Two 500 m deep investigation shafts were excavating in the granite body in Mizunami, central Japan by JAEA (Japan Nuclear Cycle Development Institute) in 2004-2012. Groundwater with volume of 700 m3 was generally pump...Two 500 m deep investigation shafts were excavating in the granite body in Mizunami, central Japan by JAEA (Japan Nuclear Cycle Development Institute) in 2004-2012. Groundwater with volume of 700 m3 was generally pumping a day to prevent the shafts from submerging in 2012 following the excavating. As a result of pumping the groundwater, the ground water level lowered to 60 m in the borehole with the distance of 200 m from the excavating shafts in 2012. Leveling network extending 2 km × 2 km around the shafts was established to detect the vertical deformation around the shafts in 2004, and precise leveling was done every year. An 18 mm ground subsidence was detected in the benchmark close to the shafts for 8 years in 2004-2012, and time series of subsidence at benchmark was consistent with the groundwater drawdown. The groundwater drawdown and ground subsidence were caused by the pumping ground water in excavating shafts.展开更多
A telecommunication network used for the transmission of astronomical observation data,telescope remote control and other astronomical research purposes is a critical infrastructure.The monitoring and analysis of netw...A telecommunication network used for the transmission of astronomical observation data,telescope remote control and other astronomical research purposes is a critical infrastructure.The monitoring and analysis of network traffic,which help improve the network performance and the utilization of network resources,are a challenging task.The accurate identification of the astronomical data traffic will effectively improve transmission efficiency.In this paper,a classification method applied to types of traffic containing astronomical data using deep learning is proposed.The advantages of a convolutional neural network model in image classification are exploited to classify types of traffic containing astronomical data.The objective is to identify the mixed traffic in the network and accurately identify types of traffic containing astronomical data.The effectiveness of the model in improving classification accuracy is also discussed.Actual traffic data captured by Tcpdump and Wireshark are tested,and the experimental results indicate that the proposed method can accurately classify types of traffic containing astronomical data.展开更多
Drilling and blasting methods have been used as a common driving technique for shallow-hole driving and blasting in rock roadways.With the advent of digital electronic detonators and the need for increased production ...Drilling and blasting methods have been used as a common driving technique for shallow-hole driving and blasting in rock roadways.With the advent of digital electronic detonators and the need for increased production efciency,the traditional blasting design is no longer suitable for deep hole blasting.In this paper,a disperse charge cut blasting method was proposed to address the issues of low excavation depth and high block rate in deep hole undercut blasting.First,a blasting model was used to illustrate the mechanism of the deep hole dispersive charge cut blasting process.Then,continuous charge and dispersed charge blasting models were developed using the smooth particle hydrodynamics-fnite element method(SPHFEM).The cutting parameters were determined theoretically,and the cutting efciency was introduced to evaluate the cutting efect.The blasting efects of the two charging models were analyzed utilizing the evolution law of rock damage,the number of rock particles thrown,and the cutting efciency.The results show that using a dispersed charge improves the cutting efciency by about 20%and the rock breakage for the deep hole cut blasting compared to the traditional continuous charge.In addition,important parameters such as cutting hole spacing,cutting hole depth and upper charge proportion also have a signifcant impact on the cutting efect.Finally,the deep hole dispersed charge cut blasting technology is combined with the digital electronic detonator through the feld engineering practice.It provides a reference for the subsequent deep hole cutting blasting and the use of electronic detonators in rock roadways.展开更多
Under the dual influence of the mining disturbance of the previous working face and the advanced mining of the working face,the roadway is prone to large deformation,failure,and rockburst.Roadway stabilization has alw...Under the dual influence of the mining disturbance of the previous working face and the advanced mining of the working face,the roadway is prone to large deformation,failure,and rockburst.Roadway stabilization has always significantly influenced deep mining safety.In this article we used the research background of the large deformation failure roadway of Fa-er Coal Mine in Guizhou Province of China to propose two control methods:bolt-cable-mesh+concrete blocks+directional energy-gathering blasting(BCM-CBDE method)and 1st Generation-Negative Poisson’s Ratio(1G NPR)cable+directional energy-gathering blasting+dynamic pressure stage support(πgirder+single hydraulic prop+retractable U steel)(NPR-DEDP method).Meantime,we compared the validity of the large deformation failure control method in a deep gob-side roadway based on theoretical analysis,numerical simulations,and field experiments.The results show that directional energy-gathering blasting can weaken the pressure acting on the concrete blocks.However,the vertical stress of the surrounding rock of the roadway is still concentrated in the entity coal side and the concrete blocks,showing a’bimodal’distribution.BCM-CBDE method cannot effectively control the stability of the roadway.NPR-DEDP method removed the concrete blocks.It shows using the 1G NPR cable with periodic slipping-sticking characteristics can adapt to repeated mining disturbances.The peak value of the vertical stress of the roadway is reduced and transferred to the deep part of the surrounding rock mass,which promotes the collapse of the gangue in the goaf and fills the goaf.The pressure of the roadway roof is reduced,and the gob-side roadway is fundamentally protected.Meantime,the dynamic pressure stage support method withπgirder+single hydraulic prop+retractable U steel as the core effectively protects the roadway from dynamic pressure impact when the main roof is periodically broken.After the on-site implementation of NPR-DEDP method,the deformation of the roadway is reduced by more than 45%,and the deformation rate is reduced by more than 50%.展开更多
The boundary condition is a crucial factor affecting the permeability variation due to suffusion.An experimental investigation on the permeability of gap-graded soil due to horizontal suffusion considering the boundar...The boundary condition is a crucial factor affecting the permeability variation due to suffusion.An experimental investigation on the permeability of gap-graded soil due to horizontal suffusion considering the boundary effect is conducted,where the hydraulic head difference(DH)varies,and the boundary includes non-loss and soil-loss conditions.Soil samples are filled into seven soil storerooms connected in turn.After evaluation,the variation in content of fine sand(ΔR_(f))and the hydraulic conductivity of soils in each storeroom(C_(i))are analyzed.In the non-loss test,the soil sample filling area is divided into runoff,transited,and accumulated areas according to the negative or positive ΔR_(f) values.ΔR_(f) increases from negative to positive along the seepage path,and Ci decreases from runoff area to transited area and then rebounds in accumulated area.In the soil-loss test,all soil sample filling areas belong to the runoff area,where the gentle-loss,strengthened-loss,and alleviated-loss parts are further divided.ΔR_(f) decreases from the gentle-loss part to the strengthened-loss part and then rebounds in the alleviated-loss part,and C_(i) increases and then decreases along the seepage path.The relationship between ΔR_(f) and Ci is different with the boundary condition.Ci exponentially decreases with ΔR_(f) in the non-loss test and increases with ΔR_(f) generally in the soil-loss test.展开更多
