E. Stone in the article “18 Mysteries and Unanswered Questions About Our Solar System. Little Astronomy” wrote: One of the great things about astronomy is that there is still so much out there for us to discover. Th...E. Stone in the article “18 Mysteries and Unanswered Questions About Our Solar System. Little Astronomy” wrote: One of the great things about astronomy is that there is still so much out there for us to discover. There are so many unanswered questions and mysteries about the universe. There is always a puzzle to solve and that is part of beauty. Even in our own neighborhood, the Solar System, there are many questions we still have not been able to answer [1]. In the present paper, we explain the majority of these Mysteries and some other unexplained phenomena in the Solar System (SS) in frames of the developed Hypersphere World-Universe Model (WUM) [2].展开更多
Despite low-income countries producing only a quarter of per capita plastic waste compared to high-income countries,the related environmental,health,and economic costs of plastic could be up to 10 times higher than in...Despite low-income countries producing only a quarter of per capita plastic waste compared to high-income countries,the related environmental,health,and economic costs of plastic could be up to 10 times higher than in wealthier countries,declared Who Pays for Plastic Pollution?Enabling Global Equity in the Plastic Value Chain,a report released by World Wild Fund(WWF).The report highlighted significant inequalities within the global plastic value chain and explained how cost disparities exert a substantial impact on low and middle-income countries.展开更多
In the current landscape of the COVID-19 pandemic,the utilization of deep learning in medical imaging,especially in chest computed tomography(CT)scan analysis for virus detection,has become increasingly significant.De...In the current landscape of the COVID-19 pandemic,the utilization of deep learning in medical imaging,especially in chest computed tomography(CT)scan analysis for virus detection,has become increasingly significant.Despite its potential,deep learning’s“black box”nature has been a major impediment to its broader acceptance in clinical environments,where transparency in decision-making is imperative.To bridge this gap,our research integrates Explainable AI(XAI)techniques,specifically the Local Interpretable Model-Agnostic Explanations(LIME)method,with advanced deep learning models.This integration forms a sophisticated and transparent framework for COVID-19 identification,enhancing the capability of standard Convolutional Neural Network(CNN)models through transfer learning and data augmentation.Our approach leverages the refined DenseNet201 architecture for superior feature extraction and employs data augmentation strategies to foster robust model generalization.The pivotal element of our methodology is the use of LIME,which demystifies the AI decision-making process,providing clinicians with clear,interpretable insights into the AI’s reasoning.This unique combination of an optimized Deep Neural Network(DNN)with LIME not only elevates the precision in detecting COVID-19 cases but also equips healthcare professionals with a deeper understanding of the diagnostic process.Our method,validated on the SARS-COV-2 CT-Scan dataset,demonstrates exceptional diagnostic accuracy,with performance metrics that reinforce its potential for seamless integration into modern healthcare systems.This innovative approach marks a significant advancement in creating explainable and trustworthy AI tools for medical decisionmaking in the ongoing battle against COVID-19.展开更多
Accurate prediction of the rate of penetration(ROP)is significant for drilling optimization.While the intelligent ROP prediction model based on fully connected neural networks(FNN)outperforms traditional ROP equations...Accurate prediction of the rate of penetration(ROP)is significant for drilling optimization.While the intelligent ROP prediction model based on fully connected neural networks(FNN)outperforms traditional ROP equations and machine learning algorithms,its lack of interpretability undermines its credibility.This study proposes a novel interpretation and characterization method for the FNN ROP prediction model using the Rectified Linear Unit(ReLU)activation function.By leveraging the derivative of the ReLU function,the FNN function calculation process is transformed into vector operations.The FNN model is linearly characterized through further simplification,enabling its interpretation and analysis.The proposed method is applied in ROP prediction scenarios using drilling data from three vertical wells in the Tarim Oilfield.The results demonstrate that the FNN ROP prediction model with ReLU as the activation function performs exceptionally well.The relative activation frequency curve of hidden layer neurons aids in analyzing the overfitting of the FNN ROP model and determining drilling data similarity.In the well sections with similar drilling data,averaging the weight parameters enables linear characterization of the FNN ROP prediction model,leading to the establishment of a corresponding linear representation equation.Furthermore,the quantitative analysis of each feature's influence on ROP facilitates the proposal of drilling parameter optimization schemes for the current well section.The established linear characterization equation exhibits high precision,strong stability,and adaptability through the application and validation across multiple well sections.展开更多
In the era of advanced machine learning techniques,the development of accurate predictive models for complex medical conditions,such as thyroid cancer,has shown remarkable progress.Accurate predictivemodels for thyroi...In the era of advanced machine learning techniques,the development of accurate predictive models for complex medical conditions,such as thyroid cancer,has shown remarkable progress.Accurate predictivemodels for thyroid cancer enhance early detection,improve resource allocation,and reduce overtreatment.However,the widespread adoption of these models in clinical practice demands predictive performance along with interpretability and transparency.This paper proposes a novel association-rule based feature-integratedmachine learning model which shows better classification and prediction accuracy than present state-of-the-artmodels.Our study also focuses on the application of SHapley Additive exPlanations(SHAP)values as a powerful tool for explaining thyroid cancer prediction models.In the proposed method,the association-rule based feature integration framework identifies frequently occurring attribute combinations in the dataset.The original dataset is used in trainingmachine learning models,and further used in generating SHAP values fromthesemodels.In the next phase,the dataset is integrated with the dominant feature sets identified through association-rule based analysis.This new integrated dataset is used in re-training the machine learning models.The new SHAP values generated from these models help in validating the contributions of feature sets in predicting malignancy.The conventional machine learning models lack interpretability,which can hinder their integration into clinical decision-making systems.In this study,the SHAP values are introduced along with association-rule based feature integration as a comprehensive framework for understanding the contributions of feature sets inmodelling the predictions.The study discusses the importance of reliable predictive models for early diagnosis of thyroid cancer,and a validation framework of explainability.The proposed model shows an accuracy of 93.48%.Performance metrics such as precision,recall,F1-score,and the area under the receiver operating characteristic(AUROC)are also higher than the baseline models.The results of the proposed model help us identify the dominant feature sets that impact thyroid cancer classification and prediction.The features{calcification}and{shape}consistently emerged as the top-ranked features associated with thyroid malignancy,in both association-rule based interestingnessmetric values and SHAPmethods.The paper highlights the potential of the rule-based integrated models with SHAP in bridging the gap between the machine learning predictions and the interpretability of this prediction which is required for real-world medical applications.展开更多
