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
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
极深因子分解机(eXtreme deep factorization machine,xDeepFM)是一种基于上下文感知的推荐模型,它提出了一种压缩交叉网络对特征进行阶数可控的特征交叉,并将该网络与深度神经网络进行结合以优化推荐效果。为了进一步提升xDeepFM在推...极深因子分解机(eXtreme deep factorization machine,xDeepFM)是一种基于上下文感知的推荐模型,它提出了一种压缩交叉网络对特征进行阶数可控的特征交叉,并将该网络与深度神经网络进行结合以优化推荐效果。为了进一步提升xDeepFM在推荐场景下的表现,提出一种基于场因子分解的xDeepFM改进模型。该模型通过场信息增强了特征的表达能力,并建立了多个交叉压缩网络以学习高阶组合特征。最后分析了用户场、项目场设定的合理性,并在3个不同规模的MovieLens系列数据集上通过受试者工作特征曲线下面积、对数似然损失指标进行性能评估,验证了该改进模型的有效性。展开更多
By automatically learning the priors embedded in images with powerful modelling ca-pabilities,deep learning-based algorithms have recently made considerable progress in reconstructing the high-resolution hyperspectral...By automatically learning the priors embedded in images with powerful modelling ca-pabilities,deep learning-based algorithms have recently made considerable progress in reconstructing the high-resolution hyperspectral(HR-HS)image.With previously collected large-amount of external data,these methods are intuitively realised under the full supervision of the ground-truth data.Thus,the database construction in merging the low-resolution(LR)HS(LR-HS)and HR multispectral(MS)or RGB image research paradigm,commonly named as HSI SR,requires collecting corresponding training triplets:HR-MS(RGB),LR-HS and HR-HS image simultaneously,and often faces dif-ficulties in reality.The learned models with the training datasets collected simultaneously under controlled conditions may significantly degrade the HSI super-resolved perfor-mance to the real images captured under diverse environments.To handle the above-mentioned limitations,the authors propose to leverage the deep internal and self-supervised learning to solve the HSI SR problem.The authors advocate that it is possible to train a specific CNN model at test time,called as deep internal learning(DIL),by on-line preparing the training triplet samples from the observed LR-HS/HR-MS(or RGB)images and the down-sampled LR-HS version.However,the number of the training triplets extracted solely from the transformed data of the observation itself is extremely few particularly for the HSI SR tasks with large spatial upscale factors,which would result in limited reconstruction performance.To solve this problem,the authors further exploit deep self-supervised learning(DSL)by considering the observations as the unlabelled training samples.Specifically,the degradation modules inside the network were elaborated to realise the spatial and spectral down-sampling procedures for transforming the generated HR-HS estimation to the high-resolution RGB/LR-HS approximation,and then the reconstruction errors of the observations were formulated for measuring the network modelling performance.By consolidating the DIL and DSL into a unified deep framework,the authors construct a more robust HSI SR method without any prior training and have great potential of flexible adaptation to different settings per obser-vation.To verify the effectiveness of the proposed approach,extensive experiments have been conducted on two benchmark HS datasets,including the CAVE and Harvard datasets,and demonstrate the great performance gain of the proposed method over the state-of-the-art methods.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
Spectral compressive imaging has emerged as a powerful technique to collect the 3D spectral information as 2D measurements.The algorithm for restoring the original 3D hyperspectral images(HSIs)from compressive measure...Spectral compressive imaging has emerged as a powerful technique to collect the 3D spectral information as 2D measurements.The algorithm for restoring the original 3D hyperspectral images(HSIs)from compressive measurements is pivotal in the imaging process.Early approaches painstakingly designed networks to directly map compressive measurements to HSIs,resulting in the lack of interpretability without exploiting the imaging priors.While some recent works have introduced the deep unfolding framework for explainable reconstruction,the performance of these methods is still limited by the weak information transmission between iterative stages.In this paper,we propose a Memory-Augmented deep Unfolding Network,termed MAUN,for explainable and accurate HSI reconstruction.Specifically,MAUN implements a novel CNN scheme to facilitate a better extrapolation step of the fast iterative shrinkage-thresholding algorithm,introducing an extra momentum incorporation step for each iteration to alleviate the information loss.Moreover,to exploit the high correlation of intermediate images from neighboring iterations,we customize a cross-stage transformer(CSFormer)as the deep denoiser to simultaneously capture self-similarity from both in-stage and cross-stage features,which is the first attempt to model the long-distance dependencies between iteration stages.Extensive experiments demonstrate that the proposed MAUN is superior to other state-of-the-art methods both visually and metrically.Our code is publicly available at https://github.com/HuQ1an/MAUN.展开更多
