that the neighboring Te atom modulates the local coordination environment of the central Fe site,elevating the d-band center closer to the Fermi level and strengthening the d-p orbital hybridization between the catalyst and sulfur species,thereby immobilizing polysulfides and improving the bidirectional catalysis of Li-S redox.Consequently,the Fe-Te atom pair catalyst endows Li-S batteries with exceptional rate performance,achieving a high specific capacity of 735 mAh g^(−1) at 5 C,and remarkable cycling stability with a low decay rate of 0.038%per cycle over 1000 cycles at 1 C.This work provides fundamental insights into the electronic structure modulation of SACs and establishes a clear correlation between precisely engineered atomic configurations and their enhanced catalytic performance in Li-S electrochemistry.
基金supported by the National Key Research and Development Program of China(No.2024YFB3212901)National Natural Science Foundation of China(12072189)the Medicine and Engineering Interdisciplinary Research Fund of Shanghai Jiao Tong University(No.YG2025ZD05)。
文摘Pipelines are extensively used in environments such as nuclear power plants,chemical factories,and medical devices to transport gases and liquids.These tubular environments often feature complex geometries,confined spaces,and millimeter-scale height restrictions,presenting significant challenges to conventional inspection methods.Here,we present an ultrasonic microrobot(weight,80 mg;dimensions,24 mm×7 mm;thickness,210μm)to realize agile and bidirectional navigation in narrow pipelines.The ultrathin structural design of the robot is achieved through a high-performance piezoelectric composite film microstructure based on MEMS technology.The robot exhibits various vibration modes when driven by ultrasonic frequency signals,its motion speed reaches81 cm s-1 at 54.8 k Hz,exceeding that of the fastest piezoelectric microrobots,and its forward and backward motion direction is controllable through frequency modulation,while the minimum driving voltage for initial movement can be as low as 3 VP-P.Additionally,the robot can effortlessly climb slopes up to 24.25°and carry loads more than 36 times its weight.The robot is capable of agile navigation through curved L-shaped pipes,pipes made of various materials(acrylic,stainless steel,and polyvinyl chloride),and even over water.To further demonstrate its inspection capabilities,a micro-endoscope camera is integrated into the robot,enabling real-time image capture inside glass pipes.
基金Institute of Technology Research Fund Program for Young Scholars21C Innovation Laboratory Contemporary Amperex Technology Co.,Limited,Ninde, 352100, China (21C–OP-202314)。
文摘Lithium-sulfur (Li-S) batteries have gained great attention due to the high theoretical energy density and low cost,yet their further commercialization has been obstructed by the notorious shuttle effect and sluggish redox dynamics.Herein,we supply a strategy to optimize the electron structure of Ni_(2)P by concurrently introducing B-doped atoms and P vacancies in Ni_(2)P (Vp-B-Ni_(2)P),thereby enhancing the bidirectional sulfur conversion.The study indicates that the simultaneous introduction of B-doped atoms and P vacancies in Ni_(2)P causes the redistribution of electron around Ni atoms,bringing about the upward shift of d-band center of Ni atoms and effective d-p orbital hybridization between Ni atoms and sulfur species,thus strengthening the chemical anchoring for lithium polysulfides (LiPSs) as well as expediting the bidirectional conversion kinetics of sulfur species.Meanwhile,theoretical calculations reveal that the incorporation of B-doped atoms and P vacancies in Ni_(2)P selectively promotes Li2S dissolution and nucleation processes.Thus,the Li-S batteries with Vp-B-Ni_(2)P-separators present outstanding rate ability of 777 m A h g^(-1)at 5 C and high areal capacity of 8.03 mA h cm^(-2)under E/S of 5μL mg^(-1)and sulfur loading of 7.20 mg cm^(-2).This work elucidates that introducing heteroatom and vacancy in metal phosphide collaboratively regulates the electron structure to accelerate bidirectional sulfur conversion.
