Improving Federated Learning through Abnormal Client Detection and Incentive

Data sharing and privacy protection are made possible by federated learning,which allows for continuous model parameter sharing between several clients and a central server.Multiple reliable and high-quality clients must participate in practical applications for the federated learning global model to be accurate,but because the clients are independent,the central server cannot fully control their behavior.The central server has no way of knowing the correctness of the model parameters provided by each client in this round,so clients may purposefully or unwittingly submit anomalous data,leading to abnormal behavior,such as becoming malicious attackers or defective clients.To reduce their negative consequences,it is crucial to quickly detect these abnormalities and incentivize them.In this paper,we propose a Federated Learning framework for Detecting and Incentivizing Abnormal Clients(FL-DIAC)to accomplish efficient and security federated learning.We build a detector that introduces an auto-encoder for anomaly detection and use it to perform anomaly identification and prevent the involvement of abnormal clients,in particular for the anomaly client detection problem.Among them,before the model parameters are input to the detector,we propose a Fourier transform-based anomaly data detectionmethod for dimensionality reduction in order to reduce the computational complexity.Additionally,we create a credit scorebased incentive structure to encourage clients to participate in training in order tomake clients actively participate.Three training models(CNN,MLP,and ResNet-18)and three datasets(MNIST,Fashion MNIST,and CIFAR-10)have been used in experiments.According to theoretical analysis and experimental findings,the FL-DIAC is superior to other federated learning schemes of the same type in terms of effectiveness.

Research on the Reform of the Course“Reading of Concrete Structure Plan and Construction Drawings”Under the Background of“Promoting Teaching and Learning Through Competitions”

The inherent teaching approach can no longer meet the demands of society.In this paper,current issues within the teaching landscape of architectural engineering technology in higher vocational colleges as well as the policies and teaching demands that formed the basis of this model were analyzed.The study shows the importance of the implementation of the teaching model“promoting teaching and learning through competitions.”This model puts emphasis on the curriculum and teaching resources,while also integrating the teaching process and evaluation with competition.These efforts aim to drive education reform in order to better align with the objectives of vocational education personnel training,while also acting as a reference for similar courses.

Multiagent reinforcement learning through merging individually learned value functions

In cooperative multiagent systems, to learn the optimal policies of multiagents is very difficult. As the numbers of states and actions increase exponentially with the number of agents, their action policies become more intractable. By learning these value functions, an agent can learn its optimal action policies for a task. If a task can be decomposed into several subtasks and the agents have learned the optimal value functions for each subtask, this knowledge can be helpful for the agents in learning the optimal action policies for the whole task when they are acting simultaneously. When merging the agents’ independently learned optimal value functions, a novel multiagent online reinforcement learning algorithm LU-Q is proposed. By applying a transformation to the individually learned value functions, the constraints on the optimal value functions of each subtask are loosened. In each learning iteration process in algorithm LU-Q, the agents’ joint action set in a state is processed. Some actions of that state are pruned from the available action set according to the defined multiagent value function in LU-Q. As the items of the available action set of each state are reduced gradually in the iteration process of LU-Q, the convergence of the value functions is accelerated. LU-Q’s effectiveness, soundness and convergence are analyzed, and the experimental results show that the learning performance of LU-Q is better than the performance of standard Q learning.

Impact of learning through credit and value creation on the efficiency of Japanese commercial banks

This study investigates the learning curve of commercial banks regarding the efficiency of credit and value creation.However,current empirical methods for accessing the learning curve in organizations are not suitable for use in financial institutions.Considering bank-specific characteristics,we introduce a dynamic learning curve using a cost function adjusted to capture learning-by-doing in banks.Using the model,we test several hypotheses on the impact of bank intermediary experience(learning)on the efficiency of credit and value creation in Japanese commercial banks.The findings show that bank intermediary learning significantly improves the cost efficiency gain in the gross value created,total credit created,and investment.However,bank intermediary experience has no significant effect on the efficiency of the economic value created for all the banks analyzed.These findings have practical implications for evaluating cost dynamics in bank credit and value creation,risk management,lending to the real sector,and shareholder value creation.