Read a conversation between a biology student and his friend.So,Simon,you’re studying biology.Can you explain a little bit about it?Biology is about all the things on our world that are alive-plants,animals,as well a...Read a conversation between a biology student and his friend.So,Simon,you’re studying biology.Can you explain a little bit about it?Biology is about all the things on our world that are alive-plants,animals,as well as very small living things that we cannot see.Biology tries to explain why life is like it is.It sounds complicated.There are so many different kinds of plants and animals.展开更多
阅读理解One large dinosaur hid in the thick jungle(热带雨林).With small,hungry eyes he watched a larger dinosaur,about 90 feet long!It was eating grass by a lake.The one in the jungle stood 20 feet tall on his powerfu...阅读理解One large dinosaur hid in the thick jungle(热带雨林).With small,hungry eyes he watched a larger dinosaur,about 90 feet long!It was eating grass by a lake.The one in the jungle stood 20 feet tall on his powerful back legs.His two front legs were short,with sharp claws on the feet.His teeth were like long knives.展开更多
An international team of astronomers discovered delays in radio and optical fluxes from a black hole(BH)binary-about 8 and 17 days respectively-compared with the X-ray outburst from the same object.These delays,as exp...An international team of astronomers discovered delays in radio and optical fluxes from a black hole(BH)binary-about 8 and 17 days respectively-compared with the X-ray outburst from the same object.These delays,as explained by the authors,can be interpreted as evident formation of a magnetically arrested disk(MAD),a scenario predicted by a theoretical model that has long sought observational evidence for support.展开更多
Deep learning(DL) is progressively popular as a viable alternative to traditional signal processing(SP) based methods for fault diagnosis. However, the lack of explainability makes DL-based fault diagnosis methods dif...Deep learning(DL) is progressively popular as a viable alternative to traditional signal processing(SP) based methods for fault diagnosis. However, the lack of explainability makes DL-based fault diagnosis methods difficult to be trusted and understood by industrial users. In addition, the extraction of weak fault features from signals with heavy noise is imperative in industrial applications. To address these limitations, inspired by the Filterbank-Feature-Decision methodology, we propose a new Signal Processing Informed Neural Network(SPINN) framework by embedding SP knowledge into the DL model. As one of the practical implementations for SPINN, a denoising fault-aware wavelet network(DFAWNet) is developed, which consists of fused wavelet convolution(FWConv), dynamic hard thresholding(DHT),index-based soft filtering(ISF), and a classifier. Taking advantage of wavelet transform, FWConv extracts multiscale features while learning wavelet scales and selecting important wavelet bases automatically;DHT dynamically eliminates noise-related components via point-wise hard thresholding;inspired by index-based filtering, ISF optimizes and selects optimal filters for diagnostic feature extraction. It’s worth noting that SPINN may be readily applied to different deep learning networks by simply adding filterbank and feature modules in front. Experiments results demonstrate a significant diagnostic performance improvement over other explainable or denoising deep learning networks. The corresponding code is available at https://github. com/alber tszg/DFAWn et.展开更多
Artificial intelligence(AI)continues to transform data analysis in many domains.Progress in each domain is driven by a growing body of annotated data,increased computational resources,and technological innovations.In ...Artificial intelligence(AI)continues to transform data analysis in many domains.Progress in each domain is driven by a growing body of annotated data,increased computational resources,and technological innovations.In medicine,the sensitivity of the data,the complexity of the tasks,the potentially high stakes,and a requirement of accountability give rise to a particular set of challenges.In this review,we focus on three key methodological approaches that address some of the particular challenges in AI-driven medical decision making.1)Explainable AI aims to produce a human-interpretable justification for each output.Such models increase confidence if the results appear plausible and match the clinicians expectations.However,the absence of a plausible explanation does not imply an inaccurate model.Especially in highly non-linear,complex models that are tuned to maximize accuracy,such interpretable representations only reflect a small portion of the justification.2)Domain adaptation and transfer learning enable AI models to be trained and applied across multiple domains.For example,a classification task based on images acquired on different acquisition hardware.3)Federated learning enables learning large-scale models without exposing sensitive personal health information.Unlike centralized AI learning,where the centralized learning machine has access to the entire training data,the federated learning process iteratively updates models across multiple sites by exchanging only parameter updates,not personal health data.This narrative review covers the basic concepts,highlights relevant corner-stone and stateof-the-art research in the field,and discusses perspectives.展开更多
