To improve locomotion and operation integration, this paper presents an integrated leg-arm quadruped robot(ILQR) that has a reconfigurable joint. First, the reconfigurable joint is designed and assembled at the end of...To improve locomotion and operation integration, this paper presents an integrated leg-arm quadruped robot(ILQR) that has a reconfigurable joint. First, the reconfigurable joint is designed and assembled at the end of the legarm chain. When the robot performs a task, reconfigurable configuration and mode switching can be achieved using this joint. In contrast from traditional quadruped robots, this robot can stack in a designated area to optimize the occupied volume in a nonworking state. Kinematics modeling and dynamics modeling are established to evaluate the mechanical properties for multiple modes. All working modes of the robot are classified, which can be defined as deployable mode, locomotion mode and operation mode. Based on the stability margin and mechanical modeling, switching analysis and evaluation between each mode is carried out. Finally, the prototype experimental results verify the function realization and switching stability of multimode and provide a design method to integrate and perform multimode for quadruped robots with deployable characteristics.展开更多
Optical endoscopy has become an essential diagnostic and therapeutic approach in modern biomedicine for directly observing organs and tissues deep inside the human body,enabling non-invasive,rapid diagnosis and treatm...Optical endoscopy has become an essential diagnostic and therapeutic approach in modern biomedicine for directly observing organs and tissues deep inside the human body,enabling non-invasive,rapid diagnosis and treatment.Optical fiber endoscopy is highly competitive among various endoscopic imaging techniques due to its high flexibility,compact structure,excellent resolution,and resistance to electromagnetic interference.Over the past decade,endoscopes based on a single multimode optical fiber(MMF)have attracted widespread research interest due to their potential to significantly reduce the footprint of optical fiber endoscopes and enhance imaging capabilities.In comparison with other imaging principles of MMF endoscopes,the scanning imaging method based on the wavefront shaping technique is highly developed and provides benefits including excellent imaging contrast,broad applicability to complex imaging scenarios,and good compatibility with various well-established scanning imaging modalities.In this review,various technical routes to achieve light focusing through MMF and procedures to conduct the scanning imaging of MMF endoscopes are introduced.The advancements in imaging performance enhancements,integrations of various imaging modalities with MMF scanning endoscopes,and applications are summarized.Challenges specific to this endoscopic imaging technology are analyzed,and potential remedies and avenues for future developments are discussed.展开更多
The majority of nonlinear stochastic systems can be expressed as the quasi-Hamiltonian systems in science and engineering. Moreover, the corresponding Hamiltonian system offers two concepts of integrability and resona...The majority of nonlinear stochastic systems can be expressed as the quasi-Hamiltonian systems in science and engineering. Moreover, the corresponding Hamiltonian system offers two concepts of integrability and resonance that can fully describe the global relationship among the degrees-of-freedom(DOFs) of the system. In this work, an effective and promising approximate semi-analytical method is proposed for the steady-state response of multi-dimensional quasi-Hamiltonian systems. To be specific, the trial solution of the reduced Fokker–Plank–Kolmogorov(FPK) equation is obtained by using radial basis function(RBF) neural networks. Then, the residual generated by substituting the trial solution into the reduced FPK equation is considered, and a loss function is constructed by combining random sampling technique. The unknown weight coefficients are optimized by minimizing the loss function through the Lagrange multiplier method. Moreover, an efficient sampling strategy is employed to promote the implementation of algorithms. Finally, two numerical examples are studied in detail, and all the semi-analytical solutions are compared with Monte Carlo simulations(MCS) results. The results indicate that the complex nonlinear dynamic features of the system response can be captured through the proposed scheme accurately.展开更多
This paper is focused on electrode design for piezoelectric tuning fork resonators.The relationship between the performance and electrode pattern of aluminum nitride piezoelectric tuning fork resonators vibrating in t...This paper is focused on electrode design for piezoelectric tuning fork resonators.The relationship between the performance and electrode pattern of aluminum nitride piezoelectric tuning fork resonators vibrating in the in-plane flexural mode is investigated based on a set of resonators with different electrode lengths,widths,and ratios.Experimental and simulation results show that the electrode design impacts greatly the multimode effect induced from torsional modes but has little influence on other loss mechanisms.Optimizing the electrode design suppresses the torsional mode successfully,thereby increasing the ratio of impedance at parallel and series resonant frequencies(R_(p)/R_(s))by more than 80%and achieving a quality factor(Q)of 7753,an effective electromechanical coupling coefficient(kt_(eff)^(2))of 0.066%,and an impedance at series resonant frequency(R_(m))of 23.6 kΩ.The proposed approach shows great potential for high-performance piezoelectric resonators,which are likely to be fundamental building blocks for sensors with high sensitivity and low noise and power consumption.展开更多
We propose an adaptive stencil construction for high-order accurate finite volume schemes a posteriori stabilized devoted to solve one-dimensional steady-state hyperbolic equations.High accuracy(up to the sixth-order ...We propose an adaptive stencil construction for high-order accurate finite volume schemes a posteriori stabilized devoted to solve one-dimensional steady-state hyperbolic equations.High accuracy(up to the sixth-order presently)is achieved,thanks to polynomial recon-structions while stability is provided with an a posteriori MOOD method which controls the cell polynomial degree for eliminating non-physical oscillations in the vicinity of dis-continuities.We supplemented this scheme with a stencil construction allowing to reduce even further the numerical dissipation.The stencil is shifted away from troubles(shocks,discontinuities,etc.)leading to less oscillating polynomial reconstructions.Experimented on linear,Burgers',and Euler equations,we demonstrate that the adaptive stencil technique manages to retrieve smooth solutions with optimal order of accuracy but also irregular ones without spurious oscillations.Moreover,we numerically show that the approach allows to reduce the dissipation still maintaining the essentially non-oscillatory behavior.展开更多
In a magnetohydrodynamic(MHD)driven fluid cell,a plane non-parallel flow in a square domain satisfying a free-slip boundary condition is examined.The energy dissipation of the flow is controlled by the viscosity and l...In a magnetohydrodynamic(MHD)driven fluid cell,a plane non-parallel flow in a square domain satisfying a free-slip boundary condition is examined.The energy dissipation of the flow is controlled by the viscosity and linear friction.The latter arises from the influence of the Hartmann bottom boundary layer in a three-dimensional(3D)MHD experiment in a square bottomed cell.The basic flow in this fluid system is a square eddy flow exhibiting a network of N~2 vortices rotating alternately in clockwise and anticlockwise directions.When N is odd,the instability of the flow gives rise to secondary steady-state flows and secondary time-periodic flows,exhibiting similar characteristics to those observed when N=3.For this reason,this study focuses on the instability of the square eddy flow of nine vortices.It is shown that there exist eight bi-critical values corresponding to the existence of eight neutral eigenfunction spaces.Especially,there exist non-real neutral eigenfunctions,which produce secondary time-periodic flows exhibiting vortices merging in an oscillatory manner.This Hopf bifurcation phenomenon has not been observed in earlier investigations.展开更多
