Identifying drug-drug interactions(DDIs)is essential to prevent adverse effects from polypharmacy.Although deep learning has advanced DDI identification,the gap between powerful models and their lack of clinical appli...Identifying drug-drug interactions(DDIs)is essential to prevent adverse effects from polypharmacy.Although deep learning has advanced DDI identification,the gap between powerful models and their lack of clinical application and evaluation has hindered clinical benefits.Here,we developed a Multi-Dimensional Feature Fusion model named MDFF,which integrates one-dimensional simplified molec-ular input line entry system sequence features,two-dimensional molecular graph features,and three-dimensional geometric features to enhance drug representations for predicting DDIs.MDFF was trained and validated on two DDI datasets,evaluated across three distinct scenarios,and compared with advanced DDI prediction models using accuracy,precision,recall,area under the curve,and F1 score metrics.MDFF achieved state-of-the-art performance across all metrics.Ablation experiments showed that integrating multi-dimensional drug features yielded the best results.More importantly,we obtained adverse drug reaction reports uploaded by Xiangya Hospital of Central South University from 2021 to 2023 and used MDFF to identify potential adverse DDIs.Among 12 real-world adverse drug reaction reports,the predictions of 9 reports were supported by relevant evidence.Additionally,MDFF demon-strated the ability to explain adverse DDI mechanisms,providing insights into the mechanisms behind one specific report and highlighting its potential to assist practitioners in improving medical practice.展开更多
Lip language provides a silent,intuitive,and efficient mode of communication,offering a promising solution for individuals with speech impairments.Its articulation relies on complex movements of the jaw and the muscle...Lip language provides a silent,intuitive,and efficient mode of communication,offering a promising solution for individuals with speech impairments.Its articulation relies on complex movements of the jaw and the muscles surrounding it.However,the accurate and real-time acquisition and decoding of these movements into reliable silent speech signals remains a significant challenge.In this work,we propose a real-time silent speech recognition system,which integrates a triboelectric nanogenerator-based flexible pressure sensor(FPS)with a deep learning framework.The FPS employs a porous pyramid-structured silicone film as the negative triboelectric layer,enabling highly sensitive pressure detection in the low-force regime(1 V N^(-1) for 0-10 N and 4.6 V N^(-1) for 10-24 N).This allows it to precisely capture jaw movements during speech and convert them into electrical signals.To decode the signals,we proposed a convolutional neural networklong short-term memory(CNN-LSTM)hybrid network,combining CNN and LSTM model to extract both local spatial features and temporal dynamics.The model achieved 95.83%classification accuracy in 30 categories of daily words.Furthermore,the decoded silent speech signals can be directly translated into executable commands for contactless and precise control of the smartphone.The system can also be connected to AR glasses,offering a novel human-machine interaction approach with promising potential in AR/VR applications.展开更多
Electromyography(EMG)has already been broadly used in human-machine interaction(HMI)applications.Determining how to decode the information inside EMG signals robustly and accurately is a key problem for which we urgen...Electromyography(EMG)has already been broadly used in human-machine interaction(HMI)applications.Determining how to decode the information inside EMG signals robustly and accurately is a key problem for which we urgently need a solution.Recently,many EMG pattern recognition tasks have been addressed using deep learning methods.In this paper,we analyze recent papers and present a literature review describing the role that deep learning plays in EMG-based HMI.An overview of typical network structures and processing schemes will be provided.Recent progress in typical tasks such as movement classification,joint angle prediction,and force/torque estimation will be introduced.New issues,including multimodal sensing,inter-subject/inter-session,and robustness toward disturbances will be discussed.We attempt to provide a comprehensive analysis of current research by discussing the advantages,challenges,and opportunities brought by deep learning.We hope that deep learning can aid in eliminating factors that hinder the development of EMG-based HMI systems.Furthermore,possible future directions will be presented to pave the way for future research.展开更多
To improve the training efficiency and recommendation accuracy in cold-start interactive recommendation systems,a new graph structure called item similarity graph is proposed on the basis of real data from a public da...To improve the training efficiency and recommendation accuracy in cold-start interactive recommendation systems,a new graph structure called item similarity graph is proposed on the basis of real data from a public dataset.The proposed graph is built from collaborative interactions and a deep reinforcement learning-based graph-enhanced neural interactive collaborative filtering(GE-ICF)model.The GE-ICF framework is developed with a deep reinforcement learning framework and comprises an embedding propagation layer designed with graph neural networks.Extensive experiments are conducted to investigate the efficiency of the proposed graph structure and the superiority of the proposed GE-ICF framework.Results show that in cold-start interactive recommendation systems,the proposed item similarity graph performs well in data relationship modeling,with the training efficiency showing significant improvement.The proposed GE-ICF framework also demonstrates superiority in decision modeling,thereby increasing the recommendation accuracy remarkably.展开更多
This paper describes the interaction between deep-seated landslides and man-made structures such as dams, penstocks, viaducts, and tunnels. Selected case studies are reported first with the intent to gain insights int...This paper describes the interaction between deep-seated landslides and man-made structures such as dams, penstocks, viaducts, and tunnels. Selected case studies are reported first with the intent to gain insights into the complexities associated with the interaction of these structures with deep-seated landslides(generally referred to as deep-seated gravity slope deformations, DSGSDs). The main features, which characterize these landslides, are mentioned together with the interaction problems encountered in each case. Given the main objective of this paper, the numerical modeling methods adopted are outlined as means for increase in the understanding of the interaction problems being investigated. With the above in mind, the attention moves to an important and unique case history dealing with the interaction of a large-size twin-tunnel excavated with an earth pressure balance(EPB)tunnel boring machine(TBM) and a deep-seated landslide, which was reactivated due to the stress changes induced by tunnel excavation in landslide shear zone. The geological and geotechnical conditions are described together with the available monitoring data on the landslide movements, based on the advanced and conventional monitoring tools used. Numerical modeling is illustrated as an aid to back-analyze the monitored surface and subsurface deformations and to assist in finding the appropriate engineering solution for putting the tunnel into service and as a follow-up means for future understanding and control of the interaction problems. The simulation is based on a novel time-dependent model representing the landslide behavior.展开更多
