This Highlight discusses the landmark study by Zhao et al.(Science,2025)that presents a transformative strategy against citrus Huanglongbing(HLB).The work identifies the E3 ubiquitin ligase PUB21 as a central suscepti...This Highlight discusses the landmark study by Zhao et al.(Science,2025)that presents a transformative strategy against citrus Huanglongbing(HLB).The work identifies the E3 ubiquitin ligase PUB21 as a central susceptibility(S)factor,degrading the defense regulator MYC2.Crucially,the study harnesses natural resistance(dominantnegative PUB21DN mutant)and pioneers AI-driven design to develop a 14-amino acid peptide(APP3-14).This peptide dually combats HLB by stabilizing MYC2(inhibiting PUB21)and directly targeting the unculturable pathogen Candidatus Liberibacter asiaticus(CLas),achieving>90%bacterial reduction in field trials.The research also exposes how a CLas effector(SDE5,Sec-delivered effector 5)hijacks the PUB21-MYC2 axis.This work establishes"defense protein stabilization"as a powerful new paradigm for breeding resistant crops and controlling recalcitrant pathogens,exemplified by the innovative integration of AI in peptide therapeutics for plants.展开更多
Magnesium-ion batteries hold promise as future energy storage solutions,yet current Mg cathodes are challenged by low voltage and specific capacity.Herein,we present an AI-driven workflow for discovering high-performa...Magnesium-ion batteries hold promise as future energy storage solutions,yet current Mg cathodes are challenged by low voltage and specific capacity.Herein,we present an AI-driven workflow for discovering high-performance Mg cathode materials.Utilizing the common characteristics of various ionic intercalation-type electrodes,we design and train a Crystal Graph Convolutional Neural Network model that can accurately predict electrode voltages for various ions with mean absolute errors(MAE)between0.25 and 0.33 V.By deploying the trained model to stable Mg compounds from Materials Project and GNoME AI dataset,we identify 160 high voltage structures out of 15,308 candidates with voltages above3.0 V and volumetric capacity over 800 mA h/cm^(3).We further train a precise NequIP model to facilitate accurate and rapid simulations of Mg ionic conductivity.From the 160 high voltage structures,the machine learning molecular dynamics simulations have selected 23 cathode materials with both high energy density and high ionic conductivity.This Al-driven workflow dramatically boosts the efficiency and precision of material discovery for multivalent ion batteries,paving the way for advanced Mg battery development.展开更多
Recent advances in artificial intelligence(AI)have led to the development of sophisticated algorithms that significantly improve image analysis capabilities.This combination of AI and microscopic imaging is transformi...Recent advances in artificial intelligence(AI)have led to the development of sophisticated algorithms that significantly improve image analysis capabilities.This combination of AI and microscopic imaging is transforming the way we interpret and analyze imaging data,simplifying complex tasks and enabling innovative experimental methods previously thought impossible.In smart manufacturing,these improvements are especially impactful,increasing precision and efficiency in production processes.This review examines the convergence of AI with particle image analysis,an area we refer to as“particle vision analysis(PVA).”We offer a detailed overview of how this technology integrates into and impacts various fields within the physical sciences and materials sectors,where it plays a crucial role in both innovation and operational improvements.We explore four key areas of advancement-namely,particle classification,detection,segmentation,and object tracking-along with a look into the emerging field of augmented microscopy.This paper also underscores the vital role of the existing datasets and implementations that support these applications,which provide essential insights and resources that drive continuous research and development in this fast-evolving field.Our thorough analysis aims to outline the transformative potential of AI-driven PVA in improving precision in future manufacturing at the microscopic scale and thereby preparing the ground for significant technological progress and broad industrial applications in nanomanufacturing,biomanufacturing,and pharmaceutical manufacturing.This exploration not only highlights the advantages of integrating AI into conventional manufacturing processes but also anticipates the rise of next-generation smart manufacturing,which is set to revolutionize industry standards and operational practices.展开更多