Neuropathy is nerve damage that can cause chronic neuropathic pain, which is challenging to cure and has a significant financial burden. Exercise therapies, including High-Intensity Interval Training (HIIT) and steady...Neuropathy is nerve damage that can cause chronic neuropathic pain, which is challenging to cure and has a significant financial burden. Exercise therapies, including High-Intensity Interval Training (HIIT) and steady-state cardio, are being explored as potential treatments for neuropathic pain. This systematic review compares the effectiveness of HIIT and steady-state cardio for improving function in neurological patients. This article provides an overview of the systematic review conducted on the effects of exercise on neuropathic patients, with a focus on high-intensity interval training (HIIT) and steady-state cardio. The authors conducted a comprehensive search of various databases, identified relevant studies based on predetermined inclusion criteria, and used the EPPI automation application to process the data. The final selection of studies was based on validity and relevance, with redundant articles removed. The article reviews four studies that compare high-intensity interval training (HIIT) to moderate-intensity continuous training (MICT) on various health outcomes. The studies found that HIIT can improve aerobic fitness, cerebral blood flow, and brain function in stroke patients;lower diastolic blood pressure more than MICT and improve insulin sensitivity and skeletal muscle mitochondrial content in obese individuals, potentially helping with the prevention and management of type 2 diabetes. In people with multiple sclerosis, acute exercise can decrease the plasma neurofilament light chain while increasing the flow of the kynurenine pathway. The available clinical and preclinical data suggest that further study on high-intensity interval training (HIIT) and its potential to alleviate neuropathic pain is justified. Randomized controlled trials are needed to investigate the type, intensity, frequency, and duration of exercise, which could lead to consensus and specific HIIT-based advice for patients with neuropathies.展开更多
Multimodal freight transportation emerges as the go-to strategy for cost-effectively and sustainably moving goods over long distances. In a multimodal freight system, where a single contract includes various transport...Multimodal freight transportation emerges as the go-to strategy for cost-effectively and sustainably moving goods over long distances. In a multimodal freight system, where a single contract includes various transportation methods, businesses aiming for economic success must make well-informed decisions about which modes of transport to use. These decisions prioritize secure deliveries, competitive cost advantages, and the minimization of environmental footprints associated with transportation-related pollution. Within the dynamic landscape of logistics innovation, various multicriteria decision-making (MCDM) approaches empower businesses to evaluate freight transport options thoroughly. In this study, we utilize a case study to demonstrate the application of the Technique for Order Preference by Similarity to the Ideal Solution (TOPSIS) algorithm for MCDM decision-making in freight mode selection. We further enhance the TOPSIS framework by integrating the entropy weight coefficient method. This enhancement aids in assigning precise weights to each criterion involved in mode selection, leading to a more reliable decision-making process. The proposed model provides cost-effective and timely deliveries, minimizing environmental footprint and meeting consumers’ needs. Our findings reveal that freight carbon footprint is the primary concern, followed by freight cost, time sensitivity, and service reliability. The study identifies the combination of Rail/Truck as the ideal mode of transport and containers in flat cars (COFC) as the next best option for the selected case. The proposed algorithm, incorporating the enhanced TOPSIS framework, benefits companies navigating the complexities of multimodal transport. It empowers making more strategic and informed transportation decisions. This demonstration will be increasingly valuable as companies navigate the ever-growing trade within the global supply chains.展开更多
In multimodal multiobjective optimization problems(MMOPs),there are several Pareto optimal solutions corre-sponding to the identical objective vector.This paper proposes a new differential evolution algorithm to solve...In multimodal multiobjective optimization problems(MMOPs),there are several Pareto optimal solutions corre-sponding to the identical objective vector.This paper proposes a new differential evolution algorithm to solve MMOPs with higher-dimensional decision variables.Due to the increase in the dimensions of decision variables in real-world MMOPs,it is diffi-cult for current multimodal multiobjective optimization evolu-tionary algorithms(MMOEAs)to find multiple Pareto optimal solutions.The proposed algorithm adopts a dual-population framework and an improved environmental selection method.It utilizes a convergence archive to help the first population improve the quality of solutions.The improved environmental selection method enables the other population to search the remaining decision space and reserve more Pareto optimal solutions through the information of the first population.The combination of these two strategies helps to effectively balance and enhance conver-gence and diversity performance.In addition,to study the per-formance of the proposed algorithm,a novel set of multimodal multiobjective optimization test functions with extensible decision variables is designed.The proposed MMOEA is certified to be effective through comparison with six state-of-the-art MMOEAs on the test functions.展开更多
As social networks become increasingly complex, contemporary fake news often includes textual descriptionsof events accompanied by corresponding images or videos. Fake news in multiple modalities is more likely tocrea...As social networks become increasingly complex, contemporary fake news often includes textual descriptionsof events accompanied by corresponding images or videos. Fake news in multiple modalities is more likely tocreate a misleading perception among users. While early research primarily focused on text-based features forfake news detection mechanisms, there has been relatively limited exploration of learning shared representationsin multimodal (text and visual) contexts. To address these limitations, this paper introduces a multimodal modelfor detecting fake news, which relies on similarity reasoning and adversarial networks. The model employsBidirectional Encoder Representation from Transformers (BERT) and Text Convolutional Neural Network (Text-CNN) for extracting textual features while utilizing the pre-trained Visual Geometry Group 19-layer (VGG-19) toextract visual features. Subsequently, the model establishes similarity representations between the textual featuresextracted by Text-CNN and visual features through similarity learning and reasoning. Finally, these features arefused to enhance the accuracy of fake news detection, and adversarial networks have been employed to investigatethe relationship between fake news and events. This paper validates the proposed model using publicly availablemultimodal datasets from Weibo and Twitter. Experimental results demonstrate that our proposed approachachieves superior performance on Twitter, with an accuracy of 86%, surpassing traditional unimodalmodalmodelsand existing multimodal models. In contrast, the overall better performance of our model on the Weibo datasetsurpasses the benchmark models across multiple metrics. The application of similarity reasoning and adversarialnetworks in multimodal fake news detection significantly enhances detection effectiveness in this paper. However,current research is limited to the fusion of only text and image modalities. Future research directions should aimto further integrate features fromadditionalmodalities to comprehensively represent themultifaceted informationof fake news.展开更多