文摘BACKGROUND Propofol has been widely used in bidirectional gastrointestinal endoscopy sedation;however,it frequently leads to cardiovascular adverse events and respiratory depression.Propofol target-controlled infusion(TCI)can provide safe sedation but may require higher dosages of propofol.On the contrary,etomidate offers hemodynamic stability.AIM To evaluate the effect of different dose etomidate added to propofol TCI sedation during same-visit bidirectional endoscopy.METHODS A total of 330 patients from Fujian Provincial Hospital were randomly divided into three groups:P,0.1EP,and 0.15EP.Patients in the P group received propofol TCI only,with an initial effect-site concentration of the propofol TCI system of 3.0 mg/mL.Patients in the 0.1EP and 0.15EP groups received 0.1 and 0.15 mg/kg etomidate intravenous injection,respectively,followed by propofol TCI.RESULTS Patients in the 0.15EP group had higher mean blood pressure after induction than the other groups(P group:78 mmHg,0.1EP group:82 mmHg,0.15EP group:88 mmHg;P<0.05).Total doses of propofol consumption significantly decreased in the 0.15EP group compared with that in the other groups(P group:260.6 mg,0.1EP group:228.1 mg,0.15EP group:201.2 mg;P<0.05).The induction time was longer in the P group than in the other groups(P group:1.9±0.7 minutes,0.1EP group:1.2±0.4 minutes,0.15EP group:1.1±0.3 minutes;P<0.01).The recovery time was shorter in the 0.15EP group than in the other groups(P group:4.8±2.1 minutes,0.1EP group:4.5±1.6 minutes,0.15EP group:3.9±1.4 minutes;P<0.01).The incidence of hypotension(P group:36.4%,0.1EP group:29.1%,0.15EP group:11.8%;P<0.01)and injection pain was lower in the 0.15EP group than in the other groups(P<0.05).Furthermore,the incidence of respiratory depression was lower in the 0.15EP group than in the P group(P<0.05).Additionally,the satisfaction of the patient,endoscopist,and anesthesiologist was higher in the 0.15EP group than in the other groups(P<0.05).CONCLUSION Our findings suggest that 0.15 mg/kg etomidate plus propofol TCI can significantly reduce propofol consumption,which is followed by fewer cardiovascular adverse events and respiratory depression,along with higher patient,endoscopist,and anesthesiologist satisfaction.
文摘Motivated by the early works on bidirectional interaction and the breakthrough to estimate seismic response to bidirectional shaking via unidirectional analysis,it is essential to answer the question:When is the interaction effect significant?Early works concluded that the effect of interaction is pronounced for stiff systems;consequently,the straightforward method for estimating seismic response to bidirectional excitation by using unidirectional analyses is verified primarily for short period systems.Hence,it is essential to identify the domain of significance for bidirectional interaction before adopting this simple methodology in design.Several parametrically defined systems with elastoplastic and degrading hysteresis models are studied under near-fault motions,assuming strength-independent and strength-dependent stiffness.The force-based and displacement-based analyses,conducted in parallel,reveal that the interaction effect is considerable for stiff systems,especially with degrading characteristics in a relatively low inelasticity range.However,the bidirectional effect may be significant even for highly flexible systems,especially for residual deformation,which in earlier works was shrouded.The range of significance depends on the hysteresis model,system parameters,and response indices.Regression analysis is carried out with the results of the case studies,and the derived regression models may be used for a preliminary assessment of the impact of interaction in advance.
基金supported by the National Natural Science Foundation of China (82230071, 82172098)the Integrated Project of Major Research Plan of National Natural Science Foundation of China (92249303)+2 种基金the Laboratory Animal Research Project of Shanghai Committee of Science and Technology (23141900600)the Shanghai Clinical Research Plan (SHDC2023CRT01)the Young Elite Scientist Sponsorship Program by China Association for Science and Technology (YESS20230049)。
文摘In addition to its recognized role in providing structural support, bone plays a crucial role in maintaining the functionality and balance of various organs by secreting specific cytokines(also known as osteokines). This reciprocal influence extends to these organs modulating bone homeostasis and development, although this aspect has yet to be systematically reviewed. This review aims to elucidate this bidirectional crosstalk, with a particular focus on the role of osteokines. Additionally, it presents a unique compilation of evidence highlighting the critical function of extracellular vesicles(EVs) within bone-organ axes for the first time. Moreover, it explores the implications of this crosstalk for designing and implementing bone-on-chips and assembloids, underscoring the importance of comprehending these interactions for advancing physiologically relevant in vitro models. Consequently, this review establishes a robust theoretical foundation for preventing, diagnosing, and treating diseases related to the bone-organ axis from the perspective of cytokines, EVs, hormones, and metabolites.
基金funded by the Deanship of Scientific Research(DSR)at King Abdulaziz University,Jeddah,under grant No.(IPP:421-611-2025).
