LKMT:Linguistics Knowledge-Driven Multi-Task Neural Machine Translation for Urdu and English

Thanks to the strong representation capability of pre-trained language models,supervised machine translation models have achieved outstanding performance.However,the performances of these models drop sharply when the scale of the parallel training corpus is limited.Considering the pre-trained language model has a strong ability for monolingual representation,it is the key challenge for machine translation to construct the in-depth relationship between the source and target language by injecting the lexical and syntactic information into pre-trained language models.To alleviate the dependence on the parallel corpus,we propose a Linguistics Knowledge-Driven MultiTask(LKMT)approach to inject part-of-speech and syntactic knowledge into pre-trained models,thus enhancing the machine translation performance.On the one hand,we integrate part-of-speech and dependency labels into the embedding layer and exploit large-scale monolingual corpus to update all parameters of pre-trained language models,thus ensuring the updated language model contains potential lexical and syntactic information.On the other hand,we leverage an extra self-attention layer to explicitly inject linguistic knowledge into the pre-trained language model-enhanced machine translation model.Experiments on the benchmark dataset show that our proposed LKMT approach improves the Urdu-English translation accuracy by 1.97 points and the English-Urdu translation accuracy by 2.42 points,highlighting the effectiveness of our LKMT framework.Detailed ablation experiments confirm the positive impact of part-of-speech and dependency parsing on machine translation.

Improving Low-Resource Machine Translation Using Reinforcement Learning from Human Feedback

Neural Machine Translation is one of the key research directions in Natural Language Processing.However,limited by the scale and quality of parallel corpus,the translation quality of low-resource Neural Machine Translation has always been unsatisfactory.When Reinforcement Learning from Human Feedback(RLHF)is applied to lowresource machine translation,commonly encountered issues of substandard preference data quality and the higher cost associated with manual feedback data.Therefore,a more cost-effective method for obtaining feedback data is proposed.At first,optimizing the quality of preference data through the prompt engineering of the Large Language Model(LLM),then combining human feedback to complete the evaluation.In this way,the reward model could acquire more semantic information and human preferences during the training phase,thereby enhancing feedback efficiency and the result’s quality.Experimental results demonstrate that compared with the traditional RLHF method,our method has been proven effective on multiple datasets and exhibits a notable improvement of 1.07 in BLUE.Meanwhile,it is also more favorably received in the assessments conducted by human evaluators and GPT-4o.

Neural Machine Translation Models with Attention-Based Dropout Layer

In bilingual translation,attention-based Neural Machine Translation(NMT)models are used to achieve synchrony between input and output sequences and the notion of alignment.NMT model has obtained state-of-the-art performance for several language pairs.However,there has been little work exploring useful architectures for Urdu-to-English machine translation.We conducted extensive Urdu-to-English translation experiments using Long short-term memory(LSTM)/Bidirectional recurrent neural networks(Bi-RNN)/Statistical recurrent unit(SRU)/Gated recurrent unit(GRU)/Convolutional neural network(CNN)and Transformer.Experimental results show that Bi-RNN and LSTM with attention mechanism trained iteratively,with a scalable data set,make precise predictions on unseen data.The trained models yielded competitive results by achieving 62.6%and 61%accuracy and 49.67 and 47.14 BLEU scores,respectively.From a qualitative perspective,the translation of the test sets was examined manually,and it was observed that trained models tend to produce repetitive output more frequently.The attention score produced by Bi-RNN and LSTM produced clear alignment,while GRU showed incorrect translation for words,poor alignment and lack of a clear structure.Therefore,we considered refining the attention-based models by defining an additional attention-based dropout layer.Attention dropout fixes alignment errors and minimizes translation errors at the word level.After empirical demonstration and comparison with their counterparts,we found improvement in the quality of the resulting translation system and a decrease in the perplexity and over-translation score.The ability of the proposed model was evaluated using Arabic-English and Persian-English datasets as well.We empirically concluded that adding an attention-based dropout layer helps improve GRU,SRU,and Transformer translation and is considerably more efficient in translation quality and speed.