The prediction of precipitation at subseasonal to seasonal(S2S)timescales remains an enormous challenge because of the gap between weather and climate predictions.This study compares three deep learning algorithms,nam...The prediction of precipitation at subseasonal to seasonal(S2S)timescales remains an enormous challenge because of the gap between weather and climate predictions.This study compares three deep learning algorithms,namely,the long short-term memory recurrent(LSTM),gated recurrent unit(GRU),and recurrent neural network(RNN),and selects the optimal algorithm to establish an S2S precipitation prediction model.The models were evaluated in four subregions of the Sichuan Province:the Plateau,Valley,eastern Basin,and western Basin.The results showed that the RNN model had better performance than the LSTM and GRU models.This could be because the RNN model had an advantage over the LSTM model in the transformation of climate indices with positive and negative variations.In the validation of test datasets,the RNN model successfully predicted the precipitation trend in most years during the wet season(May-October).The RNN model had a lower prediction bias(within±10%),higher sign accuracy of the precipitation trend(~88.95%),and greater accuracy of the maximum precipitation month(>0.85).For the prediction of different lead times,the RNN model was able to provide a stable trend prediction for summer precipitation,and the time correlation coefficient score was higher than that of the National Climate Center of China.Furthermore,this study proposed a method to measure the sensitivity of the RNN model to different input features,which may provide unprecedented insights into the nonlinear relationship and complicated feedback process among climate systems.The results of the sensitivity distribution are as follows.First,the Niño 4 and Niño 3.4 indices were equally important for the prediction of wet season precipitation.Second,the sensitivity of the snow cover on the Tibetan Plateau was higher than that in the Northern Hemisphere.Third,an opposite sensitivity appeared in two different patterns of the Indian Ocean and sea ice concentrations in the Arctic and the Barents Sea.展开更多
Intrusion detection involves identifying unauthorized network activity and recognizing whether the data constitute an abnormal network transmission.Recent research has focused on using semi-supervised learning mechani...Intrusion detection involves identifying unauthorized network activity and recognizing whether the data constitute an abnormal network transmission.Recent research has focused on using semi-supervised learning mechanisms to identify abnormal network traffic to deal with labeled and unlabeled data in the industry.However,real-time training and classifying network traffic pose challenges,as they can lead to the degradation of the overall dataset and difficulties preventing attacks.Additionally,existing semi-supervised learning research might need to analyze the experimental results comprehensively.This paper proposes XA-GANomaly,a novel technique for explainable adaptive semi-supervised learning using GANomaly,an image anomalous detection model that dynamically trains small subsets to these issues.First,this research introduces a deep neural network(DNN)-based GANomaly for semi-supervised learning.Second,this paper presents the proposed adaptive algorithm for the DNN-based GANomaly,which is validated with four subsets of the adaptive dataset.Finally,this study demonstrates a monitoring system that incorporates three explainable techniques—Shapley additive explanations,reconstruction error visualization,and t-distributed stochastic neighbor embedding—to respond effectively to attacks on traffic data at each feature engineering stage,semi-supervised learning,and adaptive learning.Compared to other single-class classification techniques,the proposed DNN-based GANomaly achieves higher scores for Network Security Laboratory-Knowledge Discovery in Databases and UNSW-NB15 datasets at 13%and 8%of F1 scores and 4.17%and 11.51%for accuracy,respectively.Furthermore,experiments of the proposed adaptive learning reveal mostly improved results over the initial values.An analysis and monitoring system based on the combination of the three explainable methodologies is also described.Thus,the proposed method has the potential advantages to be applied in practical industry,and future research will explore handling unbalanced real-time datasets in various scenarios.展开更多
The exponential use of artificial intelligence(AI)to solve and automated complex tasks has catapulted its popularity generating some challenges that need to be addressed.While AI is a powerfulmeans to discover interes...The exponential use of artificial intelligence(AI)to solve and automated complex tasks has catapulted its popularity generating some challenges that need to be addressed.While AI is a powerfulmeans to discover interesting patterns and obtain predictive models,the use of these algorithms comes with a great responsibility,as an incomplete or unbalanced set of training data or an unproper interpretation of the models’outcomes could result in misleading conclusions that ultimately could become very dangerous.For these reasons,it is important to rely on expert knowledge when applying these methods.However,not every user can count on this specific expertise;non-AIexpert users could also benefit from applying these powerful algorithms to their domain problems,but they need basic guidelines to obtain themost out of AI models.The goal of this work is to present a systematic review of the literature to analyze studies whose outcomes are explainable rules and heuristics to select suitable AI algorithms given a set of input features.The systematic review follows the methodology proposed by Kitchenham and other authors in the field of software engineering.As a result,9 papers that tackle AI algorithmrecommendation through tangible and traceable rules and heuristics were collected.The reduced number of retrieved papers suggests a lack of reporting explicit rules and heuristics when testing the suitability and performance of AI algorithms.展开更多
Explainable AI extracts a variety of patterns of data in the learning process and draws hidden information through the discovery of semantic relationships.It is possible to offer the explainable basis of decision-maki...Explainable AI extracts a variety of patterns of data in the learning process and draws hidden information through the discovery of semantic relationships.It is possible to offer the explainable basis of decision-making for inference results.Through the causality of risk factors that have an ambiguous association in big medical data,it is possible to increase transparency and reliability of explainable decision-making that helps to diagnose disease status.In addition,the technique makes it possible to accurately predict disease risk for anomaly detection.Vision transformer for anomaly detection from image data makes classification through MLP.Unfortunately,in MLP,a vector value depends on patch sequence information,and thus a weight changes.This should solve the problem that there is a difference in the result value according to the change in the weight.In addition,since the deep learning model is a black box model,there is a problem that it is difficult to interpret the results determined by the model.Therefore,there is a need for an explainablemethod for the part where the disease exists.To solve the problem,this study proposes explainable anomaly detection using vision transformerbasedDeep Support Vector Data Description(SVDD).The proposed method applies the SVDD to solve the problem of MLP in which a result value is different depending on a weight change that is influenced by patch sequence information used in the vision transformer.In order to draw the explainability of model results,it visualizes normal parts through Grad-CAM.In health data,both medical staff and patients are able to identify abnormal parts easily.In addition,it is possible to improve the reliability of models and medical staff.For performance evaluation normal/abnormal classification accuracy and f-measure are evaluated,according to whether to apply SVDD.Evaluation Results The results of classification by applying the proposed SVDD are evaluated excellently.Therefore,through the proposed method,it is possible to improve the reliability of decision-making by identifying the location of the disease and deriving consistent results.展开更多