Engaging College Students in Experiential Learning： Learning Through Serving, Inspiring Through Experience, and Creating Identity Through Bilingual Poetry

Experiential learning is the opportunity to meld teaching with experience; ＂to do＂ the things students learn about in the classroom, yet outside the classroom walls. I am an instructor that embraces experiential learning. Every other year, I lead a Chican@ Literature class which, after the semester is finished, culminates with a two-week excursion to New Mexico. While on-campus I highlight specific themes within Chicano narrative and poetry. Discussions focus on several key aspects regarding Chican@ Literature whose purpose is to create a voice for those whom have been marginalized within mainstream American culture. Chican@ Literature emphasizes a concept of origin which is reiterated in New Mexico through a sense of place in nature. A second topic often addressed in Chican@ Literature is the idea of aprendizaje. This is a journey of knowledge. In each episode experienced, the narrative voice gains a broader understanding of identity. This aprendizaje is also shared by my students as they gain a sense of self as defined by their own community in juxtaposition with their New Mexican fieldwork and the bilingual poetry they write. Lastly, Chican@ Literature often reveals an author or poet＇s personal culture clash or cultural fusion within the creative work itself. Once again, my students write about their own perspectives in a poetry workshop and presented their pieces during a poetry slam. Some of these pieces are included in this manuscript.

A study on Promoting Non-English Major Students＇ Autonomous Learning through Metacognitive Strategy Training

Improving Non-English major students＇ autonomous learning is a focus for the teachers in the high vocational and technical college. Furthermore, promoting students＇ autonomous learning through metcacognitive strategies training has been received increasing attention. The research reports an empirical study on the relationship between metacognitive strategies and English autonomous learning. Finally, the teaching experiment was proved to be feasible and valid.

Improving Chinese Language Learning through Collaborative Kahoot Mode

This study used quantitative methods to assess students'Chinese language learning attitudes and learning habits on Kahoot,a game-based learning platform.Kahoot enables teachers to transform bland Chinese vocabulary memorization into exciting,game-like situations.It makes Chinese language learning fun and interactive.The study aims to compare Kahoot team play mode with individual play mode.Sixty-four fifth graders participated.In the experimental group,students grouped by themselves or the teacher to compete with one another.They enjoyed working together to share what they knew and learned from each other.Students were tested prior to the course(pretest)and following the course(post-test).Observation notes,lesson plans,and surveys were also included.Analysis of the multiple types of data strengthens the conclusion that Kahoot can be an effective tool for teaching Chinese vocabulary,sentences,and culture.

A Qualitative Study of Individual and Organizational Learning through Physiotherapists’ Participation in a Research Project

The need for evidence-based practice has been recognized by physiotherapy organizations over the past decades. Earlier studies have documented facilitators and barriers that affect the use and implementation of evidence-based practice. Less is known about what kind of interventions might be useful to implement evidence-based practice. This study explores what physiotherapists learn through participation in a research project relevant to their professional development towards achieving a more evidence-based physiotherapy practice. To what extent this learning was transferred to colleagues for organizational learning is also examined. This study was set in Sweden, where health care is publicly funded. Patients do not need a referral from a physician to consult a physiotherapist. Eleven interviews were conducted with physiotherapists who had participated in a randomized, controlled, multicenter, physiotherapy intervention investigating neck-specific exercise for patients with whiplash disorder. Gadamer’s hermeneutics was used to analyze the data. The physiotherapists described a range of learning experiences from their project participation, including instrumental learning (the concrete application of knowledge to achieve changes in practice) and conceptual learning (changes in knowledge, understanding or attitudes). The research project enabled the physiotherapists to develop new treatment techniques for broader application and extend their competence in techniques already known (instrumental learning). The physiotherapists believed that project participation enhanced their overall competence as physiotherapists, increased their job motivation and strengthened their self-confidence and self-efficacy (conceptual learning). Physiotherapists’ participation in the research project yielded many individual learning experiences, fostered positive attitudes to research and was conducive to achieving a more research-informed physiotherapy practice. Participation was associated with a deeper understanding of the challenges involved in conducting research. The transfer from individual learning to the wider organization in terms of organizational learning was limited.

An Effective Way of Foreign Language Learning Through Reading

This study examined the overall effectiveness of reading proficiency especially the extensive reading in ESL.In order to investi-gate the process of acquisition more efficiently,author used reading-to-write approach to investigate the connection between readingand foreign language learning.The research also shows that learners need to be provided with plenty of interesting and comprehensiblebooks and they are supposed to use strategies that they will acquire anyway as they read.

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.