Recent developments in Computer Vision have presented novel opportunities to tackle complex healthcare issues,particularly in the field of lung disease diagnosis.One promising avenue involves the use of chest X-Rays,w...Recent developments in Computer Vision have presented novel opportunities to tackle complex healthcare issues,particularly in the field of lung disease diagnosis.One promising avenue involves the use of chest X-Rays,which are commonly utilized in radiology.To fully exploit their potential,researchers have suggested utilizing deep learning methods to construct computer-aided diagnostic systems.However,constructing and compressing these systems presents a significant challenge,as it relies heavily on the expertise of data scientists.To tackle this issue,we propose an automated approach that utilizes an evolutionary algorithm(EA)to optimize the design and compression of a convolutional neural network(CNN)for X-Ray image classification.Our approach accurately classifies radiography images and detects potential chest abnormalities and infections,including COVID-19.Furthermore,our approach incorporates transfer learning,where a pre-trainedCNNmodel on a vast dataset of chest X-Ray images is fine-tuned for the specific task of detecting COVID-19.This method can help reduce the amount of labeled data required for the task and enhance the overall performance of the model.We have validated our method via a series of experiments against state-of-the-art architectures.展开更多
Dear Editor,This letter presents a novel segmentation approach that leverages dendritic neurons to tackle the challenges of medical imaging segmentation.In this study,we enhance the segmentation accuracy based on a Se...Dear Editor,This letter presents a novel segmentation approach that leverages dendritic neurons to tackle the challenges of medical imaging segmentation.In this study,we enhance the segmentation accuracy based on a SegNet variant including an encoder-decoder structure,an upsampling index,and a deep supervision method.Furthermore,we introduce a dendritic neuron-based convolutional block to enable nonlinear feature mapping,thereby further improving the effectiveness of our approach.展开更多
Solving constrained multi-objective optimization problems with evolutionary algorithms has attracted considerable attention.Various constrained multi-objective optimization evolutionary algorithms(CMOEAs)have been dev...Solving constrained multi-objective optimization problems with evolutionary algorithms has attracted considerable attention.Various constrained multi-objective optimization evolutionary algorithms(CMOEAs)have been developed with the use of different algorithmic strategies,evolutionary operators,and constraint-handling techniques.The performance of CMOEAs may be heavily dependent on the operators used,however,it is usually difficult to select suitable operators for the problem at hand.Hence,improving operator selection is promising and necessary for CMOEAs.This work proposes an online operator selection framework assisted by Deep Reinforcement Learning.The dynamics of the population,including convergence,diversity,and feasibility,are regarded as the state;the candidate operators are considered as actions;and the improvement of the population state is treated as the reward.By using a Q-network to learn a policy to estimate the Q-values of all actions,the proposed approach can adaptively select an operator that maximizes the improvement of the population according to the current state and thereby improve the algorithmic performance.The framework is embedded into four popular CMOEAs and assessed on 42 benchmark problems.The experimental results reveal that the proposed Deep Reinforcement Learning-assisted operator selection significantly improves the performance of these CMOEAs and the resulting algorithm obtains better versatility compared to nine state-of-the-art CMOEAs.展开更多
Breast cancer(BC)is one of the leading causes of death among women worldwide,as it has emerged as the most commonly diagnosed malignancy in women.Early detection and effective treatment of BC can help save women’s li...Breast cancer(BC)is one of the leading causes of death among women worldwide,as it has emerged as the most commonly diagnosed malignancy in women.Early detection and effective treatment of BC can help save women’s lives.Developing an efficient technology-based detection system can lead to non-destructive and preliminary cancer detection techniques.This paper proposes a comprehensive framework that can effectively diagnose cancerous cells from benign cells using the Curated Breast Imaging Subset of the Digital Database for Screening Mammography(CBIS-DDSM)data set.The novelty of the proposed framework lies in the integration of various techniques,where the fusion of deep learning(DL),traditional machine learning(ML)techniques,and enhanced classification models have been deployed using the curated dataset.The analysis outcome proves that the proposed enhanced RF(ERF),enhanced DT(EDT)and enhanced LR(ELR)models for BC detection outperformed most of the existing models with impressive results.展开更多
Highway safety researchers focus on crash injury severity,utilizing deep learning—specifically,deep neural networks(DNN),deep convolutional neural networks(D-CNN),and deep recurrent neural networks(D-RNN)—as the pre...Highway safety researchers focus on crash injury severity,utilizing deep learning—specifically,deep neural networks(DNN),deep convolutional neural networks(D-CNN),and deep recurrent neural networks(D-RNN)—as the preferred method for modeling accident severity.Deep learning’s strength lies in handling intricate relation-ships within extensive datasets,making it popular for accident severity level(ASL)prediction and classification.Despite prior success,there is a need for an efficient system recognizing ASL in diverse road conditions.To address this,we present an innovative Accident Severity Level Prediction Deep Learning(ASLP-DL)framework,incorporating DNN,D-CNN,and D-RNN models fine-tuned through iterative hyperparameter selection with Stochastic Gradient Descent.The framework optimizes hidden layers and integrates data augmentation,Gaussian noise,and dropout regularization for improved generalization.Sensitivity and factor contribution analyses identify influential predictors.Evaluated on three diverse crash record databases—NCDB 2018–2019,UK 2015–2020,and US 2016–2021—the D-RNN model excels with an ACC score of 89.0281%,a Roc Area of 0.751,an F-estimate of 0.941,and a Kappa score of 0.0629 over the NCDB dataset.The proposed framework consistently outperforms traditional methods,existing machine learning,and deep learning techniques.展开更多