The dark energy concept in the standard cosmological model can explain the expansion of the universe.However,the mysteries surrounding dark energy remain,such as its source,its unusual negative pressure,its longrange ...The dark energy concept in the standard cosmological model can explain the expansion of the universe.However,the mysteries surrounding dark energy remain,such as its source,its unusual negative pressure,its longrange force,and its unchanged density as the universe expands.We propose a graviton momentum hypothesis,develop a semiclassical model of gravitons,and explain the pervasive dark matter and accelerating universe.The graviton momentum hypothesis is incorporated into the standard model and explains well the mysteries related to dark energy.展开更多
Urgent care clinics and emergency departments around the world periodically suffer from extended wait times beyond patient expectations due to surges in patient flows.The delays arising from inadequate staffing levels...Urgent care clinics and emergency departments around the world periodically suffer from extended wait times beyond patient expectations due to surges in patient flows.The delays arising from inadequate staffing levels during these periods have been linked with adverse clinical outcomes.Previous research into forecasting patient flows has mostly used statistical techniques.These studies have also predominately focussed on short‐term forecasts,which have limited practicality for the resourcing of medical personnel.This study joins an emerging body of work which seeks to explore the potential of machine learning algorithms to generate accurate forecasts of patient presentations.Our research uses datasets covering 10 years from two large urgent care clinics to develop long‐term patient flow forecasts up to one quarter ahead using a range of state‐of‐the‐art algo-rithms.A distinctive feature of this study is the use of eXplainable Artificial Intelligence(XAI)tools like Shapely and LIME that enable an in‐depth analysis of the behaviour of the models,which would otherwise be uninterpretable.These analysis tools enabled us to explore the ability of the models to adapt to the volatility in patient demand during the COVID‐19 pandemic lockdowns and to identify the most impactful variables,resulting in valuable insights into their performance.The results showed that a novel combination of advanced univariate models like Prophet as well as gradient boosting,into an ensemble,delivered the most accurate and consistent solutions on average.This approach generated improvements in the range of 16%-30%over the existing in‐house methods for esti-mating the daily patient flows 90 days ahead.展开更多
Artificial intelligence(AI)[1,2]allows computers to think and behave like humans,so it is now becoming more and more influential in almost every field[3].Hence,users in businesses,industries,hospitals[4],etc.,need to ...Artificial intelligence(AI)[1,2]allows computers to think and behave like humans,so it is now becoming more and more influential in almost every field[3].Hence,users in businesses,industries,hospitals[4],etc.,need to understand how these AI models work[5]and the potential impact of using them.展开更多
One of the most widely used smartphone operating systems,Android,is vulnerable to cutting-edge malware that employs sophisticated logic.Such malware attacks could lead to the execution of unauthorized acts on the vict...One of the most widely used smartphone operating systems,Android,is vulnerable to cutting-edge malware that employs sophisticated logic.Such malware attacks could lead to the execution of unauthorized acts on the victims’devices,stealing personal information and causing hardware damage.In previous studies,machine learning(ML)has shown its efficacy in detecting malware events and classifying their types.However,attackers are continuously developing more sophisticated methods to bypass detection.Therefore,up-to-date datasets must be utilized to implement proactive models for detecting malware events in Android mobile devices.Therefore,this study employed ML algorithms to classify Android applications into malware or goodware using permission and application programming interface(API)-based features from a recent dataset.To overcome the dataset imbalance issue,RandomOverSampler,synthetic minority oversampling with tomek links(SMOTETomek),and RandomUnderSampler were applied to the Dataset in different experiments.The results indicated that the extra tree(ET)classifier achieved the highest accuracy of 99.53%within an elapsed time of 0.0198 s in the experiment that utilized the RandomOverSampler technique.Furthermore,the explainable Artificial Intelligence(EAI)technique has been applied to add transparency to the high-performance ET classifier.The global explanation using the Shapely values indicated that the top three features contributing to the goodware class are:Ljava/net/URL;->openConnection,Landroid/location/LocationManager;->getLastKgoodwarewnLocation,and Vibrate.On the other hand,the top three features contributing to themalware class are Receive_Boot_Completed,Get_Tasks,and Kill_Background_Processes.It is believed that the proposedmodel can contribute to proactively detectingmalware events in Android devices to reduce the number of victims and increase users’trust.展开更多
Our previous work has introduced the newly generated program using the code transformation model GPT-2,verifying the generated programming codes through simhash(SH)and longest common subsequence(LCS)algo-rithms.Howeve...Our previous work has introduced the newly generated program using the code transformation model GPT-2,verifying the generated programming codes through simhash(SH)and longest common subsequence(LCS)algo-rithms.However,the entire code transformation process has encountered a time-consuming problem.Therefore,the objective of this study is to speed up the code transformation process signicantly.This paper has proposed deep learning approaches for modifying SH using a variational simhash(VSH)algorithm and replacing LCS with a piecewise longest common subsequence(PLCS)algorithm to faster the verication process in the test phase.Besides the code transformation model GPT-2,this study has also introduced MicrosoMASS and Facebook BART for a comparative analysis of their performance.Meanwhile,the explainable AI technique using local interpretable model-agnostic explanations(LIME)can also interpret the decision-making ofAImodels.The experimental results show that VSH can reduce the number of qualied programs by 22.11%,and PLCS can reduce the execution time of selected pocket programs by 32.39%.As a result,the proposed approaches can signicantly speed up the entire code transformation process by 1.38 times on average compared with our previous work.展开更多
文摘E. Stone in the article “18 Mysteries and Unanswered Questions About Our Solar System. Little Astronomy” wrote: One of the great things about astronomy is that there is still so much out there for us to discover. There are so many unanswered questions and mysteries about the universe. There is always a puzzle to solve and that is part of beauty. Even in our own neighborhood, the Solar System, there are many questions we still have not been able to answer [1]. In the present paper, we explain the majority of these Mysteries and some other unexplained phenomena in the Solar System (SS) in frames of the developed Hypersphere World-Universe Model (WUM) [2].
