WebFLex:A Framework for Web Browsers-Based Peer-to-Peer Federated Learning Systems Using WebRTC

Scalability and information personal privacy are vital for training and deploying large-scale deep learning models.Federated learning trains models on exclusive information by aggregating weights from various devices and taking advantage of the device-agnostic environment of web browsers.Nevertheless,relying on a main central server for internet browser-based federated systems can prohibit scalability and interfere with the training process as a result of growing client numbers.Additionally,information relating to the training dataset can possibly be extracted from the distributed weights,potentially reducing the privacy of the local data used for training.In this research paper,we aim to investigate the challenges of scalability and data privacy to increase the efficiency of distributed training models.As a result,we propose a web-federated learning exchange(WebFLex)framework,which intends to improve the decentralization of the federated learning process.WebFLex is additionally developed to secure distributed and scalable federated learning systems that operate in web browsers across heterogeneous devices.Furthermore,WebFLex utilizes peer-to-peer interactions and secure weight exchanges utilizing browser-to-browser web real-time communication(WebRTC),efficiently preventing the need for a main central server.WebFLex has actually been measured in various setups using the MNIST dataset.Experimental results show WebFLex’s ability to improve the scalability of federated learning systems,allowing a smooth increase in the number of participating devices without central data aggregation.In addition,WebFLex can maintain a durable federated learning procedure even when faced with device disconnections and network variability.Additionally,it improves data privacy by utilizing artificial noise,which accomplishes an appropriate balance between accuracy and privacy preservation.

Guest Editorial:Knowledge‐based deep learning system in bio‐medicine

Numerous healthcare procedures can be viewed as medical sector decisions.In the modern era,computers have become indispensable in the realm of medical decision‐making.How-ever,the common view of computers in the medical field typically extends only to applications that support doctors in diagnosing diseases.To more tightly intertwine computers with the biomedical sciences,professionals are now more frequently utilising knowledge‐driven deep learning systems(KDLS)and their foundational technologies,especially in the domain of neuroimaging(NI).

Retinal vascular morphological characteristics in diabetic retinopathy: an artificial intelligence study using a transfer learning system to analyze ultra-wide field images

AIM:To investigate the morphological characteristics of retinal vessels in patients with different severity of diabetic retinopathy(DR)and in patients with or without diabetic macular edema(DME).METHODS:The 239 eyes of DR patients and 100 eyes of healthy individuals were recruited for the study.The severity of DR patients was graded as mild,moderate and severe non-proliferative diabetic retinopathy(NPDR)according to the international clinical diabetic retinopathy(ICDR)disease severity scale classification,and retinal vascular morphology was quantitatively analyzed in ultra-wide field images using RU-net and transfer learning methods.The presence of DME was determined by optical coherence tomography(OCT),and differences in vascular morphological characteristics were compared between patients with and without DME.RESULTS:Retinal vessel segmentation using RU-net and transfer learning system had an accuracy of 99%and a Dice metric of 0.76.Compared with the healthy group,the DR group had smaller vessel angles(33.68±3.01 vs 37.78±1.60),smaller fractal dimension(Df)values(1.33±0.05 vs 1.41±0.03),less vessel density(1.12±0.44 vs 2.09±0.36)and fewer vascular branches(206.1±88.8 vs 396.5±91.3),all P<0.001.As the severity of DR increased,Df values decreased,P=0.031.No significant difference between the DME and non-DME groups were observed in vascular morphological characteristics.CONCLUSION:In this study,an artificial intelligence retinal vessel segmentation system is used with 99%accuracy,thus providing with relatively satisfactory performance in the evaluation of quantitative vascular morphology.DR patients have a tendency of vascular occlusion and dropout.The presence of DME does not compromise the integral retinal vascular pattern.

Transparent and Accountable Training Data Sharing in Decentralized Machine Learning Systems

In Decentralized Machine Learning(DML)systems,system participants contribute their resources to assist others in developing machine learning solutions.Identifying malicious contributions in DML systems is challenging,which has led to the exploration of blockchain technology.Blockchain leverages its transparency and immutability to record the provenance and reliability of training data.However,storing massive datasets or implementing model evaluation processes on smart contracts incurs high computational costs.Additionally,current research on preventing malicious contributions in DML systems primarily focuses on protecting models from being exploited by workers who contribute incorrect or misleading data.However,less attention has been paid to the scenario where malicious requesters intentionally manipulate test data during evaluation to gain an unfair advantage.This paper proposes a transparent and accountable training data sharing method that securely shares data among potentially malicious system participants.First,we introduce a blockchain-based DML system architecture that supports secure training data sharing through the IPFS network.Second,we design a blockchain smart contract to transparently split training datasets into training and test datasets,respectively,without involving system participants.Under the system,transparent and accountable training data sharing can be achieved with attribute-based proxy re-encryption.We demonstrate the security analysis for the system,and conduct experiments on the Ethereum and IPFS platforms to show the feasibility and practicality of the system.