Dear Editor,This letter presents a multi-automated guided vehicles(AGV) routing planning method based on deep reinforcement learning(DRL)and recurrent neural network(RNN), specifically utilizing proximal policy optimi...Dear Editor,This letter presents a multi-automated guided vehicles(AGV) routing planning method based on deep reinforcement learning(DRL)and recurrent neural network(RNN), specifically utilizing proximal policy optimization(PPO) and long short-term memory(LSTM).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
Dear Editor,This letter develops a novel method to implement event-triggered optimal control(ETOC) for discrete-time nonlinear systems using parallel control and deep reinforcement learning(DRL), referred to as Deep-E...Dear Editor,This letter develops a novel method to implement event-triggered optimal control(ETOC) for discrete-time nonlinear systems using parallel control and deep reinforcement learning(DRL), referred to as Deep-ETOC. The developed Deep-ETOC method introduces the communication cost into the performance index through parallel control, so that the developed method enables control systems to learn ETOC policies directly without triggering conditions.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
The tell tail is usually placed on the triangular sail to display the running state of the air flow on the sail surface.It is of great significance to make accurate judgement on the drift of the tell tail of the sailb...The tell tail is usually placed on the triangular sail to display the running state of the air flow on the sail surface.It is of great significance to make accurate judgement on the drift of the tell tail of the sailboat during sailing for the best sailing effect.Normally it is difficult for sailors to keep an eye for a long time on the tell sail for accurate judging its changes,affected by strong sunlight and visual fatigue.In this case,we adopt computer vision technology in hope of helping the sailors judge the changes of the tell tail in ease with ease.This paper proposes for the first time a method to classify sailboat tell tails based on deep learning and an expert guidance system,supported by a sailboat tell tail classification data set on the expert guidance system of interpreting the tell tails states in different sea wind conditions,including the feature extraction performance.Considering the expression capabilities that vary with the computational features in different visual tasks,the paper focuses on five tell tail computing features,which are recoded by an automatic encoder and classified by a SVM classifier.All experimental samples were randomly divided into five groups,and four groups were selected from each group as the training set to train the classifier.The remaining one group was used as the test set for testing.The highest resolution value of the ResNet network was 80.26%.To achieve better operational results on the basis of deep computing features obtained through the ResNet network in the experiments.The method can be used to assist the sailors in making better judgement about the tell tail changes during sailing.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
Object Constraint Language(OCL)is one kind of lightweight formal specification,which is widely used for software verification and validation in NASA and Object Management Group projects.Although OCL provides a simple ...Object Constraint Language(OCL)is one kind of lightweight formal specification,which is widely used for software verification and validation in NASA and Object Management Group projects.Although OCL provides a simple expressive syntax,it is hard for the developers to write correctly due to lacking knowledge of the mathematical foundations of the first-order logic,which is approximately half accurate at the first stage of devel-opment.A deep neural network named DeepOCL is proposed,which takes the unre-stricted natural language as inputs and automatically outputs the best-scored OCL candidates without requiring a domain conceptual model that is compulsively required in existing rule-based generation approaches.To demonstrate the validity of our proposed approach,ablation experiments were conducted on a new sentence-aligned dataset named OCLPairs.The experiments show that the proposed DeepOCL can achieve state of the art for OCL statement generation,scored 74.30 on BLEU,and greatly outperformed experienced developers by 35.19%.The proposed approach is the first deep learning approach to generate the OCL expression from the natural language.It can be further developed as a CASE tool for the software industry.展开更多