In this study the structure and seasonal variations of deep mean circulation in the East/lapan Sea （E/S） were numerically simulated using a mid-resolution ocean general circulation model with two different parameter...In this study the structure and seasonal variations of deep mean circulation in the East/lapan Sea （E/S） were numerically simulated using a mid-resolution ocean general circulation model with two different parameterizations for the eddy-topography interaction （ETI）. The strong deep mean circulations observed in the EIS are well reproduced when using the ETI parameterizations. The seasonal variability in the EIS deep layer is shown by using ETI parameterization based on the potential vorticity approach, while it is not shown in the statistical dynamical parameterization. The driving mechanism of the strong deep mean currents in the E/S are discussed by investigating the effects of model grids and parameterizations. The deep mean circulation is more closely related to the baroclinic process and potential vorticity than it is to the wind driven circulation.展开更多
Explicit solution techniques have been widely used in geotechnical engineering for simulating the coupled hydro-mechanical(H-M) interaction of fluid flow and deformation induced by structures built above and under sat...Explicit solution techniques have been widely used in geotechnical engineering for simulating the coupled hydro-mechanical(H-M) interaction of fluid flow and deformation induced by structures built above and under saturated ground, i.e. circular footing and deep tunnel. However, the technique is only conditionally stable and requires small time steps, portending its inefficiency for simulating large-scale H-M problems. To improve its efficiency, the unconditionally stable alternating direction explicit(ADE)scheme could be used to solve the flow problem. The standard ADE scheme, however, is only moderately accurate and is restricted to uniform grids and plane strain flow conditions. This paper aims to remove these drawbacks by developing a novel high-order ADE scheme capable of solving flow problems in nonuniform grids and under axisymmetric conditions. The new scheme is derived by performing a fourthorder finite difference(FD) approximation to the spatial derivatives of the axisymmetric fluid-diffusion equation in a non-uniform grid configuration. The implicit Crank-Nicolson technique is then applied to the resulting approximation, and the subsequent equation is split into two alternating direction sweeps,giving rise to a new axisymmetric ADE scheme. The pore pressure solutions from the new scheme are then sequentially coupled with an existing geomechanical simulator in the computer code fast Lagrangian analysis of continua(FLAC). This coupling procedure is called the sequentially-explicit coupling technique based on the fourth-order axisymmetric ADE scheme or SEA-4-AXI. Application of SEA-4-AXI for solving axisymmetric consolidation of a circular footing and of advancing tunnel in deep saturated ground shows that SEA-4-AXI reduces computer runtime up to 42%-50% that of FLAC’s basic scheme without numerical instability. In addition, it produces high numerical accuracy of the H-M solutions with average percentage difference of only 0.5%-1.8%.展开更多
Human Interaction Recognition(HIR)was one of the challenging issues in computer vision research due to the involvement of multiple individuals and their mutual interactions within video frames generated from their mov...Human Interaction Recognition(HIR)was one of the challenging issues in computer vision research due to the involvement of multiple individuals and their mutual interactions within video frames generated from their movements.HIR requires more sophisticated analysis than Human Action Recognition(HAR)since HAR focuses solely on individual activities like walking or running,while HIR involves the interactions between people.This research aims to develop a robust system for recognizing five common human interactions,such as hugging,kicking,pushing,pointing,and no interaction,from video sequences using multiple cameras.In this study,a hybrid Deep Learning(DL)and Machine Learning(ML)model was employed to improve classification accuracy and generalizability.The dataset was collected in an indoor environment with four-channel cameras capturing the five types of interactions among 13 participants.The data was processed using a DL model with a fine-tuned ResNet(Residual Networks)architecture based on 2D Convolutional Neural Network(CNN)layers for feature extraction.Subsequently,machine learning models were trained and utilized for interaction classification using six commonly used ML algorithms,including SVM,KNN,RF,DT,NB,and XGBoost.The results demonstrate a high accuracy of 95.45%in classifying human interactions.The hybrid approach enabled effective learning,resulting in highly accurate performance across different interaction types.Future work will explore more complex scenarios involving multiple individuals based on the application of this architecture.展开更多
Nowadays,smart healthcare and biomedical research have marked a substantial growth rate in terms of their presence in the literature,computational approaches,and discoveries,owing to which a massive quantity of experi...Nowadays,smart healthcare and biomedical research have marked a substantial growth rate in terms of their presence in the literature,computational approaches,and discoveries,owing to which a massive quantity of experimental datasets was published and generated(Big Data)for describing and validating such novelties.Drug-drug interaction(DDI)significantly contributed to drug administration and development.It continues as the main obstacle in offering inexpensive and safe healthcare.It normally happens for patients with extensive medication,leading them to take many drugs simultaneously.DDI may cause side effects,either mild or severe health problems.This reduced victims’quality of life and increased hospital healthcare expenses by increasing their recovery time.Several efforts were made to formulate new methods for DDI prediction to overcome this issue.In this aspect,this study designs a new Spotted Hyena Optimizer Driven Deep Learning based Drug-Drug Interaction Prediction(SHODL-DDIP)model in a big data environment.In the presented SHODL-DDIP technique,the relativity and characteristics of the drugs can be identified from different sources for prediction.The input data is preprocessed at the primary level to improve its quality.Next,the salp swarm optimization algorithm(SSO)is used to select features.In this study,the deep belief network(DBN)model is exploited to predict the DDI accurately.The SHO algorithm is involved in improvising the DBN model’s predictive outcomes,showing the novelty of the work.The experimental result analysis of the SHODL-DDIP technique is tested using drug databases,and the results signified the improvements of the SHODLDDIP technique over other recent models in terms of different performance measures.展开更多