文摘Despite low-income countries producing only a quarter of per capita plastic waste compared to high-income countries,the related environmental,health,and economic costs of plastic could be up to 10 times higher than in wealthier countries,declared Who Pays for Plastic Pollution?Enabling Global Equity in the Plastic Value Chain,a report released by World Wild Fund(WWF).The report highlighted significant inequalities within the global plastic value chain and explained how cost disparities exert a substantial impact on low and middle-income countries.
基金the Deanship for Research Innovation,Ministry of Education in Saudi Arabia,for funding this research work through project number IFKSUDR-H122.
文摘In the current landscape of the COVID-19 pandemic,the utilization of deep learning in medical imaging,especially in chest computed tomography(CT)scan analysis for virus detection,has become increasingly significant.Despite its potential,deep learning’s“black box”nature has been a major impediment to its broader acceptance in clinical environments,where transparency in decision-making is imperative.To bridge this gap,our research integrates Explainable AI(XAI)techniques,specifically the Local Interpretable Model-Agnostic Explanations(LIME)method,with advanced deep learning models.This integration forms a sophisticated and transparent framework for COVID-19 identification,enhancing the capability of standard Convolutional Neural Network(CNN)models through transfer learning and data augmentation.Our approach leverages the refined DenseNet201 architecture for superior feature extraction and employs data augmentation strategies to foster robust model generalization.The pivotal element of our methodology is the use of LIME,which demystifies the AI decision-making process,providing clinicians with clear,interpretable insights into the AI’s reasoning.This unique combination of an optimized Deep Neural Network(DNN)with LIME not only elevates the precision in detecting COVID-19 cases but also equips healthcare professionals with a deeper understanding of the diagnostic process.Our method,validated on the SARS-COV-2 CT-Scan dataset,demonstrates exceptional diagnostic accuracy,with performance metrics that reinforce its potential for seamless integration into modern healthcare systems.This innovative approach marks a significant advancement in creating explainable and trustworthy AI tools for medical decisionmaking in the ongoing battle against COVID-19.
基金The authors greatly thanked the financial support from the National Key Research and Development Program of China(funded by National Natural Science Foundation of China,No.2019YFA0708300)the Strategic Cooperation Technology Projects of CNPC and CUPB(funded by China National Petroleum Corporation,No.ZLZX2020-03)+1 种基金the National Science Fund for Distinguished Young Scholars(funded by National Natural Science Foundation of China,No.52125401)Science Foundation of China University of Petroleum,Beijing(funded by China University of petroleum,Beijing,No.2462022SZBH002).
文摘Accurate prediction of the rate of penetration(ROP)is significant for drilling optimization.While the intelligent ROP prediction model based on fully connected neural networks(FNN)outperforms traditional ROP equations and machine learning algorithms,its lack of interpretability undermines its credibility.This study proposes a novel interpretation and characterization method for the FNN ROP prediction model using the Rectified Linear Unit(ReLU)activation function.By leveraging the derivative of the ReLU function,the FNN function calculation process is transformed into vector operations.The FNN model is linearly characterized through further simplification,enabling its interpretation and analysis.The proposed method is applied in ROP prediction scenarios using drilling data from three vertical wells in the Tarim Oilfield.The results demonstrate that the FNN ROP prediction model with ReLU as the activation function performs exceptionally well.The relative activation frequency curve of hidden layer neurons aids in analyzing the overfitting of the FNN ROP model and determining drilling data similarity.In the well sections with similar drilling data,averaging the weight parameters enables linear characterization of the FNN ROP prediction model,leading to the establishment of a corresponding linear representation equation.Furthermore,the quantitative analysis of each feature's influence on ROP facilitates the proposal of drilling parameter optimization schemes for the current well section.The established linear characterization equation exhibits high precision,strong stability,and adaptability through the application and validation across multiple well sections.
文摘In the era of advanced machine learning techniques,the development of accurate predictive models for complex medical conditions,such as thyroid cancer,has shown remarkable progress.Accurate predictivemodels for thyroid cancer enhance early detection,improve resource allocation,and reduce overtreatment.However,the widespread adoption of these models in clinical practice demands predictive performance along with interpretability and transparency.This paper proposes a novel association-rule based feature-integratedmachine learning model which shows better classification and prediction accuracy than present state-of-the-artmodels.Our study also focuses on the application of SHapley Additive exPlanations(SHAP)values as a powerful tool for explaining thyroid cancer prediction models.In the proposed method,the association-rule based feature integration framework identifies frequently occurring attribute combinations in the dataset.The original dataset is used in trainingmachine learning models,and further used in generating SHAP values fromthesemodels.In the next phase,the dataset is integrated with the dominant feature sets identified through association-rule based analysis.This new integrated dataset is used in re-training the machine learning models.The new SHAP values generated from these models help in validating the contributions of feature sets in predicting malignancy.The conventional machine learning models lack interpretability,which can hinder their integration into clinical decision-making systems.In this study,the SHAP values are introduced along with association-rule based feature integration as a comprehensive framework for understanding the contributions of feature sets inmodelling the predictions.The study discusses the importance of reliable predictive models for early diagnosis of thyroid cancer,and a validation framework of explainability.The proposed model shows an accuracy of 93.48%.Performance metrics such as precision,recall,F1-score,and the area under the receiver operating characteristic(AUROC)are also higher than the baseline models.The results of the proposed model help us identify the dominant feature sets that impact thyroid cancer classification and prediction.The features{calcification}and{shape}consistently emerged as the top-ranked features associated with thyroid malignancy,in both association-rule based interestingnessmetric values and SHAPmethods.The paper highlights the potential of the rule-based integrated models with SHAP in bridging the gap between the machine learning predictions and the interpretability of this prediction which is required for real-world medical applications.
