The precise identification of quartz minerals is crucial in mineralogy and geology due to their widespread occurrence and industrial significance.Traditional methods of quartz identification in thin sections are labor...The precise identification of quartz minerals is crucial in mineralogy and geology due to their widespread occurrence and industrial significance.Traditional methods of quartz identification in thin sections are labor-intensive and require significant expertise,often complicated by the coexistence of other minerals.This study presents a novel approach leveraging deep learning techniques combined with hyperspectral imaging to automate the identification process of quartz minerals.The utilizied four advanced deep learning models—PSPNet,U-Net,FPN,and LinkNet—has significant advancements in efficiency and accuracy.Among these models,PSPNet exhibited superior performance,achieving the highest intersection over union(IoU)scores and demonstrating exceptional reliability in segmenting quartz minerals,even in complex scenarios.The study involved a comprehensive dataset of 120 thin sections,encompassing 2470 hyperspectral images prepared from 20 rock samples.Expert-reviewed masks were used for model training,ensuring robust segmentation results.This automated approach not only expedites the recognition process but also enhances reliability,providing a valuable tool for geologists and advancing the field of mineralogical analysis.展开更多
This study proposes an automatic control system for Autonomous Underwater Vehicle(AUV)docking,utilizing a digital twin(DT)environment based on the HoloOcean platform,which integrates six-degree-of-freedom(6-DOF)motion...This study proposes an automatic control system for Autonomous Underwater Vehicle(AUV)docking,utilizing a digital twin(DT)environment based on the HoloOcean platform,which integrates six-degree-of-freedom(6-DOF)motion equations and hydrodynamic coefficients to create a realistic simulation.Although conventional model-based and visual servoing approaches often struggle in dynamic underwater environments due to limited adaptability and extensive parameter tuning requirements,deep reinforcement learning(DRL)offers a promising alternative.In the positioning stage,the Twin Delayed Deep Deterministic Policy Gradient(TD3)algorithm is employed for synchronized depth and heading control,which offers stable training,reduced overestimation bias,and superior handling of continuous control compared to other DRL methods.During the searching stage,zig-zag heading motion combined with a state-of-the-art object detection algorithm facilitates docking station localization.For the docking stage,this study proposes an innovative Image-based DDPG(I-DDPG),enhanced and trained in a Unity-MATLAB simulation environment,to achieve visual target tracking.Furthermore,integrating a DT environment enables efficient and safe policy training,reduces dependence on costly real-world tests,and improves sim-to-real transfer performance.Both simulation and real-world experiments were conducted,demonstrating the effectiveness of the system in improving AUV control strategies and supporting the transition from simulation to real-world operations in underwater environments.The results highlight the scalability and robustness of the proposed system,as evidenced by the TD3 controller achieving 25%less oscillation than the adaptive fuzzy controller when reaching the target depth,thereby demonstrating superior stability,accuracy,and potential for broader and more complex autonomous underwater tasks.展开更多
The increased interest in geothermal energy is evident,along with the exploitation of traditional hydrothermal systems,in the growing research and projects developing around the reuse of already-drilled oil,gas,and ex...The increased interest in geothermal energy is evident,along with the exploitation of traditional hydrothermal systems,in the growing research and projects developing around the reuse of already-drilled oil,gas,and exploration wells.The Republic of Croatia has around 4000 wells,however,due to a long period since most of these wells were drilled and completed,there is uncertainty about how many are available for retrofitting as deep-borehole heat exchangers.Nevertheless,as hydrocarbon production decreases,it is expected that the number of wells available for the revitalization and exploitation of geothermal energy will increase.The revitalization of wells via deep-borehole heat exchangers involves installing a coaxial heat exchanger and circulating the working fluid in a closed system,during which heat is transferred from the surrounding rock medium to the circulating fluid.Since drilled wells are not of uniformdepth and are located in areas with different thermal rock properties and geothermal gradients,an analysis was conducted to determine available thermal energy as a function of well depth,geothermal gradient,and circulating fluid flow rate.Additionally,an economic analysis was performed to determine the benefits of retrofitting existing assets,such as drilled wells,compared to drilling new wells to obtain the same amount of thermal energy.展开更多
At present,energy consumption is one of the main bottlenecks in autonomous mobile robot development.To address the challenge of high energy consumption in path planning for autonomous mobile robots navigating unknown ...At present,energy consumption is one of the main bottlenecks in autonomous mobile robot development.To address the challenge of high energy consumption in path planning for autonomous mobile robots navigating unknown and complex environments,this paper proposes an Attention-Enhanced Dueling Deep Q-Network(ADDueling DQN),which integrates a multi-head attention mechanism and a prioritized experience replay strategy into a Dueling-DQN reinforcement learning framework.A multi-objective reward function,centered on energy efficiency,is designed to comprehensively consider path length,terrain slope,motion smoothness,and obstacle avoidance,enabling optimal low-energy trajectory generation in 3D space from the source.The incorporation of a multihead attention mechanism allows the model to dynamically focus on energy-critical state features—such as slope gradients and obstacle density—thereby significantly improving its ability to recognize and avoid energy-intensive paths.Additionally,the prioritized experience replay mechanism accelerates learning from key decision-making experiences,suppressing inefficient exploration and guiding the policy toward low-energy solutions more rapidly.The effectiveness of the proposed path planning algorithm is validated through simulation experiments conducted in multiple off-road scenarios.Results demonstrate that AD-Dueling DQN consistently achieves the lowest average energy consumption across all tested environments.Moreover,the proposed method exhibits faster convergence and greater training stability compared to baseline algorithms,highlighting its global optimization capability under energy-aware objectives in complex terrains.This study offers an efficient and scalable intelligent control strategy for the development of energy-conscious autonomous navigation systems.展开更多
Rock residual strength,as an important input parameter,plays an indispensable role in proposing the reasonable and scientific scheme about stope design,underground tunnel excavation and stability evaluation of deep ch...Rock residual strength,as an important input parameter,plays an indispensable role in proposing the reasonable and scientific scheme about stope design,underground tunnel excavation and stability evaluation of deep chambers.Therefore,previous residual strength models of rocks established were reviewed.And corresponding related problems were stated.Subsequently,starting from the effects of bedding and whole life-cycle evolution process,series of triaxial mechanical tests of deep bedded sandstone with five bedding angles were conducted under different confining pressures.Then,six residual strength models considering the effects of bedding and whole life-cycle evolution process were established and evaluated.Finally,a cohesion loss model for determining residual strength of deep bedded sandstone was verified.The results showed that the effects of bedding and whole life-cycle evolution process had both significant influences on the evolution characteristic of residual strength of deep bedded sandstone.Additionally,residual strength parameters:residual cohesion and residual internal friction angle of deep bedded sandstone were not constant,which both significantly changed with increasing bedding angle.Besides,the cohesion loss model was the most suitable for determining and estimating the residual strength of bedded rocks,which could provide more accurate theoretical guidance for the stability control of deep chambers.展开更多
