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.

Ultra‑High Sensitivity Anisotropic Piezoelectric Sensors for Structural Health Monitoring and Robotic Perception

Monitoring minuscule mechanical signals,both in magnitude and direction,is imperative in many application scenarios,e.g.,structural health monitoring and robotic sensing systems.However,the piezoelectric sensor struggles to satisfy the requirements for directional recognition due to the limited piezoelectric coefficient matrix,and achieving sensitivity for detecting micrometer-scale deformations is also challenging.Herein,we develop a vector sensor composed of lead zirconate titanate-electronic grade glass fiber composite filaments with oriented arrangement,capable of detecting minute anisotropic deformations.The as-prepared vector sensor can identify the deformation directions even when subjected to an unprecedented nominal strain of 0.06%,thereby enabling its utility in accurately discerning the 5μm-height wrinkles in thin films and in monitoring human pulse waves.The ultra-high sensitivity is attributed to the formation of porous ferroelectret and the efficient load transfer efficiency of continuous lead zirconate titanate phase.Additionally,when integrated with machine learning techniques,the sensor’s capability to recognize multi-signals enables it to differentiate between 10 types of fine textures with 100%accuracy.The structural design in piezoelectric devices enables a more comprehensive perception of mechanical stimuli,offering a novel perspective for enhancing recognition accuracy.

Congruent Feature Selection Method to Improve the Efficacy of Machine Learning-Based Classification in Medical Image Processing

Machine learning(ML)is increasingly applied for medical image processing with appropriate learning paradigms.These applications include analyzing images of various organs,such as the brain,lung,eye,etc.,to identify specific flaws/diseases for diagnosis.The primary concern of ML applications is the precise selection of flexible image features for pattern detection and region classification.Most of the extracted image features are irrelevant and lead to an increase in computation time.Therefore,this article uses an analytical learning paradigm to design a Congruent Feature Selection Method to select the most relevant image features.This process trains the learning paradigm using similarity and correlation-based features over different textural intensities and pixel distributions.The similarity between the pixels over the various distribution patterns with high indexes is recommended for disease diagnosis.Later,the correlation based on intensity and distribution is analyzed to improve the feature selection congruency.Therefore,the more congruent pixels are sorted in the descending order of the selection,which identifies better regions than the distribution.Now,the learning paradigm is trained using intensity and region-based similarity to maximize the chances of selection.Therefore,the probability of feature selection,regardless of the textures and medical image patterns,is improved.This process enhances the performance of ML applications for different medical image processing.The proposed method improves the accuracy,precision,and training rate by 13.19%,10.69%,and 11.06%,respectively,compared to other models for the selected dataset.The mean error and selection time is also reduced by 12.56%and 13.56%,respectively,compared to the same models and dataset.

A Comprehensive Survey on Federated Learning Applications in Computational Mental Healthcare

Mental health is a significant issue worldwide,and the utilization of technology to assist mental health has seen a growing trend.This aims to alleviate the workload on healthcare professionals and aid individuals.Numerous applications have been developed to support the challenges in intelligent healthcare systems.However,because mental health data is sensitive,privacy concerns have emerged.Federated learning has gotten some attention.This research reviews the studies on federated learning and mental health related to solving the issue of intelligent healthcare systems.It explores various dimensions of federated learning in mental health,such as datasets(their types and sources),applications categorized based on mental health symptoms,federated mental health frameworks,federated machine learning,federated deep learning,and the benefits of federated learning in mental health applications.This research conducts surveys to evaluate the current state of mental health applications,mainly focusing on the role of Federated Learning(FL)and related privacy and data security concerns.The survey provides valuable insights into how these applications are emerging and evolving,specifically emphasizing FL’s impact.

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.

MARIE:One-Stage Object Detection Mechanism for Real-Time Identifying of Firearms

Security and safety remain paramount concerns for both governments and individuals worldwide.In today’s context,the frequency of crimes and terrorist attacks is alarmingly increasing,becoming increasingly intolerable to society.Consequently,there is a pressing need for swift identification of potential threats to preemptively alert law enforcement and security forces,thereby preventing potential attacks or violent incidents.Recent advancements in big data analytics and deep learning have significantly enhanced the capabilities of computer vision in object detection,particularly in identifying firearms.This paper introduces a novel automatic firearm detection surveillance system,utilizing a one-stage detection approach named MARIE(Mechanism for Realtime Identification of Firearms).MARIE incorporates the Single Shot Multibox Detector(SSD)model,which has been specifically optimized to balance the speed-accuracy trade-off critical in firearm detection applications.The SSD model was further refined by integrating MobileNetV2 and InceptionV2 architectures for superior feature extraction capabilities.The experimental results demonstrate that this modified SSD configuration provides highly satisfactory performance,surpassing existing methods trained on the same dataset in terms of the critical speedaccuracy trade-off.Through these innovations,MARIE sets a new standard in surveillance technology,offering a robust solution to enhance public safety effectively.