文摘Read a conversation between a biology student and his friend.So,Simon,you’re studying biology.Can you explain a little bit about it?Biology is about all the things on our world that are alive-plants,animals,as well as very small living things that we cannot see.Biology tries to explain why life is like it is.It sounds complicated.There are so many different kinds of plants and animals.
文摘阅读理解One large dinosaur hid in the thick jungle(热带雨林).With small,hungry eyes he watched a larger dinosaur,about 90 feet long!It was eating grass by a lake.The one in the jungle stood 20 feet tall on his powerful back legs.His two front legs were short,with sharp claws on the feet.His teeth were like long knives.
文摘An international team of astronomers discovered delays in radio and optical fluxes from a black hole(BH)binary-about 8 and 17 days respectively-compared with the X-ray outburst from the same object.These delays,as explained by the authors,can be interpreted as evident formation of a magnetically arrested disk(MAD),a scenario predicted by a theoretical model that has long sought observational evidence for support.
基金National Natural Science Foundation of China (Grant Nos. 51835009, 52105116)China Postdoctoral Science Foundation (Grant Nos. 2021M692557, 2021TQ0263)。
文摘Deep learning(DL) is progressively popular as a viable alternative to traditional signal processing(SP) based methods for fault diagnosis. However, the lack of explainability makes DL-based fault diagnosis methods difficult to be trusted and understood by industrial users. In addition, the extraction of weak fault features from signals with heavy noise is imperative in industrial applications. To address these limitations, inspired by the Filterbank-Feature-Decision methodology, we propose a new Signal Processing Informed Neural Network(SPINN) framework by embedding SP knowledge into the DL model. As one of the practical implementations for SPINN, a denoising fault-aware wavelet network(DFAWNet) is developed, which consists of fused wavelet convolution(FWConv), dynamic hard thresholding(DHT),index-based soft filtering(ISF), and a classifier. Taking advantage of wavelet transform, FWConv extracts multiscale features while learning wavelet scales and selecting important wavelet bases automatically;DHT dynamically eliminates noise-related components via point-wise hard thresholding;inspired by index-based filtering, ISF optimizes and selects optimal filters for diagnostic feature extraction. It’s worth noting that SPINN may be readily applied to different deep learning networks by simply adding filterbank and feature modules in front. Experiments results demonstrate a significant diagnostic performance improvement over other explainable or denoising deep learning networks. The corresponding code is available at https://github. com/alber tszg/DFAWn et.
基金This work was supported in part by the National Natural Science Foundation of China(82260360)the Foreign Young Talent Program(QN2021033002L).
文摘Artificial intelligence(AI)continues to transform data analysis in many domains.Progress in each domain is driven by a growing body of annotated data,increased computational resources,and technological innovations.In medicine,the sensitivity of the data,the complexity of the tasks,the potentially high stakes,and a requirement of accountability give rise to a particular set of challenges.In this review,we focus on three key methodological approaches that address some of the particular challenges in AI-driven medical decision making.1)Explainable AI aims to produce a human-interpretable justification for each output.Such models increase confidence if the results appear plausible and match the clinicians expectations.However,the absence of a plausible explanation does not imply an inaccurate model.Especially in highly non-linear,complex models that are tuned to maximize accuracy,such interpretable representations only reflect a small portion of the justification.2)Domain adaptation and transfer learning enable AI models to be trained and applied across multiple domains.For example,a classification task based on images acquired on different acquisition hardware.3)Federated learning enables learning large-scale models without exposing sensitive personal health information.Unlike centralized AI learning,where the centralized learning machine has access to the entire training data,the federated learning process iteratively updates models across multiple sites by exchanging only parameter updates,not personal health data.This narrative review covers the basic concepts,highlights relevant corner-stone and stateof-the-art research in the field,and discusses perspectives.
基金the National Natural Science Foundation of China(Nos.U20A2097,42175042)the Natural Science Foundation of Sichuan(Nos.2022NSFSC1056,2023NSFSC0246)+3 种基金the China Scholarship Council(No.201908510031)the Plateau and Basin Rainstorm,Drought and Flood Key Laboratory of Sichuan Province(Nos.SCQXKJZD202102-6,SCQXKJYJXMS202102)the Innovation Team Fund of Southwest Regional Meteorological Center,China Meteorological Administration(No.XNQYCXTD202201)the Sichuan Science and Technology Program(No.2022YFS0544).