Since the 1950s,when the Turing Test was introduced,there has been notable progress in machine language intelligence.Language modeling,crucial for AI development,has evolved from statistical to neural models over the ...Since the 1950s,when the Turing Test was introduced,there has been notable progress in machine language intelligence.Language modeling,crucial for AI development,has evolved from statistical to neural models over the last two decades.Recently,transformer-based Pre-trained Language Models(PLM)have excelled in Natural Language Processing(NLP)tasks by leveraging large-scale training corpora.Increasing the scale of these models enhances performance significantly,introducing abilities like context learning that smaller models lack.The advancement in Large Language Models,exemplified by the development of ChatGPT,has made significant impacts both academically and industrially,capturing widespread societal interest.This survey provides an overview of the development and prospects from Large Language Models(LLM)to Large Multimodal Models(LMM).It first discusses the contributions and technological advancements of LLMs in the field of natural language processing,especially in text generation and language understanding.Then,it turns to the discussion of LMMs,which integrates various data modalities such as text,images,and sound,demonstrating advanced capabilities in understanding and generating cross-modal content,paving new pathways for the adaptability and flexibility of AI systems.Finally,the survey highlights the prospects of LMMs in terms of technological development and application potential,while also pointing out challenges in data integration,cross-modal understanding accuracy,providing a comprehensive perspective on the latest developments in this field.展开更多
BACKGROUND According to clinical data,a significant percentage of patients experience pain after surgery,highlighting the importance of alleviating postoperative pain.The current approach involves intravenous self-con...BACKGROUND According to clinical data,a significant percentage of patients experience pain after surgery,highlighting the importance of alleviating postoperative pain.The current approach involves intravenous self-control analgesia,often utilizing opioid analgesics such as morphine,sufentanil,and fentanyl.Surgery for colo-rectal cancer typically involves general anesthesia.Therefore,optimizing anes-thetic management and postoperative analgesic programs can effectively reduce perioperative stress and enhance postoperative recovery.The study aims to analyze the impact of different anesthesia modalities with multimodal analgesia on patients'postoperative pain.AIM To explore the effects of different anesthesia methods coupled with multi-mode analgesia on postoperative pain in patients with colorectal cancer.METHODS Following the inclusion criteria and exclusion criteria,a total of 126 patients with colorectal cancer admitted to our hospital from January 2020 to December 2022 were included,of which 63 received general anesthesia coupled with multi-mode labor pain and were set as the control group,and 63 received general anesthesia associated with epidural anesthesia coupled with multi-mode labor pain and were set as the research group.After data collection,the effects of postoperative analgesia,sedation,and recovery were compared.RESULTS Compared to the control group,the research group had shorter recovery times for orientation,extubation,eye-opening,and spontaneous respiration(P<0.05).The research group also showed lower Visual analog scale scores at 24 h and 48 h,higher Ramany scores at 6 h and 12 h,and improved cognitive function at 24 h,48 h,and 72 h(P<0.05).Additionally,interleukin-6 and interleukin-10 levels were significantly reduced at various time points in the research group compared to the control group(P<0.05).Levels of CD3+,CD4+,and CD4+/CD8+were also lower in the research group at multiple time points(P<0.05).CONCLUSION For patients with colorectal cancer,general anesthesia coupled with epidural anesthesia and multi-mode analgesia can achieve better postoperative analgesia and sedation effects,promote postoperative rehabilitation of patients,improve inflammatory stress and immune status,and have higher safety.展开更多
In practical engineering,multi-objective optimization often encounters situations where multiple Pareto sets(PS)in the decision space correspond to the same Pareto front(PF)in the objective space,known as Multi-Modal ...In practical engineering,multi-objective optimization often encounters situations where multiple Pareto sets(PS)in the decision space correspond to the same Pareto front(PF)in the objective space,known as Multi-Modal Multi-Objective Optimization Problems(MMOP).Locating multiple equivalent global PSs poses a significant challenge in real-world applications,especially considering the existence of local PSs.Effectively identifying and locating both global and local PSs is a major challenge.To tackle this issue,we introduce an immune-inspired reproduction strategy designed to produce more offspring in less crowded,promising regions and regulate the number of offspring in areas that have been thoroughly explored.This approach achieves a balanced trade-off between exploration and exploitation.Furthermore,we present an interval allocation strategy that adaptively assigns fitness levels to each antibody.This strategy ensures a broader survival margin for solutions in their initial stages and progressively amplifies the differences in individual fitness values as the population matures,thus fostering better population convergence.Additionally,we incorporate a multi-population mechanism that precisely manages each subpopulation through the interval allocation strategy,ensuring the preservation of both global and local PSs.Experimental results on 21 test problems,encompassing both global and local PSs,are compared with eight state-of-the-art multimodal multi-objective optimization algorithms.The results demonstrate the effectiveness of our proposed algorithm in simultaneously identifying global Pareto sets and locally high-quality PSs.展开更多
Cross-lingual image description,the task of generating image captions in a target language from images and descriptions in a source language,is addressed in this study through a novel approach that combines neural net...Cross-lingual image description,the task of generating image captions in a target language from images and descriptions in a source language,is addressed in this study through a novel approach that combines neural network models and semantic matching techniques.Experiments conducted on the Flickr8k and AraImg2k benchmark datasets,featuring images and descriptions in English and Arabic,showcase remarkable performance improvements over state-of-the-art methods.Our model,equipped with the Image&Cross-Language Semantic Matching module and the Target Language Domain Evaluation module,significantly enhances the semantic relevance of generated image descriptions.For English-to-Arabic and Arabic-to-English cross-language image descriptions,our approach achieves a CIDEr score for English and Arabic of 87.9%and 81.7%,respectively,emphasizing the substantial contributions of our methodology.Comparative analyses with previous works further affirm the superior performance of our approach,and visual results underscore that our model generates image captions that are both semantically accurate and stylistically consistent with the target language.In summary,this study advances the field of cross-lingual image description,offering an effective solution for generating image captions across languages,with the potential to impact multilingual communication and accessibility.Future research directions include expanding to more languages and incorporating diverse visual and textual data sources.展开更多
Multimodal sentiment analysis utilizes multimodal data such as text,facial expressions and voice to detect people’s attitudes.With the advent of distributed data collection and annotation,we can easily obtain and sha...Multimodal sentiment analysis utilizes multimodal data such as text,facial expressions and voice to detect people’s attitudes.With the advent of distributed data collection and annotation,we can easily obtain and share such multimodal data.However,due to professional discrepancies among annotators and lax quality control,noisy labels might be introduced.Recent research suggests that deep neural networks(DNNs)will overfit noisy labels,leading to the poor performance of the DNNs.To address this challenging problem,we present a Multimodal Robust Meta Learning framework(MRML)for multimodal sentiment analysis to resist noisy labels and correlate distinct modalities simultaneously.Specifically,we propose a two-layer fusion net to deeply fuse different modalities and improve the quality of the multimodal data features for label correction and network training.Besides,a multiple meta-learner(label corrector)strategy is proposed to enhance the label correction approach and prevent models from overfitting to noisy labels.We conducted experiments on three popular multimodal datasets to verify the superiority of ourmethod by comparing it with four baselines.展开更多