Neural Machine Translation by Fusing Key Information of Text

When the Transformer proposed by Google in 2017,it was first used for machine translation tasks and achieved the state of the art at that time.Although the current neural machine translation model can generate high quality translation results,there are still mistranslations and omissions in the translation of key information of long sentences.On the other hand,the most important part in traditional translation tasks is the translation of key information.In the translation results,as long as the key information is translated accurately and completely,even if other parts of the results are translated incorrect,the final translation results’quality can still be guaranteed.In order to solve the problem of mistranslation and missed translation effectively,and improve the accuracy and completeness of long sentence translation in machine translation,this paper proposes a key information fused neural machine translation model based on Transformer.The model proposed in this paper extracts the keywords of the source language text separately as the input of the encoder.After the same encoding as the source language text,it is fused with the output of the source language text encoded by the encoder,then the key information is processed and input into the decoder.With incorporating keyword information from the source language sentence,the model’s performance in the task of translating long sentences is very reliable.In order to verify the effectiveness of the method of fusion of key information proposed in this paper,a series of experiments were carried out on the verification set.The experimental results show that the Bilingual Evaluation Understudy(BLEU)score of the model proposed in this paper on theWorkshop on Machine Translation(WMT)2017 test dataset is higher than the BLEU score of Transformer proposed by Google on the WMT2017 test dataset.The experimental results show the advantages of the model proposed in this paper.

Research on system combination of machine translation based on Transformer

Influenced by its training corpus,the performance of different machine translation systems varies greatly.Aiming at achieving higher quality translations,system combination methods combine the translation results of multiple systems through statistical combination or neural network combination.This paper proposes a new multi-system translation combination method based on the Transformer architecture,which uses a multi-encoder to encode source sentences and the translation results of each system in order to realize encoder combination and decoder combination.The experimental verification on the Chinese-English translation task shows that this method has 1.2-2.35 more bilingual evaluation understudy(BLEU)points compared with the best single system results,0.71-3.12 more BLEU points compared with the statistical combination method,and 0.14-0.62 more BLEU points compared with the state-of-the-art neural network combination method.The experimental results demonstrate the effectiveness of the proposed system combination method based on Transformer.

Significant risk factors for intensive care unit-acquired weakness:A processing strategy based on repeated machine learning

BACKGROUND Intensive care unit-acquired weakness(ICU-AW)is a common complication that significantly impacts the patient's recovery process,even leading to adverse outcomes.Currently,there is a lack of effective preventive measures.AIM To identify significant risk factors for ICU-AW through iterative machine learning techniques and offer recommendations for its prevention and treatment.METHODS Patients were categorized into ICU-AW and non-ICU-AW groups on the 14th day post-ICU admission.Relevant data from the initial 14 d of ICU stay,such as age,comorbidities,sedative dosage,vasopressor dosage,duration of mechanical ventilation,length of ICU stay,and rehabilitation therapy,were gathered.The relationships between these variables and ICU-AW were examined.Utilizing iterative machine learning techniques,a multilayer perceptron neural network model was developed,and its predictive performance for ICU-AW was assessed using the receiver operating characteristic curve.RESULTS Within the ICU-AW group,age,duration of mechanical ventilation,lorazepam dosage,adrenaline dosage,and length of ICU stay were significantly higher than in the non-ICU-AW group.Additionally,sepsis,multiple organ dysfunction syndrome,hypoalbuminemia,acute heart failure,respiratory failure,acute kidney injury,anemia,stress-related gastrointestinal bleeding,shock,hypertension,coronary artery disease,malignant tumors,and rehabilitation therapy ratios were significantly higher in the ICU-AW group,demonstrating statistical significance.The most influential factors contributing to ICU-AW were identified as the length of ICU stay(100.0%)and the duration of mechanical ventilation(54.9%).The neural network model predicted ICU-AW with an area under the curve of 0.941,sensitivity of 92.2%,and specificity of 82.7%.CONCLUSION The main factors influencing ICU-AW are the length of ICU stay and the duration of mechanical ventilation.A primary preventive strategy,when feasible,involves minimizing both ICU stay and mechanical ventilation duration.