Recently, deep eutectic solvents (DES) have received great attention in assisting water flooding and surfactant flooding to improve oil recovery because they can reduce the interfacial tension (IFT) between oil and wa...Recently, deep eutectic solvents (DES) have received great attention in assisting water flooding and surfactant flooding to improve oil recovery because they can reduce the interfacial tension (IFT) between oil and water, inhibit surfactant adsorption, and change the wettability of rock. However, the effects of DES on the wettability of rock surface have not been thoroughly investigated in the reported studies. In this study, the effects of various DES samples on the wettability of sandstone samples are investigated using the Amott wettability measurement method. Three DES samples and several DES solutions and DES-surfactant solutions are firstly synthesized. Then, the wettability of the sandstone samples is measured using pure saline water, DES solutions, and DES-surfactant solutions, respectively. The effects of the DES samples on the wettability of the sandstone samples are investigated by comparing the measured wettability parameters, including oil displacement ratio (I_(o)), water displacement ratio (I_(w)), and wettability index (I_(A)). The Berea rock sample used in this study is weakly hydrophilic with I_(o), I_(w), and I_(A) of 0.318, 0.032, and 0.286, respectively. Being processed by the prepared DES samples, the wettability of the Berea sandstone samples is altered to hydrophilic (0.7 > I_(A) > 0.3) by increasing I_(w) but lowering Io. Similarly, DES-surfactant solutions can also modify the wettability of the Berea sandstone samples from weakly hydrophilic to hydrophilic. However, some DES-surfactant solutions can not only increase I_(w) but also increase I_(o), suggesting that the lipophilicity of those sandstone samples will be improved by the DES-surfactant solutions. In addition, micromodel flooding tests confirm the promising performance of a DES-surfactant solution in improving oil recovery and altering wettability. Moreover, the possible mechanisms of DES and DES-surfactant solutions in altering the wettability of the Berea sandstone samples are proposed. DES samples may improve the hydrophilicity by forming hydrogen bonds between rock surface and water molecules. For DES-surfactant solutions, surfactant micelles can capture oil molecules to improve the lipophilicity of those sandstone samples.展开更多
Strong tectonic activities and diagenetic evolution encourage the development of natural fractures as typical features in deep tight sandstone reservoirs of foreland thrust belts.This study focused on the Jurassic in ...Strong tectonic activities and diagenetic evolution encourage the development of natural fractures as typical features in deep tight sandstone reservoirs of foreland thrust belts.This study focused on the Jurassic in the southern Junggar Basin to comprehensively analyze the fracture characteristics and differential distribution and,ultimately,addressed the controlling mechanisms of tectonism and diagenesis on fracture effectiveness.Results revealed that the intensity of tectonic activities determines the complexity of tectonic fracture systems to create various fracture orientations when they have been stronger.The intense tectonic deformation would impact the stratum occurrence,which results in a wide range of fracture dip angles.Moreover,as the intensity of tectonic activities and deformations weakens,the scale and degree of tectonic fractures would decrease continuously.The control of tectonism on fracture effectiveness is reflected in the notable variations in the filling of multiple group fractures developed during different tectonic activity periods.Fractures formed in the early stages are more likely to be filled with minerals,causing their effectiveness to deteriorate significantly.Additionally,the strong cementation in the diagenetic evolution can cause more fractures to be filled with minerals and become barriers to fluid flow,which is detrimental to fracture effectiveness.However,dissolution is beneficial in improving their effectiveness by increasing fracture aperture and their connectivity to the pores.These insights can refine the development pattern of natural fractures and contribute to revealing the evolutionary mechanisms of fracture effectiveness in deep tight sandstone reservoirs of foreland thrust belts.展开更多
One of the pathways to attain NET ZERO is CO_(2)injection into deep saline aquifers(DSAs),which alters the saturation and pore pressure of the reservoir rocks,hence the effective stress,sʹ.This,in turn,would change th...One of the pathways to attain NET ZERO is CO_(2)injection into deep saline aquifers(DSAs),which alters the saturation and pore pressure of the reservoir rocks,hence the effective stress,sʹ.This,in turn,would change their geomechanical(i.e.peak deviatoric stress,elastic modulus,Poisson's ratio)and petrophysical(porosity and permeability)properties.Such a situation might trigger geo-hazards,like induced seismicity,ground deformation,caprock failure.Hence,reducing the risk of such hazards necessitates quantifying the spatial and temporal changes in sʹ,under specific CO_(2)and/or brine saturation,designated as S_(CO2)and S_(b),respectively,and resultant pore pressure.With this in view,a conceptual model depicting the reservoir,demarcated by five zones based on variations in saturation,pore-pressure,temperature,etc.,and the corresponding effective stress equations have been proposed based on the available literature.Furthermore,a critical review of literature has been carried out to decipher the limitations and contradictions associated with the findings from(i)laboratory studies to estimate S_(CO2)employing pwave velocity and electrical resistivity,(ii)analytical and numerical approaches for estimating the variation of pore-pressure in the reservoir rocks,and(iii)laboratory studies on variation in geomechanical and petrophysical properties under the conditions representative of the above-mentioned zones of the conceptual model.The authors consider that extensive experiments should be conducted on the rocks from different sources and tested under various conditions of the CO_(2)injection to validate the proposed model for the execution of risk-free CO_(2)storage in DSAs.展开更多
With the rapid development of modern information technology,the Internet of Things(IoT)has been integrated into various fields such as social life,industrial production,education,and medical care.Through the connectio...With the rapid development of modern information technology,the Internet of Things(IoT)has been integrated into various fields such as social life,industrial production,education,and medical care.Through the connection of various physical devices,sensors,and machines,it realizes information intercommunication and remote control among devices,significantly enhancing the convenience and efficiency of work and life.However,the rapid development of the IoT has also brought serious security problems.IoT devices have limited resources and a complex network environment,making them one of the important targets of network intrusion attacks.Therefore,from the perspective of deep learning,this paper deeply analyzes the characteristics and key points of IoT intrusion detection,summarizes the application advantages of deep learning in IoT intrusion detection,and proposes application strategies of typical deep learning models in IoT intrusion detection so as to improve the security of the IoT architecture and guarantee people’s convenient lives.展开更多