The potential for reducing greenhouse gas(GHG)emissions and energy consumption in wastewater treatment can be realized through intelligent control,with machine learning(ML)and multimodality emerging as a promising sol...The potential for reducing greenhouse gas(GHG)emissions and energy consumption in wastewater treatment can be realized through intelligent control,with machine learning(ML)and multimodality emerging as a promising solution.Here,we introduce an ML technique based on multimodal strategies,focusing specifically on intelligent aeration control in wastewater treatment plants(WWTPs).The generalization of the multimodal strategy is demonstrated on eight ML models.The results demonstrate that this multimodal strategy significantly enhances model indicators for ML in environmental science and the efficiency of aeration control,exhibiting exceptional performance and interpretability.Integrating random forest with visual models achieves the highest accuracy in forecasting aeration quantity in multimodal models,with a mean absolute percentage error of 4.4%and a coefficient of determination of 0.948.Practical testing in a full-scale plant reveals that the multimodal model can reduce operation costs by 19.8%compared to traditional fuzzy control methods.The potential application of these strategies in critical water science domains is discussed.To foster accessibility and promote widespread adoption,the multimodal ML models are freely available on GitHub,thereby eliminating technical barriers and encouraging the application of artificial intelligence in urban wastewater treatment.展开更多
In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a p...In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a promising means of preventing miscommunications and enhancing aviation safety. However, most existing speech recognition methods merely incorporate external language models on the decoder side, leading to insufficient semantic alignment between speech and text modalities during the encoding phase. Furthermore, it is challenging to model acoustic context dependencies over long distances due to the longer speech sequences than text, especially for the extended ATCC data. To address these issues, we propose a speech-text multimodal dual-tower architecture for speech recognition. It employs cross-modal interactions to achieve close semantic alignment during the encoding stage and strengthen its capabilities in modeling auditory long-distance context dependencies. In addition, a two-stage training strategy is elaborately devised to derive semantics-aware acoustic representations effectively. The first stage focuses on pre-training the speech-text multimodal encoding module to enhance inter-modal semantic alignment and aural long-distance context dependencies. The second stage fine-tunes the entire network to bridge the input modality variation gap between the training and inference phases and boost generalization performance. Extensive experiments demonstrate the effectiveness of the proposed speech-text multimodal speech recognition method on the ATCC and AISHELL-1 datasets. It reduces the character error rate to 6.54% and 8.73%, respectively, and exhibits substantial performance gains of 28.76% and 23.82% compared with the best baseline model. The case studies indicate that the obtained semantics-aware acoustic representations aid in accurately recognizing terms with similar pronunciations but distinctive semantics. The research provides a novel modeling paradigm for semantics-aware speech recognition in air traffic control communications, which could contribute to the advancement of intelligent and efficient aviation safety management.展开更多
With the rapid development of the mobile communication and the Internet,the previous web anomaly detectionand identificationmodels were built relying on security experts’empirical knowledge and attack features.Althou...With the rapid development of the mobile communication and the Internet,the previous web anomaly detectionand identificationmodels were built relying on security experts’empirical knowledge and attack features.Althoughthis approach can achieve higher detection performance,it requires huge human labor and resources to maintainthe feature library.In contrast,semantic feature engineering can dynamically discover new semantic featuresand optimize feature selection by automatically analyzing the semantic information contained in the data itself,thus reducing dependence on prior knowledge.However,current semantic features still have the problem ofsemantic expression singularity,as they are extracted from a single semantic mode such as word segmentation,character segmentation,or arbitrary semantic feature extraction.This paper extracts features of web requestsfrom dual semantic granularity,and proposes a semantic feature fusion method to solve the above problems.Themethod first preprocesses web requests,and extracts word-level and character-level semantic features of URLs viaconvolutional neural network(CNN),respectively.By constructing three loss functions to reduce losses betweenfeatures,labels and categories.Experiments on the HTTP CSIC 2010,Malicious URLs and HttpParams datasetsverify the proposedmethod.Results show that compared withmachine learning,deep learningmethods and BERTmodel,the proposed method has better detection performance.And it achieved the best detection rate of 99.16%in the dataset HttpParams.展开更多
Natural events have had a significant impact on overall flight activity,and the aviation industry plays a vital role in helping society cope with the impact of these events.As one of the most impactful weather typhoon...Natural events have had a significant impact on overall flight activity,and the aviation industry plays a vital role in helping society cope with the impact of these events.As one of the most impactful weather typhoon seasons appears and continues,airlines operating in threatened areas and passengers having travel plans during this time period will pay close attention to the development of tropical storms.This paper proposes a deep multimodal fusion and multitasking trajectory prediction model that can improve the reliability of typhoon trajectory prediction and reduce the quantity of flight scheduling cancellation.The deep multimodal fusion module is formed by deep fusion of the feature output by multiple submodal fusion modules,and the multitask generation module uses longitude and latitude as two related tasks for simultaneous prediction.With more dependable data accuracy,problems can be analysed rapidly and more efficiently,enabling better decision-making with a proactive versus reactive posture.When multiple modalities coexist,features can be extracted from them simultaneously to supplement each other’s information.An actual case study,the typhoon Lichma that swept China in 2019,has demonstrated that the algorithm can effectively reduce the number of unnecessary flight cancellations compared to existing flight scheduling and assist the new generation of flight scheduling systems under extreme weather.展开更多
Using the multimodal metaphor theory,this article studies the multimodal metaphor of emotion.Emotions can be divided into positive emotions and negative emotions.Positive emotion metaphors include happiness metaphors ...Using the multimodal metaphor theory,this article studies the multimodal metaphor of emotion.Emotions can be divided into positive emotions and negative emotions.Positive emotion metaphors include happiness metaphors and love metaphors,while negative emotion metaphors include anger metaphors,fear metaphors and sadness metaphors.They intuitively represent the source domain through physical signs,sensory effects,orientation dynamics and physical presentation close to the actual life,and the emotional multimodal metaphors in emojis have narrative and social functions.展开更多
基金Supported by National Natural Science Foundation of China (Grant Nos. 52375003, 52205006)National Key R&D Program of China (Grant No. 2019YFB1309600)。
文摘To improve locomotion and operation integration, this paper presents an integrated leg-arm quadruped robot(ILQR) that has a reconfigurable joint. First, the reconfigurable joint is designed and assembled at the end of the legarm chain. When the robot performs a task, reconfigurable configuration and mode switching can be achieved using this joint. In contrast from traditional quadruped robots, this robot can stack in a designated area to optimize the occupied volume in a nonworking state. Kinematics modeling and dynamics modeling are established to evaluate the mechanical properties for multiple modes. All working modes of the robot are classified, which can be defined as deployable mode, locomotion mode and operation mode. Based on the stability margin and mechanical modeling, switching analysis and evaluation between each mode is carried out. Finally, the prototype experimental results verify the function realization and switching stability of multimode and provide a design method to integrate and perform multimode for quadruped robots with deployable characteristics.