Prediction model for corrosion rate of low-alloy steels under atmospheric conditions using machine learning algorithms

This work constructed a machine learning(ML)model to predict the atmospheric corrosion rate of low-alloy steels(LAS).The material properties of LAS,environmental factors,and exposure time were used as the input,while the corrosion rate as the output.6 dif-ferent ML algorithms were used to construct the proposed model.Through optimization and filtering,the eXtreme gradient boosting(XG-Boost)model exhibited good corrosion rate prediction accuracy.The features of material properties were then transformed into atomic and physical features using the proposed property transformation approach,and the dominant descriptors that affected the corrosion rate were filtered using the recursive feature elimination(RFE)as well as XGBoost methods.The established ML models exhibited better predic-tion performance and generalization ability via property transformation descriptors.In addition,the SHapley additive exPlanations(SHAP)method was applied to analyze the relationship between the descriptors and corrosion rate.The results showed that the property transformation model could effectively help with analyzing the corrosion behavior,thereby significantly improving the generalization ability of corrosion rate prediction models.

Machine learning with active pharmaceutical ingredient/polymer interaction mechanism:Prediction for complex phase behaviors of pharmaceuticals and formulations

The high throughput prediction of the thermodynamic phase behavior of active pharmaceutical ingredients(APIs)with pharmaceutically relevant excipients remains a major scientific challenge in the screening of pharmaceutical formulations.In this work,a developed machine-learning model efficiently predicts the solubility of APIs in polymers by learning the phase equilibrium principle and using a few molecular descriptors.Under the few-shot learning framework,thermodynamic theory(perturbed-chain statistical associating fluid theory)was used for data augmentation,and computational chemistry was applied for molecular descriptors'screening.The results showed that the developed machine-learning model can predict the API-polymer phase diagram accurately,broaden the solubility data of APIs in polymers,and reproduce the relationship between API solubility and the interaction mechanisms between API and polymer successfully,which provided efficient guidance for the development of pharmaceutical formulations.

Machine learning applications in stroke medicine:advancements,challenges,and future prospectives

Stroke is a leading cause of disability and mortality worldwide,necessitating the development of advanced technologies to improve its diagnosis,treatment,and patient outcomes.In recent years,machine learning techniques have emerged as promising tools in stroke medicine,enabling efficient analysis of large-scale datasets and facilitating personalized and precision medicine approaches.This abstract provides a comprehensive overview of machine learning’s applications,challenges,and future directions in stroke medicine.Recently introduced machine learning algorithms have been extensively employed in all the fields of stroke medicine.Machine learning models have demonstrated remarkable accuracy in imaging analysis,diagnosing stroke subtypes,risk stratifications,guiding medical treatment,and predicting patient prognosis.Despite the tremendous potential of machine learning in stroke medicine,several challenges must be addressed.These include the need for standardized and interoperable data collection,robust model validation and generalization,and the ethical considerations surrounding privacy and bias.In addition,integrating machine learning models into clinical workflows and establishing regulatory frameworks are critical for ensuring their widespread adoption and impact in routine stroke care.Machine learning promises to revolutionize stroke medicine by enabling precise diagnosis,tailored treatment selection,and improved prognostication.Continued research and collaboration among clinicians,researchers,and technologists are essential for overcoming challenges and realizing the full potential of machine learning in stroke care,ultimately leading to enhanced patient outcomes and quality of life.This review aims to summarize all the current implications of machine learning in stroke diagnosis,treatment,and prognostic evaluation.At the same time,another purpose of this paper is to explore all the future perspectives these techniques can provide in combating this disabling disease.