With the growing adoption of Artifical Intelligence(AI),AI-driven autonomous techniques and automation systems have seen widespread applications,become pivotal in enhancing operational efficiency and task automation a...With the growing adoption of Artifical Intelligence(AI),AI-driven autonomous techniques and automation systems have seen widespread applications,become pivotal in enhancing operational efficiency and task automation across various aspects of human living.Over the past decade,AI-driven automation has advanced from simple rule-based systems to sophisticated multi-agent hybrid architectures.These technologies not only increase productivity but also enable more scalable and adaptable solutions,proving particularly beneficial in industries such as healthcare,finance,and customer service.However,the absence of a unified review for categorization,benchmarking,and ethical risk assessment hinders the AI-driven automation progress.To bridge this gap,in this survey,we present a comprehensive taxonomy of AI-driven automation methods and analyze recent advancements.We present a comparative analysis of performance metrics between production environments and industrial applications,along with an examination of cutting-edge developments.Specifically,we present a comparative analysis of the performance across various aspects in different industries,offering valuable insights for researchers to select the most suitable approaches for specific applications.Additionally,we also review multiple existing mainstream AI-driven automation applications in detail,highlighting their strengths and limitations.Finally,we outline open research challenges and suggest future directions to address the challenges of AI adoption while maximizing its potential in real-world AI-driven automation applications.展开更多
Theburgeoning e-commerce industry hasmade online customer reviews a crucial source of feedback for businesses.Sentiment analysis,a technique used to extract subjective information from text,has become essential for un...Theburgeoning e-commerce industry hasmade online customer reviews a crucial source of feedback for businesses.Sentiment analysis,a technique used to extract subjective information from text,has become essential for understanding consumer sentiment and preferences.However,traditional sentiment analysis methods often struggle with the nuances and context of natural language.To address these issues,this study proposes a comparison of deep learningmodels that figure out the optimalmethod to accurately analyze consumer reviews onwomen’s clothing.CNNs excel at capturing local features and semantic information,while LSTMs are adept at handling long-range dependencies and contextual understanding.By integrating these two deep learning techniques,our model aims to achieve better performance in sentiment classification.The models were trained and evaluated on a dataset of women’s clothing reviews sourced from Kaggle.The dataset was pre-processed to clean and tokenize the text data,and word embeddings were used to represent words as numerical vectors.The CNN component of the model extracts local features from the text,while the LSTM component captures long-range dependencies and contextual information.The outputs of the CNN and LSTM layers are then concatenated and fed into a fully connected layer for final sentiment classification.Experimental results demonstrate that the hybrid model outperforms traditional machine learning techniques and other deep learning models in terms of accuracy,precision,recall,and F1-score.By accurately classifying sentiment,identifying key themes,and predicting future trends,our model can provide valuable insights to businesses in the apparel industry.These insights can be used to improve product design,marketing strategies,and customer service,ultimately leading to increased customer satisfaction and business success.展开更多
Artificial intelligence(AI)is emerging as a transformative enabler in the development of smart textile systems,particularly those integrating powder-based functional materials.This review highlights recent progress in...Artificial intelligence(AI)is emerging as a transformative enabler in the development of smart textile systems,particularly those integrating powder-based functional materials.This review highlights recent progress in AIguided design of carbon nanomaterials,metallic nanoparticles,and framework-based powders for applications in energy harvesting,intelligent sensing,and robotic actuation.Machine learning techniques,including supervised learning,transfer learning,and Bayesian optimization are discussed for accelerating materials discovery,enhancing integration strategies,and enabling real-time adaptive control.Emphasis is placed on how AI enables multifunctional,wearable platforms that sense,process,and respond to environmental and physiological cues with high accuracy and autonomy.Representative breakthroughs in soft robotics,haptic interfaces,and assistive devices are presented,demonstrating the synergy of AI and responsive textiles.Finally,the review outlines key challenges related to data scarcity,model generalizability,manufacturing scalability,and sustainability,while proposing future directions involving multimodal learning,autonomous experimentation,and ethics-aware design.This work offers a comprehensive outlook on next-generation AI-driven textile systems that seamlessly integrate intelligence,functionality,and wearability.展开更多