Knowledge‐based deep learning system for classifying Alzheimer's disease for multi‐task learning

Deep learning has recently become a viable approach for classifying Alzheimer's disease(AD)in medical imaging.However,existing models struggle to efficiently extract features from medical images and may squander additional information resources for illness classification.To address these issues,a deep three‐dimensional convolutional neural network incorporating multi‐task learning and attention mechanisms is proposed.An upgraded primary C3D network is utilised to create rougher low‐level feature maps.It introduces a new convolution block that focuses on the structural aspects of the magnetORCID:ic resonance imaging image and another block that extracts attention weights unique to certain pixel positions in the feature map and multiplies them with the feature map output.Then,several fully connected layers are used to achieve multi‐task learning,generating three outputs,including the primary classification task.The other two outputs employ backpropagation during training to improve the primary classification job.Experimental findings show that the authors’proposed method outperforms current approaches for classifying AD,achieving enhanced classification accuracy and other in-dicators on the Alzheimer's disease Neuroimaging Initiative dataset.The authors demonstrate promise for future disease classification studies.

A Privacy Preserving Federated Learning System for IoT Devices Using Blockchain and Optimization

In this study, a blockchain based federated learning system using an enhanced weighted mean vector optimization algorithm, known as EINFO, is proposed. The proposed EINFO addresses the limitations of federated averaging during global update and model training, where data is unevenly distributed among devices and there are variations in the number of data samples. Using a well-defined structure and updating the vector positions by local searching, vector combining, and updating rules, the EINFO algorithm maximizes the shared model parameters. In order to increase the exploration and exploitation capabilities, the model convergence rate is improved and new vectors are generated through the use of a weighted mean vector based on the inverse square law. To choose validators, miners, and to propagate new blocks, a delegated proof of stake based on the reliability of blockchain nodes is suggested. Federated learning is included into the blockchain to protect nodes from both external and internal threats. To determine how well the suggested system performs in relation to current models in the literature, extensive simulations are run. The simulation results show that the proposed system outperforms existing schemes in terms of accuracy, sensitivity and specificity.

Design and Research of an Intelligent Learning System for University Physics

In order to break through the limitations of traditional teaching,realize the integration of online and offline teaching,and optimize the intelligent learning experience of university physics,this paper proposes the design of an intelligent learning system for university physics based on cloud computing platforms,and applies this system to teaching environment of university physics.It successfully integrates emerging technologies such as cloud computing,machine learning,and situational awareness,integrates learning context awareness,intelligent recording and broadcasting,resource sharing,learning performance prediction,and content planning and recommendation,and comprehensively improves the quality of university physics teaching.It can optimize the teaching process and deepen intelligent teaching reform,aiming at providing references for the teaching practice of university physics.

Target tracking method of Siamese networks based on the broad learning system

Target tracking has a wide range of applications in intelligent transportation,real‐time monitoring,human‐computer interaction and other aspects.However,in the tracking process,the target is prone to deformation,occlusion,loss,scale variation,background clutter,illumination variation,etc.,which bring great challenges to realize accurate and real‐time tracking.Tracking based on Siamese networks promotes the application of deep learning in the field of target tracking,ensuring both accuracy and real‐time performance.However,due to its offline training,it is difficult to deal with the fast motion,serious occlusion,loss and deformation of the target during tracking.Therefore,it is very helpful to improve the performance of the Siamese networks by learning new features of the target quickly and updating the target position in time online.The broad learning system(BLS)has a simple network structure,high learning efficiency,and strong feature learning ability.Aiming at the problems of Siamese networks and the characteristics of BLS,a target tracking method based on BLS is proposed.The method combines offline training with fast online learning of new features,which not only adopts the powerful feature representation ability of deep learning,but also skillfully uses the BLS for re‐learning and re‐detection.The broad re‐learning information is used for re‐detection when the target tracking appears serious occlusion and so on,so as to change the selection of the Siamese networks search area,solve the problem that the search range cannot meet the fast motion of the target,and improve the adaptability.Experimental results show that the proposed method achieves good results on three challenging datasets and improves the performance of the basic algorithm in difficult scenarios.