Machine learning-assisted efficient design of Cu-based shape memory alloy with specific phase transition temperature

The martensitic transformation temperature is the basis for the application of shape memory alloys(SMAs),and the ability to quickly and accurately predict the transformation temperature of SMAs has very important practical significance.In this work,machine learning(ML)methods were utilized to accelerate the search for shape memory alloys with targeted properties(phase transition temperature).A group of component data was selected to design shape memory alloys using reverse design method from numerous unexplored data.Component modeling and feature modeling were used to predict the phase transition temperature of the shape memory alloys.The experimental results of the shape memory alloys were obtained to verify the effectiveness of the support vector regression(SVR)model.The results show that the machine learning model can obtain target materials more efficiently and pertinently,and realize the accurate and rapid design of shape memory alloys with specific target phase transition temperature.On this basis,the relationship between phase transition temperature and material descriptors is analyzed,and it is proved that the key factors affecting the phase transition temperature of shape memory alloys are based on the strength of the bond energy between atoms.This work provides new ideas for the controllable design and performance optimization of Cu-based shape memory alloys.

Machine Learning Analysis of Impact of Western US Fires on Central US Hailstorms

Fires,including wildfires,harm air quality and essential public services like transportation,communication,and utilities.These fires can also influence atmospheric conditions,including temperature and aerosols,potentially affecting severe convective storms.Here,we investigate the remote impacts of fires in the western United States(WUS)on the occurrence of large hail(size:≥2.54 cm)in the central US(CUS)over the 20-year period of 2001–20 using the machine learning(ML),Random Forest(RF),and Extreme Gradient Boosting(XGB)methods.The developed RF and XGB models demonstrate high accuracy(>90%)and F1 scores of up to 0.78 in predicting large hail occurrences when WUS fires and CUS hailstorms coincide,particularly in four states(Wyoming,South Dakota,Nebraska,and Kansas).The key contributing variables identified from both ML models include the meteorological variables in the fire region(temperature and moisture),the westerly wind over the plume transport path,and the fire features(i.e.,the maximum fire power and burned area).The results confirm a linkage between WUS fires and severe weather in the CUS,corroborating the findings of our previous modeling study conducted on case simulations with a detailed physics model.

Enhanced prediction of anisotropic deformation behavior using machine learning with data augmentation

Mg alloys possess an inherent plastic anisotropy owing to the selective activation of deformation mechanisms depending on the loading condition.This characteristic results in a diverse range of flow curves that vary with a deformation condition.This study proposes a novel approach for accurately predicting an anisotropic deformation behavior of wrought Mg alloys using machine learning(ML)with data augmentation.The developed model combines four key strategies from data science:learning the entire flow curves,generative adversarial networks(GAN),algorithm-driven hyperparameter tuning,and gated recurrent unit(GRU)architecture.The proposed model,namely GAN-aided GRU,was extensively evaluated for various predictive scenarios,such as interpolation,extrapolation,and a limited dataset size.The model exhibited significant predictability and improved generalizability for estimating the anisotropic compressive behavior of ZK60 Mg alloys under 11 annealing conditions and for three loading directions.The GAN-aided GRU results were superior to those of previous ML models and constitutive equations.The superior performance was attributed to hyperparameter optimization,GAN-based data augmentation,and the inherent predictivity of the GRU for extrapolation.As a first attempt to employ ML techniques other than artificial neural networks,this study proposes a novel perspective on predicting the anisotropic deformation behaviors of wrought Mg alloys.