文摘Over the past few years,Malware attacks have become more and more widespread,posing threats to digital assets throughout the world.Although numerous methods have been developed to detect malicious attacks,these malware detection techniques need to be more efficient in detecting new and progressively sophisticated variants of malware.Therefore,the development of more advanced and accurate techniques is necessary for malware detection.This paper introduces a comprehensive Dual-Channel Attention Deep Bidirectional Long Short-Term Memory(DCADBiLSTM)model for malware detection and riskmitigation.The Dual Channel Attention(DCA)mechanism improves themodel’s capability to concentrate on the features that aremost appropriate in the input data,which reduces the false favourable rates.The Bidirectional Long,Short-Term Memory framework helps capture crucial interdependence from past and future circumstances,which is essential for enhancing the model’s understanding of malware behaviour.As soon as malware is detected,the risk mitigation phase is implemented,which evaluates the severity of each threat and helps mitigate threats earlier.The outcomes of the method demonstrate better accuracy of 98.96%,which outperforms traditional models.It indicates the method detects and mitigates several kinds of malware threats,thereby providing a proactive defence mechanism against the emerging challenges in cybersecurity.
基金Supported by the National Nature Science Foundation of China(62462037,62462036)Project for Academic and Technical Leader in Major Disciplines in Jiangxi Province(20232BCJ22013)+1 种基金Jiangxi Provincial Natural Science Foundation(20242BAB26017,20232BAB202010)Jiangxi Province Graduate Innovation Fund Project(YC2023-S320)。
文摘Intent detection and slot filling are two important components of natural language understanding.Because their relevance,joint training is often performed to improve performance.Existing studies mostly use a joint model of multi-intent detection and slot-filling with unidirectional interaction,which improves the overall performance of the model by fusing the intent information in the slot-filling part.On this basis,in order to further improve the overall performance of the model by exploiting the correlation between the two,this paper proposes a joint multi-intent detection and slot-filling model based on a bidirectional interaction structure,which fuses the intent encoding information in the encoding part of slot filling and fuses the slot decoding information in the decoding part of intent detection.Experimental results on two public multi-intent joint training datasets,MixATIS and MixSNIPS,show that the bidirectional interaction structure proposed in this paper can effectively improve the performance of the joint model.In addition,in order to verify the generalization of the bidirectional interaction structure between intent and slot,a joint model for single-intent scenarios is proposed on the basis of the model in this paper.This model also achieves excellent performance on two public single-intent joint training datasets,CAIS and SNIPS.
文摘Gastric cancer(GC)is a highly prevalent and life-threatening malignant tumor worldwide,posing a serious threat to human health.Depression is also highly prevalent among patients with GC.A complex bidirectional relationship exists between the two.A total of 52 articles were included in this study to synthesize the evidence on the association between depression and the risk of GC as well as the prognosis of affected patients.The findings indicated that depression can activate the sympathetic nervous system and the hypothalamic-pituitary-adrenal axis,promote the release of catecholamine neurotransmitters,and influence the proliferation,invasion,and metastasis of GC through signaling pathways such as theβ2-adrenergic receptor.Furthermore,the severity of depression is positively correlated with indicators of GC progression.At the same time,GC can induce or aggravate depression through psychological and cognitive factors,social environment interactions,and diverse pathophysiological mechanisms,including tumor biological characteristics,treatment-related damage,and metabolic disorders.These interactions form a vicious cycle.This minireview summarizes the existing evidence and provides a theoretical basis for clinical interventions aimed at improving treatment outcomes and quality of life in patients with GC.
文摘This study examines the bidirectional shaping mechanism between short-video algorithms and film narratives within the attention economy.It investigates how algorithmic logic influences cinematic storytelling and how films,in turn,contribute to the aesthetic enhancement of short-video content.Drawing on Communication Accommodation Theory and Berry’s Acculturation Theory,along with case analyses and industry data,this research demonstrates that algorithms push films toward high-stimulus,fast-paced narrative patterns—characterized by increased shot density and structural fragmentation—to capture and retain viewer attention.Conversely,films counter this influence by supplying narratively deep and artistically refined content that elevates short-video aesthetics and encourages critical audience engagement.This dynamic reflects a process of mutual adaptation rather than one-sided dominance.The study concludes that such interaction signifies a broader restructuring of cultural production logic,facilitating cross-media convergence while simultaneously posing risks to cultural diversity due to the prioritization of high-traffic content.Balancing this relationship will require policy support,algorithmic transparency,and strengthened industry self-regulation to preserve artistic integrity and cultural ecosystem diversity.
基金supported by the Xinjiang Uygur Autonomous Region Central Guided Local Science and Technology Development Fund Project(No.ZYYD2025QY17).