As society confronts increasingly complex demands and the growing need for carbon-neutral architecture,AI-driven design methodologies are evolving rapidly.However,the lack of a unified integration platform in the desi...As society confronts increasingly complex demands and the growing need for carbon-neutral architecture,AI-driven design methodologies are evolving rapidly.However,the lack of a unified integration platform in the design process continues to hinder AI’s integration into real-world workflows.To address this challenge,we introduce ArchiWeb,a web-based platform specifically built to support AI-driven processes in early-stage architectural design.ArchiWeb transforms architectural representation and problem formulation by utilizing lightweight data protocols and a modular algorithmic network within an interactive web environment.Through its cloud-native,open-architecture framework,ArchiWeb enables deeper integration of AI technologies while accelerating the accumulation,sharing,and reuse of design knowledge across projects and disciplines.Ultimately,ArchiWeb aims to drive architectural design toward greater intelligence,efficiency,and sustainability-supporting the transition to data-informed,computationally enabled,and environmentally responsible design practices.展开更多
This study explores the innovative application of intelligent technology in the task-based Chinese teaching method,focusing on the effectiveness of real-time guidance of speech recognition and intelligent analysis tec...This study explores the innovative application of intelligent technology in the task-based Chinese teaching method,focusing on the effectiveness of real-time guidance of speech recognition and intelligent analysis technology on learners'pronunciation,grammar,and vocabulary.In the experiment,100 Chinese second language learners were divided into intelligent assistant groups and traditional teaching groups for comparative observation.According to the data,the task completion efficiency of the intelligent group increased by 20%,and the language proficiency evaluation index increased by an average of 30%.More than 80%of learners reported that the instant feedback mechanism effectively improved their confidence and participation in learning.The research proves that intelligent technology can build dynamic learning paths and optimize language acquisition efficiency through personalized training modules.Although the system has technical bottlenecks in the dimension of understanding cultural context,the experimental results provide empirical support for the deep integration of intelligent technology and language teaching,and lay the technical foundation for further research and development of a culturally sensitive intelligent teaching system.展开更多
Alzheimer's disease(AD)is a common neurodegenerative disorder among the elderly population.There are currently no effective therapeutic drugs available,the multi-target-directed ligands(MTDLs)strategy has been con...Alzheimer's disease(AD)is a common neurodegenerative disorder among the elderly population.There are currently no effective therapeutic drugs available,the multi-target-directed ligands(MTDLs)strategy has been considered as the promising approach.Given the structural diversity of natural products,Rivastigmine's pharmacophore was integrated with diverse natural product scaffolds to construct a combinatorial compound library.This library was subsequently screened and optimized to identify a novel butyrylcholinesterase(Bu Ch E)inhibitor,compound 3c.The results showed that compound 3c exhibited favorable Bu Ch E inhibitory activity(half-maximal inhibitory concentration(IC_(50))=0.43μmol/L),potential anti-inflammatory potency,good Aβ_(1-42) aggregation inhibitory capacity and remarkable neuroprotective effects.The in vivo study exhibited that 3c significantly ameliorated AlCl_(3)-induced zebrafish AD model and scopolamine-induced memory impairment.Collectively,compound 3c was the artificial intelligence(AI)-driven promising multifunctional agent with Bu Ch E inhibition for the treatment of AD.展开更多
Generative Adversarial Networks(GANs)have become valuable tools in medical imaging,enabling realistic image synthesis for enhancement,augmentation,and restoration.However,their integration into clinical workflows rais...Generative Adversarial Networks(GANs)have become valuable tools in medical imaging,enabling realistic image synthesis for enhancement,augmentation,and restoration.However,their integration into clinical workflows raises concerns,particularly the risk of subtle distortions or hallucinations that may undermine diagnostic accuracy and weaken trust in AI-assisted decision-making.To address this challenge,we propose a hybrid deep learning framework designed to detect GAN-induced artifacts in medical images,thereby reinforcing the reliability of AI-driven diagnostics.The framework integrates low-level statistical descriptors,including high-frequency residuals and Gray-Level Co-occurrence Matrix(GLCM)texture