Fracturing fluid property play a critical role in developing unconventional reservoirs.Deep eutectic solvents(DESs)show fascinating potential for property improvement of clean fracturing fluids(CFFs)due to their low-p...Fracturing fluid property play a critical role in developing unconventional reservoirs.Deep eutectic solvents(DESs)show fascinating potential for property improvement of clean fracturing fluids(CFFs)due to their low-price,low-toxicity,chemical stability and flexible designability.In this work,DESs were synthesized by mixing hydrogen bond acceptors(HBAs)and a given hydrogen bond donor(HBD)to explore their underlying influence on CFF properties based on the intermolecular interactions.The hydrogen-bonding,van der Waals and electrostatic interactions between DES components and surfactants improved the CFF properties by promoting the arrangement of surfactants at interface and enhancing the micelle network strength.The HBD enhanced the resistance of CFF for Ca^(2+) due to coordination-bonding interaction.The DESs composed of choline chloride(ChCl)and malonic acid show great enhancement for surface,rheology,temperature resistance,salt tolerance,drag reduction,and gel-breaking performance of CFFs.The DESs also improved the gel-breaking CFF-oil interactions,increasing the imbibition efficiencies to 44.2%in 74 h.Adjusting HBAs can effectively strengthen the intermolecular interactions(e.g.,HBA-surfactant and HBD-surfactant interactions)to improve CFF properties.The DESs developed in this study provide a novel strategy to intensify CFF properties.展开更多
Rockbursts, which mainly affect mining roadways, are dynamic disasters arising from the surrounding rock under high stress. Understanding the interaction between supports and the surrounding rock is necessary for effe...Rockbursts, which mainly affect mining roadways, are dynamic disasters arising from the surrounding rock under high stress. Understanding the interaction between supports and the surrounding rock is necessary for effective rockburst control. In this study, the squeezing behavior of the surrounding rock is analyzed in rockburst roadways, and a mechanical model of rockbursts is established considering the dynamic support stress, thus deriving formulas and providing characteristic curves for describing the interaction between the support and surrounding rock. Design principles and parameters of supports for rockburst control are proposed. The results show that only when the geostress magnitude exceeds a critical value can it drive the formation of rockburst conditions. The main factors influencing the convergence response and rockburst occurrence around roadways are geostress, rock brittleness, uniaxial compressive strength, and roadway excavation size. Roadway support devices can play a role in controlling rockburst by suppressing the squeezing evolution of the surrounding rock towards instability points of rockburst. Further, the higher the strength and the longer the impact stroke of support devices with constant resistance, the more easily multiple balance points can be formed with the surrounding rock to control rockburst occurrence. Supports with long impact stroke allow adaptation to varying geostress levels around the roadway, aiding in rockburst control. The results offer a quantitative method for designing support systems for rockburst-prone roadways. The design criterion of supports is determined by the intersection between the convergence curve of the surrounding rock and the squeezing deformation curve of the support devices.展开更多
Drug development remains a critical issue in the field of biomedicine.With the rapid advancement of information technologies such as artificial intelligence(AI)and the advent of the big data era,AI-assisted drug devel...Drug development remains a critical issue in the field of biomedicine.With the rapid advancement of information technologies such as artificial intelligence(AI)and the advent of the big data era,AI-assisted drug development has become a new trend,particularly in predicting drug-target associations.To address the challenge of drug-target prediction,AI-driven models have emerged as powerful tools,offering innovative solutions by effectively extracting features from complex biological data,accurately modeling molecular interactions,and precisely predicting potential drug-target outcomes.Traditional machine learning(ML),network-based,and advanced deep learning architectures such as convolutional neural networks(CNNs),graph convolutional networks(GCNs),and transformers play a pivotal role.This review systematically compiles and evaluates AI algorithms for drug-and drug combination-target predictions,highlighting their theoretical frameworks,strengths,and limitations.CNNs effectively identify spatial patterns and molecular features critical for drug-target interactions.GCNs provide deep insights into molecular interactions via relational data,whereas transformers increase prediction accuracy by capturing complex dependencies within biological sequences.Network-based models offer a systematic perspective by integrating diverse data sources,and traditional ML efficiently handles large datasets to improve overall predictive accuracy.Collectively,these AI-driven methods are transforming drug-target predictions and advancing the development of personalized therapy.This review summarizes the application of AI in drug development,particularly in drug-target prediction,and offers recommendations on models and algorithms for researchers engaged in biomedical research.It also provides typical cases to better illustrate how AI can further accelerate development in the fields of biomedicine and drug discovery.展开更多