BACKGROUND Diabetic peripheral neuropathy(DPN)is a debilitating complication of diabetes mellitus with limited available treatment options.Radix Salviae,a traditional Chinese herb,has shown promise in treating DPN,but...BACKGROUND Diabetic peripheral neuropathy(DPN)is a debilitating complication of diabetes mellitus with limited available treatment options.Radix Salviae,a traditional Chinese herb,has shown promise in treating DPN,but its therapeutic mech-anisms have not been systematically investigated.AIM Radix Salviae(Danshen in pinin),a traditional Chinese medicine(TCM),is widely used to treat DPN in China.However,the mechanism through which Radix Salviae treats DPN remains unclear.Therefore,we aimed to explore the mechanism of action of Radix Salviae against DPN using network pharmacology.METHODS The active ingredients and target genes of Radix Salviae were screened using the TCM pharmacology database and analysis platform.The genes associated with DPN were obtained from the Gene Cards and OMIM databases,a drug-com-position-target-disease network was constructed,and a protein–protein inter-action network was subsequently constructed to screen the main targets.Gene Ontology(GO)functional annotation and pathway enrichment analysis were performed via the Kyoto Encyclopedia of Genes and Genomes(KEGG)using Bioconductor.RESULTS A total of 56 effective components,108 targets and 4581 DPN-related target genes of Radix Salviae were screened.Intervention with Radix Salviae for DPN mainly involved 81 target genes.The top 30 major targets were selected for enrichment analysis of GO and KEGG pathways.CONCLUSION These results suggested that Radix Salviae could treat DPN by regulating the AGE-RAGE signaling pathway and the PI3K-Akt signaling pathway.Therefore,Danshen may affect DPN by regulating inflammation and apoptosis.展开更多
In recent years,the number of smart contracts deployed on blockchain has exploded.However,the issue of vulnerability has caused incalculable losses.Due to the irreversible and immutability of smart contracts,vulnerabi...In recent years,the number of smart contracts deployed on blockchain has exploded.However,the issue of vulnerability has caused incalculable losses.Due to the irreversible and immutability of smart contracts,vulnerability detection has become particularly important.With the popular use of neural network model,there has been a growing utilization of deep learning-based methods and tools for the identification of vulnerabilities within smart contracts.This paper commences by providing a succinct overview of prevalent categories of vulnerabilities found in smart contracts.Subsequently,it categorizes and presents an overview of contemporary deep learning-based tools developed for smart contract detection.These tools are categorized based on their open-source status,the data format and the type of feature extraction they employ.Then we conduct a comprehensive comparative analysis of these tools,selecting representative tools for experimental validation and comparing them with traditional tools in terms of detection coverage and accuracy.Finally,Based on the insights gained from the experimental results and the current state of research in the field of smart contract vulnerability detection tools,we suppose to provide a reference standard for developers of contract vulnerability detection tools.Meanwhile,forward-looking research directions are also proposed for deep learning-based smart contract vulnerability detection.展开更多
Isogeometric analysis (IGA) is known to showadvanced features compared to traditional finite element approaches.Using IGA one may accurately obtain the geometrically nonlinear bending behavior of plates with functiona...Isogeometric analysis (IGA) is known to showadvanced features compared to traditional finite element approaches.Using IGA one may accurately obtain the geometrically nonlinear bending behavior of plates with functionalgrading (FG). However, the procedure is usually complex and often is time-consuming. We thus put forward adeep learning method to model the geometrically nonlinear bending behavior of FG plates, bypassing the complexIGA simulation process. A long bidirectional short-term memory (BLSTM) recurrent neural network is trainedusing the load and gradient index as inputs and the displacement responses as outputs. The nonlinear relationshipbetween the outputs and the inputs is constructed usingmachine learning so that the displacements can be directlyestimated by the deep learning network. To provide enough training data, we use S-FSDT Von-Karman IGA andobtain the displacement responses for different loads and gradient indexes. Results show that the recognition erroris low, and demonstrate the feasibility of deep learning technique as a fast and accurate alternative to IGA formodeling the geometrically nonlinear bending behavior of FG plates.展开更多
Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metavers...Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation,which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units(RSU)or unmanned aerial vehicles(UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning(MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization(MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers(e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach outperforms the MAPPO approach by around 2% and effectively reduces approximately 20% of the latency of avatar task execution in UAV-assisted vehicular Metaverses.展开更多
Battery management systems(BMSs) play a vital role in ensuring efficient and reliable operations of lithium-ion batteries.The main function of the BMSs is to estimate battery states and diagnose battery health using b...Battery management systems(BMSs) play a vital role in ensuring efficient and reliable operations of lithium-ion batteries.The main function of the BMSs is to estimate battery states and diagnose battery health using battery open-circuit voltage(OCV).However,acquiring the complete OCV data online can be a challenging endeavor due to the time-consuming measurement process or the need for specific operating conditions required by OCV estimation models.In addressing these concerns,this study introduces a deep neural network-combined framework for accurate and robust OCV estimation,utilizing partial daily charging data.We incorporate a generative deep learning model to extract aging-related features from data and generate high-fidelity OCV curves.Correlation analysis is employed to identify the optimal partial charging data,optimizing the OCV estimation precision while preserving exceptional flexibility.The validation results,using data from nickel-cobalt-magnesium(NCM) batteries,illustrate the accurate estimation of the complete OCV-capacity curve,with an average root mean square errors(RMSE) of less than 3 mAh.Achieving this level of precision for OCV estimation requires only around 50 s collection of partial charging data.Further validations on diverse battery types operating under various conditions confirm the effectiveness of our proposed method.Additional cases of precise health diagnosis based on OCV highlight the significance of conducting online OCV estimation.Our method provides a flexible approach to achieve complete OCV estimation and holds promise for generalization to other tasks in BMSs.展开更多