features,with high-level semantic representations extracted from a pre-trained ResNet18.This dual-stream approach enables detection of both pixel-level anomalies and structural inconsistencies introduced by GAN-based manipulation.We validated the framework on a curated dataset of 10,000 medical images,evenly split between authentic and GAN-generated samples across four modalities:MRI,CT,X-ray,and fundus photography.To improve generalizability to real-world clinical settings,we incorporated domain adaptation strategies such as adversarial training and style transfer,reducing domain shift by 15%.Experimental results demonstrate robust performance,achieving 92.6%accuracy and an F1-score of 0.91 on synthetic test data,and maintaining strong performance on real-world GAN-modified images with 87.3%accuracy and an F1-score of 0.85.Additionally,the model attained an AUC of 0.96 and an average precision of 0.92,outperforming conventional GAN detection pipelines and baseline Convolutional Neural Network(CNN)architectures.These findings establish the proposed framework as an effective and reliable solution for detecting GAN-induced hallucinations in medical imaging,representing an important step toward building trustworthy and clinically deployable AI systems.展开更多
The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in S...The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in Spanish is challenging due to linguistic complexity and the scarcity of annotated resources.In this paper,we compare two predominant AI-based approaches for the forensic detection of malicious hate speech:(1)finetuning encoder-only models that have been trained in Spanish and(2)In-Context Learning techniques(Zero-and Few-Shot Learning)with large-scale language models.Our approach goes beyond binary classification,proposing a comprehensive,multidimensional evaluation that labels each text by:(1)type of speech,(2)recipient,(3)level of intensity(ordinal)and(4)targeted group(multi-label).Performance is evaluated using an annotated Spanish corpus,standard metrics such as precision,recall and F1-score and stability-oriented metrics to evaluate the stability of the transition from zero-shot to few-shot prompting(Zero-to-Few Shot Retention and Zero-to-Few Shot Gain)are applied.The results indicate that fine-tuned encoder-only models(notably MarIA and BETO variants)consistently deliver the strongest and most reliable performance:in our experiments their macro F1-scores lie roughly in the range of approximately 46%–66%depending on the task.Zero-shot approaches are much less stable and typically yield substantially lower performance(observed F1-scores range approximately 0%–39%),often producing invalid outputs in practice.Few-shot prompting(e.g.,Qwen 38B,Mistral 7B)generally improves stability and recall relative to pure zero-shot,bringing F1-scores into a moderate range of approximately 20%–51%but still falling short of fully fine-tuned models.These findings highlight the importance of supervised adaptation and discuss the potential of both paradigms as components in AI-powered cybersecurity and malware forensics systems designed to identify and mitigate coordinated online hate campaigns.展开更多
The rapid expansion of the Internet of Things(IoT)and Edge Artificial Intelligence(AI)has redefined automation and connectivity acrossmodern networks.However,the heterogeneity and limited resources of IoT devices expo...The rapid expansion of the Internet of Things(IoT)and Edge Artificial Intelligence(AI)has redefined automation and connectivity acrossmodern networks.However,the heterogeneity and limited resources of IoT devices expose them to increasingly sophisticated and persistentmalware attacks.These adaptive and stealthy threats can evade conventional detection,establish remote control,propagate across devices,exfiltrate sensitive data,and compromise network integrity.This study presents a Software-Defined Internet of Things(SD-IoT)control-plane-based,AI-driven framework that integrates Gated Recurrent Units(GRU)and Long Short-TermMemory(LSTM)networks for efficient detection of evolving multi-vector,malware-driven botnet attacks.The proposed CUDA-enabled hybrid deep learning(DL)framework performs centralized real-time detection without adding computational overhead to IoT nodes.A feature selection strategy combining variable clustering,attribute evaluation,one-R attribute evaluation,correlation analysis,and principal component analysis(PCA)enhances detection accuracy and reduces complexity.The framework is rigorously evaluated using the N_BaIoT dataset under k-fold cross-validation.Experimental results achieve 99.96%detection accuracy,a false positive rate(FPR)of 0.0035%,and a detection latency of 0.18 ms,confirming its high efficiency and scalability.The findings demonstrate the framework’s potential as a robust and intelligent security solution for next-generation IoT ecosystems.展开更多
基金National Key R&D Program of China(2023YFC2604805-4)National Key Research and Development Program of Tibetan Autonomous Region(XZ202401ZY0034).