Impressive advancements and novel techniques have been witnessed in AI-based Human Intelligent-Things Interaction(HITI)systems.Several technological breakthroughs have contributed to HITI,such as Internet of Things(Io...Impressive advancements and novel techniques have been witnessed in AI-based Human Intelligent-Things Interaction(HITI)systems.Several technological breakthroughs have contributed to HITI,such as Internet of Things(IoT),deep and edge learning for deducing intelligence,and 6G for ultra-fast and ultralow-latency communication between cyber-physical HITI systems.However,human-AI teaming presents several challenges that are yet to be addressed,despite the many advancements that have been made towards human-AI teaming.Allowing human stakeholders to understand AI’s decision-making process is a novel challenge.Artificial Intelligence(AI)needs to adopt diversified human understandable features,such as ethics,non-biases,trustworthiness,explainability,safety guarantee,data privacy,system security,and auditability.While adopting these features,high system performance should be maintained,and transparent processing involved in the‘human intelligent-things teaming’should be conveyed.To this end,we introduce the fusion of four key technologies,namely an ensemble of deep learning,6G,IoT,and corresponding security/privacy techniques to support HITI.This paper presents a framework that integrates the aforementioned four key technologies to support AI-based Human Intelligent-Things Interaction.Additionally,this paper demonstrates two security applications as proof of the concept,namely intelligent smart city surveillance and handling emergency services.The paper proposes to fuse four key technologies(deep learning,6G,IoT,and security and privacy techniques)to support Human Intelligent-Things interaction,applying the proposed framework to two security applications(surveillance and emergency handling).In this research paper,we will present a comprehensive review of the existing techniques of fusing security and privacy within future HITI applications.Moreover,we will showcase two security applications as proof of concept that use the fusion of the four key technologies to offer next-generation HITI services,namely intelligent smart city surveillance and handling emergency services.This proposed research outcome is envisioned to democratize the use of AI within smart city surveillance applications.展开更多
With the growing application of intelligent robots in service,manufacturing,and medical fields,efficient and natural interaction between humans and robots has become key to improving collaboration efficiency and user ...With the growing application of intelligent robots in service,manufacturing,and medical fields,efficient and natural interaction between humans and robots has become key to improving collaboration efficiency and user experience.Gesture recognition,as an intuitive and contactless interaction method,can overcome the limitations of traditional interfaces and enable real-time control and feedback of robot movements and behaviors.This study first reviews mainstream gesture recognition algorithms and their application on different sensing platforms(RGB cameras,depth cameras,and inertial measurement units).It then proposes a gesture recognition method based on multimodal feature fusion and a lightweight deep neural network that balances recognition accuracy with computational efficiency.At system level,a modular human-robot interaction architecture is constructed,comprising perception,decision,and execution layers,and gesture commands are transmitted and mapped to robot actions in real time via the ROS communication protocol.Through multiple comparative experiments on public gesture datasets and a self-collected dataset,the proposed method’s superiority is validated in terms of accuracy,response latency,and system robustness,while user-experience tests assess the interface’s usability.The results provide a reliable technical foundation for robot collaboration and service in complex scenarios,offering broad prospects for practical application and deployment.展开更多
Accurate prediction of drug responses in cancer cell lines(CCLs)and transferable prediction of clinical drug responses using CCLs are two major tasks in personalized medicine.Despite the rapid advancements in existing...Accurate prediction of drug responses in cancer cell lines(CCLs)and transferable prediction of clinical drug responses using CCLs are two major tasks in personalized medicine.Despite the rapid advancements in existing computational methods for preclinical and clinical cancer drug response(CDR)prediction,challenges remain regarding the generalization of new drugs that are unseen in the training set.Herein,we propose a multimodal fusion deep learning(DL)model called drug-target and single-cell language based CDR(DTLCDR)to predict preclinical and clinical CDRs.The model integrates chemical descriptors,molecular graph representations,predicted protein target profiles of drugs,and cell line expression profiles with general knowledge from single cells.Among these features,a well-trained drug-target interaction(DTI)prediction model is used to generate target profiles of drugs,and a pretrained single-cell language model is integrated to provide general genomic knowledge.Comparison experiments on the cell line drug sensitivity dataset demonstrated that DTLCDR exhibited improved generalizability and robustness in predicting unseen drugs compared with previous state-of-the-art baseline methods.Further ablation studies verified the effectiveness of each component of our model,highlighting the significant contribution of target information to generalizability.Subsequently,the ability of DTLCDR to predict novel molecules was validated through in vitro cell experiments,demonstrating its potential for real-world applications.Moreover,DTLCDR was transferred to the clinical datasets,demonstrating satisfactory performance in the clinical data,regardless of whether the drugs were included in the cell line dataset.Overall,our results suggest that the DTLCDR is a promising tool for personalized drug discovery.展开更多
This study introduces a Transformer-based multimodal fusion framework for simulating multiphase flow and heat transfer in carbon dioxide(CO_(2))–water enhanced geothermal systems(EGS).The model integrates geological ...This study introduces a Transformer-based multimodal fusion framework for simulating multiphase flow and heat transfer in carbon dioxide(CO_(2))–water enhanced geothermal systems(EGS).The model integrates geological parameters,thermal gradients,and control schedules to enable fast and accurate prediction of complex reservoir dynamics.The main contributions are:(i)development of a workflow that couples physics-based reservoir simulation with a Transformer neural network architecture,(ii)design of physics-guided loss functions to enforce conservation of mass and energy,(iii)application of the surrogate model to closed-loop optimization using a differential evolution(DE)algorithm,and(iv)incorporation of economic performance metrics,such as net present value(NPV),into decision support.The proposed framework achieves root mean square error(RMSE)of 3–5%,mean absolute error(MAE)below 4%,and coefficients of determination greater than 0.95 across multiple prediction targets,including production rates,pressure distributions,and temperature fields.When compared with recurrent neural network(RNN)baselines such as gated recurrent units(GRU)and long short-term memory networks(LSTM),as well as a physics-informed reduced-order model,the Transformer-based approach demonstrates superior accuracy and computational efficiency.Optimization experiments further show a 15–20%improvement in NPV,highlighting the framework’s potential for real-time forecasting,optimization,and decision-making in geothermal reservoir engineering.展开更多
基金supported by the National Key R&D Program of China(Grant No.:2023YFC2604400)the National Natural Science Foundation of China(Grant No.:62103436).