文摘This paper introduces an Improved Bidirectional Jump Point Search(I-BJPS)algorithm to address the challenges of the traditional Jump Point Search(JPS)in mobile robot path planning.These challenges include excessive node expansions,frequent path inflexion points,slower search times,and a high number of jump points in complex environments with large areas and dense obstacles.Firstly,we improve the heuristic functions in both forward and reverse directions to minimize expansion nodes and search time.We also introduce a node optimization strategy to reduce non-essential nodes so that the path length is optimized.Secondly,we employ a second-order Bezier Curve to smooth turning points,making generated paths more suitable for mobile robot motion requirements.Then,we integrate the Dynamic Window Approach(DWA)to improve path planning safety.Finally,the simulation results demonstrate that the I-BJPS algorithm significantly outperforms both the original unidirectional JPS algorithm and the bidirectional JPS algorithm in terms of search time,the number of path inflexion points,and overall path length,the advantages of the I-BJPS algorithm are particularly pronounced in complex environments.Experimental results from real-world scenarios indicate that the proposed algorithm can efficiently and rapidly generate an optimal path that is safe,collision-free,and well-suited to the robot’s locomotion requirements.
基金supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R195),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Efficient energy management is a cornerstone of advancing cognitive cities,where AI,IoT,and cloud computing seamlessly integrate to meet escalating global energy demands.Within this context,the ability to forecast electricity consumption with precision is vital,particularly in residential settings where usage patterns are highly variable and complex.This study presents an innovative approach to energy consumption forecasting using a bidirectional Long Short-Term Memory(LSTM)network.Leveraging a dataset containing over twomillionmultivariate,time-series observations collected froma single household over nearly four years,ourmodel addresses the limitations of traditional time-series forecasting methods,which often struggle with temporal dependencies and non-linear relationships.The bidirectional LSTM architecture processes data in both forward and backward directions,capturing past and future contexts at each time step,whereas existing unidirectional LSTMs consider only a single temporal direction.This design,combined with dropout regularization,leads to a 20.6%reduction in RMSE and an 18.8%improvement in MAE over conventional unidirectional LSTMs,demonstrating a substantial enhancement in prediction accuracy and robustness.Compared to existing models—including SVM,Random Forest,MLP,ANN,and CNN—the proposed model achieves the lowest MAE of 0.0831 and RMSE of 0.2213 during testing,significantly outperforming these benchmarks.These results highlight the model’s superior ability to navigate the complexities of energy usage patterns,reinforcing its potential application in AI-driven IoT and cloud-enabled energy management systems for cognitive cities.By integrating advanced machine learning techniqueswith IoT and cloud infrastructure,this research contributes to the development of intelligent,sustainable urban environments.
文摘The initiation and progression of colorectal cancer(CRC)are profoundly influenced by the complex interplay between the gut microbiota and the immune system,underscoring the clinical importance of exploring the bidirectional regulatory mechanisms of the microbiota-immune axis within the CRC immune microenvironment.Emerging evidence indicates that the composition and functional capacity of the gut microbiota play a vital role in modulating the host’s immune responses,while the immune system,in turn,can reciprocally regulate the structure and function of the microbiota.Despite significant insights into the role of the microbiota-immune axis in CRC progression,several critical questions remain unanswered-including how microbial heterogeneity affects therapeutic outcomes and the specific consequences of dysregulated regulatory mechanisms on the immune microenvironment.This review aims to provide a comprehensive analysis of the compositional features of the CRC immune microenvironment,examine the bidirectional molecular mechanisms underpinning the microbiotaimmune axis,and evaluate the potential of targeted therapeutic strategies,thereby offering novel research perspectives and clinical applications for CRC treatment.
基金supported by the Beijing Natural Science Foundation(Grant No.:2242049)。
文摘To address the limitations of conventional energy systems and optimize the energy conversion pathways and efficiency,a type of“five-in-one”multifunctional phase-change composite with magnetothermal,electrothermal,solar-thermal,and thermoelectric energy conversion and electromagnetic shielding functions is developed for multipurpose applications.Such a novel phase-change composite is fabricated by an innovative combination of paraffin wax(PW)as a phase-change material and a carbonized polyimide/Kevlar/graphene oxide@ZIF-67 complex aerogel as a supporting material.The carbonized complex aerogel exhibits a unique bidirectional porous structure with high porosity and robust skeleton to support the loading of PW.The reduced graphene oxide and Co NC resulting from high-temperature carbonization are anchored on the aerogel skeleton to generate high thermal conduction and magnetic effect,enhancing the phonon and electron transfer of the aerogel and improving its energy conversion efficiency.The phase-change composite not only exhibits excellent solar-thermal,thermoelectric,electrothermal,and magnetothermal energy conversion performance,but also achieves high electromagnetic interference shielding effectiveness of 66.2 d B in the X-band.The introduction of PW significantly improves the thermal energy-storage capacity during multi-energy conversion.The developed composite exhibits great application potential for efficient solar energy utilization,sustainable power generation,outdoor deicing,human thermal therapy,and electronic device protection.