Cyberspace is extremely dynamic,with new attacks arising daily.Protecting cybersecurity controls is vital for network security.Deep Learning(DL)models find widespread use across various fields,with cybersecurity being...Cyberspace is extremely dynamic,with new attacks arising daily.Protecting cybersecurity controls is vital for network security.Deep Learning(DL)models find widespread use across various fields,with cybersecurity being one of the most crucial due to their rapid cyberattack detection capabilities on networks and hosts.The capabilities of DL in feature learning and analyzing extensive data volumes lead to the recognition of network traffic patterns.This study presents novel lightweight DL models,known as Cybernet models,for the detection and recognition of various cyber Distributed Denial of Service(DDoS)attacks.These models were constructed to have a reasonable number of learnable parameters,i.e.,less than 225,000,hence the name“lightweight.”This not only helps reduce the number of computations required but also results in faster training and inference times.Additionally,these models were designed to extract features in parallel from 1D Convolutional Neural Networks(CNN)and Long Short-Term Memory(LSTM),which makes them unique compared to earlier existing architectures and results in better performance measures.To validate their robustness and effectiveness,they were tested on the CIC-DDoS2019 dataset,which is an imbalanced and large dataset that contains different types of DDoS attacks.Experimental results revealed that bothmodels yielded promising results,with 99.99% for the detectionmodel and 99.76% for the recognition model in terms of accuracy,precision,recall,and F1 score.Furthermore,they outperformed the existing state-of-the-art models proposed for the same task.Thus,the proposed models can be used in cyber security research domains to successfully identify different types of attacks with a high detection and recognition rate.展开更多
Aim:This study aims to establish an artificial intelligence model,ThyroidNet,to diagnose thyroid nodules using deep learning techniques accurately.Methods:A novel method,ThyroidNet,is introduced and evaluated based on...Aim:This study aims to establish an artificial intelligence model,ThyroidNet,to diagnose thyroid nodules using deep learning techniques accurately.Methods:A novel method,ThyroidNet,is introduced and evaluated based on deep learning for the localization and classification of thyroid nodules.First,we propose the multitask TransUnet,which combines the TransUnet encoder and decoder with multitask learning.Second,we propose the DualLoss function,tailored to the thyroid nodule localization and classification tasks.It balances the learning of the localization and classification tasks to help improve the model’s generalization ability.Third,we introduce strategies for augmenting the data.Finally,we submit a novel deep learning model,ThyroidNet,to accurately detect thyroid nodules.Results:ThyroidNet was evaluated on private datasets and was comparable to other existing methods,including U-Net and TransUnet.Experimental results show that ThyroidNet outperformed these methods in localizing and classifying thyroid nodules.It achieved improved accuracy of 3.9%and 1.5%,respectively.Conclusion:ThyroidNet significantly improves the clinical diagnosis of thyroid nodules and supports medical image analysis tasks.Future research directions include optimization of the model structure,expansion of the dataset size,reduction of computational complexity and memory requirements,and exploration of additional applications of ThyroidNet in medical image analysis.展开更多
In the current landscape of the COVID-19 pandemic,the utilization of deep learning in medical imaging,especially in chest computed tomography(CT)scan analysis for virus detection,has become increasingly significant.De...In the current landscape of the COVID-19 pandemic,the utilization of deep learning in medical imaging,especially in chest computed tomography(CT)scan analysis for virus detection,has become increasingly significant.Despite its potential,deep learning’s“black box”nature has been a major impediment to its broader acceptance in clinical environments,where transparency in decision-making is imperative.To bridge this gap,our research integrates Explainable AI(XAI)techniques,specifically the Local Interpretable Model-Agnostic Explanations(LIME)method,with advanced deep learning models.This integration forms a sophisticated and transparent framework for COVID-19 identification,enhancing the capability of standard Convolutional Neural Network(CNN)models through transfer learning and data augmentation.Our approach leverages the refined DenseNet201 architecture for superior feature extraction and employs data augmentation strategies to foster robust model generalization.The pivotal element of our methodology is the use of LIME,which demystifies the AI decision-making process,providing clinicians with clear,interpretable insights into the AI’s reasoning.This unique combination of an optimized Deep Neural Network(DNN)with LIME not only elevates the precision in detecting COVID-19 cases but also equips healthcare professionals with a deeper understanding of the diagnostic process.Our method,validated on the SARS-COV-2 CT-Scan dataset,demonstrates exceptional diagnostic accuracy,with performance metrics that reinforce its potential for seamless integration into modern healthcare systems.This innovative approach marks a significant advancement in creating explainable and trustworthy AI tools for medical decisionmaking in the ongoing battle against COVID-19.展开更多
Computer vision(CV)was developed for computers and other systems to act or make recommendations based on visual inputs,such as digital photos,movies,and other media.Deep learning(DL)methods are more successful than ot...Computer vision(CV)was developed for computers and other systems to act or make recommendations based on visual inputs,such as digital photos,movies,and other media.Deep learning(DL)methods are more successful than other traditional machine learning(ML)methods inCV.DL techniques can produce state-of-the-art results for difficult CV problems like picture categorization,object detection,and face recognition.In this review,a structured discussion on the history,methods,and applications of DL methods to CV problems is presented.The sector-wise presentation of applications in this papermay be particularly useful for researchers in niche fields who have limited or introductory knowledge of DL methods and CV.This review will provide readers with context and examples of how these techniques can be applied to specific areas.A curated list of popular datasets and a brief description of them are also included for the benefit of readers.展开更多
文摘Two 500 m deep investigation shafts were excavating in the granite body in Mizunami, central Japan by JAEA (Japan Nuclear Cycle Development Institute) in 2004-2012. Groundwater with volume of 700 m3 was generally pumping a day to prevent the shafts from submerging in 2012 following the excavating. As a result of pumping the groundwater, the ground water level lowered to 60 m in the borehole with the distance of 200 m from the excavating shafts in 2012. Leveling network extending 2 km × 2 km around the shafts was established to detect the vertical deformation around the shafts in 2004, and precise leveling was done every year. An 18 mm ground subsidence was detected in the benchmark close to the shafts for 8 years in 2004-2012, and time series of subsidence at benchmark was consistent with the groundwater drawdown. The groundwater drawdown and ground subsidence were caused by the pumping ground water in excavating shafts.