基金supported by National Natural Science Foundation of China(62135007 and 61925502).
文摘Optical endoscopy has become an essential diagnostic and therapeutic approach in modern biomedicine for directly observing organs and tissues deep inside the human body,enabling non-invasive,rapid diagnosis and treatment.Optical fiber endoscopy is highly competitive among various endoscopic imaging techniques due to its high flexibility,compact structure,excellent resolution,and resistance to electromagnetic interference.Over the past decade,endoscopes based on a single multimode optical fiber(MMF)have attracted widespread research interest due to their potential to significantly reduce the footprint of optical fiber endoscopes and enhance imaging capabilities.In comparison with other imaging principles of MMF endoscopes,the scanning imaging method based on the wavefront shaping technique is highly developed and provides benefits including excellent imaging contrast,broad applicability to complex imaging scenarios,and good compatibility with various well-established scanning imaging modalities.In this review,various technical routes to achieve light focusing through MMF and procedures to conduct the scanning imaging of MMF endoscopes are introduced.The advancements in imaging performance enhancements,integrations of various imaging modalities with MMF scanning endoscopes,and applications are summarized.Challenges specific to this endoscopic imaging technology are analyzed,and potential remedies and avenues for future developments are discussed.
基金Project supported by the National Natural Science Foundation of China (Grant No. 12072118)the Natural Science Funds for Distinguished Young Scholar of the Fujian Province, China (Grant No. 2021J06024)the Project for Youth Innovation Fund of Xiamen, China (Grant No. 3502Z20206005)。
文摘The majority of nonlinear stochastic systems can be expressed as the quasi-Hamiltonian systems in science and engineering. Moreover, the corresponding Hamiltonian system offers two concepts of integrability and resonance that can fully describe the global relationship among the degrees-of-freedom(DOFs) of the system. In this work, an effective and promising approximate semi-analytical method is proposed for the steady-state response of multi-dimensional quasi-Hamiltonian systems. To be specific, the trial solution of the reduced Fokker–Plank–Kolmogorov(FPK) equation is obtained by using radial basis function(RBF) neural networks. Then, the residual generated by substituting the trial solution into the reduced FPK equation is considered, and a loss function is constructed by combining random sampling technique. The unknown weight coefficients are optimized by minimizing the loss function through the Lagrange multiplier method. Moreover, an efficient sampling strategy is employed to promote the implementation of algorithms. Finally, two numerical examples are studied in detail, and all the semi-analytical solutions are compared with Monte Carlo simulations(MCS) results. The results indicate that the complex nonlinear dynamic features of the system response can be captured through the proposed scheme accurately.
基金supported in part by the National Key Research and Development Program of China (Grant No.2020YFB2008800)the Nanchang Institute for Microtechnology of Tianjin University。
文摘This paper is focused on electrode design for piezoelectric tuning fork resonators.The relationship between the performance and electrode pattern of aluminum nitride piezoelectric tuning fork resonators vibrating in the in-plane flexural mode is investigated based on a set of resonators with different electrode lengths,widths,and ratios.Experimental and simulation results show that the electrode design impacts greatly the multimode effect induced from torsional modes but has little influence on other loss mechanisms.Optimizing the electrode design suppresses the torsional mode successfully,thereby increasing the ratio of impedance at parallel and series resonant frequencies(R_(p)/R_(s))by more than 80%and achieving a quality factor(Q)of 7753,an effective electromechanical coupling coefficient(kt_(eff)^(2))of 0.066%,and an impedance at series resonant frequency(R_(m))of 23.6 kΩ.The proposed approach shows great potential for high-performance piezoelectric resonators,which are likely to be fundamental building blocks for sensors with high sensitivity and low noise and power consumption.
基金support by FEDER-Fundo Europeu de Desenvolvimento Regional,through COMPETE 2020-Programa Operational Fatores de Competitividade,and the National Funds through FCT-Fundacao para a Ciencia e a Tecnologia,project no.UID/FIS/04650/2019support by FEDER-Fundo Europeu de Desenvolvimento Regional,through COMPETI E 2020-Programa Operacional Fatores de Competitividade,and the National Funds through FCT-Fundacao para a Ciencia e a Tecnologia,project no.POCI-01-0145-FEDER-028118
文摘We propose an adaptive stencil construction for high-order accurate finite volume schemes a posteriori stabilized devoted to solve one-dimensional steady-state hyperbolic equations.High accuracy(up to the sixth-order presently)is achieved,thanks to polynomial recon-structions while stability is provided with an a posteriori MOOD method which controls the cell polynomial degree for eliminating non-physical oscillations in the vicinity of dis-continuities.We supplemented this scheme with a stencil construction allowing to reduce even further the numerical dissipation.The stencil is shifted away from troubles(shocks,discontinuities,etc.)leading to less oscillating polynomial reconstructions.Experimented on linear,Burgers',and Euler equations,we demonstrate that the adaptive stencil technique manages to retrieve smooth solutions with optimal order of accuracy but also irregular ones without spurious oscillations.Moreover,we numerically show that the approach allows to reduce the dissipation still maintaining the essentially non-oscillatory behavior.
基金Project supported by the National Natural Science Foundation of China(No.11571240)the Shenzhen Natural Science Fund of China(the Stable Support Plan Program No.20220805175116001)。
文摘In a magnetohydrodynamic(MHD)driven fluid cell,a plane non-parallel flow in a square domain satisfying a free-slip boundary condition is examined.The energy dissipation of the flow is controlled by the viscosity and linear friction.The latter arises from the influence of the Hartmann bottom boundary layer in a three-dimensional(3D)MHD experiment in a square bottomed cell.The basic flow in this fluid system is a square eddy flow exhibiting a network of N~2 vortices rotating alternately in clockwise and anticlockwise directions.When N is odd,the instability of the flow gives rise to secondary steady-state flows and secondary time-periodic flows,exhibiting similar characteristics to those observed when N=3.For this reason,this study focuses on the instability of the square eddy flow of nine vortices.It is shown that there exist eight bi-critical values corresponding to the existence of eight neutral eigenfunction spaces.Especially,there exist non-real neutral eigenfunctions,which produce secondary time-periodic flows exhibiting vortices merging in an oscillatory manner.This Hopf bifurcation phenomenon has not been observed in earlier investigations.