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.

Variations in quantifying patient reported outcome measures to estimate treatment effect

In the practice of healthcare,patient-reported outcomes(PROs)and PRO measures(PROMs)are used as an attempt to observe the changes in complex clinical situations.They guide us in making decisions based on the evidence regarding patient care by recording the change in outcomes for a particular treatment to a given condition and finally to understand whether a patient will benefit from a particular treatment and to quantify the treatment effect.For any PROM to be usable in health care,we need it to be reliable,encapsulating the points of interest with the potential to detect any real change.Using structured outcome measures routinely in clinical practice helps the physician to understand the functional limitation of a patient that would otherwise not be clear in an office interview,and this allows the physician and patient to have a meaningful conver-sation as well as a customized plan for each patient.Having mentioned the rationale and the benefits of PROMs,understanding the quantification process is crucial before embarking on management decisions.A better interpretation of change needs to identify the treatment effect based on clinical relevance for a given condition.There are a multiple set of measurement indices to serve this effect and most of them are used interchangeably without clear demarcation on their differences.This article details the various quantification metrics used to evaluate the treatment effect using PROMs,their limitations and the scope of usage and implementation in clinical practice.

Wind Detectives

A new laser radar technology developed byChinese scientists could help Olympic sailors byaccurately measuring wind speed and

基于改进Detection Transformer的棉花幼苗与杂草检测模型研究

基于深度学习的目标检测技术在棉花幼苗与杂草检测领域已取得一定进展。论文提出了基于改进Detection Transformer的棉花幼苗与杂草检测模型,以提高杂草目标检测的准确率和效率。首先,引入了可变形注意力模块替代原始模型中的Transformer注意力模块,提高模型对特征图目标形变的处理能力。提出新的降噪训练机制,解决了二分图匹配不稳定问题。提出混合查询选择策略,提高解码器对目标类别和位置信息的利用效率。使用Swin Transformer作为网络主干,提高模型特征提取能力。通过对比原网络,论文提出的模型方法在训练过程中表现出更快的收敛速度,并且在准确率方面提高了6.7%。

IDS-INT:Intrusion detection system using transformer-based transfer learning for imbalanced network traffic

A network intrusion detection system is critical for cyber security against llegitimate attacks.In terms of feature perspectives,network traffic may include a variety of elements such as attack reference,attack type,a subcategory of attack,host information,malicious scripts,etc.In terms of network perspectives,network traffic may contain an imbalanced number of harmful attacks when compared to normal traffic.It is challenging to identify a specific attack due to complex features and data imbalance issues.To address these issues,this paper proposes an Intrusion Detection System using transformer-based transfer learning for Imbalanced Network Traffic(IDS-INT).IDS-INT uses transformer-based transfer learning to learn feature interactions in both network feature representation and imbalanced data.First,detailed information about each type of attack is gathered from network interaction descriptions,which include network nodes,attack type,reference,host information,etc.Second,the transformer-based transfer learning approach is developed to learn detailed feature representation using their semantic anchors.Third,the Synthetic Minority Oversampling Technique(SMOTE)is implemented to balance abnormal traffic and detect minority attacks.Fourth,the Convolution Neural Network(CNN)model is designed to extract deep features from the balanced network traffic.Finally,the hybrid approach of the CNN-Long Short-Term Memory(CNN-LSTM)model is developed to detect different types of attacks from the deep features.Detailed experiments are conducted to test the proposed approach using three standard datasets,i.e.,UNsWNB15,CIC-IDS2017,and NSL-KDD.An explainable AI approach is implemented to interpret the proposed method and develop a trustable model.

Esophageal cancer screening,early detection and treatment:Current insights and future directions

Esophageal cancer ranks among the most prevalent malignant tumors globally,primarily due to its highly aggressive nature and poor survival rates.According to the 2020 global cancer statistics,there were approximately 604000 new cases of esophageal cancer,resulting in 544000 deaths.The 5-year survival rate hovers around a mere 15%-25%.Notably,distinct variations exist in the risk factors associated with the two primary histological types,influencing their worldwide incidence and distribution.Squamous cell carcinoma displays a high incidence in specific regions,such as certain areas in China,where it meets the cost-effect-iveness criteria for widespread endoscopy-based early diagnosis within the local population.Conversely,adenocarcinoma(EAC)represents the most common histological subtype of esophageal cancer in Europe and the United States.The role of early diagnosis in cases of EAC originating from Barrett's esophagus(BE)remains a subject of controversy.The effectiveness of early detection for EAC,particularly those arising from BE,continues to be a debated topic.The variations in how early-stage esophageal carcinoma is treated in different regions are largely due to the differing rates of early-stage cancer diagnoses.In areas with higher incidences,such as China and Japan,early diagnosis is more common,which has led to the advancement of endoscopic methods as definitive treatments.These techniques have demonstrated remarkable efficacy with minimal complications while preserving esophageal functionality.Early screening,prompt diagnosis,and timely treatment are key strategies that can significantly lower both the occurrence and death rates associated with esophageal cancer.