基金supported by the National Key R&D Program of China(Nos.2021YFC2203502 and 2022YFF0711502)Natural Science Foundation of Xinjiang Uygur Autonomous Region(2022D01A360)+6 种基金the National Natural Science Foundation of China(NSFC)(12173077 and 12003062)the Tianshan Innovation Team Plan of Xinjiang Uygur Autonomous Region(2022D14020)the Scientific Instrument Developing Project of the Chinese Academy of Sciences(Grant No.PTYQ2022YZZD01)the Operation,Maintenance and Upgrading Fund for Astronomical Telescopes and Facility Instruments,budgeted from the Ministry of Finance of China(MOF)and administrated by the Chinese Academy of Sciences(CAS)supported by Astronomical Big Data Joint Research Centerco-founded by National Astronomical Observatories,Chinese Academy of Sciences。
文摘A telecommunication network used for the transmission of astronomical observation data,telescope remote control and other astronomical research purposes is a critical infrastructure.The monitoring and analysis of network traffic,which help improve the network performance and the utilization of network resources,are a challenging task.The accurate identification of the astronomical data traffic will effectively improve transmission efficiency.In this paper,a classification method applied to types of traffic containing astronomical data using deep learning is proposed.The advantages of a convolutional neural network model in image classification are exploited to classify types of traffic containing astronomical data.The objective is to identify the mixed traffic in the network and accurately identify types of traffic containing astronomical data.The effectiveness of the model in improving classification accuracy is also discussed.Actual traffic data captured by Tcpdump and Wireshark are tested,and the experimental results indicate that the proposed method can accurately classify types of traffic containing astronomical data.
基金the State Key Development Program for Basic Research of China(2016YFC0600903)the National Natural Science Foundation of China(51934001).
文摘Drilling and blasting methods have been used as a common driving technique for shallow-hole driving and blasting in rock roadways.With the advent of digital electronic detonators and the need for increased production efciency,the traditional blasting design is no longer suitable for deep hole blasting.In this paper,a disperse charge cut blasting method was proposed to address the issues of low excavation depth and high block rate in deep hole undercut blasting.First,a blasting model was used to illustrate the mechanism of the deep hole dispersive charge cut blasting process.Then,continuous charge and dispersed charge blasting models were developed using the smooth particle hydrodynamics-fnite element method(SPHFEM).The cutting parameters were determined theoretically,and the cutting efciency was introduced to evaluate the cutting efect.The blasting efects of the two charging models were analyzed utilizing the evolution law of rock damage,the number of rock particles thrown,and the cutting efciency.The results show that using a dispersed charge improves the cutting efciency by about 20%and the rock breakage for the deep hole cut blasting compared to the traditional continuous charge.In addition,important parameters such as cutting hole spacing,cutting hole depth and upper charge proportion also have a signifcant impact on the cutting efect.Finally,the deep hole dispersed charge cut blasting technology is combined with the digital electronic detonator through the feld engineering practice.It provides a reference for the subsequent deep hole cutting blasting and the use of electronic detonators in rock roadways.
基金funded by National Natural Science Foundation of China(52074300)Yueqi Young Scholars Project of China University of Mining and Technology Beijing(2602021RC84)+1 种基金China University of Mining and Technology(Beijing)fundamental scientific research funds—Doctoral students Top-notch Innovative Talents Fostering Funds(BBJ2023047)Guizhou Provincial Science and Technology Planning Project([2020]2Y030)。
文摘Under the dual influence of the mining disturbance of the previous working face and the advanced mining of the working face,the roadway is prone to large deformation,failure,and rockburst.Roadway stabilization has always significantly influenced deep mining safety.In this article we used the research background of the large deformation failure roadway of Fa-er Coal Mine in Guizhou Province of China to propose two control methods:bolt-cable-mesh+concrete blocks+directional energy-gathering blasting(BCM-CBDE method)and 1st Generation-Negative Poisson’s Ratio(1G NPR)cable+directional energy-gathering blasting+dynamic pressure stage support(πgirder+single hydraulic prop+retractable U steel)(NPR-DEDP method).Meantime,we compared the validity of the large deformation failure control method in a deep gob-side roadway based on theoretical analysis,numerical simulations,and field experiments.The results show that directional energy-gathering blasting can weaken the pressure acting on the concrete blocks.However,the vertical stress of the surrounding rock of the roadway is still concentrated in the entity coal side and the concrete blocks,showing a’bimodal’distribution.BCM-CBDE method cannot effectively control the stability of the roadway.NPR-DEDP method removed the concrete blocks.It shows using the 1G NPR cable with periodic slipping-sticking characteristics can adapt to repeated mining disturbances.The peak value of the vertical stress of the roadway is reduced and transferred to the deep part of the surrounding rock mass,which promotes the collapse of the gangue in the goaf and fills the goaf.The pressure of the roadway roof is reduced,and the gob-side roadway is fundamentally protected.Meantime,the dynamic pressure stage support method withπgirder+single hydraulic prop+retractable U steel as the core effectively protects the roadway from dynamic pressure impact when the main roof is periodically broken.After the on-site implementation of NPR-DEDP method,the deformation of the roadway is reduced by more than 45%,and the deformation rate is reduced by more than 50%.
基金The research work described herein was funded by the National Nature Science Foundation of China(Grant No.41877213).This financial support is gratefully acknowledged.