文摘This Highlight discusses the landmark study by Zhao et al.(Science,2025)that presents a transformative strategy against citrus Huanglongbing(HLB).The work identifies the E3 ubiquitin ligase PUB21 as a central susceptibility(S)factor,degrading the defense regulator MYC2.Crucially,the study harnesses natural resistance(dominantnegative PUB21DN mutant)and pioneers AI-driven design to develop a 14-amino acid peptide(APP3-14).This peptide dually combats HLB by stabilizing MYC2(inhibiting PUB21)and directly targeting the unculturable pathogen Candidatus Liberibacter asiaticus(CLas),achieving>90%bacterial reduction in field trials.The research also exposes how a CLas effector(SDE5,Sec-delivered effector 5)hijacks the PUB21-MYC2 axis.This work establishes"defense protein stabilization"as a powerful new paradigm for breeding resistant crops and controlling recalcitrant pathogens,exemplified by the innovative integration of AI in peptide therapeutics for plants.
基金supported by the National Key R&D Program of China(2022YFA1203400)the National Natural Science Foundation of China(W2441009)。
文摘Magnesium-ion batteries hold promise as future energy storage solutions,yet current Mg cathodes are challenged by low voltage and specific capacity.Herein,we present an AI-driven workflow for discovering high-performance Mg cathode materials.Utilizing the common characteristics of various ionic intercalation-type electrodes,we design and train a Crystal Graph Convolutional Neural Network model that can accurately predict electrode voltages for various ions with mean absolute errors(MAE)between0.25 and 0.33 V.By deploying the trained model to stable Mg compounds from Materials Project and GNoME AI dataset,we identify 160 high voltage structures out of 15,308 candidates with voltages above3.0 V and volumetric capacity over 800 mA h/cm^(3).We further train a precise NequIP model to facilitate accurate and rapid simulations of Mg ionic conductivity.From the 160 high voltage structures,the machine learning molecular dynamics simulations have selected 23 cathode materials with both high energy density and high ionic conductivity.This Al-driven workflow dramatically boosts the efficiency and precision of material discovery for multivalent ion batteries,paving the way for advanced Mg battery development.
基金funding support from the US National Science Foundation(2229092)supported by the Eric and Wendy Schmidt AI in Science Postdoctoral Fellowship,a program of Schmidt Sciences,LLC.
文摘Recent advances in artificial intelligence(AI)have led to the development of sophisticated algorithms that significantly improve image analysis capabilities.This combination of AI and microscopic imaging is transforming the way we interpret and analyze imaging data,simplifying complex tasks and enabling innovative experimental methods previously thought impossible.In smart manufacturing,these improvements are especially impactful,increasing precision and efficiency in production processes.This review examines the convergence of AI with particle image analysis,an area we refer to as“particle vision analysis(PVA).”We offer a detailed overview of how this technology integrates into and impacts various fields within the physical sciences and materials sectors,where it plays a crucial role in both innovation and operational improvements.We explore four key areas of advancement-namely,particle classification,detection,segmentation,and object tracking-along with a look into the emerging field of augmented microscopy.This paper also underscores the vital role of the existing datasets and implementations that support these applications,which provide essential insights and resources that drive continuous research and development in this fast-evolving field.Our thorough analysis aims to outline the transformative potential of AI-driven PVA in improving precision in future manufacturing at the microscopic scale and thereby preparing the ground for significant technological progress and broad industrial applications in nanomanufacturing,biomanufacturing,and pharmaceutical manufacturing.This exploration not only highlights the advantages of integrating AI into conventional manufacturing processes but also anticipates the rise of next-generation smart manufacturing,which is set to revolutionize industry standards and operational practices.