High-throughput calculations combining machine learning to investigate the corrosion properties of binary Mg alloys

Magnesium(Mg)alloys have shown great prospects as both structural and biomedical materials,while poor corrosion resistance limits their further application.In this work,to avoid the time-consuming and laborious experiment trial,a high-throughput computational strategy based on first-principles calculations is designed for screening corrosion-resistant binary Mg alloy with intermetallics,from both the thermodynamic and kinetic perspectives.The stable binary Mg intermetallics with low equilibrium potential difference with respect to the Mg matrix are firstly identified.Then,the hydrogen adsorption energies on the surfaces of these Mg intermetallics are calculated,and the corrosion exchange current density is further calculated by a hydrogen evolution reaction(HER)kinetic model.Several intermetallics,e.g.Y_(3)Mg,Y_(2)Mg and La_(5)Mg,are identified to be promising intermetallics which might effectively hinder the cathodic HER.Furthermore,machine learning(ML)models are developed to predict Mg intermetallics with proper hydrogen adsorption energy employing work function(W_(f))and weighted first ionization energy(WFIE).The generalization of the ML models is tested on five new binary Mg intermetallics with the average root mean square error(RMSE)of 0.11 eV.This study not only predicts some promising binary Mg intermetallics which may suppress the galvanic corrosion,but also provides a high-throughput screening strategy and ML models for the design of corrosion-resistant alloy,which can be extended to ternary Mg alloys or other alloy systems.

High-throughput studies and machine learning for design of β titanium alloys with optimum properties

Based on experimental data,machine learning(ML) models for Young's modulus,hardness,and hot-working ability of Ti-based alloys were constructed.In the models,the interdiffusion and mechanical property data were high-throughput re-evaluated from composition variations and nanoindentation data of diffusion couples.Then,the Ti-(22±0.5)at.%Nb-(30±0.5)at.%Zr-(4±0.5)at.%Cr(TNZC) alloy with a single body-centered cubic(BCC) phase was screened in an interactive loop.The experimental results exhibited a relatively low Young's modulus of(58±4) GPa,high nanohardness of(3.4±0.2) GPa,high microhardness of HV(520±5),high compressive yield strength of(1220±18) MPa,large plastic strain greater than 30%,and superior dry-and wet-wear resistance.This work demonstrates that ML combined with high-throughput analytic approaches can offer a powerful tool to accelerate the design of multicomponent Ti alloys with desired properties.Moreover,it is indicated that TNZC alloy is an attractive candidate for biomedical applications.

Securing Cloud-Encrypted Data:Detecting Ransomware-as-a-Service(RaaS)Attacks through Deep Learning Ensemble

Data security assurance is crucial due to the increasing prevalence of cloud computing and its widespread use across different industries,especially in light of the growing number of cybersecurity threats.A major and everpresent threat is Ransomware-as-a-Service(RaaS)assaults,which enable even individuals with minimal technical knowledge to conduct ransomware operations.This study provides a new approach for RaaS attack detection which uses an ensemble of deep learning models.For this purpose,the network intrusion detection dataset“UNSWNB15”from the Intelligent Security Group of the University of New South Wales,Australia is analyzed.In the initial phase,the rectified linear unit-,scaled exponential linear unit-,and exponential linear unit-based three separate Multi-Layer Perceptron(MLP)models are developed.Later,using the combined predictive power of these three MLPs,the RansoDetect Fusion ensemble model is introduced in the suggested methodology.The proposed ensemble technique outperforms previous studieswith impressive performance metrics results,including 98.79%accuracy and recall,98.85%precision,and 98.80%F1-score.The empirical results of this study validate the ensemble model’s ability to improve cybersecurity defenses by showing that it outperforms individual MLPmodels.In expanding the field of cybersecurity strategy,this research highlights the significance of combined deep learning models in strengthening intrusion detection systems against sophisticated cyber threats.