Superhydrophobic Surface-Assisted Preparation of Microspheres and Supraparticles and Their Applications

Superhydrophobic surface(SHS) has been well developed, as SHS renders the property of minimizing the water/solid contact interface. Water droplets deposited onto SHS with contact angles exceeding 150°, allow them to retain spherical shapes, and the low adhesion of SHS facilitates easy droplet collection when tilting the substrate. These characteristics make SHS suitable for a wide range of applications. One particularly promising application is the fabrication of microsphere and supraparticle materials. SHS offers a distinct advantage as a universal platform capable of providing customized services for a variety of microspheres and supraparticles. In this review, an overview of the strategies for fabricating microspheres and supraparticles with the aid of SHS, including cross-linking process, polymer melting,and droplet template evaporation methods, is first presented. Then, the applications of microspheres and supraparticles formed onto SHS are discussed in detail, for example, fabricating photonic devices with controllable structures and tunable structural colors, acting as catalysts with emerging or synergetic properties, being integrated into the biomedical field to construct the devices with different medicinal purposes, being utilized for inducing protein crystallization and detecting trace amounts of analytes. Finally,the perspective on future developments involved with this research field is given, along with some obstacles and opportunities.

Improvement of High-Speed Detection Algorithm for Nonwoven Material Defects Based on Machine Vision

Defect detection is vital in the nonwoven material industry,ensuring surface quality before producing finished products.Recently,deep learning and computer vision advancements have revolutionized defect detection,making it a widely adopted approach in various industrial fields.This paper mainly studied the defect detection method for nonwoven materials based on the improved Nano Det-Plus model.Using the constructed samples of defects in nonwoven materials as the research objects,transfer learning experiments were conducted based on the Nano DetPlus object detection framework.Within this framework,the Backbone,path aggregation feature pyramid network(PAFPN)and Head network models were compared and trained through a process of freezing,with the ultimate aim of bolstering the model's feature extraction abilities and elevating detection accuracy.The half-precision quantization method was used to optimize the model after transfer learning experiments,reducing model weights and computational complexity to improve the detection speed.Performance comparisons were conducted between the improved model and the original Nano Det-Plus model,YOLO,SSD and other common industrial defect detection algorithms,validating that the improved methods based on transfer learning and semi-precision quantization enabled the model to meet the practical requirements of industrial production.

A Hybrid Intrusion Detection Method Based on Convolutional Neural Network and AdaBoost

To solve the problem of poor detection and limited application range of current intrusion detection methods,this paper attempts to use deep learning neural network technology to study a new type of intrusion detection method.Hence,we proposed an intrusion detection algorithm based on convolutional neural network(CNN)and AdaBoost algorithm.This algorithm uses CNN to extract the characteristics of network traffic data,which is particularly suitable for the analysis of continuous and classified attack data.The AdaBoost algorithm is used to classify network attack data that improved the detection effect of unbalanced data classification.We adopt the UNSW-NB15 dataset to test of this algorithm in the PyCharm environment.The results show that the detection rate of algorithm is99.27%and the false positive rate is lower than 0.98%.Comparative analysis shows that this algorithm has advantages over existing methods in terms of detection rate and false positive rate for small proportion of attack data.

Underwater four-quadrant dual-beam circumferential scanning laser fuze using nonlinear adaptive backscatter filter based on pauseable SAF-LMS algorithm

The phenomenon of a target echo peak overlapping with the backscattered echo peak significantly undermines the detection range and precision of underwater laser fuzes.To overcome this issue,we propose a four-quadrant dual-beam circumferential scanning laser fuze to distinguish various interference signals and provide more real-time data for the backscatter filtering algorithm.This enhances the algorithm loading capability of the fuze.In order to address the problem of insufficient filtering capacity in existing linear backscatter filtering algorithms,we develop a nonlinear backscattering adaptive filter based on the spline adaptive filter least mean square(SAF-LMS)algorithm.We also designed an algorithm pause module to retain the original trend of the target echo peak,improving the time discrimination accuracy and anti-interference capability of the fuze.Finally,experiments are conducted with varying signal-to-noise ratios of the original underwater target echo signals.The experimental results show that the average signal-to-noise ratio before and after filtering can be improved by more than31 d B,with an increase of up to 76%in extreme detection distance.