文摘Identifying drug-drug interactions(DDIs)is essential to prevent adverse effects from polypharmacy.Although deep learning has advanced DDI identification,the gap between powerful models and their lack of clinical application and evaluation has hindered clinical benefits.Here,we developed a Multi-Dimensional Feature Fusion model named MDFF,which integrates one-dimensional simplified molec-ular input line entry system sequence features,two-dimensional molecular graph features,and three-dimensional geometric features to enhance drug representations for predicting DDIs.MDFF was trained and validated on two DDI datasets,evaluated across three distinct scenarios,and compared with advanced DDI prediction models using accuracy,precision,recall,area under the curve,and F1 score metrics.MDFF achieved state-of-the-art performance across all metrics.Ablation experiments showed that integrating multi-dimensional drug features yielded the best results.More importantly,we obtained adverse drug reaction reports uploaded by Xiangya Hospital of Central South University from 2021 to 2023 and used MDFF to identify potential adverse DDIs.Among 12 real-world adverse drug reaction reports,the predictions of 9 reports were supported by relevant evidence.Additionally,MDFF demon-strated the ability to explain adverse DDI mechanisms,providing insights into the mechanisms behind one specific report and highlighting its potential to assist practitioners in improving medical practice.
基金supported by the Natural Science Foundation of Fujian Province under Grant No.2024J010016Fujian Province Young and Middle aged Teacher Education Research Project No.JAT241317the Mindu Innovation Laboratory Project under Grant No.2020ZZ113.
文摘Lip language provides a silent,intuitive,and efficient mode of communication,offering a promising solution for individuals with speech impairments.Its articulation relies on complex movements of the jaw and the muscles surrounding it.However,the accurate and real-time acquisition and decoding of these movements into reliable silent speech signals remains a significant challenge.In this work,we propose a real-time silent speech recognition system,which integrates a triboelectric nanogenerator-based flexible pressure sensor(FPS)with a deep learning framework.The FPS employs a porous pyramid-structured silicone film as the negative triboelectric layer,enabling highly sensitive pressure detection in the low-force regime(1 V N^(-1) for 0-10 N and 4.6 V N^(-1) for 10-24 N).This allows it to precisely capture jaw movements during speech and convert them into electrical signals.To decode the signals,we proposed a convolutional neural networklong short-term memory(CNN-LSTM)hybrid network,combining CNN and LSTM model to extract both local spatial features and temporal dynamics.The model achieved 95.83%classification accuracy in 30 categories of daily words.Furthermore,the decoded silent speech signals can be directly translated into executable commands for contactless and precise control of the smartphone.The system can also be connected to AR glasses,offering a novel human-machine interaction approach with promising potential in AR/VR applications.
基金supported in part by the National Natural Science Foundation of China(U181321461773369+2 种基金61903360)the Selfplanned Project of the State Key Laboratory of Robotics(2020-Z12)China Postdoctoral Science Foundation funded project(2019M661155)。
文摘Electromyography(EMG)has already been broadly used in human-machine interaction(HMI)applications.Determining how to decode the information inside EMG signals robustly and accurately is a key problem for which we urgently need a solution.Recently,many EMG pattern recognition tasks have been addressed using deep learning methods.In this paper,we analyze recent papers and present a literature review describing the role that deep learning plays in EMG-based HMI.An overview of typical network structures and processing schemes will be provided.Recent progress in typical tasks such as movement classification,joint angle prediction,and force/torque estimation will be introduced.New issues,including multimodal sensing,inter-subject/inter-session,and robustness toward disturbances will be discussed.We attempt to provide a comprehensive analysis of current research by discussing the advantages,challenges,and opportunities brought by deep learning.We hope that deep learning can aid in eliminating factors that hinder the development of EMG-based HMI systems.Furthermore,possible future directions will be presented to pave the way for future research.
基金The National Natural Science Foundation of China(No.62173251)the Guangdong Provincial Key Laboratory of Intelligent Decision and Cooperative Control,the Fundamental Research Funds for the Central Universities.
文摘To improve the training efficiency and recommendation accuracy in cold-start interactive recommendation systems,a new graph structure called item similarity graph is proposed on the basis of real data from a public dataset.The proposed graph is built from collaborative interactions and a deep reinforcement learning-based graph-enhanced neural interactive collaborative filtering(GE-ICF)model.The GE-ICF framework is developed with a deep reinforcement learning framework and comprises an embedding propagation layer designed with graph neural networks.Extensive experiments are conducted to investigate the efficiency of the proposed graph structure and the superiority of the proposed GE-ICF framework.Results show that in cold-start interactive recommendation systems,the proposed item similarity graph performs well in data relationship modeling,with the training efficiency showing significant improvement.The proposed GE-ICF framework also demonstrates superiority in decision modeling,thereby increasing the recommendation accuracy remarkably.