文摘The prediction of precipitation at subseasonal to seasonal(S2S)timescales remains an enormous challenge because of the gap between weather and climate predictions.This study compares three deep learning algorithms,namely,the long short-term memory recurrent(LSTM),gated recurrent unit(GRU),and recurrent neural network(RNN),and selects the optimal algorithm to establish an S2S precipitation prediction model.The models were evaluated in four subregions of the Sichuan Province:the Plateau,Valley,eastern Basin,and western Basin.The results showed that the RNN model had better performance than the LSTM and GRU models.This could be because the RNN model had an advantage over the LSTM model in the transformation of climate indices with positive and negative variations.In the validation of test datasets,the RNN model successfully predicted the precipitation trend in most years during the wet season(May-October).The RNN model had a lower prediction bias(within±10%),higher sign accuracy of the precipitation trend(~88.95%),and greater accuracy of the maximum precipitation month(>0.85).For the prediction of different lead times,the RNN model was able to provide a stable trend prediction for summer precipitation,and the time correlation coefficient score was higher than that of the National Climate Center of China.Furthermore,this study proposed a method to measure the sensitivity of the RNN model to different input features,which may provide unprecedented insights into the nonlinear relationship and complicated feedback process among climate systems.The results of the sensitivity distribution are as follows.First,the Niño 4 and Niño 3.4 indices were equally important for the prediction of wet season precipitation.Second,the sensitivity of the snow cover on the Tibetan Plateau was higher than that in the Northern Hemisphere.Third,an opposite sensitivity appeared in two different patterns of the Indian Ocean and sea ice concentrations in the Arctic and the Barents Sea.
基金supported by Korea Institute for Advancement of Technology(KIAT)grant funded by theKoreaGovernment(MOTIE)(P0008703,The CompetencyDevelopment Program for Industry Specialist).
文摘Intrusion detection involves identifying unauthorized network activity and recognizing whether the data constitute an abnormal network transmission.Recent research has focused on using semi-supervised learning mechanisms to identify abnormal network traffic to deal with labeled and unlabeled data in the industry.However,real-time training and classifying network traffic pose challenges,as they can lead to the degradation of the overall dataset and difficulties preventing attacks.Additionally,existing semi-supervised learning research might need to analyze the experimental results comprehensively.This paper proposes XA-GANomaly,a novel technique for explainable adaptive semi-supervised learning using GANomaly,an image anomalous detection model that dynamically trains small subsets to these issues.First,this research introduces a deep neural network(DNN)-based GANomaly for semi-supervised learning.Second,this paper presents the proposed adaptive algorithm for the DNN-based GANomaly,which is validated with four subsets of the adaptive dataset.Finally,this study demonstrates a monitoring system that incorporates three explainable techniques—Shapley additive explanations,reconstruction error visualization,and t-distributed stochastic neighbor embedding—to respond effectively to attacks on traffic data at each feature engineering stage,semi-supervised learning,and adaptive learning.Compared to other single-class classification techniques,the proposed DNN-based GANomaly achieves higher scores for Network Security Laboratory-Knowledge Discovery in Databases and UNSW-NB15 datasets at 13%and 8%of F1 scores and 4.17%and 11.51%for accuracy,respectively.Furthermore,experiments of the proposed adaptive learning reveal mostly improved results over the initial values.An analysis and monitoring system based on the combination of the three explainable methodologies is also described.Thus,the proposed method has the potential advantages to be applied in practical industry,and future research will explore handling unbalanced real-time datasets in various scenarios.
基金funded by the Spanish Government Ministry of Economy and Competitiveness through the DEFINES Project Grant No. (TIN2016-80172-R)the Ministry of Science and Innovation through the AVisSA Project Grant No. (PID2020-118345RBI00)supported by the Spanish Ministry of Education and Vocational Training under an FPU Fellowship (FPU17/03276).
文摘The exponential use of artificial intelligence(AI)to solve and automated complex tasks has catapulted its popularity generating some challenges that need to be addressed.While AI is a powerfulmeans to discover interesting patterns and obtain predictive models,the use of these algorithms comes with a great responsibility,as an incomplete or unbalanced set of training data or an unproper interpretation of the models’outcomes could result in misleading conclusions that ultimately could become very dangerous.For these reasons,it is important to rely on expert knowledge when applying these methods.However,not every user can count on this specific expertise;non-AIexpert users could also benefit from applying these powerful algorithms to their domain problems,but they need basic guidelines to obtain themost out of AI models.The goal of this work is to present a systematic review of the literature to analyze studies whose outcomes are explainable rules and heuristics to select suitable AI algorithms given a set of input features.The systematic review follows the methodology proposed by Kitchenham and other authors in the field of software engineering.As a result,9 papers that tackle AI algorithmrecommendation through tangible and traceable rules and heuristics were collected.The reduced number of retrieved papers suggests a lack of reporting explicit rules and heuristics when testing the suitability and performance of AI algorithms.
基金This research was supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(2020R1A6A1A03040583).
文摘Explainable AI extracts a variety of patterns of data in the learning process and draws hidden information through the discovery of semantic relationships.It is possible to offer the explainable basis of decision-making for inference results.Through the causality of risk factors that have an ambiguous association in big medical data,it is possible to increase transparency and reliability of explainable decision-making that helps to diagnose disease status.In addition,the technique makes it possible to accurately predict disease risk for anomaly detection.Vision transformer for anomaly detection from image data makes classification through MLP.Unfortunately,in MLP,a vector value depends on patch sequence information,and thus a weight changes.This should solve the problem that there is a difference in the result value according to the change in the weight.In addition,since the deep learning model is a black box model,there is a problem that it is difficult to interpret the results determined by the model.Therefore,there is a need for an explainablemethod for the part where the disease exists.To solve the problem,this study proposes explainable anomaly detection using vision transformerbasedDeep Support Vector Data Description(SVDD).The proposed method applies the SVDD to solve the problem of MLP in which a result value is different depending on a weight change that is influenced by patch sequence information used in the vision transformer.In order to draw the explainability of model results,it visualizes normal parts through Grad-CAM.In health data,both medical staff and patients are able to identify abnormal parts easily.In addition,it is possible to improve the reliability of models and medical staff.For performance evaluation normal/abnormal classification accuracy and f-measure are evaluated,according to whether to apply SVDD.Evaluation Results The results of classification by applying the proposed SVDD are evaluated excellently.Therefore,through the proposed method,it is possible to improve the reliability of decision-making by identifying the location of the disease and deriving consistent results.