文摘The boundary condition is a crucial factor affecting the permeability variation due to suffusion.An experimental investigation on the permeability of gap-graded soil due to horizontal suffusion considering the boundary effect is conducted,where the hydraulic head difference(DH)varies,and the boundary includes non-loss and soil-loss conditions.Soil samples are filled into seven soil storerooms connected in turn.After evaluation,the variation in content of fine sand(ΔR_(f))and the hydraulic conductivity of soils in each storeroom(C_(i))are analyzed.In the non-loss test,the soil sample filling area is divided into runoff,transited,and accumulated areas according to the negative or positive ΔR_(f) values.ΔR_(f) increases from negative to positive along the seepage path,and Ci decreases from runoff area to transited area and then rebounds in accumulated area.In the soil-loss test,all soil sample filling areas belong to the runoff area,where the gentle-loss,strengthened-loss,and alleviated-loss parts are further divided.ΔR_(f) decreases from the gentle-loss part to the strengthened-loss part and then rebounds in the alleviated-loss part,and C_(i) increases and then decreases along the seepage path.The relationship between ΔR_(f) and Ci is different with the boundary condition.Ci exponentially decreases with ΔR_(f) in the non-loss test and increases with ΔR_(f) generally in the soil-loss test.
基金via funding from Prince Sattam bin Abdulaziz University Project Number(PSAU/2023/R/1444).
文摘Recent developments in Computer Vision have presented novel opportunities to tackle complex healthcare issues,particularly in the field of lung disease diagnosis.One promising avenue involves the use of chest X-Rays,which are commonly utilized in radiology.To fully exploit their potential,researchers have suggested utilizing deep learning methods to construct computer-aided diagnostic systems.However,constructing and compressing these systems presents a significant challenge,as it relies heavily on the expertise of data scientists.To tackle this issue,we propose an automated approach that utilizes an evolutionary algorithm(EA)to optimize the design and compression of a convolutional neural network(CNN)for X-Ray image classification.Our approach accurately classifies radiography images and detects potential chest abnormalities and infections,including COVID-19.Furthermore,our approach incorporates transfer learning,where a pre-trainedCNNmodel on a vast dataset of chest X-Ray images is fine-tuned for the specific task of detecting COVID-19.This method can help reduce the amount of labeled data required for the task and enhance the overall performance of the model.We have validated our method via a series of experiments against state-of-the-art architectures.
基金partially supported by the Japan Society for the Promotion of Science(JSPS)KAKENHI(JP22H03643)Japan Science and Technology Agency(JST)Support for Pioneering Research Initiated by the Next Generation(SPRING)(JPMJSP2145)JST through the Establishment of University Fellowships Towards the Creation of Science Technology Innovation(JPMJFS2115)。
文摘Dear Editor,This letter presents a novel segmentation approach that leverages dendritic neurons to tackle the challenges of medical imaging segmentation.In this study,we enhance the segmentation accuracy based on a SegNet variant including an encoder-decoder structure,an upsampling index,and a deep supervision method.Furthermore,we introduce a dendritic neuron-based convolutional block to enable nonlinear feature mapping,thereby further improving the effectiveness of our approach.
基金the National Natural Science Foundation of China(62076225,62073300)the Natural Science Foundation for Distinguished Young Scholars of Hubei(2019CFA081)。
文摘Solving constrained multi-objective optimization problems with evolutionary algorithms has attracted considerable attention.Various constrained multi-objective optimization evolutionary algorithms(CMOEAs)have been developed with the use of different algorithmic strategies,evolutionary operators,and constraint-handling techniques.The performance of CMOEAs may be heavily dependent on the operators used,however,it is usually difficult to select suitable operators for the problem at hand.Hence,improving operator selection is promising and necessary for CMOEAs.This work proposes an online operator selection framework assisted by Deep Reinforcement Learning.The dynamics of the population,including convergence,diversity,and feasibility,are regarded as the state;the candidate operators are considered as actions;and the improvement of the population state is treated as the reward.By using a Q-network to learn a policy to estimate the Q-values of all actions,the proposed approach can adaptively select an operator that maximizes the improvement of the population according to the current state and thereby improve the algorithmic performance.The framework is embedded into four popular CMOEAs and assessed on 42 benchmark problems.The experimental results reveal that the proposed Deep Reinforcement Learning-assisted operator selection significantly improves the performance of these CMOEAs and the resulting algorithm obtains better versatility compared to nine state-of-the-art CMOEAs.
文摘Breast cancer(BC)is one of the leading causes of death among women worldwide,as it has emerged as the most commonly diagnosed malignancy in women.Early detection and effective treatment of BC can help save women’s lives.Developing an efficient technology-based detection system can lead to non-destructive and preliminary cancer detection techniques.This paper proposes a comprehensive framework that can effectively diagnose cancerous cells from benign cells using the Curated Breast Imaging Subset of the Digital Database for Screening Mammography(CBIS-DDSM)data set.The novelty of the proposed framework lies in the integration of various techniques,where the fusion of deep learning(DL),traditional machine learning(ML)techniques,and enhanced classification models have been deployed using the curated dataset.The analysis outcome proves that the proposed enhanced RF(ERF),enhanced DT(EDT)and enhanced LR(ELR)models for BC detection outperformed most of the existing models with impressive results.
文摘Highway safety researchers focus on crash injury severity,utilizing deep learning—specifically,deep neural networks(DNN),deep convolutional neural networks(D-CNN),and deep recurrent neural networks(D-RNN)—as the preferred method for modeling accident severity.Deep learning’s strength lies in handling intricate relation-ships within extensive datasets,making it popular for accident severity level(ASL)prediction and classification.Despite prior success,there is a need for an efficient system recognizing ASL in diverse road conditions.To address this,we present an innovative Accident Severity Level Prediction Deep Learning(ASLP-DL)framework,incorporating DNN,D-CNN,and D-RNN models fine-tuned through iterative hyperparameter selection with Stochastic Gradient Descent.The framework optimizes hidden layers and integrates data augmentation,Gaussian noise,and dropout regularization for improved generalization.Sensitivity and factor contribution analyses identify influential predictors.Evaluated on three diverse crash record databases—NCDB 2018–2019,UK 2015–2020,and US 2016–2021—the D-RNN model excels with an ACC score of 89.0281%,a Roc Area of 0.751,an F-estimate of 0.941,and a Kappa score of 0.0629 over the NCDB dataset.The proposed framework consistently outperforms traditional methods,existing machine learning,and deep learning techniques.
