Early identification of stroke through deep learning with multi-modal human speech and movement data

Early identification and treatment of stroke can greatly improve patient outcomes and quality of life.Although clinical tests such as the Cincinnati Pre-hospital Stroke Scale(CPSS)and the Face Arm Speech Test(FAST)are commonly used for stroke screening,accurate administration is dependent on specialized training.In this study,we proposed a novel multimodal deep learning approach,based on the FAST,for assessing suspected stroke patients exhibiting symptoms such as limb weakness,facial paresis,and speech disorders in acute settings.We collected a dataset comprising videos and audio recordings of emergency room patients performing designated limb movements,facial expressions,and speech tests based on the FAST.We compared the constructed deep learning model,which was designed to process multi-modal datasets,with six prior models that achieved good action classification performance,including the I3D,SlowFast,X3D,TPN,TimeSformer,and MViT.We found that the findings of our deep learning model had a higher clinical value compared with the other approaches.Moreover,the multi-modal model outperformed its single-module variants,highlighting the benefit of utilizing multiple types of patient data,such as action videos and speech audio.These results indicate that a multi-modal deep learning model combined with the FAST could greatly improve the accuracy and sensitivity of early stroke identification of stroke,thus providing a practical and powerful tool for assessing stroke patients in an emergency clinical setting.

Deep eutectic solvents for separation and purification applications in critical metal metallurgy:Recent advances and perspectives

Solvent extraction,a separation and purification technology,is crucial in critical metal metallurgy.Organic solvents commonly used in solvent extraction exhibit disadvantages,such as high volatility,high toxicity,and flammability,causing a spectrum of hazards to human health and environmental safety.Neoteric solvents have been recognized as potential alternatives to these harmful organic solvents.In the past two decades,several neoteric solvents have been proposed,including ionic liquids(ILs)and deep eutectic solvents(DESs).DESs have gradually become the focus of green solvents owing to several advantages,namely,low toxicity,degradability,and low cost.In this critical review,their classification,formation mechanisms,preparation methods,characterization technologies,and special physicochemical properties based on the most recent advancements in research have been systematically described.Subsequently,the major separation and purification applications of DESs in critical metal metallurgy were comprehensively summarized.Finally,future opportunities and challenges of DESs were explored in the current research area.In conclusion,this review provides valuable insights for improving our overall understanding of DESs,and it holds important potential for expanding separation and purification applications in critical metal metallurgy.

An Enhanced Lung Cancer Detection Approach Using Dual-Model Deep Learning Technique

Lung cancer continues to be a leading cause of cancer-related deaths worldwide,emphasizing the critical need for improved diagnostic techniques.Early detection of lung tumors significantly increases the chances of successful treatment and survival.However,current diagnostic methods often fail to detect tumors at an early stage or to accurately pinpoint their location within the lung tissue.Single-model deep learning technologies for lung cancer detection,while beneficial,cannot capture the full range of features present in medical imaging data,leading to incomplete or inaccurate detection.Furthermore,it may not be robust enough to handle the wide variability in medical images due to different imaging conditions,patient anatomy,and tumor characteristics.To overcome these disadvantages,dual-model or multi-model approaches can be employed.This research focuses on enhancing the detection of lung cancer by utilizing a combination of two learning models:a Convolutional Neural Network(CNN)for categorization and the You Only Look Once(YOLOv8)architecture for real-time identification and pinpointing of tumors.CNNs automatically learn to extract hierarchical features from raw image data,capturing patterns such as edges,textures,and complex structures that are crucial for identifying lung cancer.YOLOv8 incorporates multiscale feature extraction,enabling the detection of tumors of varying sizes and scales within a single image.This is particularly beneficial for identifying small or irregularly shaped tumors that may be challenging to detect.Furthermore,through the utilization of cutting-edge data augmentation methods,such as Deep Convolutional Generative Adversarial Networks(DCGAN),the suggested approach can handle the issue of limited data and boost the models’ability to learn from diverse and comprehensive datasets.The combined method not only improved accuracy and localization but also ensured efficient real-time processing,which is crucial for practical clinical applications.The CNN achieved an accuracy of 97.67%in classifying lung tissues into healthy and cancerous categories.The YOLOv8 model achieved an Intersection over Union(IoU)score of 0.85 for tumor localization,reflecting high precision in detecting and marking tumor boundaries within the images.Finally,the incorporation of synthetic images generated by DCGAN led to a 10%improvement in both the CNN classification accuracy and YOLOv8 detection performance.