Heterogeneous decentralised machine unlearning with seed model distillation

As some recent information security legislation endowed users with unconditional rights to be forgotten by any trained machine learning model,personalised IoT service pro-viders have to put unlearning functionality into their consideration.The most straight-forward method to unlearn users'contribution is to retrain the model from the initial state,which is not realistic in high throughput applications with frequent unlearning requests.Though some machine unlearning frameworks have been proposed to speed up the retraining process,they fail to match decentralised learning scenarios.A decentralised unlearning framework called heterogeneous decentralised unlearning framework with seed(HDUS)is designed,which uses distilled seed models to construct erasable en-sembles for all clients.Moreover,the framework is compatible with heterogeneous on-device models,representing stronger scalability in real-world applications.Extensive experiments on three real-world datasets show that our HDUS achieves state-of-the-art performance.

Assessment of compressive strength of jet grouting by machine learning

Jet grouting is one of the most popular soil improvement techniques,but its design usually involves great uncertainties that can lead to economic cost overruns in construction projects.The high dispersion in the properties of the improved material leads to designers assuming a conservative,arbitrary and unjustified strength,which is even sometimes subjected to the results of the test fields.The present paper presents an approach for prediction of the uniaxial compressive strength(UCS)of jet grouting columns based on the analysis of several machine learning algorithms on a database of 854 results mainly collected from different research papers.The selected machine learning model(extremely randomized trees)relates the soil type and various parameters of the technique to the value of the compressive strength.Despite the complex mechanism that surrounds the jet grouting process,evidenced by the high dispersion and low correlation of the variables studied,the trained model allows to optimally predict the values of compressive strength with a significant improvement with respect to the existing works.Consequently,this work proposes for the first time a reliable and easily applicable approach for estimation of the compressive strength of jet grouting columns.

Machine Learning-Based Decision-Making Mechanism for Risk Assessment of Cardiovascular Disease

Cardiovascular disease(CVD)has gradually become one of the main causes of harm to the life and health of residents.Exploring the influencing factors and risk assessment methods of CVD has become a general trend.In this paper,a machine learning-based decision-making mechanism for risk assessment of CVD is designed.In this mechanism,the logistics regression analysismethod and factor analysismodel are used to select age,obesity degree,blood pressure,blood fat,blood sugar,smoking status,drinking status,and exercise status as the main pathogenic factors of CVD,and an index systemof risk assessment for CVD is established.Then,a two-stage model combining K-means cluster analysis and random forest(RF)is proposed to evaluate and predict the risk of CVD,and the predicted results are compared with the methods of Bayesian discrimination,K-means cluster analysis and RF.The results show that thepredictioneffect of theproposedtwo-stagemodel is better than that of the comparedmethods.Moreover,several suggestions for the government,the medical industry and the public are provided based on the research results.

Accurate and efficient remaining useful life prediction of batteries enabled by physics-informed machine learning

The safe and reliable operation of lithium-ion batteries necessitates the accurate prediction of remaining useful life(RUL).However,this task is challenging due to the diverse ageing mechanisms,various operating conditions,and limited measured signals.Although data-driven methods are perceived as a promising solution,they ignore intrinsic battery physics,leading to compromised accuracy,low efficiency,and low interpretability.In response,this study integrates domain knowledge into deep learning to enhance the RUL prediction performance.We demonstrate accurate RUL prediction using only a single charging curve.First,a generalisable physics-based model is developed to extract ageing-correlated parameters that can describe and explain battery degradation from battery charging data.The parameters inform a deep neural network(DNN)to predict RUL with high accuracy and efficiency.The trained model is validated under 3 types of batteries working under 7 conditions,considering fully charged and partially charged cases.Using data from one cycle only,the proposed method achieves a root mean squared error(RMSE)of 11.42 cycles and a mean absolute relative error(MARE)of 3.19%on average,which are over45%and 44%lower compared to the two state-of-the-art data-driven methods,respectively.Besides its accuracy,the proposed method also outperforms existing methods in terms of efficiency,input burden,and robustness.The inherent relationship between the model parameters and the battery degradation mechanism is further revealed,substantiating the intrinsic superiority of the proposed method.

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.