Background:Gallbladder carcinoma(GBC)is highly malignant,and its early diagnosis remains difficult.This study aimed to develop a deep learning model based on contrast-enhanced computed tomography(CT)images to assist r...Background:Gallbladder carcinoma(GBC)is highly malignant,and its early diagnosis remains difficult.This study aimed to develop a deep learning model based on contrast-enhanced computed tomography(CT)images to assist radiologists in identifying GBC.Methods:We retrospectively enrolled 278 patients with gallbladder lesions(>10 mm)who underwent contrast-enhanced CT and cholecystectomy and divided them into the training(n=194)and validation(n=84)datasets.The deep learning model was developed based on ResNet50 network.Radiomics and clinical models were built based on support vector machine(SVM)method.We comprehensively compared the performance of deep learning,radiomics,clinical models,and three radiologists.Results:Three radiomics features including LoG_3.0 gray-level size zone matrix zone variance,HHL firstorder kurtosis,and LHL gray-level co-occurrence matrix dependence variance were significantly different between benign gallbladder lesions and GBC,and were selected for developing radiomics model.Multivariate regression analysis revealed that age≥65 years[odds ratios(OR)=4.4,95%confidence interval(CI):2.1-9.1,P<0.001],lesion size(OR=2.6,95%CI:1.6-4.1,P<0.001),and CA-19-9>37 U/mL(OR=4.0,95%CI:1.6-10.0,P=0.003)were significant clinical risk factors of GBC.The deep learning model achieved the area under the receiver operating characteristic curve(AUC)values of 0.864(95%CI:0.814-0.915)and 0.857(95%CI:0.773-0.942)in the training and validation datasets,which were comparable with radiomics,clinical models and three radiologists.The sensitivity of deep learning model was the highest both in the training[90%(95%CI:82%-96%)]and validation[85%(95%CI:68%-95%)]datasets.Conclusions:The deep learning model may be a useful tool for radiologists to distinguish between GBC and benign gallbladder lesions.展开更多
This study comprehensively examines the current state of deep learning (DL) usage in indoor positioning.It emphasizes the significance and efficiency of convolutional neural networks (CNNs) and recurrent neuralnetwork...This study comprehensively examines the current state of deep learning (DL) usage in indoor positioning.It emphasizes the significance and efficiency of convolutional neural networks (CNNs) and recurrent neuralnetworks (RNNs). Unlike prior studies focused on single sensor modalities like Wi-Fi or Bluetooth, this researchexplores the integration of multiple sensor modalities (e.g.,Wi-Fi, Bluetooth, Ultra-Wideband, ZigBee) to expandindoor localization methods, particularly in obstructed environments. It addresses the challenge of precise objectlocalization, introducing a novel hybrid DL approach using received signal information (RSI), Received SignalStrength (RSS), and Channel State Information (CSI) data to enhance accuracy and stability. Moreover, thestudy introduces a device-free indoor localization algorithm, offering a significant advancement with potentialobject or individual tracking applications. It recognizes the increasing importance of indoor positioning forlocation-based services. It anticipates future developments while acknowledging challenges such as multipathinterference, noise, data standardization, and scarcity of labeled data. This research contributes significantly toindoor localization technology, offering adaptability, device independence, and multifaceted DL-based solutionsfor real-world challenges and future advancements. Thus, the proposed work addresses challenges in objectlocalization precision and introduces a novel hybrid deep learning approach, contributing to advancing locationcentricservices.While deep learning-based indoor localization techniques have improved accuracy, challenges likedata noise, standardization, and availability of training data persist. However, ongoing developments are expectedto enhance indoor positioning systems to meet real-world demands.展开更多
Glaucoma disease causes irreversible damage to the optical nerve and it has the potential to cause permanent loss of vision.Glaucoma ranks as the second most prevalent cause of permanent blindness.Traditional glaucoma...Glaucoma disease causes irreversible damage to the optical nerve and it has the potential to cause permanent loss of vision.Glaucoma ranks as the second most prevalent cause of permanent blindness.Traditional glaucoma diagnosis requires a highly experienced specialist,costly equipment,and a lengthy wait time.For automatic glaucoma detection,state-of-the-art glaucoma detection methods include a segmentation-based method to calculate the cup-to-disc ratio.Other methods include multi-label segmentation networks and learning-based methods and rely on hand-crafted features.Localizing the optic disc(OD)is one of the key features in retinal images for detecting retinal diseases,especially for glaucoma disease detection.The approach presented in this study is based on deep classifiers for OD segmentation and glaucoma detection.First,the optic disc detection process is based on object detection