Comparative analysis of empirical and deep learning models for ionospheric sporadic E layer prediction

Sporadic E(Es)layers in the ionosphere are characterized by intense plasma irregularities in the E region at altitudes of 90-130 km.Because they can significantly influence radio communications and navigation systems,accurate forecasting of Es layers is crucial for ensuring the precision and dependability of navigation satellite systems.In this study,we present Es predictions made by an empirical model and by a deep learning model,and analyze their differences comprehensively by comparing the model predictions to satellite RO measurements and ground-based ionosonde observations.The deep learning model exhibited significantly better performance,as indicated by its high coefficient of correlation(r=0.87)with RO observations and predictions,than did the empirical model(r=0.53).This study highlights the importance of integrating artificial intelligence technology into ionosphere modelling generally,and into predicting Es layer occurrences and characteristics,in particular.

DEEP NEURAL NETWORKS COMBINING MULTI-TASK LEARNING FOR SOLVING DELAY INTEGRO-DIFFERENTIAL EQUATIONS

Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.

Advancements in Liver Tumor Detection:A Comprehensive Review of Various Deep Learning Models

Liver cancer remains a leading cause of mortality worldwide,and precise diagnostic tools are essential for effective treatment planning.Liver Tumors(LTs)vary significantly in size,shape,and location,and can present with tissues of similar intensities,making automatically segmenting and classifying LTs from abdominal tomography images crucial and challenging.This review examines recent advancements in Liver Segmentation(LS)and Tumor Segmentation(TS)algorithms,highlighting their strengths and limitations regarding precision,automation,and resilience.Performance metrics are utilized to assess key detection algorithms and analytical methods,emphasizing their effectiveness and relevance in clinical contexts.The review also addresses ongoing challenges in liver tumor segmentation and identification,such as managing high variability in patient data and ensuring robustness across different imaging conditions.It suggests directions for future research,with insights into technological advancements that can enhance surgical planning and diagnostic accuracy by comparing popular methods.This paper contributes to a comprehensive understanding of current liver tumor detection techniques,provides a roadmap for future innovations,and improves diagnostic and therapeutic outcomes for liver cancer by integrating recent progress with remaining challenges.

基于Deep Forest算法的对虾急性肝胰腺坏死病(AHPND)预警数学模型构建

为预报池塘养殖凡纳对虾(Penaeus vannamei)急性肝胰腺坏死病(AHPND)的发生,自2020年开始,笔者对凡纳对虾养殖区开展了连续监测工作,包括与疾病发生相关的环境理化因子、微生物因子、虾体自身健康状况等18个候选预警因子指标,通过数据标准化处理后分析病原、宿主与环境之间的相关性,对候选预警因子进行筛选,基于Python语言编程结合Deep Forest、Light GBM、XGBoost算法进行数据建模和预测性能评判,仿真环境为Python2.7,以预警因子指标作为输入样本(即警兆),以对虾是否发病指标作为输出结果(即警情),根据输入样本和输出结果各自建立输入数据矩阵和目标数据矩阵,利用原始数据矩阵对输入样本进行初始化,结合函数方程进行拟合,拟合的源代码能利用已知环境、病原及对虾免疫指标数据对目标警情进行预测。最终建立了基于Deep Forest算法的虾体(肝胰腺内)细菌总数、虾体弧菌(Vibrio)占比、水体细菌总数和盐度的4维向量预警预报模型,准确率达89.00%。本研究将人工智能算法应用到对虾AHPND发生的预测预报,相关研究结果为对虾AHPND疾病预警预报建立了预警数学模型,并为对虾健康养殖和疾病防控提供了技术支撑和有力保障。