With the development of the future Web of Healthcare Things(WoHT),there will be a trend of densely deploying medical sensors with massive simultaneous online communication requirements.The dense deployment and simulta...With the development of the future Web of Healthcare Things(WoHT),there will be a trend of densely deploying medical sensors with massive simultaneous online communication requirements.The dense deployment and simultaneous online communication of massive medical sensors will inevitably generate overlapping interference.This will be extremely challenging to support data transmission at the medical-grade quality of service level.To handle the challenge,this paper proposes a hypergraph interference coordination-aided resource allocation based on the Deep Reinforcement Learning(DRL)method.Specifically,we build a novel hypergraph interference model for the considered WoHT by analyzing the impact of the overlapping interference.Due to the high complexity of directly solving the hypergraph interference model,the original resource allocation problem is converted into a sequential decision-making problem through the Markov Decision Process(MDP)modeling method.Then,a policy and value-based resource allocation algorithm is proposed to solve this problem under simultaneous online communication and dense deployment.In addition,to enhance the exploration ability of the optimal allocation strategy for the agent,we propose a resource allocation algorithm with an asynchronous parallel architecture.Simulation results verify that the proposed algorithms can achieve higher network throughput than the existing algorithms in the considered WoHT scenario.展开更多
Efficient resource management within Internet of Things(IoT)environments remains a pressing challenge due to the increasing number of devices and their diverse functionalities.This study introduces a neural network-ba...Efficient resource management within Internet of Things(IoT)environments remains a pressing challenge due to the increasing number of devices and their diverse functionalities.This study introduces a neural network-based model that uses Long-Short-Term Memory(LSTM)to optimize resource allocation under dynam-ically changing conditions.Designed to monitor the workload on individual IoT nodes,the model incorporates long-term data dependencies,enabling adaptive resource distribution in real time.The training process utilizes Min-Max normalization and grid search for hyperparameter tuning,ensuring high resource utilization and consistent performance.The simulation results demonstrate the effectiveness of the proposed method,outperforming the state-of-the-art approaches,including Dynamic and Efficient Enhanced Load-Balancing(DEELB),Optimized Scheduling and Collaborative Active Resource-management(OSCAR),Convolutional Neural Network with Monarch Butterfly Optimization(CNN-MBO),and Autonomic Workload Prediction and Resource Allocation for Fog(AWPR-FOG).For example,in scenarios with low system utilization,the model achieved a resource utilization efficiency of 95%while maintaining a latency of just 15 ms,significantly exceeding the performance of comparative methods.展开更多
Wearable sensors integrated with deep learning techniques have the potential to revolutionize seamless human-machine interfaces for real-time health monitoring,clinical diagnosis,and robotic applications.Nevertheless,...Wearable sensors integrated with deep learning techniques have the potential to revolutionize seamless human-machine interfaces for real-time health monitoring,clinical diagnosis,and robotic applications.Nevertheless,it remains a critical challenge to simultaneously achieve desirable mechanical and electrical performance along with biocompatibility,adhesion,self-healing,and environmental robustness with excellent sensing metrics.Herein,we report a multifunctional,anti-freezing,selfadhesive,and self-healable organogel pressure sensor composed of cobalt nanoparticle encapsulated nitrogen-doped carbon nanotubes(CoN CNT)embedded in a polyvinyl alcohol-gelatin(PVA/GLE)matrix.Fabricated using a binary solvent system of water and ethylene glycol(EG),the CoN CNT/PVA/GLE organogel exhibits excellent flexibility,biocompatibility,and temperature tolerance with remarkable environmental stability.Electrochemical impedance spectroscopy confirms near-stable performance across a broad humidity range(40%-95%RH).Freeze-tolerant conductivity under sub-zero conditions(-20℃)is attributed to the synergistic role of CoN CNT and EG,preserving mobility and network integrity.The Co N CNT/PVA/GLE organogel sensor exhibits high sensitivity of 5.75 k Pa^(-1)in the detection range from 0 to 20 k Pa,ideal for subtle biomechanical motion detection.A smart human-machine interface for English letter recognition using deep learning achieved 98%accuracy.The organogel sensor utility was extended to detect human gestures like finger bending,wrist motion,and throat vibration during speech.展开更多
Nondestructive measurement technology of phenotype can provide substantial phenotypic data support for applications such as seedling breeding,management,and quality testing.The current method of measuring seedling phe...Nondestructive measurement technology of phenotype can provide substantial phenotypic data support for applications such as seedling breeding,management,and quality testing.The current method of measuring seedling phenotypes mainly relies on manual measurement which is inefficient,subjective and destroys samples.Therefore,the paper proposes a nondestructive measurement method for the canopy phenotype of the watermelon plug seedlings based on deep learning.The Azure Kinect was used to shoot canopy color images,depth images,and RGB-D images of the watermelon plug seedlings.The Mask-RCNN network was used to classify,segment,and count the canopy leaves of the watermelon plug seedlings.To reduce the error of leaf area measurement caused by mutual occlusion of leaves,the leaves were repaired by CycleGAN,and the depth images were restored by image processing.Then,the Delaunay triangulation was adopted to measure the leaf area in the leaf point cloud.The YOLOX target detection network was used to identify the growing point position of each seedling on the plug tray.Then the depth differences between the growing point and the upper surface of the plug tray were calculated to obtain plant height.The experiment results show that the nondestructive measurement algorithm proposed in this paper achieves good measurement performance for the watermelon plug seedlings from the 1 true-leaf to 3 true-leaf stages.The average relative error of measurement is 2.33%for the number of true leaves,4.59%for the number of cotyledons,8.37%for the leaf area,and 3.27%for the plant height.The experiment results demonstrate that the proposed algorithm in this paper provides an effective solution for the nondestructive measurement of the canopy phenotype of the plug seedlings.展开更多
Effective partitioning is crucial for enabling parallel restoration of power systems after blackouts.This paper proposes a novel partitioning method based on deep reinforcement learning.First,the partitioning decision...Effective partitioning is crucial for enabling parallel restoration of power systems after blackouts.This paper proposes a novel partitioning method based on deep reinforcement learning.First,the partitioning decision process is formulated as a Markov decision process(MDP)model to maximize the modularity.Corresponding key partitioning constraints on parallel restoration are considered.Second,based on the partitioning objective and constraints,the reward function of the partitioning MDP model is set by adopting a relative deviation normalization scheme to reduce mutual interference between the reward and penalty in the reward function.The soft bonus scaling mechanism is introduced to mitigate overestimation caused by abrupt jumps in the reward.Then,the deep Q network method is applied to solve the partitioning MDP model and generate partitioning schemes.Two experience replay buffers are employed to speed up the training process of the method.Finally,case studies on the IEEE 39-bus test system demonstrate that the proposed method can generate a high-modularity partitioning result that meets all key partitioning constraints,thereby improving the parallelism and reliability of the restoration process.Moreover,simulation results demonstrate that an appropriate discount factor is crucial for ensuring both the convergence speed and the stability of the partitioning training.展开更多