文摘With the growing adoption of Artifical Intelligence(AI),AI-driven autonomous techniques and automation systems have seen widespread applications,become pivotal in enhancing operational efficiency and task automation across various aspects of human living.Over the past decade,AI-driven automation has advanced from simple rule-based systems to sophisticated multi-agent hybrid architectures.These technologies not only increase productivity but also enable more scalable and adaptable solutions,proving particularly beneficial in industries such as healthcare,finance,and customer service.However,the absence of a unified review for categorization,benchmarking,and ethical risk assessment hinders the AI-driven automation progress.To bridge this gap,in this survey,we present a comprehensive taxonomy of AI-driven automation methods and analyze recent advancements.We present a comparative analysis of performance metrics between production environments and industrial applications,along with an examination of cutting-edge developments.Specifically,we present a comparative analysis of the performance across various aspects in different industries,offering valuable insights for researchers to select the most suitable approaches for specific applications.Additionally,we also review multiple existing mainstream AI-driven automation applications in detail,highlighting their strengths and limitations.Finally,we outline open research challenges and suggest future directions to address the challenges of AI adoption while maximizing its potential in real-world AI-driven automation applications.
文摘Theburgeoning e-commerce industry hasmade online customer reviews a crucial source of feedback for businesses.Sentiment analysis,a technique used to extract subjective information from text,has become essential for understanding consumer sentiment and preferences.However,traditional sentiment analysis methods often struggle with the nuances and context of natural language.To address these issues,this study proposes a comparison of deep learningmodels that figure out the optimalmethod to accurately analyze consumer reviews onwomen’s clothing.CNNs excel at capturing local features and semantic information,while LSTMs are adept at handling long-range dependencies and contextual understanding.By integrating these two deep learning techniques,our model aims to achieve better performance in sentiment classification.The models were trained and evaluated on a dataset of women’s clothing reviews sourced from Kaggle.The dataset was pre-processed to clean and tokenize the text data,and word embeddings were used to represent words as numerical vectors.The CNN component of the model extracts local features from the text,while the LSTM component captures long-range dependencies and contextual information.The outputs of the CNN and LSTM layers are then concatenated and fed into a fully connected layer for final sentiment classification.Experimental results demonstrate that the hybrid model outperforms traditional machine learning techniques and other deep learning models in terms of accuracy,precision,recall,and F1-score.By accurately classifying sentiment,identifying key themes,and predicting future trends,our model can provide valuable insights to businesses in the apparel industry.These insights can be used to improve product design,marketing strategies,and customer service,ultimately leading to increased customer satisfaction and business success.
基金supported by the National Natural Science Foundation of China(No.52373085,52573090 and U21A2095)Department of Science and Technology of Hubei Province(No.2025CSA001 and 2024CSA076),Outstanding Young and Middle-aged Scientific and Technology Innovation Team of Higher Education Institutions of Hubei Province(No.T2024010),Natural Science Foundation of Hubei Province(No.2023AFA828 and 2024AFB238)+2 种基金Innovative Team Program of Natural Science Foundation of Hubei Province(2023AFA027)Open Fund for Hubei Integrative Technology and Innovation Center for Advanced Fiberous Materials(XC202517)National Local Joint Laboratory for Advanced Textile Processing and Clean Production(FX20240005).
文摘Artificial intelligence(AI)is emerging as a transformative enabler in the development of smart textile systems,particularly those integrating powder-based functional materials.This review highlights recent progress in AIguided design of carbon nanomaterials,metallic nanoparticles,and framework-based powders for applications in energy harvesting,intelligent sensing,and robotic actuation.Machine learning techniques,including supervised learning,transfer learning,and Bayesian optimization are discussed for accelerating materials discovery,enhancing integration strategies,and enabling real-time adaptive control.Emphasis is placed on how AI enables multifunctional,wearable platforms that sense,process,and respond to environmental and physiological cues with high accuracy and autonomy.Representative breakthroughs in soft robotics,haptic interfaces,and assistive devices are presented,demonstrating the synergy of AI and responsive textiles.Finally,the review outlines key challenges related to data scarcity,model generalizability,manufacturing scalability,and sustainability,while proposing future directions involving multimodal learning,autonomous experimentation,and ethics-aware design.This work offers a comprehensive outlook on next-generation AI-driven textile systems that seamlessly integrate intelligence,functionality,and wearability.
基金funded by the National Natural Science Foundation of China(No.52378008)Postgraduate Research Innovation Program of Jiangsu Province(No.KYCX22_0189).