文摘BACKGROUND Diabetic peripheral neuropathy(DPN)is a debilitating complication of diabetes mellitus with limited available treatment options.Radix Salviae,a traditional Chinese herb,has shown promise in treating DPN,but its therapeutic mech-anisms have not been systematically investigated.AIM Radix Salviae(Danshen in pinin),a traditional Chinese medicine(TCM),is widely used to treat DPN in China.However,the mechanism through which Radix Salviae treats DPN remains unclear.Therefore,we aimed to explore the mechanism of action of Radix Salviae against DPN using network pharmacology.METHODS The active ingredients and target genes of Radix Salviae were screened using the TCM pharmacology database and analysis platform.The genes associated with DPN were obtained from the Gene Cards and OMIM databases,a drug-com-position-target-disease network was constructed,and a protein–protein inter-action network was subsequently constructed to screen the main targets.Gene Ontology(GO)functional annotation and pathway enrichment analysis were performed via the Kyoto Encyclopedia of Genes and Genomes(KEGG)using Bioconductor.RESULTS A total of 56 effective components,108 targets and 4581 DPN-related target genes of Radix Salviae were screened.Intervention with Radix Salviae for DPN mainly involved 81 target genes.The top 30 major targets were selected for enrichment analysis of GO and KEGG pathways.CONCLUSION These results suggested that Radix Salviae could treat DPN by regulating the AGE-RAGE signaling pathway and the PI3K-Akt signaling pathway.Therefore,Danshen may affect DPN by regulating inflammation and apoptosis.
基金funded by the Major PublicWelfare Special Fund of Henan Province(No.201300210200)the Major Science and Technology Research Special Fund of Henan Province(No.221100210400).
文摘In recent years,the number of smart contracts deployed on blockchain has exploded.However,the issue of vulnerability has caused incalculable losses.Due to the irreversible and immutability of smart contracts,vulnerability detection has become particularly important.With the popular use of neural network model,there has been a growing utilization of deep learning-based methods and tools for the identification of vulnerabilities within smart contracts.This paper commences by providing a succinct overview of prevalent categories of vulnerabilities found in smart contracts.Subsequently,it categorizes and presents an overview of contemporary deep learning-based tools developed for smart contract detection.These tools are categorized based on their open-source status,the data format and the type of feature extraction they employ.Then we conduct a comprehensive comparative analysis of these tools,selecting representative tools for experimental validation and comparing them with traditional tools in terms of detection coverage and accuracy.Finally,Based on the insights gained from the experimental results and the current state of research in the field of smart contract vulnerability detection tools,we suppose to provide a reference standard for developers of contract vulnerability detection tools.Meanwhile,forward-looking research directions are also proposed for deep learning-based smart contract vulnerability detection.
基金the National Natural Science Foundation of China(NSFC)under Grant Nos.12272124 and 11972146.
文摘Isogeometric analysis (IGA) is known to showadvanced features compared to traditional finite element approaches.Using IGA one may accurately obtain the geometrically nonlinear bending behavior of plates with functionalgrading (FG). However, the procedure is usually complex and often is time-consuming. We thus put forward adeep learning method to model the geometrically nonlinear bending behavior of FG plates, bypassing the complexIGA simulation process. A long bidirectional short-term memory (BLSTM) recurrent neural network is trainedusing the load and gradient index as inputs and the displacement responses as outputs. The nonlinear relationshipbetween the outputs and the inputs is constructed usingmachine learning so that the displacements can be directlyestimated by the deep learning network. To provide enough training data, we use S-FSDT Von-Karman IGA andobtain the displacement responses for different loads and gradient indexes. Results show that the recognition erroris low, and demonstrate the feasibility of deep learning technique as a fast and accurate alternative to IGA formodeling the geometrically nonlinear bending behavior of FG plates.
基金supported in part by NSFC (62102099, U22A2054, 62101594)in part by the Pearl River Talent Recruitment Program (2021QN02S643)+9 种基金Guangzhou Basic Research Program (2023A04J1699)in part by the National Research Foundation, SingaporeInfocomm Media Development Authority under its Future Communications Research Development ProgrammeDSO National Laboratories under the AI Singapore Programme under AISG Award No AISG2-RP-2020-019Energy Research Test-Bed and Industry Partnership Funding Initiative, Energy Grid (EG) 2.0 programmeDesCartes and the Campus for Research Excellence and Technological Enterprise (CREATE) programmeMOE Tier 1 under Grant RG87/22in part by the Singapore University of Technology and Design (SUTD) (SRG-ISTD-2021- 165)in part by the SUTD-ZJU IDEA Grant SUTD-ZJU (VP) 202102in part by the Ministry of Education, Singapore, through its SUTD Kickstarter Initiative (SKI 20210204)。
文摘Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation,which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units(RSU)or unmanned aerial vehicles(UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning(MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization(MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers(e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach outperforms the MAPPO approach by around 2% and effectively reduces approximately 20% of the latency of avatar task execution in UAV-assisted vehicular Metaverses.
基金This work was supported by the National Key R&D Program of China(2021YFB2402002)the Beijing Natural Science Foundation(L223013)the Chongqing Automobile Collaborative Innovation Centre(No.2022CDJDX-004).
文摘Battery management systems(BMSs) play a vital role in ensuring efficient and reliable operations of lithium-ion batteries.The main function of the BMSs is to estimate battery states and diagnose battery health using battery open-circuit voltage(OCV).However,acquiring the complete OCV data online can be a challenging endeavor due to the time-consuming measurement process or the need for specific operating conditions required by OCV estimation models.In addressing these concerns,this study introduces a deep neural network-combined framework for accurate and robust OCV estimation,utilizing partial daily charging data.We incorporate a generative deep learning model to extract aging-related features from data and generate high-fidelity OCV curves.Correlation analysis is employed to identify the optimal partial charging data,optimizing the OCV estimation precision while preserving exceptional flexibility.The validation results,using data from nickel-cobalt-magnesium(NCM) batteries,illustrate the accurate estimation of the complete OCV-capacity curve,with an average root mean square errors(RMSE) of less than 3 mAh.Achieving this level of precision for OCV estimation requires only around 50 s collection of partial charging data.Further validations on diverse battery types operating under various conditions confirm the effectiveness of our proposed method.Additional cases of precise health diagnosis based on OCV highlight the significance of conducting online OCV estimation.Our method provides a flexible approach to achieve complete OCV estimation and holds promise for generalization to other tasks in BMSs.