A Robust Approach for Multi Classification-Based Intrusion Detection through Stacking Deep Learning Models

Intrusion detection is a predominant task that monitors and protects the network infrastructure.Therefore,many datasets have been published and investigated by researchers to analyze and understand the problem of intrusion prediction and detection.In particular,the Network Security Laboratory-Knowledge Discovery in Databases(NSL-KDD)is an extensively used benchmark dataset for evaluating intrusion detection systems(IDSs)as it incorporates various network traffic attacks.It is worth mentioning that a large number of studies have tackled the problem of intrusion detection using machine learning models,but the performance of these models often decreases when evaluated on new attacks.This has led to the utilization of deep learning techniques,which have showcased significant potential for processing large datasets and therefore improving detection accuracy.For that reason,this paper focuses on the role of stacking deep learning models,including convolution neural network(CNN)and deep neural network(DNN)for improving the intrusion detection rate of the NSL-KDD dataset.Each base model is trained on the NSL-KDD dataset to extract significant features.Once the base models have been trained,the stacking process proceeds to the second stage,where a simple meta-model has been trained on the predictions generated from the proposed base models.The combination of the predictions allows the meta-model to distinguish different classes of attacks and increase the detection rate.Our experimental evaluations using the NSL-KDD dataset have shown the efficacy of stacking deep learning models for intrusion detection.The performance of the ensemble of base models,combined with the meta-model,exceeds the performance of individual models.Our stacking model has attained an accuracy of 99%and an average F1-score of 93%for the multi-classification scenario.Besides,the training time of the proposed ensemble model is lower than the training time of benchmark techniques,demonstrating its efficiency and robustness.

Predicting the Mechanical Behavior of a Bioinspired Nanocomposite through Machine Learning

The bioinspired nacre or bone structure represents a remarkable example of tough,strong,lightweight,and multifunctional structures in biological materials that can be an inspiration to design bioinspired high-performance materials.The bioinspired structure consists of hard grains and soft material interfaces.While the material interface has a very low volume percentage,its property has the ability to determine the bulk material response.Machine learning technology nowadays is widely used in material science.A machine learning model was utilized to predict the material response based on the material interface properties in a bioinspired nanocomposite.This model was trained on a comprehensive dataset of material response and interface properties,allowing it to make accurate predictions.The results of this study demonstrate the efficiency and high accuracy of the machine learning model.The successful application of machine learning into the material property prediction process has the potential to greatly enhance both the efficiency and accuracy of the material design process.

Intelligent Machine Learning Based Brain Tumor Segmentation through Multi-Layer Hybrid U-Net with CNN Feature Integration

Brain tumors are a pressing public health concern, characterized by their high mortality and morbidity rates.Nevertheless, the manual segmentation of brain tumors remains a laborious and error-prone task, necessitatingthe development of more precise and efficient methodologies. To address this formidable challenge, we proposean advanced approach for segmenting brain tumorMagnetic Resonance Imaging (MRI) images that harnesses theformidable capabilities of deep learning and convolutional neural networks (CNNs). While CNN-based methodshave displayed promise in the realm of brain tumor segmentation, the intricate nature of these tumors, markedby irregular shapes, varying sizes, uneven distribution, and limited available data, poses substantial obstacles toachieving accurate semantic segmentation. In our study, we introduce a pioneering Hybrid U-Net framework thatseamlessly integrates the U-Net and CNN architectures to surmount these challenges. Our proposed approachencompasses preprocessing steps that enhance image visualization, a customized layered U-Net model tailoredfor precise segmentation, and the inclusion of dropout layers to mitigate overfitting during the training process.Additionally, we leverage the CNN mechanism to exploit contextual information within brain tumorMRI images,resulting in a substantial enhancement in segmentation accuracy.Our experimental results attest to the exceptionalperformance of our framework, with accuracy rates surpassing 97% across diverse datasets, showcasing therobustness and effectiveness of our approach. Furthermore, we conduct a comprehensive assessment of ourmethod’s capabilities by evaluating various performance measures, including the sensitivity, Jaccard-index, andspecificity. Our proposed model achieved 99% accuracy. The implications of our findings are profound. Theproposed Hybrid U-Net model emerges as a highly promising diagnostic tool, poised to revolutionize brain tumorimage segmentation for radiologists and clinicians.

Interpretable Machine Learning-Assisted High-Throughput Screening for Understanding NRR Electrocatalyst Performance Modulation between Active Center and C-N Coordination