基金support of Spea Ingegneria Europea SpA and Società Autostrade per l’Italia SpA
文摘This paper describes the interaction between deep-seated landslides and man-made structures such as dams, penstocks, viaducts, and tunnels. Selected case studies are reported first with the intent to gain insights into the complexities associated with the interaction of these structures with deep-seated landslides(generally referred to as deep-seated gravity slope deformations, DSGSDs). The main features, which characterize these landslides, are mentioned together with the interaction problems encountered in each case. Given the main objective of this paper, the numerical modeling methods adopted are outlined as means for increase in the understanding of the interaction problems being investigated. With the above in mind, the attention moves to an important and unique case history dealing with the interaction of a large-size twin-tunnel excavated with an earth pressure balance(EPB)tunnel boring machine(TBM) and a deep-seated landslide, which was reactivated due to the stress changes induced by tunnel excavation in landslide shear zone. The geological and geotechnical conditions are described together with the available monitoring data on the landslide movements, based on the advanced and conventional monitoring tools used. Numerical modeling is illustrated as an aid to back-analyze the monitored surface and subsurface deformations and to assist in finding the appropriate engineering solution for putting the tunnel into service and as a follow-up means for future understanding and control of the interaction problems. The simulation is based on a novel time-dependent model representing the landslide behavior.
基金The Research Program on Climate Change Adaptation(RECCA)of the Ministry of Education,Culture,Sports,Science and Technology(MEXT)of Japan
文摘In this study the structure and seasonal variations of deep mean circulation in the East/lapan Sea （E/S） were numerically simulated using a mid-resolution ocean general circulation model with two different parameterizations for the eddy-topography interaction （ETI）. The strong deep mean circulations observed in the EIS are well reproduced when using the ETI parameterizations. The seasonal variability in the EIS deep layer is shown by using ETI parameterization based on the potential vorticity approach, while it is not shown in the statistical dynamical parameterization. The driving mechanism of the strong deep mean currents in the E/S are discussed by investigating the effects of model grids and parameterizations. The deep mean circulation is more closely related to the baroclinic process and potential vorticity than it is to the wind driven circulation.
基金the support from the University Transportation Center for Underground Transportation Infrastructure at the Colorado School of Mines for partially funding this research under Grant No. 69A3551747118 of the Fixing America's Surface Transportation Act (FAST Act) of U.S. DoT FY2016
文摘Explicit solution techniques have been widely used in geotechnical engineering for simulating the coupled hydro-mechanical(H-M) interaction of fluid flow and deformation induced by structures built above and under saturated ground, i.e. circular footing and deep tunnel. However, the technique is only conditionally stable and requires small time steps, portending its inefficiency for simulating large-scale H-M problems. To improve its efficiency, the unconditionally stable alternating direction explicit(ADE)scheme could be used to solve the flow problem. The standard ADE scheme, however, is only moderately accurate and is restricted to uniform grids and plane strain flow conditions. This paper aims to remove these drawbacks by developing a novel high-order ADE scheme capable of solving flow problems in nonuniform grids and under axisymmetric conditions. The new scheme is derived by performing a fourthorder finite difference(FD) approximation to the spatial derivatives of the axisymmetric fluid-diffusion equation in a non-uniform grid configuration. The implicit Crank-Nicolson technique is then applied to the resulting approximation, and the subsequent equation is split into two alternating direction sweeps,giving rise to a new axisymmetric ADE scheme. The pore pressure solutions from the new scheme are then sequentially coupled with an existing geomechanical simulator in the computer code fast Lagrangian analysis of continua(FLAC). This coupling procedure is called the sequentially-explicit coupling technique based on the fourth-order axisymmetric ADE scheme or SEA-4-AXI. Application of SEA-4-AXI for solving axisymmetric consolidation of a circular footing and of advancing tunnel in deep saturated ground shows that SEA-4-AXI reduces computer runtime up to 42%-50% that of FLAC’s basic scheme without numerical instability. In addition, it produces high numerical accuracy of the H-M solutions with average percentage difference of only 0.5%-1.8%.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.RS-2023-00218176)and the Soonchunhyang University Research Fund.
文摘Human Interaction Recognition(HIR)was one of the challenging issues in computer vision research due to the involvement of multiple individuals and their mutual interactions within video frames generated from their movements.HIR requires more sophisticated analysis than Human Action Recognition(HAR)since HAR focuses solely on individual activities like walking or running,while HIR involves the interactions between people.This research aims to develop a robust system for recognizing five common human interactions,such as hugging,kicking,pushing,pointing,and no interaction,from video sequences using multiple cameras.In this study,a hybrid Deep Learning(DL)and Machine Learning(ML)model was employed to improve classification accuracy and generalizability.The dataset was collected in an indoor environment with four-channel cameras capturing the five types of interactions among 13 participants.The data was processed using a DL model with a fine-tuned ResNet(Residual Networks)architecture based on 2D Convolutional Neural Network(CNN)layers for feature extraction.Subsequently,machine learning models were trained and utilized for interaction classification using six commonly used ML algorithms,including SVM,KNN,RF,DT,NB,and XGBoost.The results demonstrate a high accuracy of 95.45%in classifying human interactions.The hybrid approach enabled effective learning,resulting in highly accurate performance across different interaction types.Future work will explore more complex scenarios involving multiple individuals based on the application of this architecture.