基于DeepLabv3+的船体结构腐蚀检测方法

利用图像识别方法对无人机、机器人所采集的实时图像开展船体结构腐蚀检测,可有效提高检验检测效率和数字化、智能化水平,具有极大的应用价值和潜力,将改变传统的船体结构检验检测方式。提出一种基于DeepLabv3+的船体结构腐蚀检测模型,通过收集图像样本并进行三种腐蚀类别的分割标注,基于DeepLabv3+语义分割模型进行网络的训练,预测图片中腐蚀的像素点类别和区域,模型在测试集的精准率达到52.92%,证明了使用DeepLabv3+检测船体腐蚀缺陷的可行性。

基于M-DeepLab网络的速度建模技术研究

本文提出了一种适用于速度建模方法的M-DeepLab网络框架,该网络将地震炮集记录作为输入,网络主体使用轻量级MobileNet,以此提升网络训练速度;并在编码环节ASPP模块后添加了Attention模块,且在解码环节将不同网络深度的速度特征进行了融合,既获得了更多的速度特征,又保留了网络浅部的速度信息,防止出现网络退化和过拟合问题。模型测试证明,M-DeepLab网络能够实现智能、精确的速度建模,简单模型、复杂模型以及含有噪声数据复杂模型的智能速度建模,均取得了良好的效果。相较DeepLabV3+网络,本文方法对于速度模型界面处的预测,特别是速度突变区域的预测,具有更高的预测精度,从而验证了该方法精确性、高效性、实用性和抗噪性。

基于改进DeepLabV3+的指针式仪表智能识别方法设计

针对现有仪表识别方法存在的诸如对表盘差异敏感、环境干扰严重以及图像质量依赖性强导致识别准确率不高的问题,提出了一种基于改进DeepLabV3+的指针式仪表智能识别算法。通过引入GhostNetV2作为主干网络进行特征提取,并添加注意力模块CBAM,有效提升了模型在仪表语义分割任务的精度;同时设计了多类仪表的示值识别算法,实现了对多类仪表的指针读数。通过在构建的指针式仪表识别数据集上对算法进行评估,结果表明,仪表智能识别算法能够适应多种仪表类型和复杂环境,识别准确率最高达99.67%,且改进的DeepLabV3+模型平均IoU达79.8%,性能优于原始模型,能够满足实际工业应用需求。

基于DeeplabV3+网络的轻量化语义分割算法

针对传统语义分割模型参数量大、计算速度慢且效率不高等问题,改进一种基于DeeplabV3+网络的轻量化语义分割模型Faster-DeeplabV3+。Faster-DeeplabV3+模型采用轻量级MobilenetV2代替Xception作为主干特征提取网络,大幅减少参数量,提高计算速度;引入深度可分离卷积(deep separable convolution, DSC)与空洞空间金字塔(atrous spatia pyramid pooling, ASPP)中的膨胀卷积设计成新的深度可分离膨胀卷积(depthwise separable dilated convolution, DSD-Conv),即组成深度可分离空洞空间金字塔模块(DP-ASPP),扩大感受野的同时减少原本卷积参数量,提高运算速度;加入改进的双注意力机制模块分别对编码区生成的低级特征图和高级特征图进行处理,增强网络对不同维度特征信息提取的敏感性和准确性;融合使用交叉熵和Dice Loss两种损失函数,为模型提供更全面、更多样的优化。改进模型在PASCAL VOC 2012数据集上进行测试。实验结果表明:平均交并比由76.57%提升至79.07%,分割准确度由91.2%提升至94.3%。改进模型的网络参数量(params)减少了3.86×10~6,浮点计算量(GFLOPs)减少了117.98 G。因此,Faster-DeeplabV3+算法在大幅降低参数量、提高运算速度的同时保持较高语义分割效果。