文摘The dark energy concept in the standard cosmological model can explain the expansion of the universe.However,the mysteries surrounding dark energy remain,such as its source,its unusual negative pressure,its longrange force,and its unchanged density as the universe expands.We propose a graviton momentum hypothesis,develop a semiclassical model of gravitons,and explain the pervasive dark matter and accelerating universe.The graviton momentum hypothesis is incorporated into the standard model and explains well the mysteries related to dark energy.
文摘Urgent care clinics and emergency departments around the world periodically suffer from extended wait times beyond patient expectations due to surges in patient flows.The delays arising from inadequate staffing levels during these periods have been linked with adverse clinical outcomes.Previous research into forecasting patient flows has mostly used statistical techniques.These studies have also predominately focussed on short‐term forecasts,which have limited practicality for the resourcing of medical personnel.This study joins an emerging body of work which seeks to explore the potential of machine learning algorithms to generate accurate forecasts of patient presentations.Our research uses datasets covering 10 years from two large urgent care clinics to develop long‐term patient flow forecasts up to one quarter ahead using a range of state‐of‐the‐art algo-rithms.A distinctive feature of this study is the use of eXplainable Artificial Intelligence(XAI)tools like Shapely and LIME that enable an in‐depth analysis of the behaviour of the models,which would otherwise be uninterpretable.These analysis tools enabled us to explore the ability of the models to adapt to the volatility in patient demand during the COVID‐19 pandemic lockdowns and to identify the most impactful variables,resulting in valuable insights into their performance.The results showed that a novel combination of advanced univariate models like Prophet as well as gradient boosting,into an ensemble,delivered the most accurate and consistent solutions on average.This approach generated improvements in the range of 16%-30%over the existing in‐house methods for esti-mating the daily patient flows 90 days ahead.
基金Sino-UK Education Fund(OP202006)Royal Society(RP202G0230)+8 种基金MRC(MC_PC_17171)BHF(AA/18/3/34220)Hope Foundation for Cancer Research(RM60G0680)GCRF(P202PF11)BBSRC(RM32G0178B8)Sino-UK Industrial Fund(RP202G0289)Data Science Enhancement Fund(P202RE237)LIAS(P202ED10&P202RE969)Fight for Sight(24NN201).
文摘Artificial intelligence(AI)[1,2]allows computers to think and behave like humans,so it is now becoming more and more influential in almost every field[3].Hence,users in businesses,industries,hospitals[4],etc.,need to understand how these AI models work[5]and the potential impact of using them.
基金funded by the SAUDI ARAMCO Cybersecurity Chair at Imam Abdulrahman Bin Faisal University,Saudi Arabia.
文摘One of the most widely used smartphone operating systems,Android,is vulnerable to cutting-edge malware that employs sophisticated logic.Such malware attacks could lead to the execution of unauthorized acts on the victims’devices,stealing personal information and causing hardware damage.In previous studies,machine learning(ML)has shown its efficacy in detecting malware events and classifying their types.However,attackers are continuously developing more sophisticated methods to bypass detection.Therefore,up-to-date datasets must be utilized to implement proactive models for detecting malware events in Android mobile devices.Therefore,this study employed ML algorithms to classify Android applications into malware or goodware using permission and application programming interface(API)-based features from a recent dataset.To overcome the dataset imbalance issue,RandomOverSampler,synthetic minority oversampling with tomek links(SMOTETomek),and RandomUnderSampler were applied to the Dataset in different experiments.The results indicated that the extra tree(ET)classifier achieved the highest accuracy of 99.53%within an elapsed time of 0.0198 s in the experiment that utilized the RandomOverSampler technique.Furthermore,the explainable Artificial Intelligence(EAI)technique has been applied to add transparency to the high-performance ET classifier.The global explanation using the Shapely values indicated that the top three features contributing to the goodware class are:Ljava/net/URL;->openConnection,Landroid/location/LocationManager;->getLastKgoodwarewnLocation,and Vibrate.On the other hand,the top three features contributing to themalware class are Receive_Boot_Completed,Get_Tasks,and Kill_Background_Processes.It is believed that the proposedmodel can contribute to proactively detectingmalware events in Android devices to reduce the number of victims and increase users’trust.
基金supported by the Ministry of Science and Technology,Taiwan,under Grant Nos.MOST 111-2221-E-390-012 and MOST 111-2622-E-390-001.
文摘Our previous work has introduced the newly generated program using the code transformation model GPT-2,verifying the generated programming codes through simhash(SH)and longest common subsequence(LCS)algo-rithms.However,the entire code transformation process has encountered a time-consuming problem.Therefore,the objective of this study is to speed up the code transformation process signicantly.This paper has proposed deep learning approaches for modifying SH using a variational simhash(VSH)algorithm and replacing LCS with a piecewise longest common subsequence(PLCS)algorithm to faster the verication process in the test phase.Besides the code transformation model GPT-2,this study has also introduced MicrosoMASS and Facebook BART for a comparative analysis of their performance.Meanwhile,the explainable AI technique using local interpretable model-agnostic explanations(LIME)can also interpret the decision-making ofAImodels.The experimental results show that VSH can reduce the number of qualied programs by 22.11%,and PLCS can reduce the execution time of selected pocket programs by 32.39%.As a result,the proposed approaches can signicantly speed up the entire code transformation process by 1.38 times on average compared with our previous work.