文摘Neuropathy is nerve damage that can cause chronic neuropathic pain, which is challenging to cure and has a significant financial burden. Exercise therapies, including High-Intensity Interval Training (HIIT) and steady-state cardio, are being explored as potential treatments for neuropathic pain. This systematic review compares the effectiveness of HIIT and steady-state cardio for improving function in neurological patients. This article provides an overview of the systematic review conducted on the effects of exercise on neuropathic patients, with a focus on high-intensity interval training (HIIT) and steady-state cardio. The authors conducted a comprehensive search of various databases, identified relevant studies based on predetermined inclusion criteria, and used the EPPI automation application to process the data. The final selection of studies was based on validity and relevance, with redundant articles removed. The article reviews four studies that compare high-intensity interval training (HIIT) to moderate-intensity continuous training (MICT) on various health outcomes. The studies found that HIIT can improve aerobic fitness, cerebral blood flow, and brain function in stroke patients;lower diastolic blood pressure more than MICT and improve insulin sensitivity and skeletal muscle mitochondrial content in obese individuals, potentially helping with the prevention and management of type 2 diabetes. In people with multiple sclerosis, acute exercise can decrease the plasma neurofilament light chain while increasing the flow of the kynurenine pathway. The available clinical and preclinical data suggest that further study on high-intensity interval training (HIIT) and its potential to alleviate neuropathic pain is justified. Randomized controlled trials are needed to investigate the type, intensity, frequency, and duration of exercise, which could lead to consensus and specific HIIT-based advice for patients with neuropathies.
文摘Multimodal freight transportation emerges as the go-to strategy for cost-effectively and sustainably moving goods over long distances. In a multimodal freight system, where a single contract includes various transportation methods, businesses aiming for economic success must make well-informed decisions about which modes of transport to use. These decisions prioritize secure deliveries, competitive cost advantages, and the minimization of environmental footprints associated with transportation-related pollution. Within the dynamic landscape of logistics innovation, various multicriteria decision-making (MCDM) approaches empower businesses to evaluate freight transport options thoroughly. In this study, we utilize a case study to demonstrate the application of the Technique for Order Preference by Similarity to the Ideal Solution (TOPSIS) algorithm for MCDM decision-making in freight mode selection. We further enhance the TOPSIS framework by integrating the entropy weight coefficient method. This enhancement aids in assigning precise weights to each criterion involved in mode selection, leading to a more reliable decision-making process. The proposed model provides cost-effective and timely deliveries, minimizing environmental footprint and meeting consumers’ needs. Our findings reveal that freight carbon footprint is the primary concern, followed by freight cost, time sensitivity, and service reliability. The study identifies the combination of Rail/Truck as the ideal mode of transport and containers in flat cars (COFC) as the next best option for the selected case. The proposed algorithm, incorporating the enhanced TOPSIS framework, benefits companies navigating the complexities of multimodal transport. It empowers making more strategic and informed transportation decisions. This demonstration will be increasingly valuable as companies navigate the ever-growing trade within the global supply chains.
基金supported in part by National Natural Science Foundation of China(62106230,U23A20340,62376253,62176238)China Postdoctoral Science Foundation(2023M743185)Key Laboratory of Big Data Intelligent Computing,Chongqing University of Posts and Telecommunications Open Fundation(BDIC-2023-A-007)。
文摘In multimodal multiobjective optimization problems(MMOPs),there are several Pareto optimal solutions corre-sponding to the identical objective vector.This paper proposes a new differential evolution algorithm to solve MMOPs with higher-dimensional decision variables.Due to the increase in the dimensions of decision variables in real-world MMOPs,it is diffi-cult for current multimodal multiobjective optimization evolu-tionary algorithms(MMOEAs)to find multiple Pareto optimal solutions.The proposed algorithm adopts a dual-population framework and an improved environmental selection method.It utilizes a convergence archive to help the first population improve the quality of solutions.The improved environmental selection method enables the other population to search the remaining decision space and reserve more Pareto optimal solutions through the information of the first population.The combination of these two strategies helps to effectively balance and enhance conver-gence and diversity performance.In addition,to study the per-formance of the proposed algorithm,a novel set of multimodal multiobjective optimization test functions with extensible decision variables is designed.The proposed MMOEA is certified to be effective through comparison with six state-of-the-art MMOEAs on the test functions.
基金the National Natural Science Foundation of China(No.62302540)with author F.F.S.For more information,please visit their website at https://www.nsfc.gov.cn/.Additionally,it is also funded by the Open Foundation of Henan Key Laboratory of Cyberspace Situation Awareness(No.HNTS2022020)+1 种基金where F.F.S is an author.Further details can be found at http://xt.hnkjt.gov.cn/data/pingtai/.The research is also supported by the Natural Science Foundation of Henan Province Youth Science Fund Project(No.232300420422)for more information,you can visit https://kjt.henan.gov.cn/2022/09-02/2599082.html.Lastly,it receives funding from the Natural Science Foundation of Zhongyuan University of Technology(No.K2023QN018),where F.F.S is an author.You can find more information at https://www.zut.edu.cn/.
文摘As social networks become increasingly complex, contemporary fake news often includes textual descriptionsof events accompanied by corresponding images or videos. Fake news in multiple modalities is more likely tocreate a misleading perception among users. While early research primarily focused on text-based features forfake news detection mechanisms, there has been relatively limited exploration of learning shared representationsin multimodal (text and visual) contexts. To address these limitations, this paper introduces a multimodal modelfor detecting fake news, which relies on similarity reasoning and adversarial networks. The model employsBidirectional Encoder Representation from Transformers (BERT) and Text Convolutional Neural Network (Text-CNN) for extracting textual features while utilizing the pre-trained Visual Geometry Group 19-layer (VGG-19) toextract visual features. Subsequently, the model establishes similarity representations between the textual featuresextracted by Text-CNN and visual features through similarity learning and reasoning. Finally, these features arefused to enhance the accuracy of fake news detection, and adversarial networks have been employed to investigatethe relationship between fake news and events. This paper validates the proposed model using publicly availablemultimodal datasets from Weibo and Twitter. Experimental results demonstrate that our proposed approachachieves superior performance on Twitter, with an accuracy of 86%, surpassing traditional unimodalmodalmodelsand existing multimodal models. In contrast, the overall better performance of our model on the Weibo datasetsurpasses the benchmark models across multiple metrics. The application of similarity reasoning and adversarialnetworks in multimodal fake news detection significantly enhances detection effectiveness in this paper. However,current research is limited to the fusion of only text and image modalities. Future research directions should aimto further integrate features fromadditionalmodalities to comprehensively represent themultifaceted informationof fake news.