using a Mask Region-Based Convolutional Neural Network(Mask-RCNN).The OD detection task was validated using the Dice score,intersection over union,and accuracy metrics.The OD region is then fed into the second stage for glaucoma detection.Therefore,considering only the OD area for glaucoma detection will reduce the number of classification artifacts by limiting the assessment to the optic disc area.For this task,VGG-16(Visual Geometry Group),Resnet-18(Residual Network),and Inception-v3 were pre-trained and fine-tuned.We also used the Support Vector Machine Classifier.The feature-based method uses region content features obtained by Histogram of Oriented Gradients(HOG)and Gabor Filters.The final decision is based on weighted fusion.A comparison of the obtained results from all classification approaches is provided.Classification metrics including accuracy and ROC curve are compared for each classification method.The novelty of this research project is the integration of automatic OD detection and glaucoma diagnosis in a global method.Moreover,the fusion-based decision system uses the glaucoma detection result obtained using several convolutional deep neural networks and the support vector machine classifier.These classification methods contribute to producing robust classification results.This method was evaluated using well-known retinal images available for research work and a combined dataset including retinal images with and without pathology.The performance of the models was tested on two public datasets and a combined dataset and was compared to similar research.The research findings show the potential of this methodology in the early detection of glaucoma,which will reduce diagnosis time and increase detection efficiency.The glaucoma assessment achieves about 98%accuracy in the classification rate,which is close to and even higher than that of state-of-the-art methods.The designed detection model may be used in telemedicine,healthcare,and computer-aided diagnosis systems.展开更多
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.
文摘极深因子分解机(eXtreme deep factorization machine,xDeepFM)是一种基于上下文感知的推荐模型,它提出了一种压缩交叉网络对特征进行阶数可控的特征交叉,并将该网络与深度神经网络进行结合以优化推荐效果。为了进一步提升xDeepFM在推荐场景下的表现,提出一种基于场因子分解的xDeepFM改进模型。该模型通过场信息增强了特征的表达能力,并建立了多个交叉压缩网络以学习高阶组合特征。最后分析了用户场、项目场设定的合理性,并在3个不同规模的MovieLens系列数据集上通过受试者工作特征曲线下面积、对数似然损失指标进行性能评估,验证了该改进模型的有效性。
基金Ministry of Education,Culture,Sports,Science and Technology,Grant/Award Number:20K11867。
文摘By automatically learning the priors embedded in images with powerful modelling ca-pabilities,deep learning-based algorithms have recently made considerable progress in reconstructing the high-resolution hyperspectral(HR-HS)image.With previously collected large-amount of external data,these methods are intuitively realised under the full supervision of the ground-truth data.Thus,the database construction in merging the low-resolution(LR)HS(LR-HS)and HR multispectral(MS)or RGB image research paradigm,commonly named as HSI SR,requires collecting corresponding training triplets:HR-MS(RGB),LR-HS and HR-HS image simultaneously,and often faces dif-ficulties in reality.The learned models with the training datasets collected simultaneously under controlled conditions may significantly degrade the HSI super-resolved perfor-mance to the real images captured under diverse environments.To handle the above-mentioned limitations,the authors propose to leverage the deep internal and self-supervised learning to solve the HSI SR problem.The authors advocate that it is possible to train a specific CNN model at test time,called as deep internal learning(DIL),by on-line preparing the training triplet samples from the observed LR-HS/HR-MS(or RGB)images and the down-sampled LR-HS version.However,the number of the training triplets extracted solely from the transformed data of the observation itself is extremely few particularly for the HSI SR tasks with large spatial upscale factors,which would result in limited reconstruction performance.To solve this problem,the authors further exploit deep self-supervised learning(DSL)by considering the observations as the unlabelled training samples.Specifically,the degradation modules inside the network were elaborated to realise the spatial and spectral down-sampling procedures for transforming the generated HR-HS estimation to the high-resolution RGB/LR-HS approximation,and then the reconstruction errors of the observations were formulated for measuring the network modelling performance.By consolidating the DIL and DSL into a unified deep framework,the authors construct a more robust HSI SR method without any prior training and have great potential of flexible adaptation to different settings per obser-vation.To verify the effectiveness of the proposed approach,extensive experiments have been conducted on two benchmark HS datasets,including the CAVE and Harvard datasets,and demonstrate the great performance gain of the proposed method over the state-of-the-art methods.