A Study of Multimodal Intelligent Adaptive Learning System and Its Pattern of Promoting Learners’Online Learning Engagement

As the field of artificial intelligence continues to evolve,so too does the application of multimodal learning analysis and intelligent adaptive learning systems.This trend has the potential to promote the equalization of educational resources,the intellectualization of educational methods,and the modernization of educational reform,among other benefits.This study proposes a construction framework for an intelligent adaptive learning system that is supported by multimodal data.It provides a detailed explanation of the system’s working principles and patterns,which aim to enhance learners’online engagement in behavior,emotion,and cognition.The study seeks to address the issue of intelligent adaptive learning systems diagnosing learners’learning behavior based solely on learning achievement,to improve learners’online engagement,enable them to master more required knowledge,and ultimately achieve better learning outcomes.

Detection and classification of breast lesions using multiple information on contrast-enhanced mammography by a multiprocess deep-learning system: A multicenter study

Objective: Accurate detection and classification of breast lesions in early stage is crucial to timely formulate effective treatments for patients. We aim to develop a fully automatic system to detect and classify breast lesions using multiple contrast-enhanced mammography(CEM) images.Methods: In this study, a total of 1,903 females who underwent CEM examination from three hospitals were enrolled as the training set, internal testing set, pooled external testing set and prospective testing set. Here we developed a CEM-based multiprocess detection and classification system(MDCS) to perform the task of detection and classification of breast lesions. In this system, we introduced an innovative auxiliary feature fusion(AFF)algorithm that could intelligently incorporates multiple types of information from CEM images. The average freeresponse receiver operating characteristic score(AFROC-Score) was presented to validate system’s detection performance, and the performance of classification was evaluated by area under the receiver operating characteristic curve(AUC). Furthermore, we assessed the diagnostic value of MDCS through visual analysis of disputed cases,comparing its performance and efficiency with that of radiologists and exploring whether it could augment radiologists’ performance.Results: On the pooled external and prospective testing sets, MDCS always maintained a high standalone performance, with AFROC-Scores of 0.953 and 0.963 for detection task, and AUCs for classification were 0.909[95% confidence interval(95% CI): 0.822-0.996] and 0.912(95% CI: 0.840-0.985), respectively. It also achieved higher sensitivity than all senior radiologists and higher specificity than all junior radiologists on pooled external and prospective testing sets. Moreover, MDCS performed superior diagnostic efficiency with an average reading time of 5 seconds, compared to the radiologists’ average reading time of 3.2 min. The average performance of all radiologists was also improved to varying degrees with MDCS assistance.Conclusions: MDCS demonstrated excellent performance in the detection and classification of breast lesions,and greatly enhanced the overall performance of radiologists.

Automated deep learning system for power line inspection image analysis and processing: architecture and design issues

The continuous growth in the scale of unmanned aerial vehicle (UAV) applications in transmission line inspection has resulted in a corresponding increase in the demand for UAV inspection image processing. Owing to its excellent performance in computer vision, deep learning has been applied to UAV inspection image processing tasks such as power line identification and insulator defect detection. Despite their excellent performance, electric power UAV inspection image processing models based on deep learning face several problems such as a small application scope, the need for constant retraining and optimization, and high R&D monetary and time costs due to the black-box and scene data-driven characteristics of deep learning. In this study, an automated deep learning system for electric power UAV inspection image analysis and processing is proposed as a solution to the aforementioned problems. This system design is based on the three critical design principles of generalizability, extensibility, and automation. Pre-trained models, fine-tuning (downstream task adaptation), and automated machine learning, which are closely related to these design principles, are reviewed. In addition, an automated deep learning system architecture for electric power UAV inspection image analysis and processing is presented. A prototype system was constructed and experiments were conducted on the two electric power UAV inspection image analysis and processing tasks of insulator self-detonation and bird nest recognition. The models constructed using the prototype system achieved 91.36% and 86.13% mAP for insulator self-detonation and bird nest recognition, respectively. This demonstrates that the system design concept is reasonable and the system architecture feasible .