基金Supported by The National Natural Science Foundation of China,No.82074508Fujian Provincial Natural Science Foundation,No.2023J011627+2 种基金Fujian Provincial Health and Wellness Science and Technology Plan Project,No.2023CXB003Xiamen City Support for the Development of Traditional Chinese Medicine Special TCM Scientific Research Project,No.XWZY-2023-0603The Seventh Batch of National Famous Old Traditional Chinese Medicine Experts Experience Heritage Construction Program of National Administration of TCM,No.76(2022).
文摘The recent article by Jiang et al published in World Journal of Gastroenterology reports substantial bidirectional associations between gallstone disease(GSD),non-alcoholic fatty liver disease(NAFLD),and kidney stone disease(KSD),based on multicenter cross-sectional studies and a systematic review with meta-analysis.While the findings have the potential to significantly impact clinical and pre-ventive strategies,several methodological issues merit closer examination.This letter critiques key aspects of the study,including sample population hetero-geneity,potential confounding variables,and the reliance on cross-sectional data that may limit causal inferences.We also discuss the generalizability of these results to broader populations given the study's focus on the Chinese demogra-phic.By addressing these concerns,we suggest a more nuanced interpretation of the associations between GSD,NAFLD,and KSD,advocating for longitudinal studies to validate these findings and enhance their applicability in global health contexts.
文摘Background Although studies in recent years have explored the impact of gut microbiota on various sleep characteristics,the interaction between gut microbiota and insomnia remains unclear.Aims We aimed to evaluate the mutual influences between gut microbiota and insomnia.Methods We conducted Mendelian randomisation(MR)analysis using genome-wide association studies datasets on insomnia(N=386533),gut microbiota data from the MiBioGen alliance(N=18340)and the Dutch Microbiome Project(N=8208).The inverse variance weighted(IVW)technique was selected as the primary approach.Then,Cochrane’s Q,Mendelian randomization-Egger(MR-Egger)and MR Pleiotropy RESidual Sum and Outlier test(MRPRESSO)tests were used to detect heterogeneity and pleiotropy.The leave-one-out method was used to test the stability of the MR results.In addition,we performed the Steiger test to thoroughly verify the causation.Results According to IVW,our results showed that 14 gut bacterial taxa may contribute to the risks of insomnia(odds ratio(OR):1.01 to 1.04),while 8 gut bacterial taxa displayed a protective effect on this condition(OR:0.97 to 0.99).Conversely,reverse MR analysis showed that insomnia may causally decrease the abundance of 7 taxa(OR:0.21 to 0.57)and increase the abundance of 12 taxa(OR:1.65 to 4.43).Notably,the genus Odoribacter showed a significant positive causal relationship after conducting the Steiger test.Cochrane’s Q test indicated no significant heterogeneity between most singlenucleotide polymorphisms.In addition,no significant level of pleiotropy was found according to MR-Egger and MRPRESSO.Conclusions Our study highlighted the reciprocal relationships between gut microbiota and insomnia,which may provide new insights into the treatment and prevention of insomnia.
基金support for the research,authorship,and/or publication of this paper:This study is supported by the National Science Foundation of China(Grant No.52368074)the Science Fund for Distinguished Young Scholars of Gansu Province(No.21JR7RA267)Hongliu Outstanding Young Talents Program of Lanzhou University of Technology.