基金We acknowledge funding from NSFC Grant 62306283.
文摘Since the 1950s,when the Turing Test was introduced,there has been notable progress in machine language intelligence.Language modeling,crucial for AI development,has evolved from statistical to neural models over the last two decades.Recently,transformer-based Pre-trained Language Models(PLM)have excelled in Natural Language Processing(NLP)tasks by leveraging large-scale training corpora.Increasing the scale of these models enhances performance significantly,introducing abilities like context learning that smaller models lack.The advancement in Large Language Models,exemplified by the development of ChatGPT,has made significant impacts both academically and industrially,capturing widespread societal interest.This survey provides an overview of the development and prospects from Large Language Models(LLM)to Large Multimodal Models(LMM).It first discusses the contributions and technological advancements of LLMs in the field of natural language processing,especially in text generation and language understanding.Then,it turns to the discussion of LMMs,which integrates various data modalities such as text,images,and sound,demonstrating advanced capabilities in understanding and generating cross-modal content,paving new pathways for the adaptability and flexibility of AI systems.Finally,the survey highlights the prospects of LMMs in terms of technological development and application potential,while also pointing out challenges in data integration,cross-modal understanding accuracy,providing a comprehensive perspective on the latest developments in this field.
文摘BACKGROUND According to clinical data,a significant percentage of patients experience pain after surgery,highlighting the importance of alleviating postoperative pain.The current approach involves intravenous self-control analgesia,often utilizing opioid analgesics such as morphine,sufentanil,and fentanyl.Surgery for colo-rectal cancer typically involves general anesthesia.Therefore,optimizing anes-thetic management and postoperative analgesic programs can effectively reduce perioperative stress and enhance postoperative recovery.The study aims to analyze the impact of different anesthesia modalities with multimodal analgesia on patients'postoperative pain.AIM To explore the effects of different anesthesia methods coupled with multi-mode analgesia on postoperative pain in patients with colorectal cancer.METHODS Following the inclusion criteria and exclusion criteria,a total of 126 patients with colorectal cancer admitted to our hospital from January 2020 to December 2022 were included,of which 63 received general anesthesia coupled with multi-mode labor pain and were set as the control group,and 63 received general anesthesia associated with epidural anesthesia coupled with multi-mode labor pain and were set as the research group.After data collection,the effects of postoperative analgesia,sedation,and recovery were compared.RESULTS Compared to the control group,the research group had shorter recovery times for orientation,extubation,eye-opening,and spontaneous respiration(P<0.05).The research group also showed lower Visual analog scale scores at 24 h and 48 h,higher Ramany scores at 6 h and 12 h,and improved cognitive function at 24 h,48 h,and 72 h(P<0.05).Additionally,interleukin-6 and interleukin-10 levels were significantly reduced at various time points in the research group compared to the control group(P<0.05).Levels of CD3+,CD4+,and CD4+/CD8+were also lower in the research group at multiple time points(P<0.05).CONCLUSION For patients with colorectal cancer,general anesthesia coupled with epidural anesthesia and multi-mode analgesia can achieve better postoperative analgesia and sedation effects,promote postoperative rehabilitation of patients,improve inflammatory stress and immune status,and have higher safety.
基金supported in part by the Science and Technology Project of Yunnan Tobacco Industrial Company under Grant JB2022YL02in part by the Natural Science Foundation of Henan Province of China under Grant 242300421413in part by the Henan Province Science and Technology Research Projects under Grants 242102110334 and 242102110375.
文摘In practical engineering,multi-objective optimization often encounters situations where multiple Pareto sets(PS)in the decision space correspond to the same Pareto front(PF)in the objective space,known as Multi-Modal Multi-Objective Optimization Problems(MMOP).Locating multiple equivalent global PSs poses a significant challenge in real-world applications,especially considering the existence of local PSs.Effectively identifying and locating both global and local PSs is a major challenge.To tackle this issue,we introduce an immune-inspired reproduction strategy designed to produce more offspring in less crowded,promising regions and regulate the number of offspring in areas that have been thoroughly explored.This approach achieves a balanced trade-off between exploration and exploitation.Furthermore,we present an interval allocation strategy that adaptively assigns fitness levels to each antibody.This strategy ensures a broader survival margin for solutions in their initial stages and progressively amplifies the differences in individual fitness values as the population matures,thus fostering better population convergence.Additionally,we incorporate a multi-population mechanism that precisely manages each subpopulation through the interval allocation strategy,ensuring the preservation of both global and local PSs.Experimental results on 21 test problems,encompassing both global and local PSs,are compared with eight state-of-the-art multimodal multi-objective optimization algorithms.The results demonstrate the effectiveness of our proposed algorithm in simultaneously identifying global Pareto sets and locally high-quality PSs.
文摘Cross-lingual image description,the task of generating image captions in a target language from images and descriptions in a source language,is addressed in this study through a novel approach that combines neural network models and semantic matching techniques.Experiments conducted on the Flickr8k and AraImg2k benchmark datasets,featuring images and descriptions in English and Arabic,showcase remarkable performance improvements over state-of-the-art methods.Our model,equipped with the Image&Cross-Language Semantic Matching module and the Target Language Domain Evaluation module,significantly enhances the semantic relevance of generated image descriptions.For English-to-Arabic and Arabic-to-English cross-language image descriptions,our approach achieves a CIDEr score for English and Arabic of 87.9%and 81.7%,respectively,emphasizing the substantial contributions of our methodology.Comparative analyses with previous works further affirm the superior performance of our approach,and visual results underscore that our model generates image captions that are both semantically accurate and stylistically consistent with the target language.In summary,this study advances the field of cross-lingual image description,offering an effective solution for generating image captions across languages,with the potential to impact multilingual communication and accessibility.Future research directions include expanding to more languages and incorporating diverse visual and textual data sources.
基金supported by STI 2030-Major Projects 2021ZD0200400National Natural Science Foundation of China(62276233 and 62072405)Key Research Project of Zhejiang Province(2023C01048).