基于YOLO+DeepSort的出租车检测及交通流影响研究

为了解决出租车与黄色小型车辆外观相似、不易区分的问题,以哈尔滨市出租车为研究对象,以YOLOv5+DeepSort为基本框架,新增交通量与速度检测模块。基于视频采集数据,建立出租车目标检测数据集与出租车图像数据集,采用深度学习方法构建车型识别模型。建立了考虑出租车比例因素的速度影响模型,分析了畅行状态下出租车运行特征。结果表明:结合深度学习的出租车车型识别精确率高达0.88;畅行状态下出租车平均速度比其他车型高5~15 km/h;出租车比例对全局平均速度及速度-流量曲线增长趋势存在一定影响;考虑出租车比例的速度影响模型在继承传统BPR模型优点的同时,精度提升了20%左右。

基于注意力机制改进的DeepLabV3+遥感图像分割算法

DeepLabV3+分割算法具有高效的编解码结构,常用在图像分割任务中。针对DeepLabV3+高分辨率遥感图像语义分割中存在的分割目标边缘不精确和孔洞缺陷问题,提出了一种基于注意力机制改进的DeepLabV3+遥感图像分割算法。构建ECBA(Efficient Convolutional Block Attention Module)注意力机制,将ECBA添加至DeepLabV3+主干网络Xception,增强其特征提取能力,得到注意力加权的高层特征。同时,将ECBA添加至编码器和解码器的连接支路,得到注意力加权后的低层特征。解码器将两种特征进行特征融合,以增强网络对不同分割目标的边缘以及同一目标内部的感知。实验结果表明,改进后的算法在ISPRS Potsdam数据集上的平均交并比(mean Intersection over Union,mIoU)和F1指数分别达到了79.80%和75.88%,比DeepLabV3+算法提高了11.06%和6.32%。

Deep Learning Hybrid Model for Lithium-Ion Battery Aging Estimation and Prediction

The degradation process of lithium-ion batteries is intricately linked to their entire lifecycle as power sources and energy storage devices,encompassing aspects such as performance delivery and cycling utilization.Consequently,the accurate and expedient estimation or prediction of the aging state of lithium-ion batteries has garnered extensive attention.Nonetheless,prevailing research predominantly concentrates on either aging estimation or prediction,neglecting the dynamic fusion of both facets.This paper proposes a hybrid model for capacity aging estimation and prediction based on deep learning,wherein salient features highly pertinent to aging are extracted from charge and discharge relaxation processes.By amalgamating historical capacity decay data,the model dynamically furnishes estimations of the present capacity and forecasts of future capacity for lithium-ion batteries.Our approach is validated against a novel dataset involving charge and discharge cycles at varying rates.Specifically,under a charging condition of 0.25 C,a mean absolute percentage error(MAPE)of 0.29%is achieved.This outcome underscores the model's adeptness in harnessing relaxation processes commonly encountered in the real world and synergizing with historical capacity records within battery management systems(BMS),thereby affording estimations and prognostications of capacity decline with heightened precision.

Dendritic Deep Learning for Medical Segmentation

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.

Deep learning-based inpainting of saturation artifacts in optical coherence tomography images

Limited by the dynamic range of the detector,saturation artifacts usually occur in optical coherence tomography(OCT)imaging for high scattering media.The available methods are difficult to remove saturation artifacts and restore texture completely in OCT images.We proposed a deep learning-based inpainting method of saturation artifacts in this paper.The generation mechanism of saturation artifacts was analyzed,and experimental and simulated datasets were built based on the mechanism.Enhanced super-resolution generative adversarial networks were trained by the clear–saturated phantom image pairs.The perfect reconstructed results of experimental zebrafish and thyroid OCT images proved its feasibility,strong generalization,and robustness.