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supported by the National Natural Science Foundation of China(62276192)。
文摘Spectral compressive imaging has emerged as a powerful technique to collect the 3D spectral information as 2D measurements.The algorithm for restoring the original 3D hyperspectral images(HSIs)from compressive measurements is pivotal in the imaging process.Early approaches painstakingly designed networks to directly map compressive measurements to HSIs,resulting in the lack of interpretability without exploiting the imaging priors.While some recent works have introduced the deep unfolding framework for explainable reconstruction,the performance of these methods is still limited by the weak information transmission between iterative stages.In this paper,we propose a Memory-Augmented deep Unfolding Network,termed MAUN,for explainable and accurate HSI reconstruction.Specifically,MAUN implements a novel CNN scheme to facilitate a better extrapolation step of the fast iterative shrinkage-thresholding algorithm,introducing an extra momentum incorporation step for each iteration to alleviate the information loss.Moreover,to exploit the high correlation of intermediate images from neighboring iterations,we customize a cross-stage transformer(CSFormer)as the deep denoiser to simultaneously capture self-similarity from both in-stage and cross-stage features,which is the first attempt to model the long-distance dependencies between iteration stages.Extensive experiments demonstrate that the proposed MAUN is superior to other state-of-the-art methods both visually and metrically.Our code is publicly available at https://github.com/HuQ1an/MAUN.
基金supported by the National Natural Science Foundation of China (62202352,61902039,61972300)the Basic and Applied Basic Research Program of Guangdong Province (2021A1515110518)the Key Research and Development Program of Shaanxi Province (2020ZDLGY09-04)。
文摘Dear Editor,This letter presents a multi-automated guided vehicles(AGV) routing planning method based on deep reinforcement learning(DRL)and recurrent neural network(RNN), specifically utilizing proximal policy optimization(PPO) and long short-term memory(LSTM).
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.
基金supported by the Motion G,Inc.Collaborative Research Project for Fundamental Modeling and Parallel Drive-Control of Servo Drive Systems。
文摘Dear Editor,This letter develops a novel method to implement event-triggered optimal control(ETOC) for discrete-time nonlinear systems using parallel control and deep reinforcement learning(DRL), referred to as Deep-ETOC. The developed Deep-ETOC method introduces the communication cost into the performance index through parallel control, so that the developed method enables control systems to learn ETOC policies directly without triggering conditions.
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.
基金supported by the Shandong Provin-cial Key Research Project of Undergraduate Teaching Reform(No.Z2022218)the Fundamental Research Funds for the Central University(No.202113028)+1 种基金the Graduate Education Promotion Program of Ocean University of China(No.HDJG20006)supported by the Sailing Laboratory of Ocean University of China.