An Intelligent SDN-IoT Enabled Intrusion Detection System for Healthcare Systems Using a Hybrid Deep Learning and Machine Learning Approach

The advent of pandemics such as COVID-19 significantly impacts human behaviour and lives every day.Therefore,it is essential to make medical services connected to internet,available in every remote location during these situations.Also,the security issues in the Internet of Medical Things(IoMT)used in these service,make the situation even more critical because cyberattacks on the medical devices might cause treatment delays or clinical failures.Hence,services in the healthcare ecosystem need rapid,uninterrupted,and secure facilities.The solution provided in this research addresses security concerns and services availability for patients with critical health in remote areas.This research aims to develop an intelligent Software Defined Networks(SDNs)enabled secure framework for IoT healthcare ecosystem.We propose a hybrid of machine learning and deep learning techniques(DNN+SVM)to identify network intrusions in the sensor-based healthcare data.In addition,this system can efficiently monitor connected devices and suspicious behaviours.Finally,we evaluate the performance of our proposed framework using various performance metrics based on the healthcare application scenarios.the experimental results show that the proposed approach effectively detects and mitigates attacks in the SDN-enabled IoT networks and performs better that other state-of-art-approaches.

Leveraging machine learning for early recurrence prediction in hepatocellular carcinoma:A step towards precision medicine

The high rate of early recurrence in hepatocellular carcinoma(HCC)post curative surgical intervention poses a substantial clinical hurdle,impacting patient outcomes and complicating postoperative management.The advent of machine learning provides a unique opportunity to harness vast datasets,identifying subtle patterns and factors that elude conventional prognostic methods.Machine learning models,equipped with the ability to analyse intricate relationships within datasets,have shown promise in predicting outcomes in various medical disciplines.In the context of HCC,the application of machine learning to predict early recurrence holds potential for personalized postoperative care strategies.This editorial comments on the study carried out exploring the merits and efficacy of random survival forests(RSF)in identifying significant risk factors for recurrence,stratifying patients at low and high risk of HCC recurrence and comparing this to traditional COX proportional hazard models(CPH).In doing so,the study demonstrated that the RSF models are superior to traditional CPH models in predicting recurrence of HCC and represent a giant leap towards precision medicine.

Outsmarting Android Malware with Cutting-Edge Feature Engineering and Machine Learning Techniques

The growing usage of Android smartphones has led to a significant rise in incidents of Android malware andprivacy breaches.This escalating security concern necessitates the development of advanced technologies capableof automatically detecting andmitigatingmalicious activities in Android applications(apps).Such technologies arecrucial for safeguarding user data and maintaining the integrity of mobile devices in an increasingly digital world.Current methods employed to detect sensitive data leaks in Android apps are hampered by two major limitationsthey require substantial computational resources and are prone to a high frequency of false positives.This meansthat while attempting to identify security breaches,these methods often consume considerable processing powerand mistakenly flag benign activities as malicious,leading to inefficiencies and reduced reliability in malwaredetection.The proposed approach includes a data preprocessing step that removes duplicate samples,managesunbalanced datasets,corrects inconsistencies,and imputes missing values to ensure data accuracy.The Minimaxmethod is then used to normalize numerical data,followed by feature vector extraction using the Gain ratio andChi-squared test to identify and extract the most significant characteristics using an appropriate prediction model.This study focuses on extracting a subset of attributes best suited for the task and recommending a predictivemodel based on domain expert opinion.The proposed method is evaluated using Drebin and TUANDROMDdatasets containing 15,036 and 4,464 benign and malicious samples,respectively.The empirical result shows thatthe RandomForest(RF)and Support VectorMachine(SVC)classifiers achieved impressive accuracy rates of 98.9%and 98.8%,respectively,in detecting unknown Androidmalware.A sensitivity analysis experiment was also carriedout on all three ML-based classifiers based on MAE,MSE,R2,and sensitivity parameters,resulting in a flawlessperformance for both datasets.This approach has substantial potential for real-world applications and can serve asa valuable tool for preventing the spread of Androidmalware and enhancing mobile device security.