Understanding the correlation between the fundamental descriptors and catalytic performance is meaningful to guide the design of high-performance electrochemical catalysts.However,exploring key factors that affect catalytic performance in the vast catalyst space remains challenging for people.Herein,to accurately identify the factors that affect the performance of N2 reduction,we apply interpretable machine learning(ML)to analyze high-throughput screening results,which is also suited to other surface reactions in catalysis.To expound on the paradigm,33 promising catalysts are screened from 168 carbon-supported candidates,specifically single-atom catalysts(SACs)supported by a BC_(3)monolayer(TM@V_(B/C)-N_(n)=_(0-3)-BC_(3))via high-throughput screening.Subsequently,the hybrid sampling method and XGBoost model are selected to classify eligible and non-eligible catalysts.Through feature interpretation using Shapley Additive Explanations(SHAP)analysis,two crucial features,that is,the number of valence electrons(N_(v))and nitrogen substitution(N_(n)),are screened out.Combining SHAP analysis and electronic structure calculations,the synergistic effect between an active center with low valence electron numbers and reasonable C-N coordination(a medium fraction of nitrogen substitution)can exhibit high catalytic performance.Finally,six superior catalysts with a limiting potential lower than-0.4 V are predicted.Our workflow offers a rational approach to obtaining key information on catalytic performance from high-throughput screening results to design efficient catalysts that can be applied to other materials and reactions.

Improving Prediction Efficiency of Machine Learning Models for Cardiovascular Disease in IoST-Based Systems through Hyperparameter Optimization

This study explores the impact of hyperparameter optimization on machine learning models for predicting cardiovascular disease using data from an IoST(Internet of Sensing Things)device.Ten distinct machine learning approaches were implemented and systematically evaluated before and after hyperparameter tuning.Significant improvements were observed across various models,with SVM and Neural Networks consistently showing enhanced performance metrics such as F1-Score,recall,and precision.The study underscores the critical role of tailored hyperparameter tuning in optimizing these models,revealing diverse outcomes among algorithms.Decision Trees and Random Forests exhibited stable performance throughout the evaluation.While enhancing accuracy,hyperparameter optimization also led to increased execution time.Visual representations and comprehensive results support the findings,confirming the hypothesis that optimizing parameters can effectively enhance predictive capabilities in cardiovascular disease.This research contributes to advancing the understanding and application of machine learning in healthcare,particularly in improving predictive accuracy for cardiovascular disease management and intervention strategies.

Identifying influencing factors and characterizing key issues in urban sustainable development capacity through machine learning

In response to the United Nations Sustainable Development Goals and China’s“Dual Carbon”Goals(DCGs means the goals of“Carbon Peak and carbon neutrality”),this paper from the perspective of the construction of China’s Innovation Demonstration Zones for Sustainable Development Agenda(IDZSDAs),combines carbon emission-related metrics to construct a comprehensive assessment system for Urban Sustainable Development Capacity(USDC).After obtaining USDC assessment results through the assessment system,an approach combining Least Absolute Shrinkage and Selection Operator(LASSO)regression and Random Forest(RF)based on machine learning is proposed for identifying influencing factors and characterizing key issues.Combining Coupling Coordination Degree(CCD)analysis,the study further summarizes the systemic patterns and future directions of urban sustainable development.A case study on the IDZSDAs from 2015 to 2022 reveals that:(1)the combined identification method based on machine learning and CCD models effectively quantifies influencing factors and key issues in the urban sustainable development process;(2)the correspondence between influencing factors and key subsystems identified by the LASSO-RF combination model is generally consistent with the development situations in various cities;and(3)the machine learning-based combined recognition method is scalable and dynamic.It enables decision-makers to accurately identify influencing factors and characterize key issues based on actual urban development needs.

Improving the Short-Range Precipitation Forecast of Numerical Weather Prediction through a Deep Learning-Based Mask Approach

Due to various technical issues,existing numerical weather prediction(NWP)models often perform poorly at forecasting rainfall in the first several hours.To correct the bias of an NWP model and improve the accuracy of short-range precipitation forecasting,we propose a deep learning-based approach called UNet Mask,which combines NWP forecasts with the output of a convolutional neural network called UNet.The UNet Mask involves training the UNet on historical data from the NWP model and gridded rainfall observations for 6-hour precipitation forecasting.The overlap of the UNet output and the NWP forecasts at the same rainfall threshold yields a mask.The UNet Mask blends the UNet output and the NWP forecasts by taking the maximum between them and passing through the mask,which provides the corrected 6-hour rainfall forecasts.We evaluated UNet Mask on a test set and in real-time verification.The results showed that UNet Mask outperforms the NWP model in 6-hour precipitation prediction by reducing the FAR and improving CSI scores.Sensitivity tests also showed that different small rainfall thresholds applied to the UNet and the NWP model have different effects on UNet Mask's forecast performance.This study shows that UNet Mask is a promising approach for improving rainfall forecasting of NWP models.