文摘Cyberspace is extremely dynamic,with new attacks arising daily.Protecting cybersecurity controls is vital for network security.Deep Learning(DL)models find widespread use across various fields,with cybersecurity being one of the most crucial due to their rapid cyberattack detection capabilities on networks and hosts.The capabilities of DL in feature learning and analyzing extensive data volumes lead to the recognition of network traffic patterns.This study presents novel lightweight DL models,known as Cybernet models,for the detection and recognition of various cyber Distributed Denial of Service(DDoS)attacks.These models were constructed to have a reasonable number of learnable parameters,i.e.,less than 225,000,hence the name“lightweight.”This not only helps reduce the number of computations required but also results in faster training and inference times.Additionally,these models were designed to extract features in parallel from 1D Convolutional Neural Networks(CNN)and Long Short-Term Memory(LSTM),which makes them unique compared to earlier existing architectures and results in better performance measures.To validate their robustness and effectiveness,they were tested on the CIC-DDoS2019 dataset,which is an imbalanced and large dataset that contains different types of DDoS attacks.Experimental results revealed that bothmodels yielded promising results,with 99.99% for the detectionmodel and 99.76% for the recognition model in terms of accuracy,precision,recall,and F1 score.Furthermore,they outperformed the existing state-of-the-art models proposed for the same task.Thus,the proposed models can be used in cyber security research domains to successfully identify different types of attacks with a high detection and recognition rate.
基金supported by MRC,UK (MC_PC_17171)Royal Society,UK (RP202G0230)+8 种基金BHF,UK (AA/18/3/34220)Hope Foundation for Cancer Research,UK (RM60G0680)GCRF,UK (P202PF11)Sino-UK Industrial Fund,UK (RP202G0289)LIAS,UK (P202ED10,P202RE969)Data Science Enhancement Fund,UK (P202RE237)Fight for Sight,UK (24NN201)Sino-UK Education Fund,UK (OP202006)BBSRC,UK (RM32G0178B8).
文摘Aim:This study aims to establish an artificial intelligence model,ThyroidNet,to diagnose thyroid nodules using deep learning techniques accurately.Methods:A novel method,ThyroidNet,is introduced and evaluated based on deep learning for the localization and classification of thyroid nodules.First,we propose the multitask TransUnet,which combines the TransUnet encoder and decoder with multitask learning.Second,we propose the DualLoss function,tailored to the thyroid nodule localization and classification tasks.It balances the learning of the localization and classification tasks to help improve the model’s generalization ability.Third,we introduce strategies for augmenting the data.Finally,we submit a novel deep learning model,ThyroidNet,to accurately detect thyroid nodules.Results:ThyroidNet was evaluated on private datasets and was comparable to other existing methods,including U-Net and TransUnet.Experimental results show that ThyroidNet outperformed these methods in localizing and classifying thyroid nodules.It achieved improved accuracy of 3.9%and 1.5%,respectively.Conclusion:ThyroidNet significantly improves the clinical diagnosis of thyroid nodules and supports medical image analysis tasks.Future research directions include optimization of the model structure,expansion of the dataset size,reduction of computational complexity and memory requirements,and exploration of additional applications of ThyroidNet in medical image analysis.
基金the Deanship for Research Innovation,Ministry of Education in Saudi Arabia,for funding this research work through project number IFKSUDR-H122.
文摘In the current landscape of the COVID-19 pandemic,the utilization of deep learning in medical imaging,especially in chest computed tomography(CT)scan analysis for virus detection,has become increasingly significant.Despite its potential,deep learning’s“black box”nature has been a major impediment to its broader acceptance in clinical environments,where transparency in decision-making is imperative.To bridge this gap,our research integrates Explainable AI(XAI)techniques,specifically the Local Interpretable Model-Agnostic Explanations(LIME)method,with advanced deep learning models.This integration forms a sophisticated and transparent framework for COVID-19 identification,enhancing the capability of standard Convolutional Neural Network(CNN)models through transfer learning and data augmentation.Our approach leverages the refined DenseNet201 architecture for superior feature extraction and employs data augmentation strategies to foster robust model generalization.The pivotal element of our methodology is the use of LIME,which demystifies the AI decision-making process,providing clinicians with clear,interpretable insights into the AI’s reasoning.This unique combination of an optimized Deep Neural Network(DNN)with LIME not only elevates the precision in detecting COVID-19 cases but also equips healthcare professionals with a deeper understanding of the diagnostic process.Our method,validated on the SARS-COV-2 CT-Scan dataset,demonstrates exceptional diagnostic accuracy,with performance metrics that reinforce its potential for seamless integration into modern healthcare systems.This innovative approach marks a significant advancement in creating explainable and trustworthy AI tools for medical decisionmaking in the ongoing battle against COVID-19.
基金supported by the Project SP2023/074 Application of Machine and Process Control Advanced Methods supported by the Ministry of Education,Youth and Sports,Czech Republic.
文摘Computer vision(CV)was developed for computers and other systems to act or make recommendations based on visual inputs,such as digital photos,movies,and other media.Deep learning(DL)methods are more successful than other traditional machine learning(ML)methods inCV.DL techniques can produce state-of-the-art results for difficult CV problems like picture categorization,object detection,and face recognition.In this review,a structured discussion on the history,methods,and applications of DL methods to CV problems is presented.The sector-wise presentation of applications in this papermay be particularly useful for researchers in niche fields who have limited or introductory knowledge of DL methods and CV.This review will provide readers with context and examples of how these techniques can be applied to specific areas.A curated list of popular datasets and a brief description of them are also included for the benefit of readers.