Improved YOLOv8n Model for Detecting Helmets and License Plates on Electric Bicycles

Wearing helmetswhile riding electric bicycles can significantly reduce head injuries resulting fromtraffic accidents.To effectively monitor compliance,the utilization of target detection algorithms through traffic cameras plays a vital role in identifying helmet usage by electric bicycle riders and recognizing license plates on electric bicycles.However,manual enforcement by traffic police is time-consuming and labor-intensive.Traditional methods face challenges in accurately identifying small targets such as helmets and license plates using deep learning techniques.This paper proposes an enhanced model for detecting helmets and license plates on electric bicycles,addressing these challenges.The proposedmodel improves uponYOLOv8n by deepening the network structure,incorporating weighted connections,and introducing lightweight convolutional modules.These modifications aim to enhance the precision of small target recognition while reducing the model’s parameters,making it suitable for deployment on low-performance devices in real traffic scenarios.Experimental results demonstrate that the model achieves an mAP@0.5 of 91.8%,showing an 11.5%improvement over the baselinemodel,with a 16.2%reduction in parameters.Additionally,themodel achieves a frames per second(FPS)rate of 58,meeting the accuracy and speed requirements for detection in actual traffic scenarios.

Road Traffic Monitoring from Aerial Images Using Template Matching and Invariant Features

Road traffic monitoring is an imperative topic widely discussed among researchers.Systems used to monitor traffic frequently rely on cameras mounted on bridges or roadsides.However,aerial images provide the flexibility to use mobile platforms to detect the location and motion of the vehicle over a larger area.To this end,different models have shown the ability to recognize and track vehicles.However,these methods are not mature enough to produce accurate results in complex road scenes.Therefore,this paper presents an algorithm that combines state-of-the-art techniques for identifying and tracking vehicles in conjunction with image bursts.The extracted frames were converted to grayscale,followed by the application of a georeferencing algorithm to embed coordinate information into the images.The masking technique eliminated irrelevant data and reduced the computational cost of the overall monitoring system.Next,Sobel edge detection combined with Canny edge detection and Hough line transform has been applied for noise reduction.After preprocessing,the blob detection algorithm helped detect the vehicles.Vehicles of varying sizes have been detected by implementing a dynamic thresholding scheme.Detection was done on the first image of every burst.Then,to track vehicles,the model of each vehicle was made to find its matches in the succeeding images using the template matching algorithm.To further improve the tracking accuracy by incorporating motion information,Scale Invariant Feature Transform(SIFT)features have been used to find the best possible match among multiple matches.An accuracy rate of 87%for detection and 80%accuracy for tracking in the A1 Motorway Netherland dataset has been achieved.For the Vehicle Aerial Imaging from Drone(VAID)dataset,an accuracy rate of 86%for detection and 78%accuracy for tracking has been achieved.

Edge enhanced depth perception with binocular meta-lens

The increasing popularity of the metaverse has led to a growing interest and market size in spatial computing from both academia and industry.Developing portable and accurate imaging and depth sensing systems is crucial for advancing next-generation virtual reality devices.This work demonstrates an intelligent,lightweight,and compact edge-enhanced depth perception system that utilizes a binocular meta-lens for spatial computing.The miniaturized system comprises a binocular meta-lens,a 532 nm filter,and a CMOS sensor.For disparity computation,we propose a stereo-matching neural network with a novel H-Module.The H-Module incorporates an attention mechanism into the Siamese network.The symmetric architecture,with cross-pixel interaction and cross-view interaction,enables a more comprehensive analysis of contextual information in stereo images.Based on spatial intensity discontinuity,the edge enhancement eliminates illposed regions in the image where ambiguous depth predictions may occur due to a lack of texture.With the assistance of deep learning,our edge-enhanced system provides prompt responses in less than 0.15 seconds.This edge-enhanced depth perception meta-lens imaging system will significantly contribute to accurate 3D scene modeling,machine vision,autonomous driving,and robotics development.

Automated Vulnerability Detection of Blockchain Smart Contacts Based on BERT Artificial Intelligent Model

The widespread adoption of blockchain technology has led to the exploration of its numerous applications in various fields.Cryptographic algorithms and smart contracts are critical components of blockchain security.Despite the benefits of virtual currency,vulnerabilities in smart contracts have resulted in substantial losses to users.While researchers have identified these vulnerabilities and developed tools for detecting them,the accuracy of these tools is still far from satisfactory,with high false positive and false negative rates.In this paper,we propose a new method for detecting vulnerabilities in smart contracts using the BERT pre-training model,which can quickly and effectively process and detect smart contracts.More specifically,we preprocess and make symbol substitution in the contract,which can make the pre-training model better obtain contract features.We evaluate our method on four datasets and compare its performance with other deep learning models and vulnerability detection tools,demonstrating its superior accuracy.