This systematic review aims to comprehensively examine and compare deep learning methods for brain tumor segmentation and classification using MRI and other imaging modalities,focusing on recent trends from 2022 to 20...This systematic review aims to comprehensively examine and compare deep learning methods for brain tumor segmentation and classification using MRI and other imaging modalities,focusing on recent trends from 2022 to 2025.The primary objective is to evaluate methodological advancements,model performance,dataset usage,and existing challenges in developing clinically robust AI systems.We included peer-reviewed journal articles and highimpact conference papers published between 2022 and 2025,written in English,that proposed or evaluated deep learning methods for brain tumor segmentation and/or classification.Excluded were non-open-access publications,books,and non-English articles.A structured search was conducted across Scopus,Google Scholar,Wiley,and Taylor&Francis,with the last search performed in August 2025.Risk of bias was not formally quantified but considered during full-text screening based on dataset diversity,validation methods,and availability of performance metrics.We used narrative synthesis and tabular benchmarking to compare performance metrics(e.g.,accuracy,Dice score)across model types(CNN,Transformer,Hybrid),imaging modalities,and datasets.A total of 49 studies were included(43 journal articles and 6 conference papers).These studies spanned over 9 public datasets(e.g.,BraTS,Figshare,REMBRANDT,MOLAB)and utilized a range of imaging modalities,predominantly MRI.Hybrid models,especially ResViT and UNetFormer,consistently achieved high performance,with classification accuracy exceeding 98%and segmentation Dice scores above 0.90 across multiple studies.Transformers and hybrid architectures showed increasing adoption post2023.Many studies lacked external validation and were evaluated only on a few benchmark datasets,raising concerns about generalizability and dataset bias.Few studies addressed clinical interpretability or uncertainty quantification.Despite promising results,particularly for hybrid deep learning models,widespread clinical adoption remains limited due to lack of validation,interpretability concerns,and real-world deployment barriers.展开更多
Underwater pipeline inspection plays a vital role in the proactive maintenance and management of critical marine infrastructure and subaquatic systems.However,the inspection of underwater pipelines presents a challeng...Underwater pipeline inspection plays a vital role in the proactive maintenance and management of critical marine infrastructure and subaquatic systems.However,the inspection of underwater pipelines presents a challenge due to factors such as light scattering,absorption,restricted visibility,and ambient noise.The advancement of deep learning has introduced powerful techniques for processing large amounts of unstructured and imperfect data collected from underwater environments.This study evaluated the efficacy of the You Only Look Once(YOLO)algorithm,a real-time object detection and localization model based on convolutional neural networks,in identifying and classifying various types of pipeline defects in underwater settings.YOLOv8,the latest evolution in the YOLO family,integrates advanced capabilities,such as anchor-free detection,a cross-stage partial network backbone for efficient feature extraction,and a feature pyramid network+path aggregation network neck for robust multi-scale object detection,which make it particularly well-suited for complex underwater environments.Due to the lack of suitable open-access datasets for underwater pipeline defects,a custom dataset was captured using a remotely operated vehicle in a controlled environment.This application has the following assets available for use.Extensive experimentation demonstrated that YOLOv8 X-Large consistently outperformed other models in terms of pipe defect detection and classification and achieved a strong balance between precision and recall in identifying pipeline cracks,rust,corners,defective welds,flanges,tapes,and holes.This research establishes the baseline performance of YOLOv8 for underwater defect detection and showcases its potential to enhance the reliability and efficiency of pipeline inspection tasks in challenging underwater environments.展开更多
Deep learning-based methods have become alternatives to traditional numerical weather prediction systems,offering faster computation and the ability to utilize large historical datasets.However,the application of deep...Deep learning-based methods have become alternatives to traditional numerical weather prediction systems,offering faster computation and the ability to utilize large historical datasets.However,the application of deep learning to medium-range regional weather forecasting with limited data remains a significant challenge.In this work,three key solutions are proposed:(1)motivated by the need to improve model performance in data-scarce regional forecasting scenarios,the authors innovatively apply semantic segmentation models,to better capture spatiotemporal features and improve prediction accuracy;(2)recognizing the challenge of overfitting and the inability of traditional noise-based data augmentation methods to effectively enhance model robustness,a novel learnable Gaussian noise mechanism is introduced that allows the model to adaptively optimize perturbations for different locations,ensuring more effective learning;and(3)to address the issue of error accumulation in autoregressive prediction,as well as the challenge of learning difficulty and the lack of intermediate data utilization in one-shot prediction,the authors propose a cascade prediction approach that effectively resolves these problems while significantly improving model forecasting performance.The method achieves a competitive result in The East China Regional AI Medium Range Weather Forecasting Competition.Ablation experiments further validate the effectiveness of each component,highlighting their contributions to enhancing prediction performance.展开更多
With the growing advancement of wireless communication technologies,WiFi-based human sensing has gained increasing attention as a non-intrusive and device-free solution.Among the available signal types,Channel State I...With the growing advancement of wireless communication technologies,WiFi-based human sensing has gained increasing attention as a non-intrusive and device-free solution.Among the available signal types,Channel State Information(CSI)offers fine-grained temporal,frequency,and spatial insights into multipath propagation,making it a crucial data source for human-centric sensing.Recently,the integration of deep learning has significantly improved the robustness and automation of feature extraction from CSI in complex environments.This paper provides a comprehensive review of deep learning-enhanced human sensing based on CSI.We first outline mainstream CSI acquisition tools and their hardware specifications,then provide a detailed discussion of preprocessing methods such as denoising,time–frequency transformation,data segmentation,and augmentation.Subsequently,we categorize deep learning approaches according to sensing tasks—namely detection,localization,and recognition—and highlight representative models across application scenarios.Finally,we examine key challenges including domain generalization,multi-user interference,and limited data availability,and we propose future research directions involving lightweight model deployment,multimodal data fusion,and semantic-level sensing.展开更多
文摘The precise identification of quartz minerals is crucial in mineralogy and geology due to their widespread occurrence and industrial significance.Traditional methods of quartz identification in thin sections are labor-intensive and require significant expertise,often complicated by the coexistence of other minerals.This study presents a novel approach leveraging deep learning techniques combined with hyperspectral imaging to automate the identification process of quartz minerals.The utilizied four advanced deep learning models—PSPNet,U-Net,FPN,and LinkNet—has significant advancements in efficiency and accuracy.Among these models,PSPNet exhibited superior performance,achieving the highest intersection over union(IoU)scores and demonstrating exceptional reliability in segmenting quartz minerals,even in complex scenarios.The study involved a comprehensive dataset of 120 thin sections,encompassing 2470 hyperspectral images prepared from 20 rock samples.Expert-reviewed masks were used for model training,ensuring robust segmentation results.This automated approach not only expedites the recognition process but also enhances reliability,providing a valuable tool for geologists and advancing the field of mineralogical analysis.