A Novel Ensemble Learning System for Cyberattack Classification

Nowadays,IT systems rely mainly on artificial intelligence(AI)algorithms to process data.AI is generally used to extract knowledge from stored information and,depending on the nature of data,it may be necessary to apply different AI algorithms.In this article,a novel perspective on the use of AI to ensure the cybersecurity through the study of network traffic is presented.This is done through the construction of a two-stage cyberattack classification ensemble model addressing class imbalance following a one-vs-rest(OvR)approach.With the growing trend of cyberattacks,it is essential to implement techniques that ensure legitimate access to information.To address this issue,this work proposes a network traffic classification system for different categories based on several AI techniques.In the first task,binary models are generated to clearly differentiate each type of traffic from the rest.With binary models generated,an ensemble model is developed in two phases,which allows the separation of legitimate and illegitimate traffic(phase 1)while also identifying the type of illegitimate traffic(phase 2).In this way,the proposed system allows a complete multiclass classification of network traffic.The estimation of global performance is done using a modern dataset(UNSW-NB15),evaluated using two approaches and compared with other state-of-art works.Our proposal,based on the construction of a two-step model,reaches an F1 of 0.912 for the first level of binary classification and 0.7754 for the multiclass classification.These results show that the proposed system outperforms other state-of-the-art approaches(+0.75%and+3.54%for binary and multiclass classification,respectively)in terms of F1,as demon-strated through comparison together with other relevant classification metrics.

Performance Analysis of Intelligent Neural-Based Deep Learning System on Rank Images Classification

The use of the internet is increasing all over the world on a daily basis in the last two decades.The increase in the internet causes many sexual crimes,such as sexual misuse,domestic violence,and child pornography.Various research has been done for pornographic image detection and classification.Most of the used models used machine learning techniques and deep learning models which show less accuracy,while the deep learning model ware used for classification and detection performed better as compared to machine learning.Therefore,this research evaluates the performance analysis of intelligent neural-based deep learning models which are based on Convolution neural network(CNN),Visual geometry group(VGG-16),VGG-14,and Residual Network(ResNet-50)with the expanded dataset,trained using transfer learning approaches applied in the fully connected layer for datasets to classify rank(Pornographic vs.Nonpornographic)classification in images.The simulation result shows that VGG-16 performed better than the used model in this study without augmented data.The VGG-16 model with augmented data reached a training and validation accuracy of 0.97,0.94 with a loss of 0.070,0.16.The precision,recall,and f-measure values for explicit and non-explicit images are(0.94,0.94,0.94)and(0.94,0.94,0.94).Similarly,The VGG-14 model with augmented data reached a training and validation accuracy of 0.98,0.96 with a loss of 0.059,0.11.The f-measure,recall,and precision values for explicit and non-explicit images are(0.98,0.98,0.98)and(0.98,0.98,0.98).The CNN model with augmented data reached a training and validation accuracy of 0.776&0.78 with losses of 0.48&0.46.The f-measure,recall,and precision values for explicit and non-explicit images are(0.80,0.80,0.80)and(0.78,0.79,0.78).The ResNet-50 model with expanded data reached with training accuracy of 0.89 with a loss of 0.389 and 0.86 of validation accuracy and a loss of 0.47.The f-measure,recall,and precision values for explicit and non-explicit images are(0.86,0.97,0.91)and(0.86,0.93,0.89).Where else without augmented data the VGG-16 model reached a training and validation accuracy of 0.997,0.986 with a loss of 0.008,0.056.The f-measure,recall,and precision values for explicit and non-explicit images are(0.94,0.99,0.97)and(0.99,0.93,0.96)which outperforms the used models with the augmented dataset in this study.

On the Use of E-Learning Software Data--with Speexx Foreign Lan guage Learning System Being the Case

E-learning produces the data on the learners’utilization of the software,which helps the teacher to perceive the learners’mental status and learning efficiency,so it is of great value to make full use of the data.With Speexx foreign language learning system being the case,this thesis introduces the function of such data and the modes of how to use them to facilitate the blendedteaching and learning.

Development and Evaluation of a Distance Learning System Based on CSCW

This paper described a distance learning system, which allows Internet users to conduct a lesson in real time from any kinds attached computers. Participants can jointly view and edit relevant multimedia information distributed through Internet. Teachers and students can also simultaneously communicate by voice and text to discuss the problems. Teacher can broadcast streaming PowerPoint presentation in real time to network users. In addition to sliders, presenters can broadcast video and audio simultaneously to deliver a live multimedia show online, and store their presentations for on demand playback. Teachers distributed in different places can also use cooperative editing tool to edit and encode existing digital content. We discussed some important design principles of the system. Then, the system configuration and the results of evaluation are also presented. The system has proved to be applicable to the distance learning based on CSCW (Computer Support Cooperative Work) in Internet.