文摘To address the vibration issues of wind turbine towers,this paper proposes a bidirectional tuned bellow liquid column damper(BTBLCD).The configuration of the proposed BTBLCD is first described in detail,and its energy dissipation mechanism is derived through theoretical analysis.A refined dynamic model of the wind turbine tower equipped with the BTBLCD is then developed.The vibration energy dissipation performance of the BTBLCD in multiple directions is evaluated through two-way fluid-structure coupling numerical simulations.Finally,a 1/10 scaled model of the wind turbine tower is constructed,and the energy dissipation performance of the BTBLCD is validated using a shaking table test.The results show that the vibration energy dissipation performance of the BTBLCD outperforms that of the bidirectional tuned liquid column damper(BTLCD)in multiple directions.The shaking table test and dynamic response analysis demonstrate a maximum reduction of 61.0%in acceleration and 47.9%in displacement response.Furthermore,the vibration control and energy dissipation performance of the BTBLCD are influenced by the direction and amplitude of vibrations.This study contributes to the development of more effective and versatile vibration mitigation strategies for wind turbine tower structures in various engineering scenarios.
基金supported by the National Key Research and Development Project(Grant Number 2023YFB3709601)the National Natural Science Foundation of China(Grant Numbers 62373215,62373219,62073193)+2 种基金the Key Research and Development Plan of Shandong Province(Grant Numbers 2021CXGC010204,2022CXGC020902)the Fundamental Research Funds of Shandong University(Grant Number 2021JCG008)the Natural Science Foundation of Shandong Province(Grant Number ZR2023MF100).
文摘The remaining useful life prediction of rolling bearing is vital in safety and reliability guarantee.In engineering scenarios,only a small amount of bearing performance degradation data can be obtained through accelerated life testing.In the absence of lifetime data,the hidden long-term correlation between performance degradation data is challenging to mine effectively,which is the main factor that restricts the prediction precision and engineering application of the residual life prediction method.To address this problem,a novel method based on the multi-layer perception neural network and bidirectional long short-term memory network is proposed.Firstly,a nonlinear health indicator(HI)calculation method based on kernel principal component analysis(KPCA)and exponential weighted moving average(EWMA)is designed.Then,using the raw vibration data and HI,a multi-layer perceptron(MLP)neural network is trained to further calculate the HI of the online bearing in real time.Furthermore,The bidirectional long short-term memory model(BiLSTM)optimized by particle swarm optimization(PSO)is used to mine the time series features of HI and predict the remaining service life.Performance verification experiments and comparative experiments are carried out on the XJTU-SY bearing open dataset.The research results indicate that this method has an excellent ability to predict future HI and remaining life.
基金funded by the National Natural Science Foundation of China,grant number 624010funded by the Natural Science Foundation of Anhui Province,grant number 2408085QF202+1 种基金funded by the Anhui Future Technology Research Institute Industry Guidance Fund Project,grant number 2023cyyd04funded by the Project of Research of Anhui Polytechnic University,grant number Xjky2022150.
文摘Pedestrian trajectory prediction is pivotal and challenging in applications such as autonomous driving,social robotics,and intelligent surveillance systems.Pedestrian trajectory is governed not only by individual intent but also by interactions with surrounding agents.These interactions are critical to trajectory prediction accuracy.While prior studies have employed Convolutional Neural Networks(CNNs)and Graph Convolutional Networks(GCNs)to model such interactions,these methods fail to distinguish varying influence levels among neighboring pedestrians.To address this,we propose a novel model based on a bidirectional graph attention network and spatio-temporal graphs to capture dynamic interactions.Specifically,we construct temporal and spatial graphs encoding the sequential evolution and spatial proximity among pedestrians.These features are then fused and processed by the Bidirectional Graph Attention Network(Bi-GAT),which models the bidirectional interactions between the target pedestrian and its neighbors.The model computes node attention weights(i.e.,similarity scores)to differentially aggregate neighbor information,enabling fine-grained interaction representations.Extensive experiments conducted on two widely used pedestrian trajectory prediction benchmark datasets demonstrate that our approach outperforms existing state-of-theartmethods regarding Average Displacement Error(ADE)and Final Displacement Error(FDE),highlighting its strong prediction accuracy and generalization capability.
文摘This article provides a method by which the scour depth and scour width below pipelines,and the scour depth around single vertical piles as well as the time scales of scour for both structures due to bichromatic and bidirectional waves are calculated.The scour and time scale formulae summarized by Sumer and Fredsøe(2002)as well as the bottom shear stress formulae under bichromatic and bidirectional waves by Myrhaug et al.(2023)are used.Results for unidirectional bichromatic waves and symmetrically bidirectional monochromatic waves are provided,showing qualitative agreement with what is expected physically.Qualitative comparisons are made with the data from Schendel et al.’s(2020)small scale laboratory tests on scour around a monopile induced by directionally spread waves.Applications to related cases for pipelines are also suggested.In order to conclude regarding the validity of the method for pipelines and vertical piles,it is required to compare with data in its validity range.