基金supported by the National Science and Technology Council,Taiwan[Grant NSTC 111-2628-E-006-005-MY3]supported by the Ocean Affairs Council,Taiwansponsored in part by Higher Education Sprout Project,Ministry of Education to the Headquarters of University Advancement at National Cheng Kung University(NCKU).
文摘This study proposes an automatic control system for Autonomous Underwater Vehicle(AUV)docking,utilizing a digital twin(DT)environment based on the HoloOcean platform,which integrates six-degree-of-freedom(6-DOF)motion equations and hydrodynamic coefficients to create a realistic simulation.Although conventional model-based and visual servoing approaches often struggle in dynamic underwater environments due to limited adaptability and extensive parameter tuning requirements,deep reinforcement learning(DRL)offers a promising alternative.In the positioning stage,the Twin Delayed Deep Deterministic Policy Gradient(TD3)algorithm is employed for synchronized depth and heading control,which offers stable training,reduced overestimation bias,and superior handling of continuous control compared to other DRL methods.During the searching stage,zig-zag heading motion combined with a state-of-the-art object detection algorithm facilitates docking station localization.For the docking stage,this study proposes an innovative Image-based DDPG(I-DDPG),enhanced and trained in a Unity-MATLAB simulation environment,to achieve visual target tracking.Furthermore,integrating a DT environment enables efficient and safe policy training,reduces dependence on costly real-world tests,and improves sim-to-real transfer performance.Both simulation and real-world experiments were conducted,demonstrating the effectiveness of the system in improving AUV control strategies and supporting the transition from simulation to real-world operations in underwater environments.The results highlight the scalability and robustness of the proposed system,as evidenced by the TD3 controller achieving 25%less oscillation than the adaptive fuzzy controller when reaching the target depth,thereby demonstrating superior stability,accuracy,and potential for broader and more complex autonomous underwater tasks.
文摘The increased interest in geothermal energy is evident,along with the exploitation of traditional hydrothermal systems,in the growing research and projects developing around the reuse of already-drilled oil,gas,and exploration wells.The Republic of Croatia has around 4000 wells,however,due to a long period since most of these wells were drilled and completed,there is uncertainty about how many are available for retrofitting as deep-borehole heat exchangers.Nevertheless,as hydrocarbon production decreases,it is expected that the number of wells available for the revitalization and exploitation of geothermal energy will increase.The revitalization of wells via deep-borehole heat exchangers involves installing a coaxial heat exchanger and circulating the working fluid in a closed system,during which heat is transferred from the surrounding rock medium to the circulating fluid.Since drilled wells are not of uniformdepth and are located in areas with different thermal rock properties and geothermal gradients,an analysis was conducted to determine available thermal energy as a function of well depth,geothermal gradient,and circulating fluid flow rate.Additionally,an economic analysis was performed to determine the benefits of retrofitting existing assets,such as drilled wells,compared to drilling new wells to obtain the same amount of thermal energy.
文摘At present,energy consumption is one of the main bottlenecks in autonomous mobile robot development.To address the challenge of high energy consumption in path planning for autonomous mobile robots navigating unknown and complex environments,this paper proposes an Attention-Enhanced Dueling Deep Q-Network(ADDueling DQN),which integrates a multi-head attention mechanism and a prioritized experience replay strategy into a Dueling-DQN reinforcement learning framework.A multi-objective reward function,centered on energy efficiency,is designed to comprehensively consider path length,terrain slope,motion smoothness,and obstacle avoidance,enabling optimal low-energy trajectory generation in 3D space from the source.The incorporation of a multihead attention mechanism allows the model to dynamically focus on energy-critical state features—such as slope gradients and obstacle density—thereby significantly improving its ability to recognize and avoid energy-intensive paths.Additionally,the prioritized experience replay mechanism accelerates learning from key decision-making experiences,suppressing inefficient exploration and guiding the policy toward low-energy solutions more rapidly.The effectiveness of the proposed path planning algorithm is validated through simulation experiments conducted in multiple off-road scenarios.Results demonstrate that AD-Dueling DQN consistently achieves the lowest average energy consumption across all tested environments.Moreover,the proposed method exhibits faster convergence and greater training stability compared to baseline algorithms,highlighting its global optimization capability under energy-aware objectives in complex terrains.This study offers an efficient and scalable intelligent control strategy for the development of energy-conscious autonomous navigation systems.
基金Projects(2024YFC3013801,2022YFC3004602)supported by the National Key R&D Program of ChinaProjects(U23B2093,52034009)supported by the National Natural Science Foundation of China。
文摘Rock residual strength,as an important input parameter,plays an indispensable role in proposing the reasonable and scientific scheme about stope design,underground tunnel excavation and stability evaluation of deep chambers.Therefore,previous residual strength models of rocks established were reviewed.And corresponding related problems were stated.Subsequently,starting from the effects of bedding and whole life-cycle evolution process,series of triaxial mechanical tests of deep bedded sandstone with five bedding angles were conducted under different confining pressures.Then,six residual strength models considering the effects of bedding and whole life-cycle evolution process were established and evaluated.Finally,a cohesion loss model for determining residual strength of deep bedded sandstone was verified.The results showed that the effects of bedding and whole life-cycle evolution process had both significant influences on the evolution characteristic of residual strength of deep bedded sandstone.Additionally,residual strength parameters:residual cohesion and residual internal friction angle of deep bedded sandstone were not constant,which both significantly changed with increasing bedding angle.Besides,the cohesion loss model was the most suitable for determining and estimating the residual strength of bedded rocks,which could provide more accurate theoretical guidance for the stability control of deep chambers.