文摘As society confronts increasingly complex demands and the growing need for carbon-neutral architecture,AI-driven design methodologies are evolving rapidly.However,the lack of a unified integration platform in the design process continues to hinder AI’s integration into real-world workflows.To address this challenge,we introduce ArchiWeb,a web-based platform specifically built to support AI-driven processes in early-stage architectural design.ArchiWeb transforms architectural representation and problem formulation by utilizing lightweight data protocols and a modular algorithmic network within an interactive web environment.Through its cloud-native,open-architecture framework,ArchiWeb enables deeper integration of AI technologies while accelerating the accumulation,sharing,and reuse of design knowledge across projects and disciplines.Ultimately,ArchiWeb aims to drive architectural design toward greater intelligence,efficiency,and sustainability-supporting the transition to data-informed,computationally enabled,and environmentally responsible design practices.
文摘This study explores the innovative application of intelligent technology in the task-based Chinese teaching method,focusing on the effectiveness of real-time guidance of speech recognition and intelligent analysis technology on learners'pronunciation,grammar,and vocabulary.In the experiment,100 Chinese second language learners were divided into intelligent assistant groups and traditional teaching groups for comparative observation.According to the data,the task completion efficiency of the intelligent group increased by 20%,and the language proficiency evaluation index increased by an average of 30%.More than 80%of learners reported that the instant feedback mechanism effectively improved their confidence and participation in learning.The research proves that intelligent technology can build dynamic learning paths and optimize language acquisition efficiency through personalized training modules.Although the system has technical bottlenecks in the dimension of understanding cultural context,the experimental results provide empirical support for the deep integration of intelligent technology and language teaching,and lay the technical foundation for further research and development of a culturally sensitive intelligent teaching system.
基金financially supported by the China Postdoctoral Science Foundation(No.2022M712153)The National Natural Science Foundation of China(Nos.22367007 and 82304384)+1 种基金The Fundamental Research Funds for Hainan University(No.KYQD(ZR)23002)Hainan Provincial Natural Science Foundation of China(No.824RC500)。
文摘Alzheimer's disease(AD)is a common neurodegenerative disorder among the elderly population.There are currently no effective therapeutic drugs available,the multi-target-directed ligands(MTDLs)strategy has been considered as the promising approach.Given the structural diversity of natural products,Rivastigmine's pharmacophore was integrated with diverse natural product scaffolds to construct a combinatorial compound library.This library was subsequently screened and optimized to identify a novel butyrylcholinesterase(Bu Ch E)inhibitor,compound 3c.The results showed that compound 3c exhibited favorable Bu Ch E inhibitory activity(half-maximal inhibitory concentration(IC_(50))=0.43μmol/L),potential anti-inflammatory potency,good Aβ_(1-42) aggregation inhibitory capacity and remarkable neuroprotective effects.The in vivo study exhibited that 3c significantly ameliorated AlCl_(3)-induced zebrafish AD model and scopolamine-induced memory impairment.Collectively,compound 3c was the artificial intelligence(AI)-driven promising multifunctional agent with Bu Ch E inhibition for the treatment of AD.
基金supported and funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University(IMSIU)(grant number IMSIU-DDRSP2601).
文摘Generative Adversarial Networks(GANs)have become valuable tools in medical imaging,enabling realistic image synthesis for enhancement,augmentation,and restoration.However,their integration into clinical workflows raises concerns,particularly the risk of subtle distortions or hallucinations that may undermine diagnostic accuracy and weaken trust in AI-assisted decision-making.To address this challenge,we propose a hybrid deep learning framework designed to detect GAN-induced artifacts in medical images,thereby reinforcing the reliability of AI-driven diagnostics.The framework integrates low-level statistical descriptors,including high-frequency residuals and Gray-Level Co-occurrence Matrix(GLCM)texture features,with high-level semantic representations extracted from a pre-trained ResNet18.This dual-stream approach enables detection of both pixel-level anomalies and structural inconsistencies introduced by GAN-based manipulation.We validated the framework on a curated dataset of 10,000 medical images,evenly split between authentic and GAN-generated samples across four modalities:MRI,CT,X-ray,and fundus photography.To improve generalizability to real-world clinical settings,we incorporated domain adaptation strategies such as adversarial training and style transfer,reducing domain shift by 15%.Experimental results demonstrate robust performance,achieving 92.6%accuracy and an F1-score of 0.91 on synthetic test data,and maintaining strong performance on real-world GAN-modified images with 87.3%accuracy and an F1-score of 0.85.Additionally,the model attained an AUC of 0.96 and an average precision of 0.92,outperforming conventional GAN detection pipelines and baseline Convolutional Neural Network(CNN)architectures.These findings establish the proposed framework as an effective and reliable solution for detecting GAN-induced hallucinations in medical imaging,representing an important step toward building trustworthy and clinically deployable AI systems.