文摘The tell tail is usually placed on the triangular sail to display the running state of the air flow on the sail surface.It is of great significance to make accurate judgement on the drift of the tell tail of the sailboat during sailing for the best sailing effect.Normally it is difficult for sailors to keep an eye for a long time on the tell sail for accurate judging its changes,affected by strong sunlight and visual fatigue.In this case,we adopt computer vision technology in hope of helping the sailors judge the changes of the tell tail in ease with ease.This paper proposes for the first time a method to classify sailboat tell tails based on deep learning and an expert guidance system,supported by a sailboat tell tail classification data set on the expert guidance system of interpreting the tell tails states in different sea wind conditions,including the feature extraction performance.Considering the expression capabilities that vary with the computational features in different visual tasks,the paper focuses on five tell tail computing features,which are recoded by an automatic encoder and classified by a SVM classifier.All experimental samples were randomly divided into five groups,and four groups were selected from each group as the training set to train the classifier.The remaining one group was used as the test set for testing.The highest resolution value of the ResNet network was 80.26%.To achieve better operational results on the basis of deep computing features obtained through the ResNet network in the experiments.The method can be used to assist the sailors in making better judgement about the tell tail changes during sailing.
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.
基金The National Key Research and Development Program of China,Grant/Award Number:2021YFB2501301。
文摘Object Constraint Language(OCL)is one kind of lightweight formal specification,which is widely used for software verification and validation in NASA and Object Management Group projects.Although OCL provides a simple expressive syntax,it is hard for the developers to write correctly due to lacking knowledge of the mathematical foundations of the first-order logic,which is approximately half accurate at the first stage of devel-opment.A deep neural network named DeepOCL is proposed,which takes the unre-stricted natural language as inputs and automatically outputs the best-scored OCL candidates without requiring a domain conceptual model that is compulsively required in existing rule-based generation approaches.To demonstrate the validity of our proposed approach,ablation experiments were conducted on a new sentence-aligned dataset named OCLPairs.The experiments show that the proposed DeepOCL can achieve state of the art for OCL statement generation,scored 74.30 on BLEU,and greatly outperformed experienced developers by 35.19%.The proposed approach is the first deep learning approach to generate the OCL expression from the natural language.It can be further developed as a CASE tool for the software industry.
基金the National Natural Science Foundation of China(81572975)Key Research and Devel-opment Project of Science and Technology Department of Zhejiang(2015C03053)+1 种基金Chen Xiao-Ping Foundation for the Development of Science and Technology of Hubei Province(CXPJJH11900009-07)Zhejiang Provincial Program for the Cultivation of High-level Innovative Health Talents.
文摘Background:Gallbladder carcinoma(GBC)is highly malignant,and its early diagnosis remains difficult.This study aimed to develop a deep learning model based on contrast-enhanced computed tomography(CT)images to assist radiologists in identifying GBC.Methods:We retrospectively enrolled 278 patients with gallbladder lesions(>10 mm)who underwent contrast-enhanced CT and cholecystectomy and divided them into the training(n=194)and validation(n=84)datasets.The deep learning model was developed based on ResNet50 network.Radiomics and clinical models were built based on support vector machine(SVM)method.We comprehensively compared the performance of deep learning,radiomics,clinical models,and three radiologists.Results:Three radiomics features including LoG_3.0 gray-level size zone matrix zone variance,HHL firstorder kurtosis,and LHL gray-level co-occurrence matrix dependence variance were significantly different between benign gallbladder lesions and GBC,and were selected for developing radiomics model.Multivariate regression analysis revealed that age≥65 years[odds ratios(OR)=4.4,95%confidence interval(CI):2.1-9.1,P<0.001],lesion size(OR=2.6,95%CI:1.6-4.1,P<0.001),and CA-19-9>37 U/mL(OR=4.0,95%CI:1.6-10.0,P=0.003)were significant clinical risk factors of GBC.The deep learning model achieved the area under the receiver operating characteristic curve(AUC)values of 0.864(95%CI:0.814-0.915)and 0.857(95%CI:0.773-0.942)in the training and validation datasets,which were comparable with radiomics,clinical models and three radiologists.The sensitivity of deep learning model was the highest both in the training[90%(95%CI:82%-96%)]and validation[85%(95%CI:68%-95%)]datasets.Conclusions:The deep learning model may be a useful tool for radiologists to distinguish between GBC and benign gallbladder lesions.