基金supported by the Scientific Research and Technology Development Projects of PetroChina(2023ZZ22-02)the Local Efficient Reform and Development Funds for Personnel Training Projectsthe China Scholarship Council(CSC)via a Ph.D.Scholarship(No.202008510128).
文摘Recently, deep eutectic solvents (DES) have received great attention in assisting water flooding and surfactant flooding to improve oil recovery because they can reduce the interfacial tension (IFT) between oil and water, inhibit surfactant adsorption, and change the wettability of rock. However, the effects of DES on the wettability of rock surface have not been thoroughly investigated in the reported studies. In this study, the effects of various DES samples on the wettability of sandstone samples are investigated using the Amott wettability measurement method. Three DES samples and several DES solutions and DES-surfactant solutions are firstly synthesized. Then, the wettability of the sandstone samples is measured using pure saline water, DES solutions, and DES-surfactant solutions, respectively. The effects of the DES samples on the wettability of the sandstone samples are investigated by comparing the measured wettability parameters, including oil displacement ratio (I_(o)), water displacement ratio (I_(w)), and wettability index (I_(A)). The Berea rock sample used in this study is weakly hydrophilic with I_(o), I_(w), and I_(A) of 0.318, 0.032, and 0.286, respectively. Being processed by the prepared DES samples, the wettability of the Berea sandstone samples is altered to hydrophilic (0.7 > I_(A) > 0.3) by increasing I_(w) but lowering Io. Similarly, DES-surfactant solutions can also modify the wettability of the Berea sandstone samples from weakly hydrophilic to hydrophilic. However, some DES-surfactant solutions can not only increase I_(w) but also increase I_(o), suggesting that the lipophilicity of those sandstone samples will be improved by the DES-surfactant solutions. In addition, micromodel flooding tests confirm the promising performance of a DES-surfactant solution in improving oil recovery and altering wettability. Moreover, the possible mechanisms of DES and DES-surfactant solutions in altering the wettability of the Berea sandstone samples are proposed. DES samples may improve the hydrophilicity by forming hydrogen bonds between rock surface and water molecules. For DES-surfactant solutions, surfactant micelles can capture oil molecules to improve the lipophilicity of those sandstone samples.
基金supported by the CNPC Innovation Found(No.2023DQ02-0103)National Major Science and Technology Projects of China(No.2016ZX05003-001).
文摘Strong tectonic activities and diagenetic evolution encourage the development of natural fractures as typical features in deep tight sandstone reservoirs of foreland thrust belts.This study focused on the Jurassic in the southern Junggar Basin to comprehensively analyze the fracture characteristics and differential distribution and,ultimately,addressed the controlling mechanisms of tectonism and diagenesis on fracture effectiveness.Results revealed that the intensity of tectonic activities determines the complexity of tectonic fracture systems to create various fracture orientations when they have been stronger.The intense tectonic deformation would impact the stratum occurrence,which results in a wide range of fracture dip angles.Moreover,as the intensity of tectonic activities and deformations weakens,the scale and degree of tectonic fractures would decrease continuously.The control of tectonism on fracture effectiveness is reflected in the notable variations in the filling of multiple group fractures developed during different tectonic activity periods.Fractures formed in the early stages are more likely to be filled with minerals,causing their effectiveness to deteriorate significantly.Additionally,the strong cementation in the diagenetic evolution can cause more fractures to be filled with minerals and become barriers to fluid flow,which is detrimental to fracture effectiveness.However,dissolution is beneficial in improving their effectiveness by increasing fracture aperture and their connectivity to the pores.These insights can refine the development pattern of natural fractures and contribute to revealing the evolutionary mechanisms of fracture effectiveness in deep tight sandstone reservoirs of foreland thrust belts.
基金The authors would like to acknowledge the grant of fellowship(DST/TMD/EWO/2K21/ACT/2021/02(G))under Project SHARP,received from the Department of Science and Technology,Government of India.
文摘One of the pathways to attain NET ZERO is CO_(2)injection into deep saline aquifers(DSAs),which alters the saturation and pore pressure of the reservoir rocks,hence the effective stress,sʹ.This,in turn,would change their geomechanical(i.e.peak deviatoric stress,elastic modulus,Poisson's ratio)and petrophysical(porosity and permeability)properties.Such a situation might trigger geo-hazards,like induced seismicity,ground deformation,caprock failure.Hence,reducing the risk of such hazards necessitates quantifying the spatial and temporal changes in sʹ,under specific CO_(2)and/or brine saturation,designated as S_(CO2)and S_(b),respectively,and resultant pore pressure.With this in view,a conceptual model depicting the reservoir,demarcated by five zones based on variations in saturation,pore-pressure,temperature,etc.,and the corresponding effective stress equations have been proposed based on the available literature.Furthermore,a critical review of literature has been carried out to decipher the limitations and contradictions associated with the findings from(i)laboratory studies to estimate S_(CO2)employing pwave velocity and electrical resistivity,(ii)analytical and numerical approaches for estimating the variation of pore-pressure in the reservoir rocks,and(iii)laboratory studies on variation in geomechanical and petrophysical properties under the conditions representative of the above-mentioned zones of the conceptual model.The authors consider that extensive experiments should be conducted on the rocks from different sources and tested under various conditions of the CO_(2)injection to validate the proposed model for the execution of risk-free CO_(2)storage in DSAs.
基金the research result of the 2022 Municipal Education Commission Science and Technology Research Plan Project“Research on the Technology of Detecting Double-Surface Cracks in Concrete Lining of Highway Tunnels Based on Image Blast”(KJQN02202403)the first batch of school-level classroom teaching reform projects“Principles Applications of Embedded Systems”(23JG2166)the school-level reform research project“Continuous Results-Oriented Practice Research Based on BOPPPS Teaching Model-Taking the‘Programming Fundamentals’Course as an Example”(22JG332).
文摘With the rapid development of modern information technology,the Internet of Things(IoT)has been integrated into various fields such as social life,industrial production,education,and medical care.Through the connection of various physical devices,sensors,and machines,it realizes information intercommunication and remote control among devices,significantly enhancing the convenience and efficiency of work and life.However,the rapid development of the IoT has also brought serious security problems.IoT devices have limited resources and a complex network environment,making them one of the important targets of network intrusion attacks.Therefore,from the perspective of deep learning,this paper deeply analyzes the characteristics and key points of IoT intrusion detection,summarizes the application advantages of deep learning in IoT intrusion detection,and proposes application strategies of typical deep learning models in IoT intrusion detection so as to improve the security of the IoT architecture and guarantee people’s convenient lives.