基金the research project LaTe4PoliticES(PID2022-138099OB-I00)funded by MCIN/AEI/10.13039/501100011033 and the European Fund for Regional Development(ERDF)-a way to make Europe.Tomás Bernal-Beltrán is supported by University of Murcia through the predoctoral programme.
文摘The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in Spanish is challenging due to linguistic complexity and the scarcity of annotated resources.In this paper,we compare two predominant AI-based approaches for the forensic detection of malicious hate speech:(1)finetuning encoder-only models that have been trained in Spanish and(2)In-Context Learning techniques(Zero-and Few-Shot Learning)with large-scale language models.Our approach goes beyond binary classification,proposing a comprehensive,multidimensional evaluation that labels each text by:(1)type of speech,(2)recipient,(3)level of intensity(ordinal)and(4)targeted group(multi-label).Performance is evaluated using an annotated Spanish corpus,standard metrics such as precision,recall and F1-score and stability-oriented metrics to evaluate the stability of the transition from zero-shot to few-shot prompting(Zero-to-Few Shot Retention and Zero-to-Few Shot Gain)are applied.The results indicate that fine-tuned encoder-only models(notably MarIA and BETO variants)consistently deliver the strongest and most reliable performance:in our experiments their macro F1-scores lie roughly in the range of approximately 46%–66%depending on the task.Zero-shot approaches are much less stable and typically yield substantially lower performance(observed F1-scores range approximately 0%–39%),often producing invalid outputs in practice.Few-shot prompting(e.g.,Qwen 38B,Mistral 7B)generally improves stability and recall relative to pure zero-shot,bringing F1-scores into a moderate range of approximately 20%–51%but still falling short of fully fine-tuned models.These findings highlight the importance of supervised adaptation and discuss the potential of both paradigms as components in AI-powered cybersecurity and malware forensics systems designed to identify and mitigate coordinated online hate campaigns.
基金supported by Princess Nourah bint Abdulrahman University Researchers Supporting ProjectNumber(PNURSP2025R97),PrincessNourah bint AbdulrahmanUniversity,Riyadh,Saudi Arabia.
文摘The rapid expansion of the Internet of Things(IoT)and Edge Artificial Intelligence(AI)has redefined automation and connectivity acrossmodern networks.However,the heterogeneity and limited resources of IoT devices expose them to increasingly sophisticated and persistentmalware attacks.These adaptive and stealthy threats can evade conventional detection,establish remote control,propagate across devices,exfiltrate sensitive data,and compromise network integrity.This study presents a Software-Defined Internet of Things(SD-IoT)control-plane-based,AI-driven framework that integrates Gated Recurrent Units(GRU)and Long Short-TermMemory(LSTM)networks for efficient detection of evolving multi-vector,malware-driven botnet attacks.The proposed CUDA-enabled hybrid deep learning(DL)framework performs centralized real-time detection without adding computational overhead to IoT nodes.A feature selection strategy combining variable clustering,attribute evaluation,one-R attribute evaluation,correlation analysis,and principal component analysis(PCA)enhances detection accuracy and reduces complexity.The framework is rigorously evaluated using the N_BaIoT dataset under k-fold cross-validation.Experimental results achieve 99.96%detection accuracy,a false positive rate(FPR)of 0.0035%,and a detection latency of 0.18 ms,confirming its high efficiency and scalability.The findings demonstrate the framework’s potential as a robust and intelligent security solution for next-generation IoT ecosystems.