文摘Nowadays,smart healthcare and biomedical research have marked a substantial growth rate in terms of their presence in the literature,computational approaches,and discoveries,owing to which a massive quantity of experimental datasets was published and generated(Big Data)for describing and validating such novelties.Drug-drug interaction(DDI)significantly contributed to drug administration and development.It continues as the main obstacle in offering inexpensive and safe healthcare.It normally happens for patients with extensive medication,leading them to take many drugs simultaneously.DDI may cause side effects,either mild or severe health problems.This reduced victims’quality of life and increased hospital healthcare expenses by increasing their recovery time.Several efforts were made to formulate new methods for DDI prediction to overcome this issue.In this aspect,this study designs a new Spotted Hyena Optimizer Driven Deep Learning based Drug-Drug Interaction Prediction(SHODL-DDIP)model in a big data environment.In the presented SHODL-DDIP technique,the relativity and characteristics of the drugs can be identified from different sources for prediction.The input data is preprocessed at the primary level to improve its quality.Next,the salp swarm optimization algorithm(SSO)is used to select features.In this study,the deep belief network(DBN)model is exploited to predict the DDI accurately.The SHO algorithm is involved in improvising the DBN model’s predictive outcomes,showing the novelty of the work.The experimental result analysis of the SHODL-DDIP technique is tested using drug databases,and the results signified the improvements of the SHODLDDIP technique over other recent models in terms of different performance measures.
基金support from the National Natural Science Foundation of China(Nos.52120105007,51834010)the National Science Fund for Distinguished Young Scholars(No.52222403).
文摘Fracturing fluid property play a critical role in developing unconventional reservoirs.Deep eutectic solvents(DESs)show fascinating potential for property improvement of clean fracturing fluids(CFFs)due to their low-price,low-toxicity,chemical stability and flexible designability.In this work,DESs were synthesized by mixing hydrogen bond acceptors(HBAs)and a given hydrogen bond donor(HBD)to explore their underlying influence on CFF properties based on the intermolecular interactions.The hydrogen-bonding,van der Waals and electrostatic interactions between DES components and surfactants improved the CFF properties by promoting the arrangement of surfactants at interface and enhancing the micelle network strength.The HBD enhanced the resistance of CFF for Ca^(2+) due to coordination-bonding interaction.The DESs composed of choline chloride(ChCl)and malonic acid show great enhancement for surface,rheology,temperature resistance,salt tolerance,drag reduction,and gel-breaking performance of CFFs.The DESs also improved the gel-breaking CFF-oil interactions,increasing the imbibition efficiencies to 44.2%in 74 h.Adjusting HBAs can effectively strengthen the intermolecular interactions(e.g.,HBA-surfactant and HBD-surfactant interactions)to improve CFF properties.The DESs developed in this study provide a novel strategy to intensify CFF properties.
基金funded by the National Natural Science Foundation of China (No. 52304133)the National Key R&D Program of China (No. 2022YFC3004605)the Department of Science and Technology of Liaoning Province (No. 2023-BS-083)。
文摘Rockbursts, which mainly affect mining roadways, are dynamic disasters arising from the surrounding rock under high stress. Understanding the interaction between supports and the surrounding rock is necessary for effective rockburst control. In this study, the squeezing behavior of the surrounding rock is analyzed in rockburst roadways, and a mechanical model of rockbursts is established considering the dynamic support stress, thus deriving formulas and providing characteristic curves for describing the interaction between the support and surrounding rock. Design principles and parameters of supports for rockburst control are proposed. The results show that only when the geostress magnitude exceeds a critical value can it drive the formation of rockburst conditions. The main factors influencing the convergence response and rockburst occurrence around roadways are geostress, rock brittleness, uniaxial compressive strength, and roadway excavation size. Roadway support devices can play a role in controlling rockburst by suppressing the squeezing evolution of the surrounding rock towards instability points of rockburst. Further, the higher the strength and the longer the impact stroke of support devices with constant resistance, the more easily multiple balance points can be formed with the surrounding rock to control rockburst occurrence. Supports with long impact stroke allow adaptation to varying geostress levels around the roadway, aiding in rockburst control. The results offer a quantitative method for designing support systems for rockburst-prone roadways. The design criterion of supports is determined by the intersection between the convergence curve of the surrounding rock and the squeezing deformation curve of the support devices.
基金supported by grants from the National Natural Science Foundation of China(Grant No.:T2341008)Intelligent and Precise Research on TCM for Spleen and Stomach Diseases(20233930063).
文摘Drug development remains a critical issue in the field of biomedicine.With the rapid advancement of information technologies such as artificial intelligence(AI)and the advent of the big data era,AI-assisted drug development has become a new trend,particularly in predicting drug-target associations.To address the challenge of drug-target prediction,AI-driven models have emerged as powerful tools,offering innovative solutions by effectively extracting features from complex biological data,accurately modeling molecular interactions,and precisely predicting potential drug-target outcomes.Traditional machine learning(ML),network-based,and advanced deep learning architectures such as convolutional neural networks(CNNs),graph convolutional networks(GCNs),and transformers play a pivotal role.This review systematically compiles and evaluates AI algorithms for drug-and drug combination-target predictions,highlighting their theoretical frameworks,strengths,and limitations.CNNs effectively identify spatial patterns and molecular features critical for drug-target interactions.GCNs provide deep insights into molecular interactions via relational data,whereas transformers increase prediction accuracy by capturing complex dependencies within biological sequences.Network-based models offer a systematic perspective by integrating diverse data sources,and traditional ML efficiently handles large datasets to improve overall predictive accuracy.Collectively,these AI-driven methods are transforming drug-target predictions and advancing the development of personalized therapy.This review summarizes the application of AI in drug development,particularly in drug-target prediction,and offers recommendations on models and algorithms for researchers engaged in biomedical research.It also provides typical cases to better illustrate how AI can further accelerate development in the fields of biomedicine and drug discovery.