基金supported in part by the National Natural Science Foundation of China under Grant No.62301094in part by the Researchers Supporting Project Number(RSPD2024R681)King Saud University,Riyadh,Saudi Arabia,in part by the Science and Technology Research Program of the Chongqing Education Commission of China under Grants KJQN202201157 and KJQN202301135.
文摘With the development of the future Web of Healthcare Things(WoHT),there will be a trend of densely deploying medical sensors with massive simultaneous online communication requirements.The dense deployment and simultaneous online communication of massive medical sensors will inevitably generate overlapping interference.This will be extremely challenging to support data transmission at the medical-grade quality of service level.To handle the challenge,this paper proposes a hypergraph interference coordination-aided resource allocation based on the Deep Reinforcement Learning(DRL)method.Specifically,we build a novel hypergraph interference model for the considered WoHT by analyzing the impact of the overlapping interference.Due to the high complexity of directly solving the hypergraph interference model,the original resource allocation problem is converted into a sequential decision-making problem through the Markov Decision Process(MDP)modeling method.Then,a policy and value-based resource allocation algorithm is proposed to solve this problem under simultaneous online communication and dense deployment.In addition,to enhance the exploration ability of the optimal allocation strategy for the agent,we propose a resource allocation algorithm with an asynchronous parallel architecture.Simulation results verify that the proposed algorithms can achieve higher network throughput than the existing algorithms in the considered WoHT scenario.
基金funding of the Deanship of Graduate Studies and Scientific Research,Jazan University,Saudi Arabia,through Project Number:ISP-2024.
文摘Efficient resource management within Internet of Things(IoT)environments remains a pressing challenge due to the increasing number of devices and their diverse functionalities.This study introduces a neural network-based model that uses Long-Short-Term Memory(LSTM)to optimize resource allocation under dynam-ically changing conditions.Designed to monitor the workload on individual IoT nodes,the model incorporates long-term data dependencies,enabling adaptive resource distribution in real time.The training process utilizes Min-Max normalization and grid search for hyperparameter tuning,ensuring high resource utilization and consistent performance.The simulation results demonstrate the effectiveness of the proposed method,outperforming the state-of-the-art approaches,including Dynamic and Efficient Enhanced Load-Balancing(DEELB),Optimized Scheduling and Collaborative Active Resource-management(OSCAR),Convolutional Neural Network with Monarch Butterfly Optimization(CNN-MBO),and Autonomic Workload Prediction and Resource Allocation for Fog(AWPR-FOG).For example,in scenarios with low system utilization,the model achieved a resource utilization efficiency of 95%while maintaining a latency of just 15 ms,significantly exceeding the performance of comparative methods.
基金supported by the Basic Science Research Program(2023R1A2C3004336,RS-202300243807)&Regional Leading Research Center(RS-202400405278)through the National Research Foundation of Korea(NRF)grant funded by the Korea Government(MSIT)。
文摘Wearable sensors integrated with deep learning techniques have the potential to revolutionize seamless human-machine interfaces for real-time health monitoring,clinical diagnosis,and robotic applications.Nevertheless,it remains a critical challenge to simultaneously achieve desirable mechanical and electrical performance along with biocompatibility,adhesion,self-healing,and environmental robustness with excellent sensing metrics.Herein,we report a multifunctional,anti-freezing,selfadhesive,and self-healable organogel pressure sensor composed of cobalt nanoparticle encapsulated nitrogen-doped carbon nanotubes(CoN CNT)embedded in a polyvinyl alcohol-gelatin(PVA/GLE)matrix.Fabricated using a binary solvent system of water and ethylene glycol(EG),the CoN CNT/PVA/GLE organogel exhibits excellent flexibility,biocompatibility,and temperature tolerance with remarkable environmental stability.Electrochemical impedance spectroscopy confirms near-stable performance across a broad humidity range(40%-95%RH).Freeze-tolerant conductivity under sub-zero conditions(-20℃)is attributed to the synergistic role of CoN CNT and EG,preserving mobility and network integrity.The Co N CNT/PVA/GLE organogel sensor exhibits high sensitivity of 5.75 k Pa^(-1)in the detection range from 0 to 20 k Pa,ideal for subtle biomechanical motion detection.A smart human-machine interface for English letter recognition using deep learning achieved 98%accuracy.The organogel sensor utility was extended to detect human gestures like finger bending,wrist motion,and throat vibration during speech.
基金funded by the National Key Research and Development Program of China(Grant No.2019YFD1001900)the HZAU-AGIS Cooperation Fund(Grant No.SZYJY2022006).
文摘Nondestructive measurement technology of phenotype can provide substantial phenotypic data support for applications such as seedling breeding,management,and quality testing.The current method of measuring seedling phenotypes mainly relies on manual measurement which is inefficient,subjective and destroys samples.Therefore,the paper proposes a nondestructive measurement method for the canopy phenotype of the watermelon plug seedlings based on deep learning.The Azure Kinect was used to shoot canopy color images,depth images,and RGB-D images of the watermelon plug seedlings.The Mask-RCNN network was used to classify,segment,and count the canopy leaves of the watermelon plug seedlings.To reduce the error of leaf area measurement caused by mutual occlusion of leaves,the leaves were repaired by CycleGAN,and the depth images were restored by image processing.Then,the Delaunay triangulation was adopted to measure the leaf area in the leaf point cloud.The YOLOX target detection network was used to identify the growing point position of each seedling on the plug tray.Then the depth differences between the growing point and the upper surface of the plug tray were calculated to obtain plant height.The experiment results show that the nondestructive measurement algorithm proposed in this paper achieves good measurement performance for the watermelon plug seedlings from the 1 true-leaf to 3 true-leaf stages.The average relative error of measurement is 2.33%for the number of true leaves,4.59%for the number of cotyledons,8.37%for the leaf area,and 3.27%for the plant height.The experiment results demonstrate that the proposed algorithm in this paper provides an effective solution for the nondestructive measurement of the canopy phenotype of the plug seedlings.
基金funded by the Beijing Engineering Research Center of Electric Rail Transportation.