基金the Fundamental Research Grant Scheme-FRGS/1/2021/ICT09/MMU/02/1,Ministry of Higher Education,Malaysia.
文摘This study comprehensively examines the current state of deep learning (DL) usage in indoor positioning.It emphasizes the significance and efficiency of convolutional neural networks (CNNs) and recurrent neuralnetworks (RNNs). Unlike prior studies focused on single sensor modalities like Wi-Fi or Bluetooth, this researchexplores the integration of multiple sensor modalities (e.g.,Wi-Fi, Bluetooth, Ultra-Wideband, ZigBee) to expandindoor localization methods, particularly in obstructed environments. It addresses the challenge of precise objectlocalization, introducing a novel hybrid DL approach using received signal information (RSI), Received SignalStrength (RSS), and Channel State Information (CSI) data to enhance accuracy and stability. Moreover, thestudy introduces a device-free indoor localization algorithm, offering a significant advancement with potentialobject or individual tracking applications. It recognizes the increasing importance of indoor positioning forlocation-based services. It anticipates future developments while acknowledging challenges such as multipathinterference, noise, data standardization, and scarcity of labeled data. This research contributes significantly toindoor localization technology, offering adaptability, device independence, and multifaceted DL-based solutionsfor real-world challenges and future advancements. Thus, the proposed work addresses challenges in objectlocalization precision and introduces a novel hybrid deep learning approach, contributing to advancing locationcentricservices.While deep learning-based indoor localization techniques have improved accuracy, challenges likedata noise, standardization, and availability of training data persist. However, ongoing developments are expectedto enhance indoor positioning systems to meet real-world demands.
基金Deanship of Scientific Research,Princess Nourah bint Abdulrahman University,through the Program of Research Project Funding after Publication,Grant No(43-PRFA-P-31).
文摘Glaucoma disease causes irreversible damage to the optical nerve and it has the potential to cause permanent loss of vision.Glaucoma ranks as the second most prevalent cause of permanent blindness.Traditional glaucoma diagnosis requires a highly experienced specialist,costly equipment,and a lengthy wait time.For automatic glaucoma detection,state-of-the-art glaucoma detection methods include a segmentation-based method to calculate the cup-to-disc ratio.Other methods include multi-label segmentation networks and learning-based methods and rely on hand-crafted features.Localizing the optic disc(OD)is one of the key features in retinal images for detecting retinal diseases,especially for glaucoma disease detection.The approach presented in this study is based on deep classifiers for OD segmentation and glaucoma detection.First,the optic disc detection process is based on object detection using a Mask Region-Based Convolutional Neural Network(Mask-RCNN).The OD detection task was validated using the Dice score,intersection over union,and accuracy metrics.The OD region is then fed into the second stage for glaucoma detection.Therefore,considering only the OD area for glaucoma detection will reduce the number of classification artifacts by limiting the assessment to the optic disc area.For this task,VGG-16(Visual Geometry Group),Resnet-18(Residual Network),and Inception-v3 were pre-trained and fine-tuned.We also used the Support Vector Machine Classifier.The feature-based method uses region content features obtained by Histogram of Oriented Gradients(HOG)and Gabor Filters.The final decision is based on weighted fusion.A comparison of the obtained results from all classification approaches is provided.Classification metrics including accuracy and ROC curve are compared for each classification method.The novelty of this research project is the integration of automatic OD detection and glaucoma diagnosis in a global method.Moreover,the fusion-based decision system uses the glaucoma detection result obtained using several convolutional deep neural networks and the support vector machine classifier.These classification methods contribute to producing robust classification results.This method was evaluated using well-known retinal images available for research work and a combined dataset including retinal images with and without pathology.The performance of the models was tested on two public datasets and a combined dataset and was compared to similar research.The research findings show the potential of this methodology in the early detection of glaucoma,which will reduce diagnosis time and increase detection efficiency.The glaucoma assessment achieves about 98%accuracy in the classification rate,which is close to and even higher than that of state-of-the-art methods.The designed detection model may be used in telemedicine,healthcare,and computer-aided diagnosis systems.