文摘Impressive advancements and novel techniques have been witnessed in AI-based Human Intelligent-Things Interaction(HITI)systems.Several technological breakthroughs have contributed to HITI,such as Internet of Things(IoT),deep and edge learning for deducing intelligence,and 6G for ultra-fast and ultralow-latency communication between cyber-physical HITI systems.However,human-AI teaming presents several challenges that are yet to be addressed,despite the many advancements that have been made towards human-AI teaming.Allowing human stakeholders to understand AI’s decision-making process is a novel challenge.Artificial Intelligence(AI)needs to adopt diversified human understandable features,such as ethics,non-biases,trustworthiness,explainability,safety guarantee,data privacy,system security,and auditability.While adopting these features,high system performance should be maintained,and transparent processing involved in the‘human intelligent-things teaming’should be conveyed.To this end,we introduce the fusion of four key technologies,namely an ensemble of deep learning,6G,IoT,and corresponding security/privacy techniques to support HITI.This paper presents a framework that integrates the aforementioned four key technologies to support AI-based Human Intelligent-Things Interaction.Additionally,this paper demonstrates two security applications as proof of the concept,namely intelligent smart city surveillance and handling emergency services.The paper proposes to fuse four key technologies(deep learning,6G,IoT,and security and privacy techniques)to support Human Intelligent-Things interaction,applying the proposed framework to two security applications(surveillance and emergency handling).In this research paper,we will present a comprehensive review of the existing techniques of fusing security and privacy within future HITI applications.Moreover,we will showcase two security applications as proof of concept that use the fusion of the four key technologies to offer next-generation HITI services,namely intelligent smart city surveillance and handling emergency services.This proposed research outcome is envisioned to democratize the use of AI within smart city surveillance applications.
文摘With the growing application of intelligent robots in service,manufacturing,and medical fields,efficient and natural interaction between humans and robots has become key to improving collaboration efficiency and user experience.Gesture recognition,as an intuitive and contactless interaction method,can overcome the limitations of traditional interfaces and enable real-time control and feedback of robot movements and behaviors.This study first reviews mainstream gesture recognition algorithms and their application on different sensing platforms(RGB cameras,depth cameras,and inertial measurement units).It then proposes a gesture recognition method based on multimodal feature fusion and a lightweight deep neural network that balances recognition accuracy with computational efficiency.At system level,a modular human-robot interaction architecture is constructed,comprising perception,decision,and execution layers,and gesture commands are transmitted and mapped to robot actions in real time via the ROS communication protocol.Through multiple comparative experiments on public gesture datasets and a self-collected dataset,the proposed method’s superiority is validated in terms of accuracy,response latency,and system robustness,while user-experience tests assess the interface’s usability.The results provide a reliable technical foundation for robot collaboration and service in complex scenarios,offering broad prospects for practical application and deployment.
基金supported by the National Key Research and Development Program of China(Grant No.:2023YFC2605002)the National Key R&D Program of China(Grant No.:2022YFF1203003)+2 种基金Beijing AI Health Cultivation Project,China(Grant No.:Z221100003522022)the National Natural Science Foundation of China(Grant No.:82273772)the Beijing Natural Science Foundation,China(Grant No.:7212152).
文摘Accurate prediction of drug responses in cancer cell lines(CCLs)and transferable prediction of clinical drug responses using CCLs are two major tasks in personalized medicine.Despite the rapid advancements in existing computational methods for preclinical and clinical cancer drug response(CDR)prediction,challenges remain regarding the generalization of new drugs that are unseen in the training set.Herein,we propose a multimodal fusion deep learning(DL)model called drug-target and single-cell language based CDR(DTLCDR)to predict preclinical and clinical CDRs.The model integrates chemical descriptors,molecular graph representations,predicted protein target profiles of drugs,and cell line expression profiles with general knowledge from single cells.Among these features,a well-trained drug-target interaction(DTI)prediction model is used to generate target profiles of drugs,and a pretrained single-cell language model is integrated to provide general genomic knowledge.Comparison experiments on the cell line drug sensitivity dataset demonstrated that DTLCDR exhibited improved generalizability and robustness in predicting unseen drugs compared with previous state-of-the-art baseline methods.Further ablation studies verified the effectiveness of each component of our model,highlighting the significant contribution of target information to generalizability.Subsequently,the ability of DTLCDR to predict novel molecules was validated through in vitro cell experiments,demonstrating its potential for real-world applications.Moreover,DTLCDR was transferred to the clinical datasets,demonstrating satisfactory performance in the clinical data,regardless of whether the drugs were included in the cell line dataset.Overall,our results suggest that the DTLCDR is a promising tool for personalized drug discovery.
文摘This study introduces a Transformer-based multimodal fusion framework for simulating multiphase flow and heat transfer in carbon dioxide(CO_(2))–water enhanced geothermal systems(EGS).The model integrates geological parameters,thermal gradients,and control schedules to enable fast and accurate prediction of complex reservoir dynamics.The main contributions are:(i)development of a workflow that couples physics-based reservoir simulation with a Transformer neural network architecture,(ii)design of physics-guided loss functions to enforce conservation of mass and energy,(iii)application of the surrogate model to closed-loop optimization using a differential evolution(DE)algorithm,and(iv)incorporation of economic performance metrics,such as net present value(NPV),into decision support.The proposed framework achieves root mean square error(RMSE)of 3–5%,mean absolute error(MAE)below 4%,and coefficients of determination greater than 0.95 across multiple prediction targets,including production rates,pressure distributions,and temperature fields.When compared with recurrent neural network(RNN)baselines such as gated recurrent units(GRU)and long short-term memory networks(LSTM),as well as a physics-informed reduced-order model,the Transformer-based approach demonstrates superior accuracy and computational efficiency.Optimization experiments further show a 15–20%improvement in NPV,highlighting the framework’s potential for real-time forecasting,optimization,and decision-making in geothermal reservoir engineering.