文摘Effective partitioning is crucial for enabling parallel restoration of power systems after blackouts.This paper proposes a novel partitioning method based on deep reinforcement learning.First,the partitioning decision process is formulated as a Markov decision process(MDP)model to maximize the modularity.Corresponding key partitioning constraints on parallel restoration are considered.Second,based on the partitioning objective and constraints,the reward function of the partitioning MDP model is set by adopting a relative deviation normalization scheme to reduce mutual interference between the reward and penalty in the reward function.The soft bonus scaling mechanism is introduced to mitigate overestimation caused by abrupt jumps in the reward.Then,the deep Q network method is applied to solve the partitioning MDP model and generate partitioning schemes.Two experience replay buffers are employed to speed up the training process of the method.Finally,case studies on the IEEE 39-bus test system demonstrate that the proposed method can generate a high-modularity partitioning result that meets all key partitioning constraints,thereby improving the parallelism and reliability of the restoration process.Moreover,simulation results demonstrate that an appropriate discount factor is crucial for ensuring both the convergence speed and the stability of the partitioning training.
文摘This systematic review aims to comprehensively examine and compare deep learning methods for brain tumor segmentation and classification using MRI and other imaging modalities,focusing on recent trends from 2022 to 2025.The primary objective is to evaluate methodological advancements,model performance,dataset usage,and existing challenges in developing clinically robust AI systems.We included peer-reviewed journal articles and highimpact conference papers published between 2022 and 2025,written in English,that proposed or evaluated deep learning methods for brain tumor segmentation and/or classification.Excluded were non-open-access publications,books,and non-English articles.A structured search was conducted across Scopus,Google Scholar,Wiley,and Taylor&Francis,with the last search performed in August 2025.Risk of bias was not formally quantified but considered during full-text screening based on dataset diversity,validation methods,and availability of performance metrics.We used narrative synthesis and tabular benchmarking to compare performance metrics(e.g.,accuracy,Dice score)across model types(CNN,Transformer,Hybrid),imaging modalities,and datasets.A total of 49 studies were included(43 journal articles and 6 conference papers).These studies spanned over 9 public datasets(e.g.,BraTS,Figshare,REMBRANDT,MOLAB)and utilized a range of imaging modalities,predominantly MRI.Hybrid models,especially ResViT and UNetFormer,consistently achieved high performance,with classification accuracy exceeding 98%and segmentation Dice scores above 0.90 across multiple studies.Transformers and hybrid architectures showed increasing adoption post2023.Many studies lacked external validation and were evaluated only on a few benchmark datasets,raising concerns about generalizability and dataset bias.Few studies addressed clinical interpretability or uncertainty quantification.Despite promising results,particularly for hybrid deep learning models,widespread clinical adoption remains limited due to lack of validation,interpretability concerns,and real-world deployment barriers.
文摘Underwater pipeline inspection plays a vital role in the proactive maintenance and management of critical marine infrastructure and subaquatic systems.However,the inspection of underwater pipelines presents a challenge due to factors such as light scattering,absorption,restricted visibility,and ambient noise.The advancement of deep learning has introduced powerful techniques for processing large amounts of unstructured and imperfect data collected from underwater environments.This study evaluated the efficacy of the You Only Look Once(YOLO)algorithm,a real-time object detection and localization model based on convolutional neural networks,in identifying and classifying various types of pipeline defects in underwater settings.YOLOv8,the latest evolution in the YOLO family,integrates advanced capabilities,such as anchor-free detection,a cross-stage partial network backbone for efficient feature extraction,and a feature pyramid network+path aggregation network neck for robust multi-scale object detection,which make it particularly well-suited for complex underwater environments.Due to the lack of suitable open-access datasets for underwater pipeline defects,a custom dataset was captured using a remotely operated vehicle in a controlled environment.This application has the following assets available for use.Extensive experimentation demonstrated that YOLOv8 X-Large consistently outperformed other models in terms of pipe defect detection and classification and achieved a strong balance between precision and recall in identifying pipeline cracks,rust,corners,defective welds,flanges,tapes,and holes.This research establishes the baseline performance of YOLOv8 for underwater defect detection and showcases its potential to enhance the reliability and efficiency of pipeline inspection tasks in challenging underwater environments.
基金supported by the National Natural Science Foundation of China[grant number 62376217]the Young Elite Scientists Sponsorship Program by CAST[grant number 2023QNRC001]the Joint Research Project for Meteorological Capacity Improvement[grant number 24NLTSZ003]。
文摘Deep learning-based methods have become alternatives to traditional numerical weather prediction systems,offering faster computation and the ability to utilize large historical datasets.However,the application of deep learning to medium-range regional weather forecasting with limited data remains a significant challenge.In this work,three key solutions are proposed:(1)motivated by the need to improve model performance in data-scarce regional forecasting scenarios,the authors innovatively apply semantic segmentation models,to better capture spatiotemporal features and improve prediction accuracy;(2)recognizing the challenge of overfitting and the inability of traditional noise-based data augmentation methods to effectively enhance model robustness,a novel learnable Gaussian noise mechanism is introduced that allows the model to adaptively optimize perturbations for different locations,ensuring more effective learning;and(3)to address the issue of error accumulation in autoregressive prediction,as well as the challenge of learning difficulty and the lack of intermediate data utilization in one-shot prediction,the authors propose a cascade prediction approach that effectively resolves these problems while significantly improving model forecasting performance.The method achieves a competitive result in The East China Regional AI Medium Range Weather Forecasting Competition.Ablation experiments further validate the effectiveness of each component,highlighting their contributions to enhancing prediction performance.
基金supported by National Natural Science Foundation of China(NSFC)under grant U23A20310.
文摘With the growing advancement of wireless communication technologies,WiFi-based human sensing has gained increasing attention as a non-intrusive and device-free solution.Among the available signal types,Channel State Information(CSI)offers fine-grained temporal,frequency,and spatial insights into multipath propagation,making it a crucial data source for human-centric sensing.Recently,the integration of deep learning has significantly improved the robustness and automation of feature extraction from CSI in complex environments.This paper provides a comprehensive review of deep learning-enhanced human sensing based on CSI.We first outline mainstream CSI acquisition tools and their hardware specifications,then provide a detailed discussion of preprocessing methods such as denoising,time–frequency transformation,data segmentation,and augmentation.Subsequently,we categorize deep learning approaches according to sensing tasks—namely detection,localization,and recognition—and highlight representative models across application scenarios.Finally,we examine key challenges including domain generalization,multi-user interference,and limited data availability,and we propose future research directions involving lightweight model deployment,multimodal data fusion,and semantic-level sensing.