240 nm AlGaN-based deep ultraviolet micro-LEDs:size effect versus edge effect

240 nm AlGaN-based micro-LEDs with different sizes are designed and fabricated.Then,the external quantum efficiency(EQE)and light extraction efficiency(LEE)are systematically investigated by comparing size and edge effects.Here,it is revealed that the peak optical output power increases by 81.83%with the size shrinking from 50.0 to 25.0μm.Thereinto,the LEE increases by 26.21%and the LEE enhancement mainly comes from the sidewall light extraction.Most notably,transversemagnetic(TM)mode light intensifies faster as the size shrinks due to the tilted mesa side-wall and Al reflector design.However,when it turns to 12.5μm sized micro-LEDs,the output power is lower than 25.0μm sized ones.The underlying mechanism is that even though protected by SiO2 passivation,the edge effect which leads to current leakage and Shockley-Read-Hall(SRH)recombination deteriorates rapidly with the size further shrinking.Moreover,the ratio of the p-contact area to mesa area is much lower,which deteriorates the p-type current spreading at the mesa edge.These findings show a role of thumb for the design of high efficiency micro-LEDs with wavelength below 250 nm,which will pave the way for wide applications of deep ultraviolet(DUV)micro-LEDs.

Well-defined high entropy-metal nanoparticles:Detection of the multi-element particles by deep learning

Characterizing and control the chemical compositions of multi-element particles as single metal nanoparticles(mNPs) on the surfaces of catalytic metal oxide supports is challenging.This can be attributed to the heterogeneity and large size at the nanoscale,the poorly defined catalyst nanostructure,and thermodynamic immiscibility of the strongly repelling metallic elements.To address these challenges,an ultrasonic-assisted coincident electro-oxidation-reduction-precipitation(U-SEO-P) is presented to fabricate ultra-stable PtRuAgCoCuP NPs,which produces numerous active intermediates and induces strong metal-support interactions.To sort the active high-entropy mNPs,individual NPs are described on the support surface and the role of deep learning in understanding/predicting the features of PtRuAgCoCu@TiO_(x) catalysts is explained.Notably,this deep learning approach required minimal to no human input.The as-prepared PtRuAgCoCu@TiO_(x) catalysts can be used to catalyze various important chemical reactions,such as a high reduction conversion(100% in 30 s),with no loss of catalytic activity even after 20 cycles of nitroarene and ketone/aldehyde,which is several times higher than commercial Pt@TiO_(x) owing to individual PtRuAgCoCuP NPs on TiO_(x) surface.In this study,we present the "Totally Defined Catalysis" concept,which has enormous potential for the advancement of high-activity catalysts in the reduction of organic compounds.

ST-LSTM-SA:A New Ocean Sound Velocity Field Prediction Model Based on Deep Learning

The scarcity of in-situ ocean observations poses a challenge for real-time information acquisition in the ocean.Among the crucial hydroacoustic environmental parameters,ocean sound velocity exhibits significant spatial and temporal variability and it is highly relevant to oceanic research.In this study,we propose a new data-driven approach,leveraging deep learning techniques,for the prediction of sound velocity fields(SVFs).Our novel spatiotemporal prediction model,STLSTM-SA,combines Spatiotemporal Long Short-Term Memory(ST-LSTM) with a self-attention mechanism to enable accurate and real-time prediction of SVFs.To circumvent the limited amount of observational data,we employ transfer learning by first training the model using reanalysis datasets,followed by fine-tuning it using in-situ analysis data to obtain the final prediction model.By utilizing the historical 12-month SVFs as input,our model predicts the SVFs for the subsequent three months.We compare the performance of five models:Artificial Neural Networks(ANN),Long ShortTerm Memory(LSTM),Convolutional LSTM(ConvLSTM),ST-LSTM,and our proposed ST-LSTM-SA model in a test experiment spanning 2019 to 2022.Our results demonstrate that the ST-LSTM-SA model significantly improves the prediction accuracy and stability of sound velocity in both temporal and spatial dimensions.The ST-LSTM-SA model not only accurately predicts the ocean sound velocity field(SVF),but also provides valuable insights for spatiotemporal prediction of other oceanic environmental variables.

UAV-Assisted Dynamic Avatar Task Migration for Vehicular Metaverse Services: A Multi-Agent Deep Reinforcement Learning Approach

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.