文摘Multimodal sentiment analysis utilizes multimodal data such as text,facial expressions and voice to detect people’s attitudes.With the advent of distributed data collection and annotation,we can easily obtain and share such multimodal data.However,due to professional discrepancies among annotators and lax quality control,noisy labels might be introduced.Recent research suggests that deep neural networks(DNNs)will overfit noisy labels,leading to the poor performance of the DNNs.To address this challenging problem,we present a Multimodal Robust Meta Learning framework(MRML)for multimodal sentiment analysis to resist noisy labels and correlate distinct modalities simultaneously.Specifically,we propose a two-layer fusion net to deeply fuse different modalities and improve the quality of the multimodal data features for label correction and network training.Besides,a multiple meta-learner(label corrector)strategy is proposed to enhance the label correction approach and prevent models from overfitting to noisy labels.We conducted experiments on three popular multimodal datasets to verify the superiority of ourmethod by comparing it with four baselines.
基金the financial support by the National Natural Science Foundation of China(52230004 and 52293445)the Key Research and Development Project of Shandong Province(2020CXGC011202-005)the Shenzhen Science and Technology Program(KCXFZ20211020163404007 and KQTD20190929172630447).
文摘The potential for reducing greenhouse gas(GHG)emissions and energy consumption in wastewater treatment can be realized through intelligent control,with machine learning(ML)and multimodality emerging as a promising solution.Here,we introduce an ML technique based on multimodal strategies,focusing specifically on intelligent aeration control in wastewater treatment plants(WWTPs).The generalization of the multimodal strategy is demonstrated on eight ML models.The results demonstrate that this multimodal strategy significantly enhances model indicators for ML in environmental science and the efficiency of aeration control,exhibiting exceptional performance and interpretability.Integrating random forest with visual models achieves the highest accuracy in forecasting aeration quantity in multimodal models,with a mean absolute percentage error of 4.4%and a coefficient of determination of 0.948.Practical testing in a full-scale plant reveals that the multimodal model can reduce operation costs by 19.8%compared to traditional fuzzy control methods.The potential application of these strategies in critical water science domains is discussed.To foster accessibility and promote widespread adoption,the multimodal ML models are freely available on GitHub,thereby eliminating technical barriers and encouraging the application of artificial intelligence in urban wastewater treatment.
基金This research was funded by Shenzhen Science and Technology Program(Grant No.RCBS20221008093121051)the General Higher Education Project of Guangdong Provincial Education Department(Grant No.2020ZDZX3085)+1 种基金China Postdoctoral Science Foundation(Grant No.2021M703371)the Post-Doctoral Foundation Project of Shenzhen Polytechnic(Grant No.6021330002K).
文摘In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a promising means of preventing miscommunications and enhancing aviation safety. However, most existing speech recognition methods merely incorporate external language models on the decoder side, leading to insufficient semantic alignment between speech and text modalities during the encoding phase. Furthermore, it is challenging to model acoustic context dependencies over long distances due to the longer speech sequences than text, especially for the extended ATCC data. To address these issues, we propose a speech-text multimodal dual-tower architecture for speech recognition. It employs cross-modal interactions to achieve close semantic alignment during the encoding stage and strengthen its capabilities in modeling auditory long-distance context dependencies. In addition, a two-stage training strategy is elaborately devised to derive semantics-aware acoustic representations effectively. The first stage focuses on pre-training the speech-text multimodal encoding module to enhance inter-modal semantic alignment and aural long-distance context dependencies. The second stage fine-tunes the entire network to bridge the input modality variation gap between the training and inference phases and boost generalization performance. Extensive experiments demonstrate the effectiveness of the proposed speech-text multimodal speech recognition method on the ATCC and AISHELL-1 datasets. It reduces the character error rate to 6.54% and 8.73%, respectively, and exhibits substantial performance gains of 28.76% and 23.82% compared with the best baseline model. The case studies indicate that the obtained semantics-aware acoustic representations aid in accurately recognizing terms with similar pronunciations but distinctive semantics. The research provides a novel modeling paradigm for semantics-aware speech recognition in air traffic control communications, which could contribute to the advancement of intelligent and efficient aviation safety management.
基金a grant from the National Natural Science Foundation of China(Nos.11905239,12005248 and 12105303).
文摘With the rapid development of the mobile communication and the Internet,the previous web anomaly detectionand identificationmodels were built relying on security experts’empirical knowledge and attack features.Althoughthis approach can achieve higher detection performance,it requires huge human labor and resources to maintainthe feature library.In contrast,semantic feature engineering can dynamically discover new semantic featuresand optimize feature selection by automatically analyzing the semantic information contained in the data itself,thus reducing dependence on prior knowledge.However,current semantic features still have the problem ofsemantic expression singularity,as they are extracted from a single semantic mode such as word segmentation,character segmentation,or arbitrary semantic feature extraction.This paper extracts features of web requestsfrom dual semantic granularity,and proposes a semantic feature fusion method to solve the above problems.Themethod first preprocesses web requests,and extracts word-level and character-level semantic features of URLs viaconvolutional neural network(CNN),respectively.By constructing three loss functions to reduce losses betweenfeatures,labels and categories.Experiments on the HTTP CSIC 2010,Malicious URLs and HttpParams datasetsverify the proposedmethod.Results show that compared withmachine learning,deep learningmethods and BERTmodel,the proposed method has better detection performance.And it achieved the best detection rate of 99.16%in the dataset HttpParams.
基金supported by the National Natural Science Foundation of China(62073330)。
文摘Natural events have had a significant impact on overall flight activity,and the aviation industry plays a vital role in helping society cope with the impact of these events.As one of the most impactful weather typhoon seasons appears and continues,airlines operating in threatened areas and passengers having travel plans during this time period will pay close attention to the development of tropical storms.This paper proposes a deep multimodal fusion and multitasking trajectory prediction model that can improve the reliability of typhoon trajectory prediction and reduce the quantity of flight scheduling cancellation.The deep multimodal fusion module is formed by deep fusion of the feature output by multiple submodal fusion modules,and the multitask generation module uses longitude and latitude as two related tasks for simultaneous prediction.With more dependable data accuracy,problems can be analysed rapidly and more efficiently,enabling better decision-making with a proactive versus reactive posture.When multiple modalities coexist,features can be extracted from them simultaneously to supplement each other’s information.An actual case study,the typhoon Lichma that swept China in 2019,has demonstrated that the algorithm can effectively reduce the number of unnecessary flight cancellations compared to existing flight scheduling and assist the new generation of flight scheduling systems under extreme weather.
文摘Using the multimodal metaphor theory,this article studies the multimodal metaphor of emotion.Emotions can be divided into positive emotions and negative emotions.Positive emotion metaphors include happiness metaphors and love metaphors,while negative emotion metaphors include anger metaphors,fear metaphors and sadness metaphors.They intuitively represent the source domain through physical signs,sensory effects,orientation dynamics and physical presentation close to the actual life,and the emotional multimodal metaphors in emojis have narrative and social functions.