Student Behavior Modeling for an E-Learning System Offering Personalized Learning Experiences

With the advent of computing and communication technologies,it has become possible for a learner to expand his or her knowledge irrespective of the place and time.Web-based learning promotes active and independent learning.Large scale e-learning platforms revolutionized the concept of studying and it also paved the way for innovative and effective teaching-learning process.This digital learning improves the quality of teaching and also promotes educational equity.However,the challenges in e-learning platforms include dissimilarities in learner’s ability and needs,lack of student motivation towards learning activities and provision for adaptive learning environment.The quality of learning can be enhanced by analyzing the online learner’s behavioral characteristics and their application of intelligent instructional strategy.It is not possible to identify the difficulties faced during the process through evaluation after the completion of e-learning course.It is thus essential for an e-learning system to include component offering adaptive control of learning and maintain user’s interest level.In this research work,a framework is proposed to analyze the behavior of online learners and motivate the students towards the learning process accordingly so as to increase the rate of learner’s objective attainment.Catering to the demands of e-learner,an intelligent model is presented in this study for e-learning system that apply supervised machine learning algorithm.An adaptive e-learning system suits every category of learner,improves the learner’s performance and paves way for offering personalized learning experiences.

The Adaptation of Mobile Learning System Based on Business Rules

In the mobile learning system,it is important to adapt to mobile devices.Most of mobile learning systems are not quickly suitable for mobile devices.In order to provide adaptive mobile services,the approach for adaptation is proposed in this paper.Firstly,context of mobile devices and its influence on mobile learning system are analized and business rules based on these analysis are presented.Then,using the approach,the mobile learning system is constructed.The example implies this approach can adapt the mobile service to the mobile devices flexibly.

The College Video English Visual-audio-oral Learning System

In order to respond to the need of social development,cultivate international talents,and improve the current English teaching mode,this paper studies video English visual-audio-oral learning system based on machine learning from the perspective of teaching and learning video English.It mainly analyzes the knowledge discovery process of machine learning,the design and application of video English visual-audio-oral learning system.It is found that the video English visual-audio-oral learning system based on machine learning has much higher level of practicality and efficiency compared with the traditional English language teaching in real life.The application of this system can also be of great significance in changes on language learning modes and methods in the future.

Blackboard Learning System平台下网络课程的用户体验优化设计研究

网络课程从一开始的内涵建设到后来的软件开发,直至目前网络教学开展普及,一个显著的问题日益凸显,即关于网络课程的可用性是否能够经得起检验,是否在教学效果和教学评价上取得令人满意的结论。从用户体验的角度出发,以一门基于Black-board Learning System的网络课程《图形图像Photoshop实践》为主要的研究对象,分析总结影响网络课程可用性的各种因素,并提出相应的解决办法。通过实践检验,网络课程的升级取得了较好的效果。

A rapid, low-cost deep learning system to classify strawberry disease based on cloud service

Accurate and timely classification of diseases during strawberry planting can help growers deal with them in timely manner, thereby reducing losses. However, the classification of strawberry diseases in real planting environments is facing severe challenges, including complex planting environments, multiple disease categories with small differences, and so on. Although recent mobile vision technology based deep learning has achieved some success in overcoming the above problems, a key problem is how to construct a non-destructive, fast and convenient method to improve the efficiency of strawberry disease identification for the multi-region, multi-space and multi-time classification requirements. We develop and evaluate a rapid, low-cost system for classifying diseases in strawberry cultivation. This involves designing an easy-to-use cloudbased strawberry disease identification system, combined with our novel self-supervised multi-network fusion classification model, which consists of a Location network, a Feedback network and a Classification network to identify the categories of common strawberry diseases. With the help of a novel self-supervision mechanism, the model can effectively identify diseased regions of strawberry disease images without the need for annotations such as bounding boxes. Using accuracy, precision, recall and F1 to evaluate the classification effect, the results of the test set are 92.48, 90.68, 86.32 and 88.45%, respectively. Compared with popular Convolutional Neural Networks(CNN) and five other methods, our network achieves better disease classification effect. Currently, the client(mini program) has been released on the We Chat platform. The mini program has perfect classification effect in the actual test, which verifies the feasibility and effectiveness of the system, and can provide a reference for the intelligent research and application of strawberry disease identification.